Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology

Functionality and cosmetics are two concerns for future hand prosthesis development and they both can be improved by a combination with artificial soft materials which can mimic human skin. To bridge the gap between the human and artificial side, it is essential to have a comprehensive understanding of the human skin’s biomechanics, especially the fingertip’s haptics-related mechanism. Available studies characterise the mechanical behaviour of human fingertip only by deterministic models based on either statistical data analysis or fingertip structure/viscoelasticity analysis. To take the force uncertainty into consideration, this paper proposes a novel probability-based haptics model, which includes two parts: a force prediction model to obtain the most possible contact force according to the indentation depth, and a probabilistic model based on Gaussian distribution to describe the force uncertainty. Experiments were conducted by pressing subjects’ index fingertips against a cone-shape probe with the measurement of the contact force and the indentation depth under a wide range of 0∼5 mm. Four types of non-linear regression models and the Gaussian distribution model are applied for model training and validation. Experiment results reveal that the contact force varying with the indentation depth presents the characteristics of non-linearity, dispersion, and individual difference. Model testing results confirm the effectiveness of the haptics model on force prediction and force uncertainty description. An example of its application on a virtual hand of a rehabilitation system is demonstrated.

With the advent of IoT, cloud/fog based healthcare systems have become a growing trend in modern healthcare systems. These systems comprise of smart sensors, which on integration with medical devices, generate heterogeneous medical big data that can be used in diagnosis of various diseases. However, there is a continuous flow of large quantity of data in such a systems, due to which it may face many difficulties. Among various pre-requisites for proper functioning of these systems, lifetime is a vital factor. Keeping in view these aspects, the use of new hybrid whale-PSO algorithm (HWPSO) in clustering has been proposed for prolonging the network lifetime by preserving the power of network edge devices. In addition to this, a novel fitness function with a set of relevant criteria of edge devices such as energy factor, average intra-cluster distance, average distance to cluster leader over data analytics center, average sleeping time, and computational load has been taken into account in the selection of cluster leader. The cluster leader is responsible for managing intra-cluster and inter-cluster data communication.

Recently, sentiment analysis has become a focus domain in artificial intelligence owing to the massive text reviews of modern networks. The fast increase of the domain has led to the spring up of assorted sub-areas, researchers are also focusing on subareas at various levels. This paper focuses on the key subtask in sentiment analysis: aspect-based sentiment analysis. Unlike feature-based traditional approaches and long short-term memory network based models, our work combines the strengths of linguistic resources and gating mechanism to propose an effective convolutional neural network based model for aspect-based sentiment analysis. First, the proposed regularizers from the real world linguistic resources can be of benefit to identify the aspect sentiment polarity. Second, under the guidance of the given aspect, the gating mechanism can better control the sentiment features. Last, the basic structure of model is convolutional neural network, which can perform parallel operations well in the training process. Experimental results on SemEval 2014 Restaurant Datasets demonstrate our approach can achieve excellent results on aspect-based sentiment analysis.

 The demand for Cyber Social Networks has increasingly become the main source of information propagation due to the rapid growth of micro-blogging activity between socially connected people. The process of detecting disaster events, in huge volumes, on fast-streaming platform is quite challenging. In this paper, an information entropy based event detection framework is proposed to identify the event and its location by clustering relatively high-density ratio of tweets using Twitter data. The Shannon entropy of target users, location, time intervals and hashtags are estimated to quantify the dissemination of events as “how-far about” in real- world using entropy maximization inference model. The geo-tagged (spatial) tweets are extracted for a specified time period (temporal) to identify the location of an event as “where-when about”; and visualizes the event in geo-maps. The evaluation parameters of Entropy, Cluster Score, Event Detection Hit and False Panic Rate during four major disaster events are identified to illustrate the effectiveness of the proposed framework. The retweeting activity of the Twitter user is classified as human signatures and bots. The experimental outcome determines the scope and significant dissemination direction of finding events from a new perspective which demonstrates 96% of improved event detection accuracy.

Despite the increasing awareness of cyber-attacks against Critical Infrastructure (CI), safeguarding the Supervisory Control and Data Acquisition (SCADA) systems remains inadequate. For this purpose, designing an efficient SCADA Intrusion Detection System (IDS) becomes a significant research topic of the researchers to counter cyber-attacks. Most of the existing works present several statistical and machine learning approaches to prevent the SCADA network from the cyber-attacks. Whereas, these approaches failed to concern the most common challenge, “Curse of dimensionality”. This scenario accentuates the necessity of an efficient feature selection algorithm in SCADA IDS where it identifies the relevant features and eliminates the redundant features without any loss of information. Hence, this paper proposes a novel filter-based feature selection approach for the identification of informative features based on Rough Set Theory and Hyper-clique based Binary Whale Optimization Algorithm (RST-HCBWoA). Experiments were carried out by Power system attack dataset and the performance of RST-HCBWoA was evaluated in terms of reduct size, precision, recall, classification accuracy, and time complexity.

Operational Technology (OT) often refers to the industrial control systems which are used to monitor and control the devices and processes of critical infrastructure like, water treatment plant, power grid and sewage systems. Conventionally, these OT systems are completely isolated from Information Technology (IT) infrastructure to protect their processes and devices against cyber-attacks. However, the convergence of IT and OT is inevitable to improvise the remote management of physical devices and to enhance the production by incorporating data-driven decision making by accessing and analyzing their real-time data. To achieve this, the isolated OT systems and devices need to be accessed using Internet. However, this interconnection leads both the sensor and control data of OT systems vulnerable to cyber-attacks. This research work extends our previous intrusion detection system that identifies anomalies which are deviated from process-invariants in secured water treatment (SWaT) test-bed data obtained from Singapore University of Technology and Design (SUTD). Additionally, it proposes process-invariants based timed automata wherein the attack and its detection model are represented as timed automata. The proposed system is implemented and validated using UPPAAL, a tool for validating real-time systems represented as networks of timed automata. The results conclude that the proposed system effectively identifies the attacks considered thereby recommending the timed automata as an operational tool for detecting the data-integrity attacks in critical infrastructures. The highly reported attacks that include level indicators, motorized valves, pressure indicators and analyzer indicators are detected successfully by the proposed system. Using the results, Stage 1 and Stage 3 are highly vulnerable.

 In contrast to conventional preprocessing aided spatial modulation (PSM), which carries partial information using the indexes of receive antennas, we exploit one receive antenna to implicitly convey information and meanwhile harvest energy at the remaining antennas. Based on this, we propose two novel beamforming schemes. The first scheme is to maximize the sum energy harvested by the receiver. And the second scheme is to maximize the minimum receiving power on each antenna except for the antenna that conveys information. A closed form solution and an iterative algorithm are given, respectively. Simulation results demonstrate that proposed two schemes can harvest a certain amount of energy with nearly same achievable rate compared to the benchmark schemes. But the second scheme is superior to the first scheme and PSM scheme in terms of bit error rate (BER) performance.

 This paper proposes a prediction system to identify the type of eye diseases like glaucoma and diabetic retinopathy. The proposed system processes the images captured using the fundus camera that is connected to the computer. The acquired fundus images are fed into the proposed prediction system which can be deployed in the cloud, and it identifies the type of disease. This forms a cyber-physical system. Underdeveloped countries which do not have the necessary infrastructure can utilize this service when this system is deployed in the cloud. For identifying these diseases, ophthalmologists extract parameters manually from the fundus image, which is a difficult task. Hence, this research work attempts to develop a system to automate the feature extraction from fundus images and with the extracted features, eye diseases are predicted. From the literature, it is found that many research works were focused on the binary classification of any one disease. In this paper, a novel classification methodology is proposed that helps the experts and clinicians to classify Diabetic Retinopathy, Glaucoma and healthy eye images with more accuracy. The proposed system with high accuracy is designed with the following phases: i) image acquisition, ii) image enhancement, iii) local features extraction using Speeded Up Robust Feature (SURF), iv) Bag of Features/Visual Words (BoF/BoVW) obtained through k-means clustering of local features, and v) classification using Error-Correcting Output Code (ECOC) linear SVM. It is inferred from the results that proposed method of classification using BoVW provided a maximum accuracy of 92% when compared to other state-of-the-art recent literature.

Nowadays Electronic communication is an important medium and an inevitable way for official communication. So, the email classification into spam or ham gains a lot of importance. Commonly used approaches are text-based or collaborative methods for spam detection. However, not only choosing the right classifier is very difficult but, handling poison attacks and impersonation attacks are also very important. The proposed model considers a powerful spam filtering technique which includes both social network and email factors in addition to the email data analysis for spam classification. The incoming emails are subjected to header parsing for finding the trust and reputation of senders with respect to the receivers and keyword parsing is applied to find the topic of interest using LDA with Gibbs Sampling method. Optical Character Recognition (OCR) method is applied to find the image spam e-mails. Degree and strength of the connection between the users from the social networks are also considered along with the email data factors for better message classification. Logistic Regression is used to combine all the independent input features to get an effective result. The experimental results and comparisons with the existing models vividly show the significant performance of the proposed classifier.

 Automated metering Infrastructure (AMI) is an integral part of a smart grid. Employing the data collected by the AMI from the consumers to generate accurate electricity consumption forecasts can help the utility in significantly improving the quality of service delivered to the consumer. Design and empirical validation of machine learning based electric energy consumption forecasting systems, is presented in the present study. Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Extreme Learning Machines (ELM) based models are designed and evaluated. One of the major aspects of the work is that the proposed consumption forecasting systems are designed as generalized models, i.e. one single model can be used to generate forecasts for any of the consumers considered, as opposed to the conventional technique of generating a separate model for each consumer. The forecasting systems are designed to generate half-hour-ahead and two-hour-ahead electric energy consumption forecasts. The proposed systems are validated on data for 485 Small and Medium Enterprise (SME) consumers in the CER electric energy consumption dataset. Results indicate that the models proposed in the present study result in good consumption forecast accuracy are hence, well suited for generating electric energy consumption forecast models.

 Nowadays, the purchase of every product involves a lot of critical thinking. Every buyer goes through a lot of user reviews and rating before finalizing his purchase. They do this to ensure that the product they purchase is of good quality at minimum price possible. It is evident now that online reviews are not that reliable because of fake reviews and review bots. Now you can even pay certain social media groups to give your product a fake good rating. Hence going just with the reviews of some stranger whom you do not know is not intelligent. So we propose a recommendation model based on the Trust Relations (TR) and User Credibility (UC) because it is human nature that a person feels more comfortable when he gets a review from a person he knows on a first name basis. Also, the credibility of the reviewer is an important factor while providing importance to the reviews because every person is different from other and can have different expertise. Our model takes into account the effect of credibility which is not used by any other recommendations models which increases the precision of the results of our model. We also propose the algorithm to calculate the credibility of any node in the network. The results are validated using a dataset and applying our proposed model and traditional average rating model which shows that our model performs better and gives precise results.

 In this paper, typical application of Cyber Physical System (CPS) has been highlighted for the critical-healthcare data transmission services. Sensors of CPS are providing patient’s health information via a communication network to a medical practitioner at some distant place. Needs of development of dependable routing protocol for such type of applications in healthcare are increased day-by-day. This paper proposes a quickest, critical and energy efficient routing for the CPS based healthcare system. Simulations performed to convey the appropriateness of the quality of data transmission system according to the well-defined Service Level Agreement (SLA) formulation. Proposed energy and SLA cooperation in data transmission is beneficial for the tele-operated medical service. A medical practitioner is able to monitor a patient in real-time with the help of proposed dependable and energy efficient data transmission. The results shows that CPS with consideration of different constraints such as energy and SLAs have a severe effect on its performance parameters such as mean number of QSS s-t paths, average hop counts and average energy efficiency. In addition to this comparison with existing algorithms shows the improvement in consideration with all performance components.

 Authentication based on utilization of fingerprint has become highly popular. Generally, minutiae points information obtained from the fingerprints is stored into the database. Various research works depict that by utilizing minutiae points information, original fingerprints reconstruction is possible. Adversary can obtain the user template through an attack on the database. If minutiae template of a user is compromised, then the adversary can construct original fingerprint of the user. In order to avoid this, it is essential to secure the fingerprint information. To achieve this, a technique called 3-Dimensional Secured Fingerprint Shell has been presented by Ali and Prakash, in this technique they generate a 3-dimensional spiral curve, however, ridge counts between singular and minutiae points are not secure in this technique. In the proposed technique we construct an extremely secure and efficient template for a user, by securing all features of the fingerprint used for template generation. The proposed technique is robust against the effects of rotation as well as translation and meets the essential requirements of an efficient authentication system. We evaluated the proposed technique by utilizing FVC2000, FVC2002, FVC2004, and IIT Kanpur fingerprint databases. The results obtained for the proposed technique are highly encouraging, that shows its robustness.

 Edge computing offers potential benefits to applications working in IoT (Internet of Things) and CPS (Cyber Physical Systems) environments by bringing the power of computing proximate to the devices, which demand high computational resources. As computational capabilities are currently untapped in edge devices like the IoT gateway, the computational intensive part of an application like a thread, a module or a task can be offloaded to the edge devices rather than to the cloud by the end devices. In this paper, an approach that employs Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) is used to determine the near optimal solution for scheduling offloadable components in an application, with the intent of significantly reducing the execution time of an application and energy consumption of the smart devices. With a new inertial weight equation, an Adaptive Genetic Algorithm – Particle Swarm Optimization (AGA-PSO) algorithm is proposed which uses GA’s ability in exploration and PSO’s ability in exploitation to make the offloading optimized without violating the deadline constraint of an application.

 The natural activities and human thinking forms the basis for fuzzy logic which presents based on different application perspectives. The performance of various energy storage systems life time can be improved by utilizing fuzzy logic controllers and back up in a hybrid power system especiallywhile usingrenewable sources. The Load Frequency Controllers (LFC) using classical control techniques are tuned based on trial and error methods.Also, when system complexity increases controller gives slow response, by considering the fuzzy intelligent control these system performances are improved. A soft computing fuzzy technique is employed to maximize the efficiency from solar panel to give maximumpower output.The various applications in power systems relating to energy storage system performance for energy management, controller for controlling the load-frequency in multi-area power system and for solar systems by considering the tracking efficiency which are utilized for synchronization into the grid.The fuzzy logic provides better improvement and efficiency when compared to conventional controllers. These controllers do not have any specific or particular procedure to implement in various applications. A brief review to fuzzy logic controllers (FLC) for energy storage systems LFC and PV solar MPPT is presented.

 In order to accurately assess the threat of air multi-target in the complicated and changeable air combat environment, an assessment method based on improved group generalized intuitionistic fuzzy soft set (I-GGIFSS) is proposed in this paper. Firstly, considering the characteristics of air target and the influence factors of threat assessment, a reasonable threat assessment system is established, and the appropriate assessment index is determined. Secondly, the generalized parameter matrix provided by many experts is introduced into the generalized intuitionistic fuzzy soft set (GIFSS) to form the group generalized intuitionistic fuzzy soft set (GGIFSS) to compensate for the knowledge limitation and assessment error of a single expert in traditional GIFSS. Finally, subjective weight is determined by group AHP (GAHP) and objective weight is determined by intuitionistic fuzzy entropy (IFE), then subjective weight and objective weight are combined based on relative entropy theory to determine reasonable index weight and expert weight, thus I-GGIFSS is obtained. The validity and superiority of I-GGIFSS are verified by the calculation and comparison of an example.

 3D Cardiac Magnetic Resonance Imaging (MRI) is widely used for the diagnosis of cardiac diseases such as congenital heart defect, left ventricular hypertrophy and left atrium hypertrophy etc. It is one of the noninvasive technique to examine cardiac anatomy. However this technique is semi- automatic, i.e. the images obtained directly from MRI machine have to be segmented manually. This includes the segmentation of chambers and vessels, which is quite complex and requires specialized technical knowledge. Without proper segmentation, it is extremely difficult for medical staff to examine the data. This paper suggest a fully automatic method for cardiac chamber segmentation (Left Atrium and Left Ventricle pair) in 3D cardiac MRI based on artificial intelligence. The proposed method identifies the junction of Left Atrium (LA) and Left Ventricle (LV) using neural networks. The features used for this purpose are based on shape, size and position. Then it uses traditional methods to track and stack the upper and lower slices based on neighborhood. I.e. a 3D model of the segmented LA and LV is reconstructed from the 2D format. This enhanced 3D image model helps in deducing quality information for the diagnosis of various heart diseases. The proposed algorithm shows acceptable performances for all planes of LV and LA. We have achieved 91.57% mean segmentation accuracy. The proposed algorithm is not effected by the thickness of the slices. It is simple and computationally less intensive than existing algorithms.

 In this manuscript a DC non-isolated converter model with high static voltage gain module is presented. The proposed converter has the feature of stable frequency and stable output voltage. It also achieves high voltage conversion, high efficiency, low voltage stress and less switching loss. The voltage tripler technique is implemented in the proposed model. The designed converter model attains high static gain with reduced duty cycle. The proposed single switch converter is controlled by fuzzy-PI controlled technique. The working process of the converter under Continuous Conduction Mode (CCM) is explained. The 30 V input source is boosted up to 400 V. The simulation of the presented converter is done with MATLAB simulink. The hardware prototype is also tested and results are analysed.

 Accurate activity recognition plays a major role in smart homes to provide assistance and support for users, especially elderly and cognitively impaired people. To realize this task, knowledge-driven approaches are one of the emerging research areas that have shown interesting advantages and features. However, several limitations have been associated with these approaches. The produced models are usually incomplete to capture all types of human activities. This resulted in the limited ability to accurately infer users’ activities. This paper presents an alternative approach by combining knowledge-driven with data-driven reasoning to allow activity models to evolve and adapt automatically based on users’ particularities. Firstly, a knowledge-driven reasoning is presented for inferring an initial activity model. The model is then trained using data-driven techniques to produce a dynamic activity model that learns users’ varying action. This approach has been evaluated using a publicly available dataset and the experimental results show the learned activity model yields significantly higher recognition rates compared to the initial activity model.

Rapid web growth and associated applications have proven of colossal importance for recommender systems. In the current digital world, a recommender system aims to acquire high-level prediction-based accuracy. However, many studies have suggested diversity-based recommendations are required for high-level accuracy. Group recommendation systems (GRS) recommend lists of items to a group of users according to their social activities, such as planning for a holiday tour, watching movies, etc. Using GRS, preferences/choices shared by users affected all the available aggregation with GRS leads to information loss and negatively affects ‘diversity.’ To handle the problem of ‘information loss,’ which is caused by aggregation, this paper proposes fuzzy-based GRS and argues that communicating such hesitant information will prove beneficial to generating recommendations. To find the valuable suggestions, greater focus must be dedicated to avoiding lack of variety and interest in the complete list of recommendations. In this article, we propose a novel Parallel Computing Group Recommendation System, which quantifies different approaches, chooses the right approach for group recommendation, and quickly generates optimal results. This proposed approach is an ensemble model of parallel ranking and matrix factorization that facilitates a diversified group recommendation list. Experimental evaluation signals that our model achieves higher diversity positively packed with user satisfaction.

Fuzzy inference systems have been successfully applied to many real-world applications. Traditional fuzzy inference systems are only applicable to problems with dense rule bases covering the entire problem domains, whilst fuzzy rule interpolation (FRI) works with sparse rule bases that do not cover certain inputs. Thanks to its ability to work with a rule base with less number of rules, FRI approaches have been utilised as a means to reduce system complexity for complex fuzzy models. This is implemented by removing the rules that can be approximated by their neighbours. Most of the existing fuzzy rule base generation and simplification approaches only target dense rule bases for traditional fuzzy inference systems. This paper proposes a new sparse fuzzy rule base generation method to support FRI. In particular, this approach uses curvature values to identify important rules that cannot be accurately approximated by their neighbouring ones for initialising a compact rule base. The initialised rule base is then optimised using an optimisation algorithm by fine-tuning the membership functions of the involved fuzzy sets. Experiments with a simulation model and a real-world application demonstrate the working principle and the actual performance of the proposed system, with results comparable to the traditional methods using rule bases with more rules.

 In recent years, a large number of spectrum mechanisms have been proposed, but these mechanisms ignore the security issues that arise during the design of the mechanism. In this paper, two secure models for sealed-bid spectrum auction are given based on Wang’s generic spectrum auction mechanism. One is the basic model and another improved model based on the basic model is proposed, which maximizes Social welfare while it is a Privacy-preserving Spectrum auction mechanism with public Verification namely SPSV. The SPSV scheme achieves the properties of maximizing the social welfare but also, by using the double paillier cryptosystem, it is privacy-preserving for bidders’ bids without revealing any sensitive information to auctioneer or agent during the entire spectrum auction. Oblivious transfer is applied to ensure the anonymity of bidders. Furthermore, the use of inequality comparison proof also provides the public verification of winner group to verify the comparison relationship between winner groups and losing groups. At last, the performance analysis are given.

Guaranteeing the reliability of cyber-physical systems (CPS) requires analog integrated circuits for correct functioning. Analog integrated circuits capture the continuous signal and amplify the signal for further processing in CPS applications. This paper presents the hybrid swarm intelligence based approach for determining the optimal transistors sizes and bias current values of CMOS differential amplifier and an operational amplifier. We proposed the simplex search based global optimization method called a hybrid grey wolf optimization (GWO) for solving amplifiers circuit sizing problems. Simplex and GWO techniques were combined to improve the local search capabilities of the optimization method. Our main aim is to optimize the transistor size and bias current values using hybrid GWO algorithm for an optimal design of the CMOS amplifiers. CMOS 180 nm technology was utilized to finding the circuit performance using proposed optimization approach. Simulation result shows that the proposed method provides the better result for circuit performance parameters such as DC gain, phase margin, unity gain bandwidth and power dissipation.

The demand for electricity is increasing very rapidly due to the vast development in industrialization. Generally, at present, for electric power generation, Renewable Energy Sources (RES) are considered as a better alternative option than conventional energy sources. Among the various RES, Solar and wind energy are available in abundantly and hence they can be recognized as a reliable source of power generation. More over this type of Hybrid solar and wind energy systems can be used for rural electrification and modernization of remote area. However, there will be problem of power quality issues such as harmonics, sag etc., hence, this work proposed a novel methodology to improve the power quality of the grid system interfaced with hybrid wind-solar system. In this proposed methodology, shunt active power filter with fuzzy logic based control strategy is introduced to minimize the harmonics present in the system. The proposed topology is validated through dynamic simulation using the MATLAB/Simulink Power System Toolbox. Simulation results demonstrate that the proposed system injects power into the grid from hybrid system with harmonic mitigation. This approach also eliminates the need of additional power conditioning equipment for the improvement of power quality.

The trustworthiness of consumer evaluation is an important prerequisite for reference to make a decision. Hence, a trust evaluator must recognize biased information (referred to as false recommendation), and do so dynamically. Drawing on the sociological concept of trust fusion, a new trust evaluating model is proposed, one built upon (i) Bayesian updating of the trust evaluation with each transaction, and (ii) the identification and correction of purposefully misleading evaluations according to improved evidence theory. Simulations show that the algorithm’s trust value increases slowly with successful transactions, but drops rapidly with a failed transaction, capturing the notion that trust is hard to establish, yet easy to destroy. Further simulations demonstrate the model has good robustness and error tolerance of trust evaluation against false recommendations at varying levels of deception. The algorithm effectively and robustly compensates for deception.

The development of the Internet of Things (IoT) can be attributed to the sudden rise in miniature electronic devices, as well as their computing power and ability to make interconnections. These devices exchange large volumes of confidential information from diverse locations. Similar to the Internet, the IoT has also encountered various issues with information security. Due to limited computing and energy resources in the field of IoT, it is necessary to develop a scheme to ensure feasible and more effective concealment and security properties. This paper proposes a unique methodology that captures an image using IoT sensors, which are subjected to lighter cryptographic operations for conversion into a cipher image, and is then sent to a home server. At the home server, a combined cryptography and steganography approach is employed to conceal the cipher image in a cover image, camouflaging the presence of the secret image, which is then sent to the IoT-Cloud server for storage. During the embedding process, QR decomposition is performed on the RIWT transformed secret image and RIWT - DCT transformed cover image. Modification performed on the R matrix of QR decomposition does not affect the structural properties of the cover image. A block selection algorithm is used to select optimal blocks with high contrast areas to embed the secret image. The experimental results indicate that our scheme enhances imperceptibility, robustness, and resistance to steganalysis attacks.

The rapid developments of computation, communication and control contribute to the generation of cyber physical systems (CPS). For full-time urban surveillance or military reconnaissance in complex environments, infrared and visible imaging sensors typically need to be integrated into the CPS. Furthermore, an effective and stable image fusion algorithm is important for CPS to provide images with rich information. Therefore, an image fusion algorithm for CPS is introduced in this paper. Compared with traditional multi-scale and multi-direction decomposition based algorithms, a more efficient MSMD based algorithm is proposed. Firstly, base layers reserved edges and detailed layers are obtained by multi-scale decomposition. Secondly, multi-direction decomposition is employed to base layers rather than detailed layers in traditional method. Then, serials of detailed layers and multi-directional base layers are obtained by choosing the max value based on patch. After the inverse transformation of multi-direction decomposition is conducted for multi-directional fused base layers, the reconstruction result is obtained via superposition of fused base and detail layers. Experiments prove that our algorithm outperforms the art-of-state.

Efficient servicing of requests in cloud environment has become need of the hour. Cloud services work based on zones in various locations and multiple service requests may be simultaneously considered as a batch and allocated to various zones. Experience-based Efficient Scheduling or EXES focuses on achieving minimum possible waiting time for a batch of requests, under the constraint that overall allocation cost should be less than or equal to a budget limit. Migration of tasks is also possible to balance loads if budget permits and we gain in energy. For each task in a batch and all available zones, a priority value is computed based on previous interaction experience of the zone and the site that generated this task. The zone that produces highest priority for a task, is allocated the task. An SDN controller is in charge of the entire process of priority computation and assigning tasks to zones. Priority is given to requests generating from sites that consumed lesser execution time compared to other sites that have generated requests in request queue of the zone. To the best of authors’ knowledge, no existing scheduling scheme in cloud has considered batch processing based on service process experience of zones.

This paper presents a new evolutionary approach for reconfiguration of radial systems. The framework applied for optimization is Symbiotic Organism Search Algorithm (SOSA). The algorithm is impressed by the interactive behavior opted by the living organisms for surviving and to propagate in the ecosystem. This concept aims for optimal survivability in the ecosystem involving the harm and benefits received from other organisms. The aim is to find optimal reconfiguration and to reduce the real power loss in the distribution side. This approach is examined on 16-bus and 33-bus systems. The results show a significant reduction of real power loss. The time required for execution is less when compared to other approaches. Based on the results calculated with distribution load flow algorithm the SOSA gives better results in terms of real power loss reduction and it is best suitable for digital automation systems.

 Even though, cloud computing reduces the operating cost by enabling adaptation of virtual machines, it has suffered in selection of optimal virtual machine due to shortage of resource or resource wastage, sudden changes in requirement so it requires optimal resource allocation. Resource allocation is the process of providing services and storage space to the particular task requested by the users. This is one of the important challenges in cloud computing environment and has variant level of issues like scheduling task, computational performance, reallocation, response time and cost efficiency. In this research work we introduce a three-phase scheduling method based on memory, energy and QOS in order to overcome the above issues which also yield low energy consumption, maximum storage and the high level Quality of Service (QoS). Biggest Memory First and Biggest Access First is introduced with NUMA scheduler and cache scheduler for memory scheduling and the optimal VM resulting from the three phases of scheduling is determined by Grey Wolf Optimization (GWO) algorithm. To carry the security level of optimized VMs, Streamline Security and Introspection security analysis are exhausted for detecting the malware VMs which results the secured and efficient VMs for further resource allocation. Our proposed methodology is implemented using the Cloud Sim tool and the experimental result shows the efficiency of our proposed method in terms of security, time consumption, and cost.

 Predicting the peak time load among data center and distributing the load will minimize the usage of the power consumption and also will minimize the carbon emission from data center. Reducing the carbon emission by lessening the energy consumption in a data center will impact on environment which will lead to a reduced carbon footprint. The proposed Water Shower Model (WSM) with Circular Peak Time Services (CPTS) has reduced the execution time to 10 ms comparing with Round Robin Algorithm. The load is shared among the data centers by predicting the type of request by the user as Read Only Request (ROR) or Read Write Request (RWR). The ROR will assign the load to an optimized Container and the RWR will assign the load to a Virtual Machine. CPTS is a proposed model used to measure the carbon emission right from the idle state of the server in a datacenter and till it reaches the peak time of the load and vice versa. The advantage of existing Dynamic Voltage Frequency Scaling (DVFS) techniques is used in the proposed model to optimize the resource allotment and adjust the power and speed in computing devices which allocates only the required minimal amount of power for performing a task.

 The Severe acute respiratory syndrome coronavirus (SARS-CoV) are deadly infectious disease which can easily transmit and causes severe problems in humans. It is known as a coronavirus and referred as a common form of virus that naturally causes upper-respiratory tract illnesses and the symptoms are hard to identify. It is important to recognize the patient and providing them with suitable action with constant intensive care. Healthcare amenities is constructed on fog and big-data based system and it is integrated with cyber-physical system. The role of Cyber physical system in health care domain is to fetch deep insights about the nature of disease and carry the monitoring process with early detection of infected users. The objective is to identify occurrence of SARS at initial stage. In proposed system, resemblance factor is evaluated from the extracted keywords. In order to identify the difference between SARS affected and others, the proposed scheme fetches the inputs from user’s displayed in the form of text. It is passed to deep recurrent neural network (RNN) model. It extracts useful information from the raw information given by the user. The J48graft algorithm is used to carry the classification based on the type of infection and symptoms of each user. The data is stored in the bigdata layer (mongoDB) and it detects the infected area by using the geospatial feature in mongo dB. The methodology is framed in the proposed model to prevent the spread of disease to other users. In case of any abnormality the generation of alert process is done instantaneously and directed on user’s mobile from fog layer. The final experimental outcome reveals information about the performance of proposed system in terms of Success rate, failure rate, latency and accuracy %. It shows that the proposed algorithm gives high level of accuracy when it is compared with other primitive methods.

 Ensemble pruning is usually used to improve classification ability of an ensemble using less number of classifiers, and it is an NP-hard problem. Existing ensemble pruning approaches always find the optimal sub-ensemble using diversity of classifiers or running heuristic search algorithms separately. Diversity and accuracy of classifiers are widely recognized as two important properties of an ensemble. The increase of the diversity of classifiers must lead to the decrease of the average accuracy of the whole classifiers, and vice versa, so there is a tradeoff between diversity and accuracy of classifiers. Finding the tradeoff is the key to a successful ensemble. Heuristic algorithms have good results when it comes to finding the tradeoff, but it is unfeasible to do an exhaustive search. Hence, we propose a Spread Binary Artificial Fish swarm algorithm combined with a Double-fault measure for Ensemble Pruning (SBAFDEP) using a combination of diversity measures and heuristic algorithms. First, the classifiers in an initial pool are pre-pruned using a double-fault measure, which significantly alleviates the computational complexity of ensemble pruning. Second, the final ensemble is efficiently assembled from the retaining classifiers after pre-pruning using the proposed Spread Binary Artificial Fish Swarm Algorithm (SBAFSA). Simulation and experiment results on 25 UCI datasets show that SBAFDEP performs better than other state-of-the-art pruning approaches. It provides a novel research idea for ensemble pruning.

 The acoustic resonance spectroscopy is an accurate, precise, inexpensive, and non-destructive method for identification and quantification of materials. The acoustics based inspection methods used for classification of materials in the field of food, security, and healthcare is constrained by expensive instrumentation, complicated transducer coupling, etc. Hence, a simple, inexpensive, and portable system has been devised that acquires data quickly and classifies the materials. It has two piezoelectric transducers glued to both ends of the V-shaped quartz tube, one acting as a transmitter and another as a receiver. The transmitter generates vibration by white noise excitation. The receiver detects the resultant signal after interaction with samples and recorded the acoustic signal with the help of a laptop and software. From analysis of power spectrum of signals acquired from each of the samples, seven resonant peaks were obtained. PCA analysis was carried out by selecting only two principal components as feature vectors for classification. The overall accuracy of the classifiers: LDA and Naive Bayes were 98.91% and 96.83% respectively. The classification accuracy of LDA for distilled water, sugar solution, and salt solution were found to be 100%, 98.5%, and 98.25% respectively, while the accuracy of the Naive Bayes classifier was 94%, 98.5%, and 98% respectively. The results show that the classification accuracy of LDA is better than Naive Bayes classifier. The datasets of the developed simple system show a significant capability in the classification of materials.

 Intelligent Transportation Systems (ITS) aim at reducing the risks associated with the transportation system as road accidents are becoming one of the primary causes of death in developing countries. Monitoring of driver behavior is one of the key areas of ITS and assists in vehicle safety systems. It has gained importance in order to reduce traffic accidents and ensure the safety of all the road users, from the drivers to the pedestrians. In this work, we present a context-aware system that considers the vehicle, driver and the environment for driver behavior classification as a safe or fatigue or unsafe driver (representing any other unsafe driving behavior like a drunk driver, reckless driver etc.) using a Dynamic Bayesian Network (DBN). We have designed a questionnaire to obtain the influencing factors that decide safe, unsafe and fatigue driving behavior. The collected data has been analyzed using Statistical Package for Social Sciences (SPSS). It has been observed that several techniques in the past have been proposed for driver behavior classification or detection; which either use specialized sensors or hardware devices, inbuilt smartphone sensors (like a gyroscope, accelerometer, magnetometer and GPS etc.), complex sensor fusion algorithms and techniques to detect driver behavior. The novelty of our work lies in designing and developing a context-aware system based on Android smartphone; that considers the complete driving context (driver, vehicle and surrounding environment) and classifies the driver behavior using a DBN. In order to identify driver fatigue, results from the designed questionnaire and previous research studies have been used without the need for special hardware devices. A DBN that combines all the contextual information has been created using GeNIe Modeler. Learning of DBN has been carried out using the Expec-tation–Maximization (EM) algorithm. The real-time data for DBN learning and testing has been collected on Chandigarh-Patiala National Highway, India using an Android smartphone. The proposed system yields an overall classification accuracy of 80–83%.The focus of this paper is to develop a cost-effective context-aware driver behavior classification system, to promote ITS in developing countries.

 Navigation of multiple robots is a challenging task, particularly for many robots, since individual gains may more often than not adversely affect global gain. This paper investigates the problem of multiple robots moving towards individual goals within a common workspace without colliding amongst themselves. Two solutions for coordination namely Fuzzy Logic Controller (FLC) and Genetic Algorithm based FLC (GA-FLC) have been employed and the efficacy of cooperation strategies have been compared with their non-cooperative counterparts as well as with the fundamental potential field method (PFM). Proposed coordination schemes are verified through simulations. A total of 100 scenarios are considered varying the number of robots (8, 12, 16 and 20). The obtained results show the efficacy of the proposed schemes.

 Object detection is a technologically challenging issue, which is useful for safety in outdoor environments, where this object, frequently, represents an obstacle that must be avoided. Although several object detection methods have been developed in recent years, they usually tend to produce poor results in outdoor environments, being mainly affected by sunlight, light intensity, shadows, and limited computational resources. This open problem is the main motivation for exploring the challenge of developing low-cost object detection solutions, with the characteristic of being easily adaptable and having low power requirements, such as the ones needed in on-board obstacle detection systems in automobiles. In this work, we present a trade-off analysis of several architectures using an FPGA-based design that implements ANNs (FPGA-ANN) for outdoor obstacle detection, focused in road safety. The analyzed FPGA-ANN architectures merge outdoor data gathered by a Kinect sensor, images and infrared data, to construct an outdoor environment model for object detection, which allows to detect if there is an obstacle in the near surroundings of a vehicle.

 Cryptography is the most peculiar way to secure data and most of the encryption algorithms are mainly used for textual data and not suitable for transmission data such as images. It is seen that the generation of secure key in Image cryptography has been a challenging task in the way of providing secured key generation for the transmitted data. In order to aid secured key generation in this context, an optimized secret key generation based on Chebyshev polynomial with Adaptive Firefly (FF) optimization technique is proposed. The optimized key is utilized with process of shuffling, diffusion, and swapping to get a better encrypted image. At the receiver end, reverse process is applied with optimized key to retrieve the original input image. The efficiency of our proposed method is assessed by the exhaustive experimental study. The results show that the proposed methodology provided correlation coefficient of 0.21, Number of Pixels Change Rate (NPCR) of 0.996, Unified Average Changing Intensity (UACI) of 0.3346 and Information Entropy of 7.995 as compared with the existing methods.

A cognitive radio (CR) can be programmed and configured dynamically to use best wireless channels. Such a radio automatically detects available channels in wireless spectrum, and then accordingly changes its transmission. The CR system consists of primary user or licensed user and secondary user or unlicensed user. The security attacks such as active attack and passive attack are identified between primary user and secondary user and packet loss occurs during packet transmission. The security problem occurring while transmission of signal between primary user and secondary user is rectified by using a hybrid RSA (Riverest, Shaimer and Adleman) and HMAC (Hash Message Authentication Code) algorithms where former is used for key generation and latter is used for tag generation which is sent along with signal. Additionally packet loss incurred in system incurs is reduced with aid of Markov Chain Model during transmission. The comparison results provided showefficiency of the proposed algorithm in cognitive radio system in terms of parameters such as throughput, encryption time, decryption time, Packet Delivery Ratio and energy consumption.

 The Distributed Generation (DG) systems are highly useful in recent days for increasing the penetration of renewable energy, in which the design of grid connected inverters is one of the demanding and challenging task. For this reason, different controller strategies are developed in the traditional works for controlling the inverters with increased efficiency. But, it has the major limitations of increased computational complexity, steady state error and reduced compensation capability. To solve these issues, this research work aims to design a new controller by implementing a novel Monkey King Evolution Algorithm (MKEA) for grid connected converters. The motive of this work is to increase the overall effectiveness of the power system by controlling the inverter without affecting its output. Also, it aims to provide a secure and convenient controller for the power converters. Here, the information that is obtained from the system which includes real power, distorted power due to load, reactive power of load, and apparent power of inverter are taken as the input. Later, the four numbers of monkeys are initialized, which evaluates the best solution based on these parameters. Sequentially, the monkey king obtains the best solutions from the monkeys, using which the most suitable and best solution for taking the decision is selected. Based on this, the reference current is generated by performing the voltage regulation, and abc to dq0 transformation processes. During simulation, the efficiency of the controller is analyzed by using the measures of phase voltage, phase current, active power, reactive power, apparent power, grid voltage, and output voltage. The Total Harmonic Distortion (THD) is effectively reduced by using the MKEA based controller design. Extensive simulation and experimental results are presented to validate the effectiveness of the proposed controller and control strategy.

 Context aware recommender system has become an area of rigorous research attributing to incorporate context features, thereby increases accuracy while making recommendations. Most of the researches have proved neighborhood based collaborative filtering to be one of the most efficient mechanisms in recommender systems because of its simplicity, intuitiveness and wide usage in commercial domains. However, the basic challenges observed in this area include sparsity of data, scalability and utilization of contexts effectively. In this study, a novel framework is proposed to generate recommendations independently of the count and type of context dimensions, hence pertinent for real life recommender systems. In the framework, we have used k-prototype clustering technique to group contextually similar users to get a reduced and effective set. Additionally, particle swarm optimization technique is applied on the closest cluster to find the contribution of different context features to control data sparsity problem. Also, the proposed framework employs an improved similarity measure which considers contextual condition of the user. The results came from the series of experiments using two context enriched datasets showcasing that the proposed framework increases the accuracy of recommendations over other techniques from the same domain without consuming extra cost in terms of time.

 Shared visual cryptography is a method to protect image-based secrets where an image is kept as multiple shares having less computational decoding process. Steganography is a technique to hide secret data in some carrier like-audio, image etc. Steganography technique is categorized into four categories. i) Spatial Domain Technique- Image pixel values are converted into binary and some of the binary values changed to hide secret data. ii) Transform Domain Technique- the message is hidden in cover image and then it is transformed in the frequency domain. iii) Distortion Technique-information is stored by changing the value of the pixel. iv)Visual Cryptography Technique-Image is broken into two or more parts called shares. This article proposes a hybrid visual crypto-steganography approach which exploits the advantages of both approaches to protect image based secret in communication. Most of the visual cryptography is applied on black and white images but the proposed method can be applied directly on color images having three channels. This method does not change the image size. Also an exact replica of original image can be reconstructed therefore this process does not result in image quality degradation. This article proposes novel color image share cryptography where seven shares are generated from one color image (correlated/de-correlated color space). These shares are sent to the receiver and original image is reconstructed using all those shares. Share generation and image reconstruction is based on simple operation like pixel shuffling, reversing binary string of the image information, ratio of pixel intensity values. Row key matrix and column key matrix are generated using random function. Pixel positions are shuffled using these two key matrixes. These seven shares namely Row Key, Column Key, Remainder matrix, Quotient matrix, R ratio matrix, G ratio matrix and B ratio matrix are generated. Then Row key matrix, Column key matrix, Remainder matrix, Quotient matrix and three ratio matrices are hidden into separate cover images by LSB encoding technique and sent over the network. Receiver can reconstruct the image if all shares are available only. The proposed method is applied on standard images in the literature and images captured using standard digital camera. Comparison study with existing methods shows that the proposed method performs better in terms of NIST metrics. The method has many applications in the area of visual cryptography, shared cryptography, image based authentication etc.

 The importance of the surveillance is increasing every day. Surveillance is monitoring of activities, behavior and other changing information. An intelligent automatic system to detect behavior of the human is very important in public places. For this necessity, a framework is proposed to detect suspicious human behavior as well as tracking of human who is doing some unusual activity such as fighting and threatening actions and also distinguishing the human normal activities from the suspicious behavior. The human activity is recognized by extracting the features using the convolution neural network (CNN) on the extracted optical flow slices and pre-training the activities based on the real-time activities. The obtained learned feature creates a score for each input which is used to predict the type of activity and it is classified using multi-class support vector machine (MSVM). This improved design will provide better surveillance system than existing. Such system can be used in public places like shopping mall, railway station or in a closed environment such as ATM where security is the prime concern. The performance of the system is evaluated, by using different standard datasets having different objects and achieved 95% performance as explained in experimental analysis.

 With the advent of cloud computing, a cost-effective and reliable choice to employ IT infrastructure, the cyber-physical systems (CPS) are transforming into loosely coupled cloud and fog CPS. The sensor information from physical processes at CPS is continuously processed by fog computing nodes and is forwarded for advanced data analytics offered as a service from the cloud. The computation offloaded by fog devices are initiated as Virtual Machines (VMs) in the cloud data center. The effective placement of these VMs into minimum Physical Machines (PMs) involves economic and environmental issues. Recent research works signify the use of First-Fit Decreasing (FFD) based heuristic techniques to address this NP-Hard problem as a vector bin-packing problem. In this research work, we present a set of hybrid heuristics and an ensemble heuristic to improve the solution quality. The simulation results show that the proposed heuristics are highly scalable and economical in comparison with the individual heuristic-based approaches.

 Wireless Sensor Networks (WSNs) are set to play an important role in the Internet of Things (IoT). WSNs are deployed for many IoT applications like Smart-Street Lighting, Smart-Grid, etc. Time Synchronization Protocol (TSP) is an important protocol in WSNs and it is used for many of its operations. Most of the existing TSPs for WSNs are simulation-based works, which do not fully prove their effectiveness for WSNs. Further, the Line-of-Sight (LOS) conditions in which the WSN nodes are deployed can significantly affect the performance of these TSPs. However, most of the existing protocols neither talk about the LOS conditions in which these protocols were tested nor prove their effectiveness for different LOS conditions. To address these aspects, a synchronization protocol for cluster-based WSNs called a Simple Hierarchical Algorithm for Time Synchronization (H-SATS) has been proposed in this work and its performance is tested on a densely deployed large-sized WSN testbed in different LOS conditions. Further, H-SATS has been compared with the traditional regression-based method, which is the core synchronization scheme for different synchronization protocols in clustered WSNs. Experiments show that H-SATS outperforms the regression method in terms of synchronization accuracy to a maximum of 26.7% for a 30-node network.

Education policy makers view measuring academic texts readability and profiling classroom textbooks as a primary task of education management aimed at sustaining quality of reading programs. As Russian readability metrics, i.e. “objective” features of texts determining its complexity for readers, are still a research niche, we undertook a comparative analysis of academic texts features exemplified in textbooks on Social Science and examination texts of Russian as a foreign language. Experiments for 7 classifiers and 4 methods of linear regression on Russian Readability corpus demonstrated that ranking textbooks for native speakers is a much more difficult task than ranking examination texts written (or designed) for foreign students. The authors see a possible reason for this in differences between two processes: acquiring a native language on the one hand and learning a foreign language on the other. The results of the current study are extremely relevant in modern Russia which is joining the Bologna Process and needs to provide profiled texts for all types of learners and testees. Based on a qualitative and quantitative analysis of a text, the research offers a guide for education managers to help build consensus on selecting a reading material when educators have differing views.

 Academic writing is a complex task which requires the author to be skilled in argumentation. The goal of the academic author is to communicate clear ideas and to convince the reader of the presented claims. However, few students are good arguers, and this is a skill difficult to master. Aiming to contribute to develop this skill, we present a freely available annotated corpus to support research in argumentation in Spanish. To build it, we elaborated an annotation guide to identify argumentation in paragraphs. The guide also specified how to determine segments of sentences as a claim or premise, and to indicate relations (support or attack) between such segments. Then, an annotated corpus of 300 sections was created. After its construction, the corpus was used to perform an exploratory analysis which aimed to identify and present the amount of argumentation in each section, as well as resulting patterns for argument identification. Hence, we also report an exploration of lexical features used to model automatic detection of argumentative paragraphs using machine learning techniques. The results of the experiments to evaluate argumentative paragraph detection were encouraging. In addition, we discuss a web-based prototype for argument detection in paragraphs to reach the broader academic community of students, instructors and researchers.

In this paper we present an unsupervised technique for validating the existence of verbal phraseological units in raw text. This technique employs the concept of internal and contextual attraction which basically considers a mathematical formula based on co-occurrence of terms inside and outside of the terms considered to be part of a verbal phraseological unit. The experiments carried out using a corpus of news stories report a 60% of accuracy, which highlights the challenging task of automatic validation of verbal phraseological units in raw texts.

This work introduces a lexical search model based on a type of knowledge graphs, namely word association norms. The aim of the search is to retrieve a target word, given the description of a concept, i.e., the query. This differs from traditional information retrieval models were complete documents related to the query are retrieved. Our algorithm looks for the keywords of the definition in a graph, built over a corpus of word association norms for Mexican Spanish, and computes the centrality in order to find the relevant concept. We performed experiments over a corpus of human-definitions in order to evaluate our model. The results are compared with a Boolean information retrieval (IR) model, the BM25 text-retrieval algorithm, an algorithm based on word vectors and an online onomasiological dictionary–OneLook Reverse Dictionary. The experiments show that our lexical search method outperforms the IR models in our study case.

In this paper, we present an extractive approach to document summarization based on Siamese Neural Networks. Specifically, we propose the use of Hierarchical Attention Networks to select the most relevant sentences of a text to make its summary. We train Siamese Neural Networks using document-summary pairs to determine whether the summary is appropriated for the document or not. By means of a sentence-level attention mechanism the most relevant sentences in the document can be identified. Hence, once the network is trained, it can be used to generate extractive summaries. The experimentation carried out using the CNN/DailyMail summarization corpus shows the adequacy of the proposal. In summary, we propose a novel end-to-end neural network to address extractive summarization as a binary classification problem which obtains promising results in-line with the state-of-the-art on the CNN/DailyMail corpus.

 Confused drug names are a common cause of medication errors, and are related to look-alike and sound-alike drug names. For the problem of identifying confused drug name pairs, individual similarity measures are used between the drug names. In the state-of-art, a logistic regression with the standard learning algorithm has been used to combine individual similarity measures. However, only three similarity measures have been combined but the results of previous research do not outperform with a statistical significance to any individual measure. In addition, the problem of potential confused drug names pairs presents a high unbalanced distribution of dataset that it is a hard problem to supervised machine learning models. In this paper, an improved combined logistic regression measure based on 21 individual measures is presented with the standard learning algorithm. Also, we present an evolutionary learning method for a combined logistic regression measure that allows to learn an unbalanced dataset. According to the experimentation with a gold standard dataset, our proposed combined measures outperform previous research with a statistical significance to identify pairs of confused drug names. In addition, the rankings of individual and combined similarity measures are presented.

Text Line Segmentation (TLS) methods are intended to locate and separate text lines in document images for different stages of image analysis such as word spotting, keyword search, text alignment, text recognition and other stages of indexation involved in the retrieval of information from handwritten documents. The design of the proposed methods for the TLS and the tuning of their parameters assume a level of complexity according to the language and the writing style of a document collection. Therefore, the performance of these methods is not maintained against documents of greater or lesser complexity. In this paper, we present TLS-ICI, a TLS Intrinsic Complexity Index that allows measuring the complexity of a document for the TLS task, without the necessity of a human gold standard. Through experimentation, we demonstrate how our proposed TLS-ICI provides an order to both the TLS methods and the image-based handwritten documents. In this way, with our proposed complexity index it is possible to select the most appropriated method for each document of a collection, reducing the time spent in exhaustive tests and increasing the performance. In addition, we demonstrate through a new hybrid TLS method that the TLS-ICI outperforms previous individual TLS methods. The dataset consists of several standard TLS collections of contemporary and ancient texts from different languages and alphabets such as English, Spanish, Arabic, and Chinese, Greek, Khmer, Persian, Bengali, Oriya, Kannada and Nahuatl.

The rapid growth in the extraction of clinical events from unstructured clinical records has raised considerable challenges. In this paper, we propose the use of different features with a statical modeling method called conditional random fields, which is consider an algorithm for effectively solving problems of sequence tagging. Our goal is to determine which feature selection can affect the performance of four subtasks presented in SemEval Task-12: Clinical TempEval 2016. We applied a careful preprocessing, where the proposed method was tested on real clinical records from Task-12: Clinical TempEval 2016. The comparative analyses obtained indicate that our proposal achieves good results compared to the work presented in Task-12: Clinical TempEval 2016 challenges.

 Detection of topics in Natural Language text collections is an important step towards flexible automated text handling, for tasks like text translation, summarization, etc. In the current dominant paradigm to topic modeling, topics are represented as probability distributions of terms. Although such models are theoretically sound, their high computational complexity makes them difficult to use in very large scale collections. In this work we propose an alternative topic modeling paradigm based on a simpler representation of topics as overlapping clusters of semantically similar documents, that is able to take advantage of highly-scalable clustering algorithms. Our Query-based Topic Modeling framework (QTM) is an information-theoretic method that assumes the existence of a “golden” set of queries that can capture most of the semantic information of the collection and produce models with maximum “semantic coherence”. QTM was designed with scalability in mind and was executed in parallel using a Map-Reduce implementation; further, we show complexity measures that support our scalability claims. Our experiments show that the QTM can produce models of comparable or even superior quality than those produced by state of the art probabilistic methods.

This paper tries to map the research work carried out in the field of Big Data through a detailed analysis of scholarly articles published on the theme during 2010-16, as indexed in Scopus. We have collected and analyzed all relevant publications on Big Data, as indexed in Scopus, through a quantitative as well as textual characterization. The analysis attempts to dwell into parameters like research productivity, growth of research and citations, thematic trends, top publication sources and emerging topics in this field. The analytical study also investigates country-wise publications output and impact in terms of average citations per paper, country-level collaboration patterns, authorship and leading contributors (countries, institutions) etc. The scholarly publication data is also subjected to a detailed textual analysis method to identify key themes in Big Data research, disciplinary variations and thematic trends and patterns. The results produce interesting inferences. Quantitative measures show that there has been a tremendous increase in number of publications related to Big Data during last few years. Research work in Big Data, though primarily considered a sub-discipline of Computer Science, is now carried out by researchers in many disciplines. Thematic analysis of publications in Big Data show that it’s a discipline involving research interest from fields as diverse as Medicine to Social Sciences. The paper also identifies major keywords now associated with Big Data research such as Cloud Computing, Deep Learning, Social Media and Data Analytics. This helps in a thorough understanding and visualization of the Big Data research area.

 Similarity searching is the core of many applications in artificial intelligence since it solves problems like nearest neighbor searching. A common approach to similarity searching consists in mapping the database to a metric space in order to build an index that allows for fast searching. One of the most powerful searching algorithms for high dimensional data is known as the permutation based algorithm (PBA). However, PBA has to collect the most similar permutations to a given query’s permutation. In this paper, how to speed up this process by proposing several novel hash functions for Locality Sensitive Hashing (LSH) with PBA is shown. As a matter of fact, at searching our technique allows discarding up to 50% of the database to answer the query with a candidate list obtained in constant time.

Scientific documents, which are majorly constituted of math formulae, form a primary source of scientific and technical information. However, the indexing and the search processes of conventional search engines barely account for mathematical contents of such documents. Though the recent past has witnessed a surge in number of Mathematical Information Retrieval (MIR) systems intending to retrieve math formulae from scientific documents, the low values of their evaluation measures are indicative of the scope for improvement. To cope with the challenges of MIR, and to further the performance of state-of-the-art systems, a novel approach, called Binary Vector Transformation of Math Formula (BVTMF), is introduced. The implemented system extracts MathML formulae from the documents, preprocesses them, and renders them into fairly large-sized binary vectors (vectors of ‘0’s and ‘1’s). Generated formula vector is representative of the information content of corresponding formula. For indexing and searching text contents, the system relies on Apache Lucene. Text and math search results retrieved by independent text and math sub-systems are re-ranked to prioritize the results containing text as well as math components of the user query. Quality of the retrieved search results and appreciable values of the evaluation measures substantiate competence of the proposed approach.

Natural Language Processing problems has recently been benefited for the advances in Deep Learning. Many of these problems can be addressed as a multi-label classification problem. Usually, the metrics used to evaluate classification models are different from the loss functions used in the learning process. In this paper, we present a strategy to incorporate evaluation metrics in the learning process in order to increase the performance of the classifier according to the measure we are interested to favor. Concretely, we propose soft versions of the Accuracy, micro-F₁, and macro-F₁ measures that can be used as loss functions in the back-propagation algorithm. In order to experimentally validate our approach, we tested our system in an Emotion Classification task proposed at the International Workshop on Semantic Evaluation, SemEval-2018. Using a Convolutional Neural Network trained with the proposed loss functions we obtained significant improvements both for the English and the Spanish corpora.

Emotions, which are now commonly portrayed in social media, play a fundamental role in decision making. Having this into account, this work proposes a model to predict (forecast) emotions in social networks. This model specifically predicts, for a user, the proportion of comments that will be published with a particular emotion; this proportion is defined as an emotional intensity of the user in a particular time period. On the contrary of other models, which are focused on a single emotion, the proposed model considers a basic scheme of four emotions and employs these in an interdependent manner. The model, moreover, utilizes three types of features: (1) user-related, (2) contact-related, and (3) environment-related. Prediction is performed using linear regression. Nearly 20 models, including ARIMA, are outperformed by the proposed model (with statistically significant results) when evaluated over a dataset extracted from Twitter. Some potential applications include massive opinion monitoring and recommendations to improve the emotional wellness of social media users (for example, the recommendation of joyful memories).

E-commerce websites provide an easy platform for users to put forth their viewpoints on different topics-ranging from a news item to any product in the market. Such online content encourages authors to express opinions on various aspects of an entity. Aspect based sentiment analysis deals with analyzing this textual content to look for the aspect in question. After locating the aspects, corresponding sentiment bearing words are looked for. This paper describes an integrated system that generates the opinionated aspect based graphical and extractive summaries from a large set of mobile reviews. The system focuses on three tasks (a) identification of aspects in given field, (b) computation of sentiment polarity of each aspect, and (c) generates opinionated aspect based graphical and extractive summaries. The system has been evaluated on three mobile-reviews dataset and obtains better precision and recall than baseline approach. The system generates summaries from reviews without any training.

Online user reviews play an important role in the assessment of product quality, and thus these reviews should be evaluated carefully. This study evaluates the helpfulness of game reviews on the online Steam store. It collects a large set of user reviews of different game genres and builds a classification model to predict whether these reviews are helpful or not. This model can accurately predict the helpfulness of the reviews based on different thresholds. This work also investigates various types of textual and word embedding features and analyzed their importance for predictions. Furthermore, it develops a regression-based model that can predict the score or rating of game reviews on Steam.

 Patriarchal behavior, such as other social habits, has been transferred online, appearing as misogynistic and sexist comments, posts or tweets. This online hate speech against women has serious consequences in real life, and recently, various legal cases have arisen against social platforms that scarcely block the spread of hate messages towards individuals. In this difficult context, this paper presents an approach that is able to detect the two sides of patriarchal behavior, misogyny and sexism, analyzing three collections of English tweets, and obtaining promising results.

In this paper an analysis, based on similarity metrics, was carried out in order to detect main concepts related to the superclasses in a pedagogical domain ontology. A semi-automatic corpus containing articles in Spanish was built. Afterward, the corpus was lemmatized and three representations were extracted. Four textual similarity metrics based on terms and Pointwise Mutual Information were implemented. A list of words, which was evaluated using a gold standard built by an expert in the domain, was retrieved from each experiment according to establish thresholds for the metrics. Precision and recall were used for evaluation step, where a detailed discussion by representation and class was presented. Results showed a higher precision in types of intelligences class and 5-grams representation.

 The coffee rust is a devastating disease that causes large economic losses across the world. The severity of this disease changes over time so the farmers are not fully aware of the economic importance of the rust disease in the coffee crops. From a computational science perspective, several investigations have been proposed to decrease the effects caused by the coffee rust appearance from Expert systems based on machine learning techniques. However, because samples about coffee rust incidence are few, the rules created from machine learning techniques do not contain enough information to consider the diversity of scenarios for detecting coffee rust. This paper proposes an expert system based on rules, where the rules are created considering the expert knowledge of specialists and technical reports about the behavior of the disease during a crop year. As far as we know, this is the first expert system proposed using not only expert knowledge but also technical reports in the coffee rust problem. The Buchanan methodology is used to design the proposed system. Experiment results present an average accuracy of 66,67% to detect a correct warning of coffee rust levels.

The constant increase in the production of scientific literature is making it very difficult for experts to keep up to date with the state-of-the-art knowledge in their fields. The use of Natural Language Processing (NLP) is becoming a necessary aid to tackle this challenge. In the NLP field, the task of measuring semantic similarity between two sentences plays a vital role. It is a cornerstone for tasks like Q&A, Information Retrieval, Automatic Summarization, etc., and it is a crucial element in the ultimate goal of computers being able to decode what is conveyed in human language expression.

Measuring Semantic Similarity (SS) in short texts has specific challenges. Because there are fewer words to be compared, the meaning contribution of each word is more relevant, and it is important to take into account the syntax’s contribution to the composed meaning. In addition, the highly specific and specialized vocabulary — Microbial Transcriptional-Regulation—implies the lack of massive training resources. Our approach has been to use an ensemble of similarity metrics including string, distributional, and knowledge-based metric and to combine the results of such analyses. We have trained and tested these methods in a similarity corpus developed in-house.

The task has proved very challenging, and the ensemble strategy has proved to be a good approach. Even though there is still much room for improvement in the precision of our methods concerning the human evaluation, we have managed to improve them reaching a strong correlation (ρ = 0.700).

 Caption generation requires best of both Computer Vision and Natural Language Processing. Due to recent improvements in both of them many efficient models have been developed. Automatic Image Captioning can be utilized to provide descriptions of website content or to engender frame-by-frame descriptions of video for the vision-impaired and in many such applications. In this work, a model is described which is utilized to generate novel image captions for a previously unseen image by utilizing a multimodal architecture by amalgamation of a Recurrent Neural Network (RNN) and a Convolutional Neural Network (CNN). The model is trained on Microsoft Common Objects in Context (MSCOCO), an image captioning dataset that aligns captions and images in the same representation space, so that an image is close to its relevant captions in that space and far away from dissimilar captions and dissimilar images. ResNet-50 architecture is used for extracting features from the images and GloVe embeddings are used along with Gated Recurrent Unit (GRU) in Recurrent Neural Network (RNN) for text representation. MSCOCO evaluation server is used for evaluation of the machine generated caption for a given image.

 This work focuses on bolstering the pre–existing Interpretable Semantic Textual Similarity (iSTS) method, that will enable a user to understand the behaviour of an artificial intelligent system. The proposed iSTS method explains the similarities and differences between a pair of sentences. The objective of the iSTS problem is to formalize the alignment between a pair of text segments and to label the relationship between the text fragments with a relation type and relatedness score. The overall objective of this work is to develop a 1:M multi chunk aligner for an iSTS method, which is trained on SemEval 2016 Task 2 dataset. The obtained result outperforms many state–of–art aligners, which were part of SemEval 2016 iSTS task.

Word reordering is an important problem for translation between languages which have different structures such as Subject-Verb-Object and Subject-Object-Verb. This paper presents a statistical method for extraction of linguistic rules using chunk to reorder the output of the baseline statistical machine translation system for improved performance. The experiments are based on the TDIL sample tourism corpus of English-Hindi language pair which consists of 1000 sentence pairs out of which 900 sentence pairs are used for training, 50 sentences for tuning and 50 sentences for testing. Finally, the output of the machine translation system, augmented by these rules, is evaluated by using BLEU and NIST metrics. The BLEU score improves by more than 2% in comparison to the baseline SMT system. The results are compared with those of Google translation system which has been trained on a huge corpus. We got a 0.1 point improvement in terms of NIST score, in comparison to Google Translation. Thus, we have comparable results with such a small corpus of 900 sentence pairs for training. This paper is an effort to improve the performance of SMT with a small corpus by using linguistic rules where the rules are automatically generated instead of made by linguist.

One of the most challenging research problems in natural language processing (NLP) is that of word sense induction (WSI). It involves discovering senses of a word given its contexts of usage without the use of a sense inventory which differentiates it from traditional word sense disambiguation (WSD). This paper reports a work on sense induction in Bengali, a less-resourced language, based on distributional semantics and translation based context vectors learned from parallel corpora to improve the task performance. The performance of the proposed method of sense induction was compared with the k-means algorithm, which was considered as the baseline in our work. A dataset for sense induction was created for 15 Bengali words, encompassing a total of 111 contexts. The proposed model, in both mono and cross-lingual settings, outperformed k-means in precision (P), recall (R) and F-scores. K-means based sense induction produced average P, R and F-scores of 0.71, 0.73 and 0.66 respectively. The average P, R and F-scores produced by the mono-and cross-lingual settings of the proposed algorithm are 0.77, 0.73, 0.68 and 0.81, 0.77 and 0.72 respectively.

The process of automatic identification of an author’s demographic traits like gender, age, native language, geographical location, personality type and others from his/her written text is termed as author profiling (AP). Currently, it has engaged the research community due to its promising uses in security, marketing, forensic, bogus account identification on public networks. A variety of benchmark corpora (English text) released by PAN shared task is used to perform our experiments. This study presents a Content-based approach for detection of author’s traits (age group and gender) for same-genre author profiles. In our proposed method, we used a different set of features including syntactic n-grams of part-of-speech tags, traditional n-grams of part-of-speech tags, the combination of word n-grams and combination of character n-grams. We tried a range of classifier for several profile sizes. We used the word uni-grams and character tri-grams as our baseline approaches. We achieved best accuracy of 0.496 and 0.734 for both traits, i.e., age group and gender respectively, by applying the combination of word n-grams of various sizes. Experimental results signify that the combination of word n-grams can produce good results on benchmark corpora.

We present a method for gender and language variety identification using a convolutional neural network (CNN). We compare the performance of this method with a traditional machine learning algorithm – support vector machines (SVM) trained on character n-grams (n = 3–8) and lexical features (unigrams and bigrams of words), and their combinations. We use a single multi-labeled corpus composed of news articles in different varieties of Spanish developed specifically for these tasks. We present a convolutional neural network trained on word- and sentence-level embeddings architecture that can be successfully applied to gender and language variety identification on a relatively small corpus (less than 10,000 documents). Our experiments show that the deep learning approach outperforms a traditional machine learning approach on both tasks, when named entities are present in the corpus. However, when evaluating the performance of these approaches reducing all named entities to a single symbol “NE” to avoid topic-dependent features, the drop in accuracy is higher for the deep learning approach.

 Author Profiling (AP) aims at predicting specific characteristics from a group of authors by analyzing their written documents. Many research has been focused on determining suitable features for modeling writing patterns from authors. Reported results indicate that content-based features continue to be the most relevant and discriminant features for solving this task. Thus, in this paper, we present a thorough analysis regarding the appropriateness of different distributional term representations (DTR) for the AP task. In this regard, we introduce a novel framework for supervised AP using these representations and, supported on it. We approach a comparative analysis of representations such as DOR, TCOR, SSR, and word2vec in the AP problem. We also compare the performance of the DTRs against classic approaches including popular topic-based methods. The obtained results indicate that DTRs are suitable for solving the AP task in social media domains as they achieve competitive results while providing meaningful interpretability.

 We present a new resource to analyze and detect deceptive information that is present in a huge amount of news websites. Specifically, we compiled a corpus of news in the Spanish language extracted from several websites. The corpus is annotated with two labels (real and fake) for automatic fake news detection. Furthermore, the corpus also provides the category of the news, presenting a detailed analysis on vocabulary overlap among categories. Finally, we present a style-based fake news detection method. The obtained results show that the introduced corpus is an interesting resource for future research in this area.

 It is increasingly common for internet users to have access to blogs and social networks, and common for them to express opinions on such sites. This research work is framed within the scope of opinion mining. Opinions allow us to measure people’s perception of a specific topic or product. Knowing the opinion that a person has towards a product or service is of great help for decision making, since it allows, between other things, that potential consumers to verify the quality of the product or service before using it. This research work is framed within the scope of opinion mining.

When the number of opinions is very large the analysis gets more complicated and generally resort to tools that allow this task to be performed automatically are sought out. The present work performs an automatic categorization of textual opinions corresponding to four products: books, DVDs, kitchens, and electronics. Both negative and positive opinions are considered for the experiment. Further categorization experiments are performed using different domains of learning. The basic idea is to investigate if we can undertake classification of opinions, positive and negative, of any given domain using instances of training from a different domain. Results obtained from different methods of learning are presented. The results obtained allow us to examine the feasibility of the proposed methodology.

In spite of having been investigated for over fifty years, developing a robust spoken dialog management system remains an open research issue in robotics and natural language processing. In this paper, we present a language-independent spoken dialog management module integrated into a human-robot interaction system. We adopt an algorithmic approach to dialog modeling. A mobile robot functioning as a shopping assistant exemplifies the proposed approach. The dialog module is composed of a state transition network, in which state switches are conditioned by both visual and communicative factors. We use the formalism of a finite state automaton, where the robot changes its state by performing a speech act or a non-verbal action from the set of specified act/action types.

 In this paper we propose an aggregation strategy for geolocated Twitter posts based on a hierarchical definition of the regular activity patterns within a specific region. The aggregation yields a series of documents that are used to train a topic model. The resulting model is tested against the ones produced by two other aggregation strategies proposed in the literature: aggregation by user and by hashtag. For comparison, we use quality metrics widely used on the literature. The results show that the Geographical Aggregation performs similarly to hashtag aggregation in terms of Jensen-Shannon Divergence and outperforms other aggregation schemes in its ability to reproduce the original cluster labels. One potential application behind this is the discovery of unusual events or as a basis for geolocating messages from text.

Given a question, a reference answer, and the answer given by the student, the aim of the automatic short answer grading task is to assign a grade to the student’s answer. We use for this a large number of matching rules relying on recognizing entailment relation between dependency structures of the two answers. Comparison of the grades generated by our method with those given by human judges on a computer science dataset shows a quite promising maximum correlation of 0.627.

 User generated data in social networks is often not written in its standard form. This kind of text can lead to large dispersion in the datasets and can lead to inconsistent data. Therefore, normalization of such kind of texts is a crucial preprocessing step for common Natural Language Processing tools. In this paper we explore the state-of-the-art of the machine translation approach to normalize text under low-resource conditions. We also propose an auxiliary task for the sequence-to-sequence (seq2seq) neural architecture novel to the text normalization task, that improves the base seq2seq model up to 5%. This increase of performance closes the gap between statistical machine translation approaches and neural ones for low-resource text normalization.

There are many problems were the objects under study are described by mixed data (numerical and non numerical features) and similarity functions different from the exact matching are usually employed to compare them. Some algorithms for mining frequent patterns allow the use of Boolean similarity functions different from exact matching. However, they do not allow the use of non Boolean similarity functions. Transforming a non Boolean similarity function into a Boolean one, and then applying the previous algorithms for mining frequent patterns, could lead to loss some patterns, and even more to generate some other patterns which indeed should not be considered as frequent similar patterns. In this paper, we extend the similar frequent pattern mining by allowing the use of non Boolean similarity functions. Several properties for pruning the search space of frequent similar patterns and a data structure that allows computing the frequency of patterns candidates, are proposed. Also, three algorithms for mining frequent patterns using non Boolean similarity functions are proposed. Experimental results show the efficiency and efficacy of the algorithms. The proposed algorithms obtain better patterns for classification than those patterns obtained by traditional frequent pattern miners, and miners using Boolean similarity functions.

In supervised classification if one of the classes has fewer objects than the other, we have a class imbalance problem. One of the most common solutions to address class imbalance problems is oversampling, and SMOTE is the most referenced and well-known oversampling method. However, SMOTE creates synthetic objects in a random way, therefore it produces a different result each time it is applied, and in practice the user has to apply SMOTE several times for choosing the best of all the generated balanced datasets. For this reason, in this paper, we present SMOTE-D, a deterministic version of SMOTE, and propose new deterministic SMOTE-D-based versions of some of the most recent and successful SMOTE-based methods. In our experiments, we show that all proposed deterministic methods produce as good results as random methods but our proposals need to be applied just once. This is very important from a practical point of view since our proposals save time by avoiding multiple applications of them as SMOTE does and they provide one unique result.

 Optimization algorithms are important in problems of pattern recognition and artificial intelligence, i.e., the image recognition, face recognition, data analysis, optical recognition, etc. Estimation distribution algorithms (EDAs) is kind of optimization algorithms based on substituting the crossover and mutation operators of the Genetic Algorithms by the estimation and later sampling the probability distribution learned from the selected individuals. However, a weakness of these algorithms is the efficiency in terms of the number of evaluations of the fitness function. In this paper, a Cellular Gaussian Estimation Algorithm (CEGA) for solving continuous optimization problems is proposed. CEGA is derived from evidence-based learning of independence and decentralized schemes of local populations. The experimental results showed that the present proposal reduces the number of evaluations of the fitness function in the search for optimums, maintaining its effectiveness in comparison to other algorithms of state-of-art using the same benchmark of continuous functions.

 Due to the development of modern internet-based technology, the electronically stored information is growing exponentially with time. It is highly challenging to select relevant and non-redundant features of the real-valued high dimensional datasets. Feature selection, a preprocessing technique, refers to the process of reducing the dimension of the input data in order to extract the most meaningful features for processing and analysis. One of the numerous useful applications of rough set theory is the attribute or feature selection, but it has certain limitations as it cannot be applied on real-valued data sets directly because rough set based feature selection can handle discrete data only. In order to deal with real-valued data sets, discretization method is applied to convert dataset from real-valued to discrete, which usually leads to information loss. Fuzzy rough set theory is profitably applied to address this problem and retain the semantics of real-valued datasets. However, intuitionistic fuzzy set can deal with uncertainty in a much better way when compared to fuzzy set theory as it considers membership, non-membership and hesitancy degree of an object simultaneously. In this paper, an intuitionistic fuzzy rough set model is established by combining intuitionistic fuzzy set and rough set. Furthermore, we propose a novel approach of feature selection derived from this model. Moreover, we develop an algorithm based on our proposed concept. Finally, our approach is applied to some benchmark data sets and compared with the existing fuzzy rough set based technique. The performed experiments show the superiority of our approach.

Hieroglyph retrieval has emerged as a tool to facilitate and support the cultural heritage preservation. For this task, hieroglyphs should be represented according its visual content. In the literature, the Bag of Visual Words (BoVW) model has been widely used for representing hieroglyphs with retrieval purposes. One crucial step in the BoVW model consists in replacing each local descriptor, obtained from a hieroglyph, by its nearest visual word in the vocabulary. However, it may result in similar local descriptors replaced by different visual words. Thus, the similarity of these local descriptors is lost. In this work, this problem is addressed by replacing each local descriptor by its k-nearest visual words in the vocabulary, instead of just one visual word (the nearest). Considering this multiple replacement, we introduce a hieroglyph representation that takes into account the frequency of the visual words and the co-occurrence of visual word pairs. Our experiments show that our proposed hieroglyph representation allows obtaining better retrieval results than those obtained by using state of the art representations.

In this work, we propose a practical approach to access and visualize relevant information on the spatial distribution on the anything sample about its biochemical composition. In order to carry out this analysis, we use a Raman spectroscopy technique to obtain spectral maps with specific spatial resolution (1 and 5 micrometers) over a selected region of the sample. Our study relies on the application of a Principal Component Analysis on the cross-correlations between the spectral blocks measured, within a certain spectral window of interest. The associated values of these principal components are used to build low-resolution images (with the same spatial resolution of the Raman scan) in which the relevant information on the chemical composition is already encoded. Finally, the spatial resolution of the principal components images was numerically enhanced in the post-processing through standard linear interpolation algorithms. In this way, we can map and visualize, simultaneously, the spatial and spectral information. The results suggest that the Raman spectroscopy imaging is a powerful tool for determining the biochemistry of organic and inorganic samples based on spectral scanning and thus determine compounds concentrations of medical interest. The proposed methodology is rather general and it could be extended to other spectroscopic measurement techniques where the spatial mapping of the spectral information is needed.

Human communication has been studied from different approaches and resulting in contributions to several disciplines. From the computer sciences point of view, the findings made in the area have inspired the development of Natural User Interfaces (NUI), interaction mechanisms aimed at replicating the way in which people communicate, so the information exchange with computational systems happens in similar fashion. Gestural interfaces are a specific type of NUI focused on analyzing the relationship between body motion and semantic meanings. Although, from a technical perspective, proposals found in the literature had proven high efficiency and accuracy on gestural recognition, several authors had reported lack of naturalness in the interaction with gesture-based applications, leading to the conclusion that NUIs are not usually as natural as they claim to be. Moreover, gestures are culture and language specific, which makes them ambiguous, incompletely specified, and difficult to match with semantic meaning when the context is unknown. In this paper, we propose a methodology for enabling the development of gesture-based applications, considering that accuracy and efficiency in recognition tasks must not be affected, and prioritizing the flexibility for allowing the use of gestures that are suitable for different user contexts through the exploration of user-defined gesture sets and Machine Learning techniques, and using a one-shot learning approach.

 Work is needed to advance the current understanding of tactile interaction among humans through haptic technologies. We introduce a novel language that has been designed to guide users in leader-follower dances. This language is based on a nine-word vocabulary that corresponds to nine dance steps, following the metaphor of a leader-follower dance. Our work benefits from a haptic coding that is commonly used by couples when dancing, and explores the potential of wearable technology in this scenario. A wearable prototype consisting of four vibrotactile actuators was used to test the idea. Two user studies show a high recognition rate (more than 90%) of the intended tactile vocabulary. This particular work highlights the feasibility of a haptic vocabulary to exchange full, understandable commands between users, the importance of dance as a case study, and the potential of using wearable technology to support haptic communications in scenarios similar to those in the real world, such as partner dancing. Current results show it is viable to successfully guide someone to follow dance through communication using a basic vibrotactile language.

 One of the drawbacks of the current revolution on media is that tampering with images and videos is an increasingly easy task which brings a situation where digital media cannot be trusted. Digital video forensics study the effects of attacks and tampering techniques on videos and has arisen as a solution to the problem of lack of trustworthiness on digital media. Copy-Move tampering is one of the most common attacks, with variants for delete and duplicate objects in videos, and has been studied in several video forensics works with different approaches. Despite that, there is not yet a simple method to determine multiple variants of Copy-Move attacks. This work proposes a simple yet effective method do detect Copy-Move for both subregion and full-frame duplication.

In human-computer interaction the automatic face sensing and recognition of facial expressions is still a challenging task of affective computing, psychology and biomedical applications. The main goal of this paper is to increment a recognition rate of approaches for unobtrusive face sensing and automatic interpretation of emotions. The proposed approach explores local scale invariant feature transform descriptors for extraction of face key points used for face detection, recognition and then for encoding facial deformations in terms of Ekman’s Facial Action Coding System (FACS). Real-time face tracking and recognition is provided by quadratic discriminant analysis and Bayesian approaches as classification tools. Based on detected fiducial points, the accurate automatic recognizing six prototypical human facial expressions as well as detecting affective states in real-time scenes is provided by fuzzy inference system based on the proposed reasoning model. Carried out experiments demonstrate that Ekman’s FACS traditionally used in affective computing may be extended to interpretation of non-prototypical compound emotions using Plutchik psychological model of emotional responses. Conducted tests with faces from standard databases confirm that the proposed approaches for analysis of local image features provide robust, quite accurate, fast and low computational cost face sensing and facial expression interpretation.

 The barking and other vocalizations of the domestic dog are an exciting source of information. Studies in the area of ethology have analyzed their function and the way humans and conspecifics perceive them. Without a doubt, better understanding the nature of barking can bring benefits both, to improve the welfare of dogs, and for humans who can build systems that take advantage of the information extracted from vocalizations for applications, such as, security, assistance, and entertainment. To develop automatic systems for the analysis of domestic dog vocalizations, we need to have acoustic characterization methods that allow capturing the most relevant properties of barking and thereby improving the performance of automatic classifiers. In this paper, a comparison between several acoustic characterization techniques is made to determine their relevance in the classification of two aspects of the barking, which are the context in which they were generated and the identity of the dog that emitted the bark. We classified the tested acoustic features as qualitative and quantitative. The quantitative are derived from the processing of low-level acoustic descriptors and have been used most widely in audio analysis. The qualitative ones are a type of acoustic that capture aspects related to the perception of the melody of the vocalizations and had not been previously tested in this field of application.

 Inverse parameterizations of length 12 orthogonal wavelet filters are presented, which allow to determine parameter values from filter coefficients. Its applicability is shown in a case of study of image processing where the optimization of five parameters is required. The parameterization of length N filters involves N 2 - 1 parameters, and it is easier to optimize shorter filters once they explore a subset of the search space. Under this approach, the optimization of length 12 filters is accelerated based on a nested optimization of length 4, 6, 8, and 10 filters by exporting the best solutions from shorter to larger filters via inverse parameterizations. Experimental results support the success of the nested optimization when exploring the search space. The conclusions are that the use of the inverse formulas accelerates the convergence and that parameterized filters provide better results as their length increases and achieve a better performance than standard filters.

 In this paper, we present a comparative analysis of two selection policies in the General Game Playing (GGP) context: Upper Confidence Bound (UCB) and Upper Confidence Bound Tuned (UCB-Tuned). The aim of the analysis is to identify which policy has the best performance in terms of victories in the GGP domain, a measure used in most of literature with other policies. In order to carry out the comparison, two agents were programmed using the GGP-base framework and the Monte Carlo Tree Search (MCTS) method. The games Breakthrough, Knightthrough and Connect Four were used as experimental scenarios, not compared previously to the best of our knowledge. The results show that UCB-Tuned is better when less than 100 simulations are used in MCTS; however, when 1000 simulations are used, both policies have similar performance.

 Previous research studied a problem of data collection in complex networks with failure-prone components using mobile agents and two movement strategies: random and a pheromone-based algorithm. As a main conclusion, a fast data collection implies higher robustness and success rates. In some scale-free networks with a higher standard deviation in the betweenness centrality, random exploration was faster than a pheromone-based algorithm because mobile agents remain re-exploring nodes for more time. This paper presents an improvement to selected movement algorithms to collect data in complex networks in a faster way. The proposed improvement consists of local marks in nodes to avoid re-exploration combined with the previously proposed algorithms. Experiments were performed with different failures rates. Results show that there is a significant difference between the pheromone algorithm with and without local marks providing a higher robustness in data collection tasks in scenarios with a higher standard deviation in the betweenness centrality. Possible applications include data-collection and retrieval in distributed environments like Internet of Things environments (IoT) as well as farms, clusters and clouds.

 Temporal expressions describing the so-called Allen’s relations between intervals are broadly exploited in Artificial Intelligence and engineering, for example, in a system specification. They may be formally rendered in terms of Halpern-Shoham logic. If these expressions are combined with some expressions describing differents obligations or permissions, then we need a kind of a deontic Halpern-Shoham logic to represent the combinations. If also obligations are gradable and they introduce a kind of a fuzziness, then a new multi-valued (fuzzy) deontic logic should be expected. According to it – a multi-valued deontic Halpern-Shoham logic is proposed in the paper. Its combined formulae are interpreted in the interval-based fibred semantics, which consitutes a modification of the pioneering ideas of Gabbay’s fibred semantics.

Service Robots should be able to reason about preferences when assisting people in common daily tasks. This functionality is useful, for instance, to respond to action directives that conflict with the user’s interest or wellbeing or when commands are underspecified. Preferences are defeasible knowledge as they can change with time or context, and should be stored in a non-monotonic knowledge-base system, capable of expressing incomplete knowledge, updating defaults and exceptions dynamically, and handling multiple extensions. In this paper a knowledge-base system with such an expressive power is presented. Non-monotonicity is handled using a generalization of the Principle of Specificity, which states that in case of knowledge conflict the most specific proposition should be preferred. Reasoning about preferences is used on demand through conversational protocols that are generic and domain independent. We describe the general principles underlying such protocols and their implementation through the SitLog programming language. We also show a demonstration scenario in which the robot Golem-III assists human users using such protocols and preferences stored in its non-monotonic knowledege-base service.