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

Microarray technologies help to observe the expression levels of thousands of genes. Analysis of gene expression data arising from these experiments provides insight into different subtypes of diseases and functions of genes. Gene expression data are characterized by a large number of genes and a few samples. Employing traditional supervised classifiers for prediction requires adequate labeled data. However, the limited number of samples make the prediction of disease subtypes a difficult task. Hence, we investigate the potential of semi-supervised learning to delineate the tissue samples from a few labeled data. The available labeled samples were exploited to guide the clustering of unlabeled samples. A classification system by integrating feature selection techniques with semi-supervised fuzzy c-means algorithm was built. The system was evaluated using publicly available gene expression datasets and results showed that a few labeled tissue samples can assist in the accurate prediction of disease subtypes.

In machine learning based disease diagnosis, extraction of relevant and informative features from medical image slices is vital aspect. Extracted features represent the descriptive nature of the imaging modality for machine learning. Texture description, is one such method which is used to extract the informative aspect of the object. In this paper a new texture based feature extraction algorithm is proposed for extracting relevant and informative features from brain MR Images having tumor. Suggested algorithm is based on finding the texture description using nine different variants of texture objects. Subsequently, the intermediate texture index matrix is formed using texture objects with high pass and low pass spiral filters. The resultant two index matrix are used to generate the Texture Co-occurrence Matrix (TOM). TOM helps to extract the spatial and spectral domain features that forms the hybrid feature set for brain MRI classification. Using TOM, an experimentation is performed with a dataset of 660 T1-weighted post contrast brain MR Images having 5 different types of malignant tumors. Experimental results suggest that proposed method gives significant results in abnormality classification when compared with state-of-art GLCM and Run length algorithms.

Breast cancer is one of the most commonly occurring cancers among women globally. The accurate detection and classification of the abnormalities such as masses and microcalcifications in mammograms is a challenging task for the radiologist without which the survival rate of the breast cancer patients may increase worldwide. This paper presents a novel Computer Aided Diagnosis (CAD) system which uses Cellular Neural Network (CNN) technique, which is optimized using Particle Swarm Optimization (PSO) for detection and Particle Swarm Optimised Probabilistic Neural Network (PSOPNN) for the classification of breast masses as benign or malignant. The breast mass texture feature extraction is carried out using Gray Level Co-occurrence Matrix (GLCM) and the optimal texture features are selected using a particle swarm optimized feature selection. The performance of the proposed system can be evaluated using the True Positive (TP), True Negative (TN), False Positive (FP), False Negative (FN) values.

Digital fundus photography plays a major role in the diagnosis of different retinal pathologies like hypertension, diabetic retinopathy and Glaucoma. To identify abnormal components on the retina, retinal features should be detected accurately. Retinal vessel structure is one of the important landmarks of the retina. So precise detection of retinal vessel structure is imperative. This paper presents a simple, robust retinal vessel extraction approach based on the line detectors and morphological operations. As vessel detection is basically a problem of a line detection, the green channel retinal image is applied to morphological opening using a line as structuring element. The resultant image is again applied with the line detectors and thresholded using Otsu’s thresholding. The proposed algorithm overcomes the fundamental issues of scale and orientation avoiding the need of multiple thresholds with improved values of performance measure as compared to the state of the art techniques. The proposed algorithm is applied on 3 standard databases-HRF (healthy and Diabetic), DIARETDB1 and DRIVE. Area under the ROC curve (AUC) of 97% was achieved with 91% Sensitivity and 97% Specificity for DRIVE dataset. The proposed algorithm achieved an Accuracy of 97%, Sensitivity of 85 % and Specificity of 97% for HRF database. On DIARETDB1 database too observed very good results.

One of the major eye diseases called Diabetic retinopathy (DR), which causes loss of sight if it is not noticed in the early hours. In order to keep the patient’s vision, the early detection and periodic screening of DR plays an important role in eye diagnosis by examining the deformity in retinal fundus images. During the early detection of DR, ophthalmologists identify the lesions called microaneurysms that emerge as the first symptom of the disease. The various test methods availability and the handlings of all these test methods for detection of DR are not possible in rural areas. The automatic DR detection system offers the potential to be used in large-scale screening programs. This paper presents a hybrid classifier and region-dependent integrated features for detection of DR automatically. In the proposed hybrid classifier, holoentropy enabled decision tree is combined with a feed forward neural network using the proposed score level fusion method. The performance is evaluated and compared with existing classification algorithms using sensitivity, specificity, and accuracy. Two different databases such as DIARETDB0 and DIARETDB1 are utilized for the experimentation. From the experimental results, proposed technique obtained the accuracy of 98.70%, which is better as compared with existing algorithms.

Manual analyzing and interpreting of the microscopic images of thin blood smears for diagnosis of the malaria is a tedious and challenging task. This paper aims to develop a computer assisted system for quantification of erythrocytes in microscopic images of thin blood smears. The proposed method consists of preprocessing, segmentation, morphological filtering, cell separation and clump cell segmentation. The major issues, required to be addressed to enhance the performance of the system are cell separation (i.e. isolated and clump erythrocytes classification) and clump cell segmentation. The geometric features such as cell area, compactness ratio and aspect ratio have been used to define the feature set. Further, the performance of the system in classifying the isolated and clump erythrocytes is evaluated for the different classifiers such as Naive Bayes, k-NN and SVM. Moreover, the clump erythrocytes are segmented using marker controlled watershed with h-minima as internal marker. Based on the experimental results, it may be concluded that the proposed model provides satisfactory results with an accuracy of 98.02% in comparison to the state of art method.

The traditional signal processing algorithms suffer from large execution delay for real time issues, therefore implementation of high speed algorithms is needed. The present work aims to implement multiplier less Savitzky Golay smoothing filter (SGSF) based on distributed arithmetic (DA) for pre-processing of Electro-oculographic (EOG) signals such that speed is increased along with reduction in chip area. The filter used should be efficient enough to remove the artifacts along with least deformation from the actual signal. Savitzky-Golay (SG) filter is widely employed in biomedical signal analysis but its fast and efficient implementation is not proposed yet for EOG analysis. SGSF is selected so that disease diagnosis using saccade detection of EOG signal can be done accurately. The efficiency of proposed filter is tested in terms of signal-to-signal-plus-noise ratio (SSNR) and real time computations. It is observed from the analysis that DA based architecture increases the processing speed, reduces the chip area and original features of filtered signal are preserved.

Cloud computing plays a predominant role in storage technologies. It enables the tenant user to deploy their infrastructure without any investment. Cloud storage offers flexibility with storage and sharing facilities using the Internet platform. Storing sensitive information such as clinical data requires high privacy preservation and is associated with serious concern over data privacy on the cloud platform. Privacy preservation becomes the most adherent issue when a large volume of data is stored in public clouds. Subtree anonymization using the bottom–up generalization (BUG) and top–down specialization (TDS) approaches has been widely adopted for anonymizing data sets. This ensures individual data privacy; however, it causes potential violations when the new update is received, and it suffers from valuing the k-anonymity parameter. In this proposed model, a pseudo-identity was anticipated to accomplish privacy preservation with maximum data utility on incremental data sets. Initially, the Data Set (DS) was partitioned in the preprocessing stage; subsequently, the processed data sets were clustered into groups. The genetic model was used for indexing and updating incremental data sets. This was consistent with repeatedly modified data sets. In the evaluation process, an incremental and distributed DS was deployed, and our model exhibited efficient and optimal performance for privacy preservation in comparison with existing models.

This paper presents a cascade of ensemble-based artificial neural network for multi-class intrusion detection (CANID) in computer network traffic. The proposed system learns a number of neural-networks connected as a cascade with each network trained using a small sample of training examples. The proposed cascade structure uses the trained neural network as a filter to partition the training data and hence a relatively small sample of training examples are used along with a boosting-based learning algorithm to learn an optimal set of neural network parameters for each successive partition. The performance of the proposed approach is evaluated and compared on the standard KDD CUP 1999 dataset as well as a very recent dataset, UNSW-NB15, composed of contemporary synthesized attack activities. Experimental results show that our proposed approach can efficiently detect various types of cyber attacks in computer networks.

Exponentially increasing multimedia data over the internet raises concerns over its security. In the current work, we present a new technique for encrypting digital images based upon the pixel shuffling combined with changing pixel values using 128-bit secret key using henon chaotic map. Chaotic maps are characterized by their high sensitivity towards the initial parameters, which makes it a natural choice for developing a dynamic permutation matrix or as it is mostly called, permutation map. So we used chaotic Henon map in order to dynamically generate the permutation matrix. The initial parameters of the chaotic map and the secret key for changing the pixel values are derived from an external secret key. Horizontal and vertical permutations are used to perform pixel shuffling. Shuffling is used to destroy the correlation among the neighbour or adjacent image pixels, also it helps in increasing diffusion in the image. The proposed scheme is tested against a series of tests to measure its performance. Results of such tests indicate that the proposed algorithm is highly sensitive towards the encryption key and showed high resistance against various brute-force or statistical attacks.

In biometrics authentication systems, such as palmprint recognition, fingerprint recognition, dorsal hand vein recognition and palm vein recognition etc., image enhancement play a crucial role for most of the low resolution image samples. In this work, a novel adaptive histogram equalization (AHE) variant is proposed referred as effective area-AHE (EA-AHE) with weights. Here, global adaptive histogram equalization is improved using a local AHE technique by varying the effective area with different effective weights. The method is found to improve the biometric authentication identification rate as compared to the typical AHE. To validate the proposed algorithm, IITD palmprint databases of left and right hand are used in the simulations. Finally, it is validated through results that proposed technique is superior to the existing ones.

Anomalous traffics are those unusual and colossal hits a non-popular domain gets for a small epoch period in a day. Regardless of whether these anomalies are malicious or not, it is important to analyze them as they might have a dramatic impact on a customer or an end user. Identifying these traffic anomalies is a challenge, as it requires mining and identifying patterns among huge volume of data. In this paper, we provide a statistical and dynamic reputation based approach to identify unpopular domains receiving huge volumes of traffic within a short period of time. Our aim is to develop and deploy a lightweight framework in a monitored network capable of analyzing DNS traffic and provide early warning alerts regarding domains receiving unusual hits to reduce the collateral damage faced by an end–user or customer. The authors have employed statistical analysis, supervised learning and ensemble based dynamic reputation of domains, IP addresses and name servers to distinguish benign and abnormal domains with very low false positives.

Cloud Security is of paramount importance in the new era of virtualization technology. Tenant Virtual Machine (VM) level security solutions can be easily evaded by modern attack techniques. Out-VM monitoring allows cloud administrator (CA) to monitor and control a VM from a secure location outside the VM. In this paper, we propose an out-VM monitoring based approach named as ‘Program Semantic-Aware Intrusion Detection at Network and Hypervisor Layer’ (PSI-NetVisor) to detect attacks in both network and virtualization layer in cloud. PSI-NetVisor performs network monitoring by employing behavior based intrusion detection approach (BIDA) at the network layer of centralized Cloud Network Server (CNS); providing the first level of defense from attacks. It incorporates semantic awareness in the intrusion detection approach and enables it to provide network monitoring and process monitoring at the hypervisor layer of Cloud Compute Server (CCoS); providing the second level of defense from attacks. PSI-NetVisor employs Virtual Machine Introspection (VMI) libraries based on software break point injection to extract process execution traces from hypervisor. It further applies depth first search (DFS) to construct program semantics from control flow graph of execution traces. It applies dynamic analysis and machine learning approaches to learn the behavior of anomalies which makes it secure from obfuscation and encryption based attacks. PSI-NetVisor has been validated with latest intrusion datasets (UNSW-NB & Evasive Malware) collected from research centers and results seem to be promising.

Question Answering (QA) research is a significant and challenging task in Natural Language Processing. QA aims to extract an exact answer from a relevant text snippet or a document. The motivation behind QA research is the need of user who is using state-of-the-art search engines. The user expects an exact answer rather than a list of documents that probably contain the answer. In this paper, we consider a particular issue of QA that is gathering and scoring answer evidence collected from relevant documents. The evidence is a text snippet in the large corpus which supports the answer. For Evidence Scoring (ES) several efficient features and relations are required to extract for machine learning algorithm. These features include various lexical, syntactic and semantic features. Also, new structural features are extracted from the dependency features of the question and supported document. Experimental results show that structural features perform better, and accuracy is increased when these features are combined with other features. To score the evidence, for an existing question-answer pair, Logical Form Answer Candidate Scorer technique is used. Furthermore, an algorithm is designed for learning answer evidence.

Automated processing and recognition of human speech commands under unconstrained and noisy recognition situations with a limited number of training samples is a challenging problem of interest to smart devices and systems. In practice, it is impossible to remove noise without losing class discriminative information in the speech signals. Also, any attempts to improve signal quality place an additional burden on the computational capacity in state-of-the-art speech command recognition systems. In this paper, we propose a low-level word processing system using mean-variance normalised frequency-time spectrograms and a new similarity measure that compensates for feature length mismatches such as those resulting from pronunciation variations in speech segments. We find that padding a local similarity matrix with zero similarity values to disregard the effects of a mismatch in length of speech spectrograms results in improved word recognition accuracies and reduction in between class non-discriminative signals. As opposed to the state-of-the-art approaches in spectrogram comparisons such as DTW, the proposed method, when tested using the TIMIT database, shows improved recognition accuracies, robustness to noise, lower computational requirements, and scalability to large word problems.

Maintaining large collection of documents is an important problem in many areas of science and industry. Different analysis can be performed on large document collection with ease only if a short or reduced description can be obtained. Topic modeling offers a promising solution for this. Topic modeling is a method that learns about hidden themes from a large set of unorganized documents. Different approaches and alternatives are available for finding topics, such as Latent Dirichlet Allocation (LDA), neural networks, Latent Semantic Analysis (LSA), probabilistic LSA (pLSA), probabilistic LDA (pLDA). In topic models the topics inferred are based only on observing the term occurrence. However, the terms may not be semantically related in a manner that is relevant to the topic. Understanding the semantics can yield improved topics for representing the documents. The objective of this paper is to develop a semantically oriented probabilistic model based approach for generating topic representation from the document collection. From the modified topic model, we generate 2 matrices- a document-topic and a term-topic matrix. The reduced document-term matrix derived from these two matrices has 85% similarity with the original document-term matrix i.e. we get 85% similarity between the original document collection and the documents reconstructed from the above two matrices. Also, a classifier when applied to the document-topic matrix appended with the class label, shows an 80% improvement in F-measure score. The paper also uses the perplexity metric to find out the number of topics for a test set.

In the near past, microblogging services like Twitter have gained immense popularity. The vast breadth of user base is responsible for generating information on diverse aspects ranging from product launch to sports match. However, due to the exponentially increasing number of users on Twitter platform, the volume of content generated is tremendously high. In this paper we address the information overload problem of the Twitter and present a framework for event detection with hierarchical visualization specifically for sports events. We propose a novel Event Tree algorithm which detects and generates a hierarchy of events through recursive hierarchical clustering. The different levels of the hierarchy represent the events at different granularities of time and thus offer dual advantages. Firstly, it takes care of the users with varied level of interest in the particular sports event. Secondly, the users may get finer details for specific segments of the sport holdings as per their appeal. We test and report results of our framework for the Indian Premier League Twenty20 2016 season cricket match dataset.

Current eLearning systems enable streaming of live lectures to distant students facilitating a live instructor-student interaction. However, studies have shown that there exists a marked divide in local students’ (student present in the teacher’s location) experience as compared to distant students’. One of the major factors attributing to this rift is lack of gaze aligned interaction. In this paper, we present a system architecture that receives gesture triggers as input, and dynamically calculates the perspective angle to be captured of the speaking participant, for the listener, facilitating eye contact. The gesture triggers are calculated using Microsoft Kinect sensor which extracts skeleton joint information of the instructor, and performs gesture recognition with the acquired joint information real-time. This serves as interaction-initiation triggers for dynamic perspective correction for gaze alignment during a conversation. For evaluation, we constructed a five classroom test-bed with dynamic perspective correction and user study results indicate a marked 42% enhancement in experience with the gaze correction in place.

Autism Spectrum Disorder (ASD) is defined as a condition or disorder that begins in childhood and that causes problems in establishing relationships and communicating with other people. Aarya works as a personal well-being companion to children with Autism Spectrum Disorder while they interact with a virtual environment that is gesture based. By making an ASD affected child face real world situations, we try to improve his/her confidence in facing the world and being open to learning various skills. Social interaction and communication are the major challenges faced by children with ASD. In Aarya, we use gesture-based interface that is the Microsoft Kinect so that the child can find it easier to interact in the real world environment. Through the interactions made with the children and the results obtained, we understand that this tool can be a companion while giving chance for growth and improving their interacting ability. With further refinement and expert inputs, this tool can be built better.

Computer-based testing systems take advantage of the interaction between computers and individuals to sequentially customize the presented test items to the test-taker’s ability estimate. Administering such sequential adaptive tests has many benefits including personalized tests, accurate measurement, item security, and substantial cost reduction. However, the design of such intelligent tests is a complex process and it is important to explore the impact of various parameters and options on the performance before switching from traditional tests in a particular environment. Although Monte Carlo simulation is a typical tool for achieving this purpose, it depends on generating pseudo-random samples, which may fail to effectively represent the environment under study and thus incorrect inferences can be drawn. This paper presents a comprehensive case study to evaluate and compare the performance of a number of sequential adaptive testing procedures but using post-hoc simulation, where items of a real conventional test are re-administered adaptively. The comparisons are based on the number of administered items, standard error of measurement, item exposure rates, and correlation between adaptive and non-adaptive estimates. It is found that the results varies based on the settings. However, Bayesian estimation with adaptive item selection can lead to greater savings in terms of the number of test items without jeopardizing the estimated ability. It also has the lowest average exposure rate for each item.

With the enormous growth in the volume of online data, users are flooded with a gigantic amount of information. This has made the task of Recommender systems (RSs) even more engrossing. Research in RSs has been revolving around newer concepts like social factors, context of the user and the groups they belong to. This paper presents the design and development of a Community based Collaborative Filtering Recommender System (CCFRS). Louvain method of community detection has been applied to discover communities in the dataset. The method of generating recommendations is based on the proposed idea of Item Frequency-Inverse Community Frequency (IF-ICF) score of each item in the target user’s community. IF scores help finding the set of items which are unique to a particular community. ICF values are inversely proportional to the number of communities in which an item has been rated. It is used to calculate the uniqueness of the item across the communities. The IF-ICF scores of the items are further employed to find the prediction scores of items unseen by the user in order to present a set of top ‘n’ recommendations to the user. A prototype of the system is developed using Java and experimental analysis has been carried out for the domain of books.

Proliferation of information is a major confront faced by e-commerce industry. To ease the customers from this information proliferation, Recommender Systems (RS) were introduced. To improve the computational time of a RS for large scale data, the process of recommendation can be implemented on a scalable, fault tolerant and a distributed processing framework. This paper proposes a Content-Based RS implemented on scalable, fault tolerant and distributed framework of Hadoop Map Reduce. To generate recommendations with improved computational time, the proposed technique of Map Reduce Content-Based Recommendation (MRCBR) is implemented using Hadoop Map Reduce which follows the traditional process of content-based recommendation. MRCBR technique comprises of user profiling and document feature extraction which uses the vector space model followed by computing similarity to generate recommendation for the target user. Recommendations generated for the target user is a set of Top N documents. The proposed technique of recommendation is executed on a cluster of Hadoop and is tested for News dataset. News items are collected using RSS feeds and are stored in MongoDB. Computational time of MRCBR is evaluated with a Speedup factor and performance is evaluated with the standard evaluation metric of Precision, Recall and F-Measure.

As the size of websites continues to grow, current research focuses on the development of intelligent websites which facilitate the browsing by providing a navigation aid to the website users. Web page recommendation systems provide suggestions to the website users about the webpages that may be of concern to them by evaluating the collective navigation behavior of previous website users. The main motive of this study was to explore the utilization of partially ordered sequential rules (POSR) in making future predictions for website users. Sequential rules provide the association between the events that occur in a particular sequence. In this paper, two sequential rule mining algorithms, namely TRuleGrowth and CMRules have been separately used to generate sequential rules. Then the sequential rules were used to make predictions about the future interests of the users regarding webpages. The experimental results on a real life dataset have revealed that the rules generated by TRuleGrowth algorithm were able to make predictions with higher accuracy than those generated by CMRules algorithm.

This paper presents a novel Perturb-Boost Fuzzy Logic Controller for controlling the instability of nonlinear dynamical system behavior. Several applications can make use of the small perturbation technique discussed in the paper related to industrial control, mechanical nonlinear systems, electrical systems and other systems governed by nonlinear differential equations. This paper presents the power system as an application for use of novel controller to control voltage instability problem. The power system is an electro-mechanical nonlinear dynamical system, and is described by a combination of electrical and mechanical parameter based differential equations together. The power system faces problems related to voltage instability and chaos. Voltage instability exists in almost every power system for a specific set of mechanical power, electrical loading and initial conditions. Voltage instability can be controlled by injecting a small amount of reactive power using a power electronic device called a Static Volt Ampere Reactive Compensator. The amount of reactive power to be injected is trivial for different types and sizes of the power system. To control voltage instability, reactive power in a power system needs to be boosted. Proposed controller output decides amount of reactive power which perturbs the system equation to the stable operating point. The proposed Perturb-Boost Fuzzy Logic Controller differs from conventional controllers due to its single shot boost action, which perturbs system dynamics in such a way as to push it to safe zones of voltage stability. This paper analyzes the performance of the proposed controller to control the voltage instability for the generalized three node power system benchmark model. Reactive power to be injected is momentary due to single shot boost action. Time to reach instability gets delayed by approximately fifteen seconds using proposed controller for the benchmark model. Mitigation of voltage collapse is discussed in view of simulation results using proposed novel controller.

Optimization of fuzzy Maximum Power Point Tracking (MPPT) controller using Learning Automata (LA) algorithm is proposed in this paper. The optimal duty cycle of the DC-DC converter circuit is obtained using LA for various environmental conditions through learning process. The fuzzy MPPT controller is developed using the information collected by LA through the learning process. The proposed model is developed and tested using MATLAB for standard test conditions of PV, constant temperature and varying irradiation level, constant irradiation and varying temperature level, and varying temperature and varying irradiation level. The results obtained using the proposed fuzzy MPPT are compared with the conventional Perturb and Observe (P&O) MPPT and variable step size Fuzzy MPPT based PV system. The experimental set up is developed and the test is conducted under different conditions for the solar PV system with P&O MPPT and the proposed LA Fuzzy MPPT. The results show that the proposed LA based Fuzzy MPPT method is more accurate and its tracking response is faster.

In the presented work, an intelligent model for fault classification of a transmission line is proposed. Ten different types of faults (LAG, LBG, LCG, LABG, LBCG, LCAG, LAB, LBC, LCA and LABC) have been considered along with one healthy condition on a simulated transmission line system. Post fault current signatures have been used for feature extraction for further study. Empirical Mode Decomposition (EMD) method is used to decompose post fault current signals into Intrinsic Mode Functions (IMFs). These IMFs are used as input variables to an artificial neural network (ANN) based intelligent fault classification model. Relief Attribute Evaluator with Ranker search method is used to select the most relevant input variables for fault classification of a three-phase transmission line. Proposed approach is able to select most relevant input variables and gives better result than other combinations. Ours is a first attempt at using EMD for feature selection in fault classification of transmission lines.

The paper presents a novel idea of protection of the multi-terminal Extra High Voltage (EHV) transmission line having multiple Series compensation. A statistical learning perspective for improved classification of faults using Artificial Neural Networks (ANN) has been proposed. The protective scheme uses single end cur-rent data of three phases of line to detect and classify faults. A Multiresolution Analysis (MRA) wavelet transform is employed to decompose the signals acquired and further processed to extract statistical features. The statistical features learning algorithm utilizes a set of ANN structures with a different combination of Neural Network parameters to determine the best ANN topology for Classifier. The algorithm generates different fault patterns arising out of different fault scenarios and altering system parameters in the test system. The features are selected based on ANOVA F-test statistics to determine relevance and improve classification accuracy. The features thus selected from fault patterns are given to the Hybrid Wavelet-ANN structure. The ANN once trained on a part of data set is later tested on the other part of unseen patterns and further validated on rest of the patterns. To provide a comparative Support Vector Machine Classifier is used to classify the fault patterns. A 5 fold cross validation is used on the data set to check the accuracy of SVM. It is shown that the proposed method using Pattern Recognition using Hybrid structure provides a high accuracy with reliability in identifying and classifying fault patterns as opposed to SVM.

Based on a flame image processing technology, a fuzzy based temperature monitoring system in a rotary kiln was reported. In this paper, we propose a Fuzzy based flame analysis, which consider Red, Green and Blue intensity planes, to measure the temperature from the flame image. The proposed approach integrates RGB intensity as fuzzified input variables, temperature as defuzzified output variables and fuzzy inference rules based Mamdani models. Based on the color characteristics of burning flame, temperature of different flame zones are located using a fuzzy logic controller. The temperature level at hotspot area is the highest and through the fuzzy analysis we were able to identify hotspot area from the flame image. In order to evaluate the performance of the proposed method, quantitative metric such as f-measure has been used and it was found that the f-measure metric yields high accuracy for the hotspot area. The visual inspection of the results along with the f-measure values showed the superiority of our work. Experimental results indicate that the proposed approach can be applied to a high resolution video flame image.

With the development of network technology, the Internet portals have been constantly changing. However, such portals cannot meet the requirements of Internet of Everything (IoE) communication between people and things or between things themselves. Inspired by the ideal of container, Mobile Cross-platform Application Development Framework (MCADF) and Platform as a Service (PaaS), we designed a “Cloud + Container” portal platform for IoE. The cloud provides application development, testing, deployment, operation, management, and other functions. It is also responsible for data storage, management and analysis. The terminal of user container is used to carry and manage mass applications and IoE data, and provide user access entry. In this paper, we first introduce the background of IoE and related problems, then give the detailed design of the platform. Finally, we evaluate the performance of the platform comparing with other platforms.

Due to the advancement of mobile technology, a large number of computationally intensive applications are created for smart phones. But the limitations of battery and processing power of smart phones are making it inferior to laptops and desktop computers. Mobile Cloud Offloading (MCO) allows the smart phones to offload computationally intensive tasks to the cloud, making it more effective in terms of energy, speed or both. Increased networking capacity due to the availability of high speed Wi-Fi and cellular connections like 3G/4G makes offloading more efficient. Even then, the choice of offloading is not always advisable, because of the highly dynamic context information of mobile devices and clouds. In this paper, we propose a dynamic decision making system, which will decide whether to offload or do the tasks locally, depending on the current context information and the optimization choice of the user. Metrics are developed for time, energy and combination of time and energy to assess the proposed system. A test bed is implemented and the results are showing improvements from the currently existing methods.

Radio Frequency Identification (RFID) uses sensors to enable communication among things or objects in what is called Internet of Things (IoT) technology. Web 2.0 tools, on the other hand, are used on electronic devices (phones, PDAs, computers, etc.) to transmit data contents over the internet. In this study, we used a synergy of both technologies to enhance inventory control. We proposed software architecture which combined RFID and Web 2.0 tool advantages. The proposed architecture was used to develop an inventory management software prototype focused on enterprises in developing countries in Africa, specifically South Africa. The inventory management prototype was developed and was able to detect misplaced products and low stock levels, and send notification on Twitter to update inventory managers on mobile phone. Scalability measurements of the software were taken to validate the performance of the software prototype. The findings show that the system scaled reliably with increasing numbers of items read. The contribution of this work was compared to existing literature and our findings are presented in this paper. Real- life evaluation for a specific industry will be necessary to further reveal what improvements would be required to make this architecture more relevant. Behavioural study of users will also be required to further determine the economic and social benefits of this approach.

Spectrum decision is the capability of Secondary Users to choose the best accessible spectrum band to satisfy a user’s Quality of Service (QoS) requirements. Spectrum decision comprises three primary functions; spectrum characterization, spectrum selection and dynamic reconfiguration of cognitive radio. The study of dynamic reconfiguration of transceiver parameters in spectrum decision making has been motivated because of its importance to the realization of efficient spectrum utilization and management in distributed mobile cognitive radio networks. Spectrum decision making in a distributed cognitive radio network is crucial, so as to ensure that an appropriate frequency and channel bandwidth are selected to meet the QoS requirements of different types of applications and to maintain the spectrum quality. In attempting to address the issue of dynamic reconfiguration of transceiver parameters in decision making for cognitive radio networks, different approaches can be found in the literature. However, due to some of the challenges associated with these approaches such as high computational complexity, ambiguity, non-repeatability and non-deplorability of these classical approaches, researchers are still trying to explore other techniques that will be less ambiguous, more efficient, more understandable and easier to deploy in a highly dynamic environment like distributed cognitive radio networks. Hence, this paper reviews the existing approaches, identifies the challenges and proposes a biologically inspired optimal foraging approach to address the decision making problem and other problems relating to the existing approaches.

The lifetime of a Wireless Sensor Network (WSN) depends on the efficiency of the Cluster Head (CH) selection techniques that address most of the significant issues related to network management. The existing energy based CH selection mechanisms consider that all the participating sensors are trustworthy. Conversely, the trust-based CH selection schemes assume that the sensor nodes are energy efficient. But, these assumptions of energy factor or trust assessment made by the CH selection mechanisms may not be true and the Residual Energy (RE) of the sensors may not be the sole factor to identify an effective CH in a WSN. Hence, this paper presents hybrid integrated energy and trust assessment based forecasting model known as Hyper-geometric Energy Factor based Semi-Markov Prediction Mechanism (HEFSPM) for effective CH election so as to improve the lifetime of the network. From the simulation results, it is inferred that HEFSPM is superior in improving the lifetime of the network to a maximum extent of 22% than the existing CH election mechanisms considered for investigation.

In multi carrier OFDM systems parameters like speed, throughput and hardware area can be improved by using efficient Fast Fourier Transform approach. In this paper an area efficient and high speed 32 bit floating point FFT processor for OFDM using Vedic multiplication process is presented. Proposed FFT processor is based on memory based architecture and utilizing Urdhavatiraykbhyam sutra for Vedic multiplication. As the number of inbuilt multipliers available in FPGAs are limited, hence external multiplication module are required in the multicarrier OFDM systems, in order to reduce the complexity of FPGA implementation. By the use of Vedic multiplication process in FFT of OFDM high throughput with smaller area can be achieved. Simulation results explain that the proposed scheme is having high speed and throughput.

Parallel Processing has been a widely studied field, used and implemented in computational systems. Many different types of topologies of processors have been implemented and their performance has been analyzed. The processor technology keeps evolving so their computational capability must be utilized accordingly when employed in parallel systems. In this article, new intra-parallel processor architectures (segmented/heterogeneous) has been used and an intelligent co-operative protocol has been implemented to optimally utilize the parallel components of the parallel processor design. More precisely a friendship based intelligent load balancing strategy has been designed and implemented to maximally utilize the parallel processor, which takes care of overloading and starvation problems and makes intelligent decisions regarding job scheduling. Context switching policies must also be designed carefully to stop performance degradation and with intelligent techniques this switching time can be reduced considerably. Work proposed in this article performs and executes load stability with feasible priori information about processors utilization, depending upon and based on this metric value the entire process space is partitioned among different categories. Based on the load status and state of affairs, processors are categorized and labeled and a suitable set out of those is figured-out that act as buddy for others and handles incoming process queue for overloaded processors. Further history and statistics of each processors is maintained and is utilized to make intelligent future scheduling decisions.

The night video fusion algorithms integrate the visuals captured by a security surveillance camera, which in turn improve the visual perception. The recent development in night fusion research focused on fusing both illuminated and non-illuminated areas simultaneously however, the natural color of the light area may be lost. Moreover, the contrast of the illuminated regions decreases because of the dark pixels surrounding those regions. Hence, the color and contrast should be improved to obtain the actual color of the illuminated regions. We propose a fuzzy inference system based wavelet fusion to enhance the light regions of a nonuniform illuminated night video surveillance system. To include spatial and temporal variations of the illuminated regions, a spatio-temporal illumination approach is used. A contribution index of the illuminated regions is generated using a fuzzy membership function. Subsequently, the stationary wavelets are used to decompose high-frequency and low-frequency coefficients of both night and day background frames for frame fusion. The contribution index selects the illuminated regions presented in these wavelet coefficients for fusion. Finally, the inverse wavelet transform is applied to reconstruct the illumination enhanced frame. The proposed approach effectively highlights the illuminated regions and provides a better visual perception.

Remote sensing satellites are proficient in taking earth images across various regions in visible part of electromagnetic spectrum. The images can be panchromatic image of a single band, multispectral image of three to seven different bands, and hyperspectral image taken from about 220 contiguous spectral bands. These images are used together or on its own, depending on the significance and usage of the preferred application. Pan-sharpening is one method which is used to improve the quality of a low resolution multispectral image by fusion with a high resolution panchromatic image. This paper proposes a method based on M-band wavelets for the pan-sharpening of a low resolution multispectral image. The method tries to improve the spatial characteristics while preserving the spectral quality of the data. The proposed technique uses weighted fusion rule and average fusion rule. The data used for the experiment were acquired by high resolution optical imagers onboard QuickBird, WorldView-3, WorldView-2 and GeoEye-1. A comparison with existing fusion techniques is done based on image quality metrics and visual interpretation. The experimental results and analysis suggests that the proposed pan-sharpening technique outperforms other compared pre-existing pan-sharpening methods.

Traffic congestion occurs when the number of the vehicles increases more than the existing space of the road. This deleterious problem is increasing at an alarming rate in the whole world. For any effective Intelligent Transportation System, early detection of traffic congestion is very important to take corrective action. Several techniques have been developed to detect traffic congestion, most of which are infrastructure based. Even though these techniques are widely used, but they have many downsides as well. They require large capital input for installation as well as for maintenance. In this paper, we propose an efficient and cost-effective method using smartphones to determine the traffic state of the road. The acoustic data collected from commuter’s smartphone is segmented into fixed size frames. Various time and frequency based features such as (MFCC, Delta & Delta-Delta, ZCR, STE, and RMS) are extracted from each frame and used for detecting traffic state as ’busy street’ or ’quiet street’. We have compared the accuracy of two classifiers Support Vector Machines and Neural Network by using acoustic data collected from 320 different recording sessions. Experiments have shown that feature set having features MFCC, STE and RMS, results in better classification accuracy of 91.8% with Neural Network and 93% with SVM. Furthermore, various relevant factors affecting the classification accuracy are also tested like frame size, window functions, overlapping size and different combination of features. The frame size of 8192 and hamming window function proved to be more efficient than others.

Least Mean Square (LMS) and Normalized-Least Mean Square (NLMS) algorithms are very popular and frequently used algorithms for noise cancellation in speech. But selecting the step size for updating the weight of adaptive filter is the big issue in LMS and NLMS algorithms. So as to meet disagreeing requirements of quick convergence and less MSE, step size needs to be correctly controlled. Along with step size, length of adaptive filter also plays major role in the effective noise cancellation. These two factors greatly affect the performance of the ANC. To get the best possible solution, a variety of trials of filter length and step size are required. The main motivation behind the development of proposed High Performance Self Tuning (HPST) adaptive filter algorithm is to adaptively determine the step size. The selection of length of adaptive filter is based on the distance between two microphones in the ANC system. The proposed algorithm works very well, as shown in the experiments which are carried out on NOIZEUS speech corpus as well as actually recorded noisy speech signals. Results indicate that proposed algorithm is superior to referred algorithms in terms of Mean- Square- Error (MSE), Peak- Signal to Noise ratio (PSNR), convergence time and complexity.

Detecting forged digital image has been an active research area in recent times. Tampering introduces artifacts within images that differentiate tampered images from authentic images. Forgery detection techniques try to identify these artifacts by analyzing differences in the texture properties of the image. In this paper, we propose a multi-texture description based method to detect tampering. Different texture descriptors considered are Local Binary Pattern, Local Phase Quantization, Binary Statistical Image Features and Binary Gabor Pattern. The method captures subtle texture variations at different scales and orientation using Steerable Pyramid Transform (SPT) decomposition of image. The different texture descriptors extracted from each subband image after SPT decomposition is combined to form the multi-texture representation. Then, ReliefF feature selection method is applied on this high dimensional multi-texture representation to generate a compact representation. This compact multi-texture representation is classified using Random Forest classifier. We have evaluated the performance of individual texture descriptors and multiple textures in detecting image forgery. Experimental results show that the compact multi-texture description has improved detection accuracy.

Evolutionary Algorithms (EA) are robust optimization approaches which have been successfully applied to a wide range of problems. However, these well-established metaheuristic strategies are computationally expensive because of their slow convergence rate. Opposition Based Learning (OBL) theory has managed to alleviate this problem to some extent. Through simultaneous consideration of estimates and counter estimates of a candidate solution within a definite search space, better approximation of the candidate solution can be achieved. Although it addresses the slow convergence rate to some extent, it is far from alleviating it completely. The present work proposes a novel approach towards improving the performance of OBL theory by allowing the exploration of a larger search space when computing the candidate solution. Instead of considering all the components of the candidate solution simultaneously, the proposed method considers each of component individually and attempts to find the best possible combination by using a metaheuristic technique. In the present work, this improved Opposition learning theory has been integrated with the classical HS algorithm, to accelerate its convergence rate. A comparative analysis of the proposed method against classical Opposition Based Learning has been performed on a comprehensive set of benchmark functions to prove its superior performance.

The firefly algorithm is applied to the uncapacitated facility location problem which is a well known optimization problem. The light absorption coefficient parameter γ of the firefly algorithm is examined to obtain better performance and suitable values of γ are explored for the uncapacitated facility location problem. Effectiveness of local search in the firefly algorithm is also investigated. In addition, the firefly algorithm equipped with local search is compared with the artificial bee colony algorithm with respect to average relative percent error and hit to optimum rate.

Graphs are considered to be one of the best studied data structures in discrete mathematics and computer science. Hence, data mining on graphs has become quite popular in the past few years. The problem of finding frequent itemsets in conventional data mining on transactional databases, thus transformed to the discovery of subgraphs that frequently occur in the graph dataset containing either single graph or multiple graphs. Most of the existing algorithms in the field of frequent subgraph discovery adopts an Apriori approach based on generation of candidate set and test approach. The problem with this approach is the costlier candidate set generation, particularly when there exist more number of large subgraphs. The research goals in frequent subgraph discovery are to evolve (i) mechanisms that can effectively generate candidate subgraphs excluding duplicates and (ii) mechanisms that find best processing techniques that generate only necessary candidate subgraphs in order to discover the useful and desired frequent subgraphs. In this paper, a two phase approach is proposed by integrating Apriori algorithm on graphs to frequent subgraph (FS) tree to discover frequent subgraphs in graph datasets.

Life is nothing less than a hell without any entertainment in it. Thanks to mobile phones that let us entertain ourselves on the go. Mobile phones that are being launched nowadays, come with super impressive features that revolve around entertainment. Mobile manufacturers know it pretty well that entertainment has become an indispensable part of human life in the current era. This is the reason why mobile phones are nothing but a complete portable entertainment package. The main source of portable entertainment is music. A very common but irritating problem faced by the youngsters of this era is missing their favorite beat, or pausing a song frequently while conversing with someone. This seems to be negligible, but irritates most as they have to rewind the song or even restart it from beginning for the single beat. So think about a system that stops playing when the buds are taken off, and automatically continues when it is placed back. This seems to be simple but it is not so. This will change the whole experience of enjoying media, making a new mile stone in the entertainment world. This system will bring a new generation of media players that not only allows us to listen to our favorite music whenever we want but also allows automatic access without having to unlock our phones every now and then for the same.