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

In recent years it has become popular to represent the foreign exchange market as a correlation network using the Pearson correlation coefficient as a measure of co-movement of exchange rates. We show that the Pearson correlation of financial time series could be misleading in analyzing their co-movements. We propose representing the co-movement of exchange rates as a non-directed graph using the measure of local trends associations (LTA). Each node in the graph represents a currency, and an edge between nodes represents an existing high association between currencies. We present several methods for network summary visualization showing the highest associations between nodes. One method allows comparing graphs corresponding to different correlation and association measures. Another one is appropriate for comparing graphs using the same association measure. We present a dynamic analysis of association networks and the network of associations with a selected currency named a “node of interest.” We show that the currency networks based on LTA are better explainable than networks based on Pearson correlation. LTA based relationships between currencies better reflect geographical, economic or political relationships between corresponding countries.

In many applications, including analysis of seismic signals, Daubechies wavelets perform much better than other families of wavelets. In this paper, we provide a possible theoretical explanation for the empirical success of Daubechies wavelets. Specifically, we show that these wavelets are optimal with respect to any optimality criterion that satisfies the natural properties of scale- and shift-invariance.

Neural networks – specifically, deep neural networks – are, at present, the most effective machine learning techniques. There are reasonable explanations of why deep neural networks work better than traditional “shallow” ones, but the question remains: why neural networks in the first place? why not networks consisting of non-linear functions from some other family of functions? In this paper, we provide a possible theoretical answer to this question: namely, we show that of all families with the smallest possible number of parameters, families corresponding to neurons are indeed optimal – for all optimality criteria that satisfy some reasonable requirements: namely, for all optimality criteria which are final and invariant with respect to coordinate changes, changes of measuring units, and similar linear transformations.

Sentiment analysis is a task that belongs to natural language processing and it is highly used in texts extracted from social networks. This task consists of assigning the labels or classes: positive, negative or neutral to the text. However, analyzing a piece of text extracted from social networks to determine if it represents a positive or negative sentiment is a difficult task, because social media texts contain slangs, typographical errors and cultural context. The shortcomings of traditional frequency based feature extraction models such as bag of words or TF-IDF affect the accuracy of sentiment classification. To improve the precision in the sentiment classification task, it is possible to use natural language modelling methods that are able to learn contextual information from words. In this work, word embedding such as Word2Vec, GloVe and Doc2VecC with different dimensions are used. The resulting word vectors will be used to train recurring neural networks such as LSTM, BiLSTM, GRU and BiGRU, to improve sentiment classification.

Learning relationships between nodes in a directed graph is a task that has been widely studied and it has been applied to a large number of topics and research areas. We establish a definition of particular kind of relationship, called analogy in a directed multigraph. An analogy can be defined for a certain pair of concepts, and the paths connecting them are called explanation of this analogy. We experiment with a structure built from real oneiric stories obtained from psychoanalytic descriptions (e.g. mother is represented as a bull; book represents power). Analogies found by the analysts are automatically identified by means of linguistically motivated patterns. Analogies have degrees of similarity based on the words used to describe them: represents, is a, is like a, can be a, refers to, etc. Once they are identified and graded, they are represented in the multidigraph, allowing us to provide different hypotheses in how these analogies can be explained. In order to enrich the concept graph, we added information from ConceptNet and WordNet. In addition, we propose a learning method for association rules that, given the degree of the analogy and a starting concept, allow reaching a destination concept. For example, starting from “dream”, we obtain the path <dream, psychic, neurosis, symptom>, being "dream is a symptom" a description previously given by a psychoanalyst, that was not included when training the algorithm. We evaluated 100 analogies on 171 concepts with 8,034 properties using Leave One Out cross validation, and found that the correct analogy was found within the all the possible paths for 94% of the analogies, restricted to 85% if only the top 20% possible paths are considered. This implies that, by using our method, it is possible to learn analogies between two concepts by reconstructing paths of different lengths based on local decisions considering concept, property and degree of analogy.

The Pile movement is one of the most crucial matters in designing piles and foundations that need to be estimated for any project failure. Over the variables used in forecasting Pile Settlement, many methods have been introduced to appraise it. However, existing a wide range of theoretical strategies to investigate the pile subsidence, the soil-pile interactions are still ambiguous for academic researchers. Most studies have tried to work out the subsidence rate in piles after loading passing time by artificial intelligence methods. Generally, the Artificial Neural Network (ANN) has drawn attention to show the actual views of pile settlement over the loading phase vertically. This research aims to present the Hybrid Radial Basis Function neural network integrated with the Novel Arithmetic Optimization Algorithm and Biogeography-Based Optimization to calculate the optimal number of neurons embedded in hidden layers. The transportation network of Klang Valley, Mass Rapid Transit in Kuala Lumpur, Malaysia, was chosen to analyze the piles’ settlement and earth features using HRBF-AOA and HRBF-BBO scenarios. Over the prediction process, the R-values of HRBF-AOA and HRBF-BBO were obtained at 0.9825 and 0.9724, respectively. The MAE also shows a similar trend as 0.2837 and 0.323, respectively.

The Artificial Neural Networks (ANN) are more widely used in the New Product Development (NPD) process in recent years. The product data generation process is a prerequisite for the application of the ANN algorithm. In the development of new products, the Kansei Engineering (KE) method is an effective emotion-based data generation method. The Semantic Difference (SD) method is usually used to obtain data to apply to design idea generation. Facing the data demand of product creativity, it is important to establish the relationship between consumer perception and product expression. Numerical relationships are not linear and several methods are required for solving these problems. The method of the Back Propagation (BP) neural network is simple and effective to be used in this case. This paper proposes an innovative data modeling method using digital coding and KE. This model explores a rational design method of perceptual intention and builds an intelligent model. Compared with traditional method, the modified model can quickly and accurately reflect the users’ perceptual needs, make the design more scientific, improve the design efficiency, and reduce design costs. This method is used in the design of electric welding machines, and this process can effectively provide technical support for NPD process in small and medium-sized enterprises.

Dealing with the explosive growth of web sources on the Internet requires the use of efficient systems. Automatic text summarization is capable of addressing this issue. Recent years have seen remarkable success in the use of graph theory on text extractive summarization. However, the understanding of why and how they perform so well is still not clear. In this paper, we intend to seek a better understanding of graph models, which can benefit from graph extractive summarization. Additionally, analysis has been performed qualitatively with the graph models in the design of recent graph extractive summarization. Based on the knowledge acquired from the survey, our work could provide more clues for future research on extractive summarization.

In today’s world, Steel plates play essential materials for various industries like the national defense industry, chemical industry, automobile industry, machinery manufacturing, etc. However, some defects may occur in a few plates during the manufacture of stainless-steel plates which directly impact the quality of the stainless-steel plate. If the faulted plate detection can be done manually, then it leads to errors and a time-consuming process. Hence, a computerized automated system is necessary to detect the abnormalities. In this paper, a novel Adaptive Faster Region Convolutional Neural Networks (AFRCNN) scheme has been proposed for automatic fault detection of stainless-steel plates. The proposed AFRCNN scheme comprises three phases: identification, detection, and recognition. Primarily, the damaged plates are identified using Region Proposal Network and Fully Convolutional Neural Network functioning as a combined process under AFRCNN. In the next phase, the number corresponding to the particular plate is recognized through the standard Automated Plate Number Recognition approach with the support of the character recognition technique. The simulation results manifest that the proposed AFRCNN scheme obtains a superior classification accuracy of 99.36%, specificity of 99.24%, and F1-score of 98.18% as compared with the existing state-of-the-art schemes.

Disasters occur due to naturally stirring events like earthquake, floods, tsunamis, storms hurricanes, wildfire, and other geologic measures. Social media fake image posting influence is increasing day by day regarding the natural disasters. A natural disaster can result in the death or destruction of property, as well as economic damage, the severity of which is determined by the resilience of the affected population and the infrastructure available. Many researchers applied different machine learning approaches to detect and classification of natural disaster types, but these algorithms fail to identify fake labelling occurs on disaster events images. Furthermore, when many natural disaster events occur at a time then these systems couldn’t handle the classification process and fake labelling of images. Therefore, to tackle this problem I have proposed a FLIDND-MCN: Fake Label Image Detection of Natural Disaster types with Multi Model Convolutional Neural Network for multi-phormic natural disastrous events. The main purpose of this model is to provide accurate information regarding the multi-phormic natural disastrous events for emergency response decision making for a particular disaster. The proposed approach consists of multi models’ convolutional neural network (MMCNN) architecture. The dataset used for this purpose is publicly available and consists of 4,428 images of different natural disaster events. The evaluation of proposed model is measured in the terms of different statistical values such as sensitivity, specificity, accuracy, precision, and f1-score. The proposed model shows the accuracy value of 0.93 percent for fake label disastrous images detection which is higher as compared to the already proposed state-of-the-art models.

Big Data is a popular research area where a vast amount of data is created, replicated, and consumed by society. The quality of the data used directly influences big data knowledge discovery. The existence of noise is the most prevalent problem influencing data quality. The following techniques were developed to reduce noise in data with a distributed setting: Homogenous Ensemble for Big Data (HME-BD) and Heterogeneous Ensemble for Big Data (HTE-BD). In this article, the performance of HTE-BD is improved further by developing Enhanced HTE-BD (EHTE-BD), which combines Logistic Regression based Support Vector Machine (LR-SVM) in conjunction with RF, LR, and KNN to reduce noisy data. Furthermore, the Multi-Objective Evolutionary Fuzzy Method for Subgroup Discovery throughout Big Data (MEFASD-BD) was used to resolve the multi-objective optimization challenge, and the Non-Dominated Sorting Genetic Algorithm-II (NSGA-II) was utilized to handle the rising dimensionality issue through subgroup discovery. To address the NSGA-II’s slow convergence rate, an Improved Multi-Objective Meta-Heuristic Fuzzy approach for discovering subgroups in big data is described, that contains a meta-heuristic method for subgroup discovery known as the Multi-Objective Differential Search Algorithm (MODSA). It selects the most relevant subgroups from vast amounts of data, reducing the data’s dimensionality. The Fuzzy Deep Neural Network (FDNN) classifier assesses the main subgroups. By removing noisy data and selecting the most relevant subgroups, the performance of FDNN in classifying vast amounts of data is improved.

A novel technique is presented for Maximum Power Point Tracking (MPPT) based photovoltaic (PV) system in partial shadow conditions for harvesting maximum power. In this paper, a hybrid technique is developed, which combines Black Widow Optimization (BWO) with Recurrent Neural Network (RNN). To train the data set and provide a control signal for the converter, an RNN is used. After fitting the training data sets, the suggested method achieved maximum power by utilizing BWO based on the control parameters. This proposed method minimizes the difference between actual and average power. Using an optimization technique, the main goal of this proposed strategy is to obtain peak power harvest under various conditions, including partial shading, while minimizing error function, With the help of MATLAB/Simulink software, the conclusions are revealed under various partial shading conditions. For each category, the observed results are evaluated at various time intervals. The proposed method is also compared to other techniques such as the Ant Colony Optimization (ACO)-RNN system, Particle Swarm Optimization (PSO)-RNN system, and Gravitational Search Algorithm (GSA)-RNN system. The proposed system is 36.11% faster than GSA with RNN, 39.47% faster than PSO, and 42.5% faster than ACO with RNN in terms of tracking speed. Significantly, the proposed work is 0.87% more efficient than the other models in terms of obtaining maximum power. In terms of obtaining maximum power, the proposed work BWOA-RNN is more effective than other methods.

Energy or load disaggregation, as one essential part of non-intrusive load monitoring (NILM), is an efficient way to separate the consumption information of target appliances from the whole consumption data, and can accordingly help to regulate people’s energy consumption behaviors. However, the consumptions of the target appliances are usually affected by the variance of the opening time, working condition and user interference, so it is a difficult task to realize precise disaggregation. To further improve the energy disaggregation accuracy, this paper proposes a new parallel disaggregation strategy with two subnets for the energy consumption disaggregation of the target appliances in the residential buildings. In the proposed strategy, the parallel disaggregation network contains a long-term disaggregation network and a short-term disaggregation network, which can automatically and respectively learn the long-term trend features and short-term dynamic characteristics of the electrical appliances. This parallel structure can make full use of the advantages of different methods in feature extraction, so as to model the appliance features more comprehensively. To better extract the long-term and short-term features, in the long-term disaggregation subnet, we propose the double branch bi-directional temporal convolution network (DBB-TCN) which has a wider receptive field than the traditional temporal convolution networks (TCN), while in the short-term disaggregation subnet, we adopt the convolution auto-encoder to learn the short-term characteristics of the target appliances. Finally, detailed experiments and comparisons are made with two real-world datasets. Experimental results verified that the proposed parallel disaggregation method performs better than the existing methods under various evaluation criteria.

One of the fastest-growing fields in today’s world is data analytics. Data analytics paved the way for a significant number of research and development in various fields including medicine and vaccine development, DNA analysis, artificial intelligence and many more. Data plays a very important role in providing the required results and helps in making critical decisions and predictions. However, ethical and legislative restrictions sometimes make it difficult for scientists to acquire data. For example, during the COVID-19 pandemic, data was very limited due to privacy and regulatory issues. To address data unavailability, data scientists usually leverage machine learning algorithms such as Generative Adversarial Networks (GAN) to augment data from existing samples. Today, there are over 450 algorithms that are designed to re-generate or augment data in case of unavailability of the data. With many algorithms in the market, it is practically impossible to predict which algorithm best fits the problem in question, unless many algorithms are tested. In this study, we select the most common types of GAN algorithms available for image augmentation to generate samples capable of representing a whole data distribution. To test the selected models, we used two unique datasets, namely COVID-19 CT images and COVID-19 X-Ray images. Five different GAN algorithms, namely CGAN, DCGAN, f-GAN, WGAN, and CycleGAN, were selected and applied to the samples to see how each algorithm reacts to the samples. To evaluate their performances, Visual Turing Test (VTT) and Fréchet Inception Distance (FID) were used. The VTT result shows that a human expert can accurately distinguish between different samples that were produced. Hence, CycleGAN scored 80% in CT image dataset and 77% in X-Ray image dataset. In contrast, the FID result revealed that CycleGAN had a high convergence and therefore generated high quality and clearer images on both datasets compared to CGAN, DCGAN, f-GAN, and WGAN. This study concluded that the CycleGAN model is the best when it comes to image augmentation due to its friendliness and high convergence.

In this research, UPQC (Unified Power Quality Conditioner) with optimized hybrid fuzzy controller based GBSSA (Gaussian Barebone Salp Swarm Algorithm) with EPLL (Enhanced Phase Locked Loop) have been proposed for power quality enhancement in power distribution networks. Using the proposed method, the difficulties in major of the power distribution system networks can be solved, related to power quality issues. GBSSA has been employed in this research, to improve solution accuracy and optimization efficiency. Given that, it is permissible to add some extra time cost to acquire a better solution, based on the Non-Free Lunch (NFL) theory, and that the time consumption of function evaluation is rather large, when addressing actual optimization problems, the extra time consumption can be overlooked to some extent. The EPLL control method improves the standard PLL, by reducing its fundamental flaw, which is the occurrence of main frequency errors, as well as double frequency errors. It controls the DC-bus voltage of unified power quality conditioners, during supply voltage and load voltage turbulences. The proposed UPQC control technique has been found to be resilient, to a variety of source and load perturbations, including unbalanced, transient distorted supply, voltage sag, unbalanced load and voltage swell. The proposed optimized GBSSA hybrid fuzzy controller with EPLL has been proven to be more effective in reducing the THD (Total Harmonic Distortion) to 3.22%. Moreover, comparative analysis with a conventional TSF-PLL has been performed with that of Takagi-Sugeno fuzzy controller and implemented using MATLAB (MATrix Laboratory).

The required division and exponentiation operations needed per iteration for the possibilistic c-means (PCM) clustering algorithm complicate its implementation, especially on homomorphically-encrypted data. This paper presents a novel efficient soft clustering algorithm based on the possibilistic paradigm, termed SPCM. It aims at easing future applications of PCM to encrypted data. It reduces the required exponentiation and division operations at each iteration by restricting the membership values to an ordered set of discrete values in [0,1], resulting in a better performance in terms of runtime and several other performance indices. At each iteration, distances to the new clusters’ centers are determined, then the distances are compared to the initially computed and dynamically updated range of values, that divide the entire range of distances associated with each cluster center into intervals (bins), to assign appropriate soft memberships to objects. The required number of comparisons is O(log the number of discretization levels). Thus, the computation of centers and memberships is greatly simplified during execution. Also, the use of discrete values for memberships allows soft modification (increment or decrement) of the soft memberships of identified outliers and core objects instead of rough modification (setting to zero or one) in related algorithms. Experimental results on synthetic and standard test data sets verified the efficiency and effectiveness of the proposed algorithm. The average percent of the achieved reduction in runtime is 35% and the average percent of the achieved increase in v-measure, adjusted mutual information, and adjusted rand index is 6% on five datasets compared to PCM. The larger the dataset, the higher the reduction in runtime. Also, SPCM achieved a comparable performance with less computational complexity compared to variants of related algorithms.

Software developers find it difficult to select the specific detection rules for different smell types. A set of metrics, thresholds and labels constitutes a code smells detection rule. The generated rules must be optimized efficiently to ensure successful rule selection. The objective is to identify how rules are generated from the labeled data set and selected using bio-inspired algorithms. The goals are met by employing the C4.5 and RIPPER algorithms to generate rules then, optimized using two bio-inspired algorithms, the Salp Swarm Algorithm (SSA) and Cockroach Swarm Optimization (CSO). The optimized sets of rules are evaluated using the similarity metrics which are computed with the help of expected and the detected code smells. The common rule subsets from SSA and CSO are merged to produce the optimal rule subset which can be used for code smell detection. The proposed work has been experimented on Xerces-J, Log4J, Gantt Project and JFreeChart dataset. The work detected code smells with an accuracy of 91.7% for Xerces-J, 96.7% for JFreeChart, 88.6% for Gantt Project and 98% for Log4J. The findings will be useful for both theory and research since the proposed framework allows focusing on rule selection.

Waypoints have enhanced the prospect of fully autonomous drone applications. However, Geographical Position System (GPS) spoofing and signal interferences are key issues in waypoint-based drone applications. Also, conceptual waypoint-based drone applications require accurate awareness of waypoints based on environmental cues and integration of additional sensing modalities. Additional sensor modalities may overwhelm drones’ processing resources, reducing operational time. This study proposes W-MobileNet, a denoising model for autonomous trajectory trail navigation based on precision control of a path planner, denoising capabilities of Weiner filters, and perceptual knowledge of convolutional neural networks. Creatively integrating the modules of W-MobileNet results in an intuitive drone navigation controller characterized by position, orientation, and speed estimation. Further, a generic loss function that significantly aids models to converge faster during training is proposed based on adaptive weights. An extensive evaluation of a simulated and real-world experiment shows that W-MobileNet is more favorable in precision and robustness than contemporary state-of-the-art models. W-MobileNet has the potential to become one of the standards for autonomous drone applications.

In the hot strip rolling process, accurate prediction of bending force is beneficial to improve the accuracy of strip crown and flatness, and further improve the strip shape quality. Due to outliers and noise are commonly present in the data generated in the rolling process, not only the prediction accuracy should be considered, but also the uncertainty of prediction results should be described quantitatively. Therefore, for the first time, the authors establish an interval prediction model for bending force in hot strip rolling process. In this paper, we use Artificial Neural Network (ANN) and whale optimization algorithm (WOA) to produce a prediction interval model (WOA-ANN) for bending force in hot strip rolling. Based on the point prediction by ANN, interval prediction is completed by using lower upper bound estimation (LUBE) and WOA, and three indexes are used to evaluate the performance of the model. This paper uses real world data from steel factory to determine the optimal network structure and parameters of the interval prediction model. Furthermore, the proposed WOA-ANN model is compared with other interval prediction models established by other three optimization algorithms. The experimental results show that the proposed WOA-ANN model has high reliability and narrow interval width, and can well complete the interval prediction of bending force in hot strip rolling. This study provides a more detailed and rigorous basis for setting bending force in hot strip rolling process.

Location-routing problem (LRP) contains two Np-hard problems as, facility location (FL) and vehicle routing problem (VRP), in the same content. Since both problems directly affect the cost of distributions of the products and supply chain, the decision of location and routing is important for the success of companies. Therefore, many attempts are made to solve LRP problem in the literature. Researchers proposed exact and heuristic methods for LRP. However, exact methods cannot provide solutions for considerably large instances. In this paper, a new heuristic method is proposed for continuous or planar LRP. The proposed method contains fuzzy c-means for continuous location problem and simulated annealing algorithm for vehicle routing problem, respectively. The proposed method is applied to both capacitated and uncapacitated LRP instances that are widely used in the literature. Results of the proposed method are compared with successful researches that are made on this problem in terms of the total cost.

In this paper, the classification of power quality disturbances using combined ST/MST (S-Transform/Modified S-Transform) and Radial Basis Function Neural Network (RBFNN) is proposed. The extraction of significant features from the power quality disturbance signals is one of the challenging tasks in recognizing different disturbances. The Stockwell Transform/Modified Stockwell Transform (ST/MST) based features are distinct, understandable and more immune to noise. The important attributes present in the signals are retrieved from the ST/MST contours, MST 3D plots and MST based statistical curves. The relevant features are also extracted from the statistical curves. The extracted features are given as input to the RBFNN for further classification. This method is evaluated under both noisy and noiseless conditions. The performance of the proposed approach is compared with other conventional approaches in the literature. The simulation results demonstrate that the proposed MST based RFNN technique is more effective for the detection and classification of power quality disturbances.

The aim of this paper is to introduce a Frank operator in the q-rung orthopair triangular fuzzy linguistic environment on the basis of the notion of the Frank operator and the q-rung orthopair fuzzy set. Firstly, the concept of a q-rung orthopair triangular fuzzy linguistic set (q-ROTrFLS) is proposed, then several basic operations, score, and accuracy functions to compare the q-ROTrFLS values are defined. Secondly, a series of q-rung orthopair triangular fuzzy linguistic Frank aggregation operators are developed, such as q-rung orthopair triangular fuzzy linguistic Frank weighted average (q-ROTrFLWA)operator,q-rung orthopair triangular fuzzy linguistic Frank weighted geometric (q-ROTrFLWG) operator, and we introduce several relevant properties of these operators and prove their validity, and show the relevant relationship between some operators. Thirdly, two different decision-making approaches are constructed in the q-rung orthopair triangular fuzzy linguistic environment. Furthermore, a practical example is given to explain the developed methods. Finally, a comparative study is conducted, and the relevant sensitivity analysis is also discussed, and the outcome shows the prominence and the effectiveness of the developed methods compared to previous studies.

Information system (IS) is a significant model in the field of artificial intelligence. Information structure is not only a research direction in the field of granular computing (GrC), but also an important method to study an IS. A multiset-valued information system (MVIS) refers to an IS where information values are multisets. A MVIS can be seen as a model that is the result of information fusion of multiple categorical ISs. This model helps deal with missing values in the dataset. This paper studies information structures in a MVIS on the view of GrC and consider their application for uncertainty measurement (UM). First of all, some notions of multisets and probability distribution sets (PDSs) are proposed. Naturally, relationships between multisets and PDSs are researched. Then, the concept of a MVIS based on the notion of multisets is given, and the internal structure of a MVIS is revealed by an incomplete information system (IIS). Furthermore, tolerance relations in a MVIS are defined by using Hellinger distance, and tolerance classes are obtained to construct the information structures of a MVIS. Considering the association of information structures, relationships between information structures are raised from the two aspects of dependence and separation. Moreover, some properties between information structures are provided by using information distance and inclusion degree. Finally, four UMs as the applications of information structures are investigated, and comprehensive experiments on several datasets demonstrate the feasibility and superiority of the proposed measures. These results will be helpful for establishing a framework of GrC in a MVIS and studying UM.

In this paper proposes an efficient hybrid approach for resolve the issues based on unit commitment model integrated with electric vehicles considering the responsive load. The proposed hybrid approach is the combined performance of both the Multi-fidelity meta-optimization and Turbulent Flow of water based optimization (TFWO) and later it is known as MFM-TFWO method. The major objective of proposed approach is reduction of operational costs, reduction of real power losses, and reduction of emissions and improves the voltage stability index. The proposed system is incorporated with wind turbine and photovoltaic, electrical and thermal energy storage systems. The MFM approach is performed for the optimization of the best combination of thermal unit depend on uncertainty; cost minimization, constraints of the system. For capturing the uncertainty and ensuring the demand satisfaction is performed by the TFWO approach. The proposed approach evaluates the impact of the stochastic behavior of electric vehicles and responsive load of the demand side management. The proposed method considers the uncertainty of PV, wind, thermal, electrical demands, and electric vehicles. At last, the proposed model is actualized in MATLAB/Simulink platform and the performance is compared with other techniques. The simulation results depicted that electric vehicles and responsive loads on energy management is decreasing the operation cost and emissions.

With the continuous opening up of China’s dairy market to foreign countries, dairy products import volume continues to grow rapidly. The structural vector autoregressive model (SVAR) was used in this article to analyze the impact of dairy product imports on China’s raw milk production from 1996 to 2017. It is found that, dairy product import volume has a positive impact on China’s raw milk production, and negative impact on the liquid dairy product; and mainly negative impacts on the cost control variables in the short term. The price of corn has a stronger impact on the raw milk production compared with that of the soybean meal prices and crude oil price; the impact of Domestic raw milk demand on raw milk production fluctuates frequently in the short term, and has a positive impact on the diary export. Based on this, this article believes that adjusting the milk industry policy, optimizing the dairy products import structure and the dairy cows’ source structure, and advocating scientific feeding can effectively alleviate the impact caused by dairy products import.

In wireless sensor network (WSN), routing is one of the substantial maneuvers for distributing data packets to the base station. But malevolent node outbreaks will happen during routing process, which exaggerate the wireless sensor network operations. Therefore, a secure routing protocol is required, which safeguards the routing fortification and the wireless sensor network effectiveness. The existing routing protocol is dynamically volatile during real time instances, and it is very hard to recognize the unsecured routing node performances. In this manuscript, a Deep Dropout extreme Machine learning optimized Improved Alpha-Guided Grey Wolf based Crypto Hash Signature Token fostered Blockchain Technology is proposed for secure dynamic optimal routing in Wireless Sensor Networks (SDOR-DEML-IAgGWO-CHS-BWSN). In this, Crypto Hash signature (CHS) token are generated for flow accesses with a secret key owned by each routing sensor node and it also offers an optimal path for data transmission. Then the secured dynamic optimal routing information is delivered through the proposed Blockchain based wireless sensor network platform with the help of Deep Dropout Extreme Machine learning optimized Improved Alpha-Guided Grey Wolf routing algorithm. Then the proposed method is simulated using the NS-2 (Network Simulator) tool. The simulation performance of the proposed SDOR-DEML-IAgGWO-CHS-BWSN method provide 76.26%, 65.57%, 60.85%, 48.99% and 42.9% lower delay during 30% malicious routing environment, 73.06%, 63.82%, 59.25%, 44.79% and 38.84% lower delay during 60% malicious routing environment is compared with the existing methods.

 Knowledge graphs have been introduced into recommender systems due to the rich connectivity information. Many knowledge-aware recommendation methods use graph neural networks (GNNs) to capture the high-order structural and semantic information of knowledge graphs. However, previous GNN-based methods have the following limitations: (1) they fail to make full use of the neighborhood information of entities and (2) they ignore the importance of user interaction sequences on reflecting user preferences. As such, these models are insufficient for generating accurate representations of users and items. In this study, we propose a Knowledge-aware Hierarchical Attention Network (KHAN) to provide better recommendation. Specifically, the proposed model mainly consists of an item encoder and a user encoder. The item encoder is equipped with a hierarchical attention network, which is used to generate entity (item) representations by carefully aggregating neighborhood information of entities. The user encoder is also designed to learn more informative user representations from user interaction sequences using multi-head self-attention. The learned user representations are then combined with user representations introduced in the item encoder through a gating mechanism to generate the final user representations. Extensive experiments on two real-world datasets about movie and restaurant recommendation demonstrate the effectiveness of our model.

The modified bee colony algorithm is one of the excellent methods that has been proposed in recent years for data clustering. This MBCO algorithm randomly values the primary centers of the cluster by selecting a number of data from the data set, which makes the algorithm sensitive to the presence of noise and outgoing data in the data set and reduces its performance. Therefore, to solve this problem, the proposed method used three approaches to quantify the initial centers of the clusters. In the proposed method, first the initial centers of the clusters are generated by chaos methods, KMeans++algorithm and KHM algorithm to determine the optimal position for the centers. Then the MBCO algorithm starts working with these centers. The performance of the proposed method compared to a number of other clustering methods was evaluated on 7 UCI datasets based on 6 clustering evaluation criteria. For example, in the iris data set, the proposed method with chaos approaches, KHM and KMeans++with accuracy of 0.8725, 0.8737 and 0.8725, respectively, and the MBCO method with accuracy of 0.8678, and in terms of CH criteria, the proposed method with chaotic approaches, KHM and KMeans++reached values of 0.3901, 0.54848, 0.5147 and MBCO method of 0.3620, respectively. Better achieved. In general, the results of the experiments according to the 6 evaluation criteria showed better performance of the proposed method compared to other methods in most data sets according to the 6 evaluation criteria.

We examine correlation coefficients for single-valued neutrosophic hesitant fuzzy sets (SVNHFSs) to point out their questionable results for the ideal alternative. Then, we propose three similarity measure methods to solve multi-criteria decision-making (MCDM) problems. Three applications, namely, ranking of alternatives, dysfunctional comments of turbine engine generators, and disease diagnoses for patients, illustrate the stability and effectivity of our new similarity. Our findings will help researchers deal with similarity measures in the future.

Blood vessel segmentation of the retina has become a necessary step in automatic disease identification and planning treatment in the field of Ophthalmology. To identify the disease properly, both thick and thin blood vessels should be distinguished clearly. Diagnosis of disease would be simple and easier only when the blood vessels are segmented accurately. Existing blood vessel segmentation methods are not supporting well to overcome the poor accuracy and low generalization problems because of the complex blood vessel structure of the retina. In this study, a hybrid algorithm is proposed using binarization, exclusively for segmenting the vessels from a retina image to enhance the exactness and specificity of segmentation of an image. The proposed algorithm extracts the advantages of pattern recognition techniques, such as Matched Filter (MF), Matched Filter with First-order Derivation of Gaussian (MF-FDOG), Multi-Scale Line Detector (MSLD) algorithms and developed as a hybrid algorithm. This algorithm is authenticated with the openly accessible dataset DRIVE. Using Python with OpenCV, the algorithm simulation results had attained an accurateness of 0.9602, a sensitivity of 0.6246, and a specificity of 0.9815 for the dataset. Simulation outcomes proved that the proposed hybrid algorithm accurately segments the blood vessels of the retina compared to the existing methodologies.

Enterprise Resource Planning (ERP) gives an organization a competitive edge by centralizing organization data and collaborating among supply chain networks. There are many types of software packages available, so most of the research proposed methods for prioritizing the best system. However, they did not suggest how to implement it, or which practices should be employed. So, this paper aims to propose a framework and a method for the selection of an ERP system and the best practice for implementation at the same time. A hybrid method of Logarithmic Fuzzy Preference Programming (LFPP) and Decision-Making Trial and Evaluation Laboratory (DEMATEL) is presented for solving the problem. LFPP is reliable in obtaining weights, while DEMATEL can capture interrelationships between practices. It was applied to a case study supply chain network of a Thai automotive parts manufacturer to demonstrate the applicability; it could establish the priorities of criteria, rank alternatives, and select the appropriate practices at the same time. There is no study about software and practice selection by use of this proposed method before. The comparison of LFPP and the Fuzzy Full Consistency Method (FUCOM-F) was also performed. It shows that FUCOM-F uses a smaller number of pairwise comparisons than LFPP, but the obtained weights of LFPP are more consistent with the evaluation matrix than using FUCOM-F.

IoT-Mobile Wireless Sensor Networks (IMWSNs) are being employed in a variety of simulators to visually demonstrate the exposure, energy usage situation, and expected life duration of Internet of Things (IoT) mobile sensors. The majority of academics have projected and expanded routing procedures in order to extend the network’s life cycle. In IMWSNs, clustering is the most important process for improving energy efficiency. In cluster approaches, each IoT sensor node provides the acquired data to the cluster-head of their own cluster. The cluster-head embraces the conscientiousness of gathering prepared information and directing it to the arranged network’s basestation. A fuzzy based energy proficient secure clustered routing (FEPSRC) is proposed in this research effort, which takes the residue energy, remoteness from the basestation, and compactness of IoT sensor nodes in its locality as input to the Fuzzy-Inference-System. For cluster-head selection, an eligibility ratio is calculated for each IoT sensor node. This protocol guarantees energy harmonizing by electing the preeminent IoT sensor node for the position of cluster-head, velocity of IoT sensor nodes are estimated and also provides best path for routing. The simulation consequence illustrates that projected fuzzy based energy proficient secure clustered routing condensed entire power expenditure, diminishes E-to-E delay, amplifies packet deliverance percentage and accomplishes maximal network life span.

Melanoma, a kind of fatal skin cancer, originates in melanin secreting cells of the dermis. Disease identification in the early stages assures a high survival rate for the patient. Most of the existing techniques retard the cancer detection phase. Surface-Enhanced Raman Spectroscopy (SERS) can capture fine details from the specimens that machine learning models can utilize to discriminate between healthy and diseased individuals rapidly. Our research work proposes a deep autoencoder based hybrid dimensionality reduction approach with a machine learning model on SERS spectrums of human skin fibroblast for melanoma cancer diagnostics. SERS measurements of 307 samples in total, belonging to two different classes, such as normal (157 samples) and malignant melanoma (150 samples), are used in this study. The SERS spectra measurements for both the samples lie between 100cm^-1 and 4278cm^-1. The variations in the intensity of Raman bands between both classes are intrinsically subtle. Neighborhood Component Analysis (NCA) technique has been exerted to transform 2090 dimensional spectral features into 2090 dimensional vectors and then the Deep Autoencoder (DAE) model is used to handle the nonlinearity in the data and produce the latent space, while Linear Discriminant Analysis (LDA) classifier have been employed for discriminating the normal and cancer cells. The k-fold cross-validation technique with a k value of 10 is implemented to assess the metrics of the model. The stated hybrid (NCA and DAE) model with 10-dimension latent space achieves an accuracy of 98%, the sensitivity of 99% and specificity of 97%, respectively. Due to the high-intensity nature of the SERS spectrum, the existing linear dimensionality reduction based discriminating model fails if the class label (Normal or Cancer) gets distributed on the low variance side. The proposed methodology captures both linear and nonlinear underlying structures present in the spectrums, resulting in better classification compared to the standard dimensionality reduction techniques.

In recent years, the extensions of fuzzy sets are much more familiar in almost all fields as they are reliable in defining the imprecise information of every decision-making situation. In this sequence of extensions, the cubical fuzzy sets are very efficient in dealing with imprecise information as it extends picture and spherical fuzzy sets. This article is interested in developing a new improved cubical fuzzy possibility degree measure. The desirable properties of the developed measure are also discussed. The advantage of the proposed measure is that it is capable of comparing the cubical fuzzy numbers in fuzzy nature itself and provides the degrees of preference relations between them. A comparison study is made with the existing ranking measures to exhibit the feasibility and validity of the proposed approach. Based on the improved measure, a method for ranking cubical fuzzy numbers is constructed. A solution approach to a cubical fuzzy multiple attribute decision-making problem is presented. To exhibit the potency and the practical applicability of the proposal, two real-life instances of selecting the best-cutting fluid for cutting gears have been illustrated. The results are compared with the literature.

In order to ensure the safe transmission of the information of the secondary distribution system across the regional network, this paper studies a security monitoring method of the secondary distribution system across the regional network based on the Internet of things technology and the improved fuzzy clustering algorithm. The Internet of things technology is used to collect the information transmission in cross region network of the secondary power distribution system and store it in the database; Combined with the shadow set to improve the basic fuzzy C-means clustering algorithm, the improved fuzzy C-means clustering algorithm is obtained. The cross region information transmission in the clustering database is divided into two categories: security and risk, and the risk information obtained by clustering is divided into four risk types, so as to realize the security monitoring of information transmission in cross region network of secondary power distribution system. The results show that the average monitoring rate of this method can reach 93.93%, the information collection is efficient and accurate, the number of packet losses is low, and the clustering results are stable and reliable, which can ensure the safe information transmission of cross region network of the secondary power distribution system.

This paper studies the robot-written character identification problem under an end-to-end semi-supervised deep learning framework consisting of semi-supervised learning and deep learning modules. The learning framework allows a deep neural network to be trained on labeled and pseudo-labeled samples where pseudo-labeled samples refer to the samples with labels predicted by the semi-supervised learning module. Moreover, to guarantee the feasibility of the learning framework, a two-stage strategy is proposed for training the deep neural network. Specifically, the two-stage training strategy adopts pseudo-labeled samples firstly to train a deep neural network, then the deep neural network is refined using labeled samples one more time. As a result, more samples can be used for training a deep neural network, which is significant to the performance improvement of a deep neural network in the case of inadequate labeled samples. More importantly, the deep neural networks trained under the proposed learning framework perform better than the famous deep neural networks in a robot-written character identification experiment.

Automatic segmentation of aortic true lumen based on deep learning can save the time for diagnosis of aortic dissection. However, fuzzy boundary, small true lumen region, and high similarity usually leads to inaccurate prediction. To make better use of the details supplemented by the encoder to restore boundaries, we decompose the recovery of detail features in the decoder into two sub-processes: calibration and distraction mining. And we propose a novel calibration and distraction mining (CDM) module. It utilizes deep features to calibrate shallow features so that features are concentrated in the main region. Then, it leverages the distraction mining procedure to extract false-negative features as a supplement to calibrated features and recover details of the segmentation object. We construct CDM-Net and verify its performance on the Aorta-CT dataset (private dataset), it achieves the Dice similarity coefficient of 96.94% and the Jaccard index coefficient of 94.08%, which is the best compared with 10 latest methods. Similarly, we explore its robustness on three more public datasets, including ISIC 2018 dataset (skin lesion segmentation), the 2018 data science bowl dataset (nucleus segmentation), LUNA dataset (lung segmentation). Experimental results prove that our method produces competitive results on all three data sets. Through quantitative and qualitative research, the proposed CDM-Net has good performance and can process aortic slices with complex semantic features, additional experiments show that it has good robustness, and it has the potential to be applied and expanded conveniently.

Although re-entrant hybrid flow shop scheduling is widely used in industry, its processing and delivery times are typically determined using precise values that frequently ignore the influence of machine failure, human factors, the surrounding environment, and other uncertain factors, resulting in a significant gap between theoretical research and practical application. For fuzzy re-entrant hybrid flow shop scheduling problem (FRHFSP), an integrated scheduling model is established to minimize the maximum completion time and maximize the average agreement index. According to the characteristics of the problem, a hybrid NSGA-II (HNSGA-II) algorithm is designed. Firstly, a two-layer encoding strategy based on operation and machine is designed; Then, a hybrid population initialization method is designed to improve the quality of the initial population; At the same time, crossover and mutation operators and five neighborhood search operators are designed to enhance the global and local search ability of the algorithm; Finally, a large number of simulation experiments verify the effectiveness and superiority of the algorithm.

 Many real-world knowledge graphs are complex and keep evolving over time. Inferring missing facts in temporal knowledge graphs is a fundamental and challenging task. Previous studies focus on link prediction in static knowledge graphs which hardly extracts the temporal features effectively. In this paper, we propose a novel deep learning model, namely KBGAT-BiLSTM, which is capable of solving long-term predict problems and is suitable for temporal knowledge graph with complex structures. First, we adapt the Graph Attention Network (GAT) to learn the structural features of knowledge graph. Then we utilize the Bidirectional Long Short-Term Memory Networks (BiLSTM) to learn the temporal features and obtain the low-dimensional embeddings of entities and relations. Finally, we employ a scoring function for link prediction in temporal knowledge graphs. Through extensive experiments on YAGO, WIKI, and ICEWS18 datasets, we demonstrate the effectiveness of our model, compare the performance of our model with several different state-of-the-art methods and further analyze the properties of the proposed method.

A hybrid method for transformer-less grid-tie hybrid Renewable Energy Source (HRES), such as photovoltaic (PV) and wind energy system (WES) with minimization of common mode leakage current is proposed in this manuscript. The proposed system is the combined execution of Vascular Invasive Tumor Growth (VSTG) Optimization Algorithm and extreme gradient boosting (XGBOOST) named VSTG-XGBOOST control topology. The main intention of transformerless grid-connected HRES system is “to lessen the leakage current, maximum power point (MPP) extraction and maximal power point tracking (MPPT), the active and reactive power controller, and having the unity power factor. To attain the above-mentioned aims, the following actions have been performed in this proposed work. Two turn-off snapper circuits are inserted parallel to the switches to share the input DC voltage among snubber capacitors. By then, VSTG is used to estimate the optimal gain parameters under various source currents as normal value is used to generate the optimal control signal database offline. Based on the attained dataset, the XGBOOST forecasts the optimal control signals of the grid-connected HRES inverter in the online way. This control technique allows two sources to supply the load separately depending on the availability of the energy sources and keeps common DC voltage constant.

 In this paper, we introduce a new fuzzy contraction mapping and prove that such mappings have fixed point in τ-complete fuzzy metric spaces. As an application, we shall utilize the results obtained to show the existence and uniqueness of random solution for the following random linear random operator equation. Moreover, we shall show the existence and uniqueness of the solutions for nonlinear Volterra integral equations on a kind of particular fuzzy metric space.

Cervical cancer is the most frequent and fatal malignancy among women worldwide. If this tumor is detected and treated early enough, the complications it causes can be minimized. Deep learning demonstrated significant promise when imposed on biomedical difficulties such as medical image processing and disease prognostication. Therefore, in this paper, an automatic cervical cell classification approach named IR-PapNet is developed based on Inception-ResNet which is an optimized version of Inception. The learning model’s conventional ReLu activation is replaced with the parametric-rectified linear unit (PReLu) to overcome the nullification of negative values and dying ReLu. Finally, the model loss function is minimized with the SGD optimization model by modifying the attributes of the neural network. Furthermore, we present a simple but efficient noise removal technique called 2D-Discrete Wavelet Transform (2D-DWT) algorithm for enhancing image quality. Experimental results show that this model can achieve a top-1 average identification accuracy of 99.8% on the pap smear cervical Herlev datasets, which verifies its satisfactory performance. The restructured Inception-ResNet network model can obtain significant improvements over most of the state-of-the-art models in 2-class classification, and it achieves a high learning rate without experiencing dead nodes.

 Video Processing has found enormous applications in recent times from security systems to interplanetary missions. In real-life situations, most of the videos are fuzzy/vague/uncertain. Intuitionistic fuzzy set (IFS) is one of the effective tools for handling uncertainty. Among many extensions of IFSs, temporal intuitionistic fuzzy sets (TIFSs) are very interesting as they are time-dependent. Hence, TIFSs are suitable to define a video, which is dynamic and hence depends on time-moment. In this way, this work introduces a novel VIdeo PROCessing (VIPROC) algorithm, using temporal intuitionistic fuzzy sets to enhance videos, which is first of its kind in existence. The comparison is made with fuzzy contrast intensification operation. VIPROC algorithm is designed using contrast intensification operation for video enhancement. The results are encouraging in comparison with the original test videos. The results are discussed taking into account the several frames of the test video. Further, the proposed algorithm can be applied/extended to engineering applications like motion tracking, traffic detection systems, real time videos captured through mobile (hand-held) devices, and so on. As no such algorithms are existing which use TIFSs to process a video, the authors got motivated to design and develop VIPROC algorithm.

Intelligent transport system is a greatly emerging technology in recent years. The stability and reliability of these systems is very important. In vehicular ad-hoc networks (VANET), the data transmission process can be improved by employing clustering process. The nodes can be clustered in order to utilize the maximum bandwidth of the network and improving network stability. In VANETs it is to introduce road safety and driver safety. In addition, security is a major concern and the malicious nodes need to be accurately detected. Several kinds of attacks can present in the VANETs. Hence an efficient authentication method and trust aware method is essentially required. In this work, stability assured CNN based trust aware clustering and authenticated transmission is introduced. For data authentication quantum cryptography technique is employed. In clustering process, trust degree of nodes is computed, vehicle speed is observed, direction of vehicle and distance among nodes are taken. In addition, for ensuring more safety, the critical data transmission is given higher priority. Therefore in clustering, data criticality parameter is also considered. For cluster formation, convolution neural network is employed. After the clustering process, the quantum cryptography based authentication is implemented for vehicle units and road side units. Data among these units are transmitted with quantum channel encryption key. Then simulation results are observed for validating the proposed protocol.

Inventory managers are expected to handle a large number of items in their inventory while adhering to budgetary and space limits, as well as the number of items bought from vendors. Multi-item inventory models with one or more resource constraints, such as budget, space, or number of orders. This paper talks about an EOQ model in neutrosophic multi-item inventory control models with constraints. The ordering costs, the holding costs, demands, storage area, investment amount, and the maximum average number of units are considered as triangular neutrosophic numbers, as opposed to crisp values, to make the inventory model more realistic. This idea is used to decide the neutrosophic optimal order quantities with the assistance of the Lagrange multiplier. Eventually, the proposed method is delineated with a numerical instance and the results are analysed briefly.

GPS monitoring systems and the development of driverless vehicles are almost inseparable from camera images. The images taken by traffic cameras often contain certain sky areas and noise, the traditional dark channel prior (DCP) algorithm easily produces color distortion and halo effect, when processing the hazy traffic images with sky and high brightness areas. An optimized Retinex model and dark channel prior algorithm (ORDCP) is proposed in this paper. Firstly by adjusting the calculation method of dark channel image, the proportion of dark channel is improved; Then, the transmittance image is corrected and smoothed by guided filtering and mean filtering. Finally, the Retinex model is fused to save the details.ORDCP corrects the inaccurate calculation of scene transmittance value in DCP algorithm,and modifies some dehazing problems, such as the loss of details, halo effect, contrast and color distortion,etc. Using information entropy (IE) as the objective evaluation index, combined with the subjective evaluation, it is concluded that the algorithm proposed in this paper can effectively retain the detailed information of the image, and eliminate the halo effect. Meanwhile, it meets the visual characteristics of human eyes better, and has some practicality and applicability in traffic control and intelligent detection.

An improved algorithm of image defogging was proposed based on dark channel prior in order to solve the low efficiency and color distortion in the bright area using original algorithm. If the image contains large areas of bright areas such as sky, white clouds or partial white objects and water surface, we can know that the dark channel prior theory does not apply to these areas. Firstly, it is necessary to clear the bright area of the image. According to principle that he adjacent pixel attributes have similarity, the image transmittance of the local region also has similarity, Block function is Consruted. Applied the dark channel prior, judging whether each block includes a bright area by the absolute value of difference of atmospheric intensity and dark channel, the dark and bright areas of the image are obtained. So the estimation value of the adaptive space transmittance are also obtained. Secondly, the transmittance of bright region is small and it causes deviation, so the enhancement formula is used to modify it dynamically. In order to preserve the edge details after image restoration, for bright areas, using texture function to optimize transmittance independently, for others, using gradient and texture function together. Finally, it restored the fog-free image applying the atmospheric scattering model. The experimental results showed that the restored image had obvious details and rich color and fast processing speed through the proposed algorithm. The algorithm can also be applied to outdoor visual systems, such as video surveillance, intelligent traffic and so on.

Because multiple domain cyberspace joint attacks are becoming more widespread, establishing a multiple domain cyberspace defensive paradigm is becoming more vital. However, although some physical domain and social domain information is incorporated in present approaches, total modeling of cyberspace is absent, therefore thorough modeling of cyberspace is becoming increasingly necessary. This paper proposed a knowledge graph based multiple domain cyberspace modeling approach. A knowledge graph of multiple domain cyberspace is produced by extracting multiple domain entity information and entity relations such as physical domain, social domain, network domain, and information domain, so that semantic information of multiple domain cyberspace may be described consistently. At the same time, this paper proposed a user’s permissions reasoning method based on multiple domain cyberspace knowledge graph to address the user’s permissions reasoning that relies on artificial reasoning principles. Through the model learning knowledge graph triples characteristics and rules, and implementing automatic reasoning of user’s permissions, this proposed method can abandon the artificial model of writing reasoning rules, allowing the machine to learn the reasoning rules using machine learning and other methods. Experimental results showed that the proposed method can learn relevant reasoning rules and accomplish automated reasoning of user’s permissions, and that the method’s accuracy and recall rates are higher than those of path ranking and translating embeddings.

This paper is to improve the privacy and security in the distributed virtual environment using blockchain technology. One of the feature it provides is greater security in the decentralized virtual environment. A key aspect of this technology is used for various fields like healthcare, finance, business and cloud environment. Key issue of the virtual environment is to protect the data privacy and security which is difficult to handle. To overcome this issue, a new security model to protect the virtual environment is created and will focus on different types of attacks in blockchain technology.

This paper presents the design of a grid connected hybrid system using modified Z source converter, bidirectional converter and battery storage system. The input sources for the proposed system are fed from solar and wind power systems. A modified high gain switched Z source converter is designed for supplying constant DC power to the DC-link of the inverter. A hybrid deep learning (HDL) algorithm (CNN-BiLSTM) is proposed for predicting the output power from the hybrid systems. The HDL method and the PI controller generates pulses to the proposed system. The superiority of the proposed hybrid DL method is compared with the conventional DL methods like CNN, LSTM, BiLSTM methods and the performance of the hybrid system is validated. A closed loop control framework is implemented for the proposed grid integrated hybrid system and its performance is observed by implementing the PI, Fuzzy and ANN controllers. A 1.5Kw hybrid system is designed in MATLAB/SIMULINK software and the results are validated. A prototype of the proposed system is developed in the laboratory and experimental results are obtained from it. From the simulation and experimental results, it is observed that the ANN controller with SVPWM (Space vector Pulse width Modulation) gives a THD (Total harmonic distortion) of 2.2% which is within the IEEE 519 standard. Therefore, from the results it is identified that the ANN-SVPWM method injects less harmonic currents into the grid than the other two controllers.

To safeguard private information, image steganography is extensively used. Research is focused on ways to enhance steganographic technologies so that they may increase compression ratio while maintaining steganography image integrity. Because of its essential qualities such as security, scalability, and robustness, Steganography is a preferred way of communicating protected secret information to prevent hacking and misuse. This proposed research offers a steganography approach based on Enhanced Chaotic Particle Swarm Optimization (ECPSO), which uses chaos theory to determine the optimal pixel positions in the cover picture to hide confidential information when keeping the steganography quality in the images. Both the cover and secret pictures are separated into blocks to increase hiding capacity, with each component storing a sufficient quantity of secret data by mapping the pixels. The suggested ECPSO-Stegano system has better results with the criteria of Mean Square Error (MSE) of 0.00018%, Peak-Signal-to-Noise-Ratio (PSNR) of 79.66%, Bit Error Rate (BER) of 0.45% in average, and Structural Similarity Index (SSI) of 0.98 in average for various input size. It’s also robust to statistical threats.

Chaotic systems are dynamic systems with aperiodic and pseudo-random properties, and systems in many fields exhibit chaotic time-series properties. Aiming at the fuzzy modeling problem of chaotic time series, this paper proposes a new fuzzy identification method considering the selection of important input variables. The purpose is to achieve higher model modeling and prediction accuracy by constructing a model with a simple structure. The relevant input variable was swiftly chosen in accordance with the input variable index after the Two Stage Fuzzy Curves method was used to determine the weight of the correlation between each input variable and the output from a large number of selectable input variables. The center and width of the irregular Gaussian membership function were then optimized using the fuzzy C-means clustering algorithm and the particle swarm optimization technique, which led to the determination of the fuzzy model’s underlying premise parameters. Finally, the fuzzy model’s conclusion parameters were determined using the recursive least squares method. This model is used to simulate three chaotic time series, and the outcomes of the simulation are contrasted and examined. The outcomes demonstrate that the fuzzy identification system has higher prediction accuracy based on a simpler structure, demonstrating its validity.

News feeds generate colossal amount of data consisting of important information hidden in the intricacies. State of the art methods are still at infancy in providing a very generic and publicly available solution to skim through the important information in the news from various sources and an ability to search using specific keywords in different languages. This paper focuses on designing a tool to extract semantic details from news articles published through various internet sources in various languages. The semantic information is stored within DBMS for ease of organizing and retrieving the data. Further, a querying facility to search through entire articles based on the keyword or date-based search is also proposed to view the crisp content. The news articles in English, and two Indian languages - Hindi and Malayalam are considered for experimentation. The proposed strategy consists of two main components namely, Generative model creation and Query engine. Generative model aims to extract important entities and keywords along with their relevance to the article and other similar articles using Latent Dirichlet Allocation(LDA) and Named Entity Recognition(NER). Query engine is to facilitate on the fly retrieval of semantic content from the database, based on user keyword. The search engine, along with database indexing, reduces the access time to the database thereby retrieving the information in less time. Experimental results show that the proposed method is effective in terms of quality of information and time consumed for information retrieval.

In India, most of the Science and Technology resources available are in English. Developing an Automatic Language Translation Engine from English (source language) to Tamil (target language) is very essential for the people who need to get technical resources in their native language. The challenges in designing such engines using Natural Language Processing (NLP) tools include Lexical, Structural, and Syntax level ambiguity. To solve these challenges, the development of a Part-Of-Speech (POS) tagger is essential. The Verb-Framed languages like Tamil, Japanese, and many languages in Romance, Semitic, and Mayan languages families have high morphological richness but lack either a large volume of annotated corpora or manually constructed linguistic resources for building POS tagger. Moreover, the Tamil Language has a low resource, high word sense ambiguity, and word-free order form giving rise to challenges in designing Tamil POS taggers. In this paper, we postulate a Hybrid POS tagger algorithm for Tamil Language using Cross-Lingual Transformation Learning Techniques. It is a novel Mining-based algorithm (MT), which finds equivalent words of Tamil in English on less volume of English-Tamil bilingual unannotated parallel corpus. To enhance the performance of MT, we developed Tamil language-specific auxiliary algorithms such as Keyword-based tagging algorithm (KT) and Verb pattern-based tagging algorithm (VT). We also developed a Unique pair occurrence-tagging algorithm (UT) to find the one-time occurrence of Tamil-English pair words. Our experiments show that by improving Context-based Bilingual Corpus to Bilingual parallel corpus and after leaving one-time occurrence words, the proposed Hybrid POS tagger can predict 81.15% words, with 73.51% accuracy and 90.50% precision. Evaluations prove our algorithms can generate language resources, which can improve the performance of NLP tasks in Tamil.

As technology advances, it becomes easier to share large amounts of data over the internet. Cloud computing is one of the technologies that allows for easy data sharing over the internet. It is critical to provide security for this data when they are being shared across the internet. The security of data saved in cloud storage, as well as data transport and transmitting a key required to encrypt data between two parties, has been a source of concern for the industry, as a result of the growing use of cloud services in recent years. Collective attacks are significantly more powerful than individual strikes, according to our research. Despite the fact that additional research works were studied in the previous literature review, there are some study concerns for not correcting third-party data hacking. Therefore, this paper focuses on the design of Secured Quantum Key Distribution (SQKD) with Fuzzy logic to improve the security of the shared key. Quantum Key Distribution, Post Quantum Key Distribution, and the EPR Proto-col are technologies that increase the security of data sharing. We have incorporated the Secured Quantum Key Distribution (SQKD) with Fuzzy logic in our proposed work to improve the security of the shared key. The proposed systems include some additional characteristics in addition to the existing approaches. The proposed model uses shifting algorithms and the fuzzification procedure to assure the security of the secret key in the Fuzzification of Quantum Key approach. The experimental results states that the mean value of security losses in SFQ is 1.8306051, and the mean value of QKD is 14.6448416, with standard deviations of 1.7329 and 13.863 for SFQ and QKD, respectively.

Masked face recognition embarks the interest among the researchers to find a better algorithm to improve the performance of face recognition applications, especially in the Covid-19 pandemic lately. This paper introduces a proposed masked face recognition method known as Principal Random Forest Convolutional Neural Network (PRFCNN). This method utilizes the strengths of Principal Component Analysis (PCA) with the combination of Random Forest algorithm in Convolution Neural Network to pre-train the masked face features. PRFCNN is designed to assist in extracting more salient features and prevent overfitting problems. Experiments are conducted on two benchmarked datasets, RMFD (Real-World Masked Face Dataset) and LFW Simulated Masked Face Dataset using various parameter settings. The experimental result with a minimum recognition rate of 90% accuracy promises the effectiveness of the proposed PRFCNN over the other state-of-the-art methods.

The article discusses the production of microwave components based on the technology of low-temperature co-fired ceramics (LTCC). A set of standards Continuous Acquisition and Life cycle Support (CALS) and International Organization for Standardization (ISO) and business process models in these standards are considered. Based on the basic models of the ISO and CALS standards, a structural-parametric description model (SPD) has been developed, in which the structure of ISO-9000 is preserved, and specific parameters of LTCC technology are added. The methodology of the (SPD) of this technology is proposed. Open source software for processes, resources, results, production operations, control and management has been developed for each technological operation (TO), workplace and area. The methodology for creating information support and Microsoft Access Database Management System (DBMS) of SPD is proposed. Recommendations for the development of a software-methodological complex of information support for SPD of LTCC technology are proposed.

Microgrids (MGs) are distributed generation and distribution systems that include distributed generation (DG) units, energy storage systems (ESSs), distributed reactive sources (DRSs), and resilient loads that can operate in either connected or isolated modes. When dealing with uncontrolled DGs such as Wind Energy Systems (WES) and Photovoltaic Energy Systems (PVES), MGs planners have a difficult time making decisions. The work proposed in this paper addresses three interconnected works: (i) the implementation of a rigorous hybrid optimization approach for reconfiguration and DGs placement; (ii) the performance investigation under uncertain behavior of RES-based DGs and demand; and (iii) performance enhancement realization through the replacement of hybrid DGs for RES-based DGs. An Improved Moth Flame Optimization (IMFO), which is a multi-objective optimization method, has been linked with fuzzy logic in order to handle multiple objectives in an efficient manner. These objectives include the minimization of voltage deviation, the reduction of generation cost, and the reduction of loss. The quality of the power, the amount of money saved by consumers, and the benefits to the Distribution System Operator (DSO) might all be improved with the help of a hybrid algorithm. This research is also extended to address the uncertainties of RES-based DGs by replacing hybrid DGs in the most optimal locations. IEEE 33 bus RDS is used to test radial distribution system (RDS) microgrids. For validation purposes, uses 24-hour load patterns to mimic WES and PVES’ 24-hour load dispatching behavior. The research findings clearly demonstrate the advantages of microgrids over traditional architectures. The hybrid DG requires an average generating cost of 185.33 $/kW in order to produce 100 kW of power throughout the day with significantly reduced emissions.

Fully Homomorphic Encryption (FHE) is the holy grail of encrypted communications. It opens the door to several advanced functionalities to overcome the security and trust issues of the IT world. After 2009, once Craig Gentry had shown that FHE could be achieved, a study in this field boomed, and significant improvement was made in identifying more efficient and realistic programs. FHE is primitive cryptography that enables arbitrary functions to be calculated via encrypted data. These systems are applicable in different ways since they permit users to encrypt their private information securely while still outsourcing the processing of protected data without fearing disclosing the real data. In 2012, LTV12 presented the first multi-key FHE system and demonstrated the possibility of using multi-key systems in somewhat homomorphic encryption (SHE). Like in the one key context, there have been many advances in the field, but no effort has been made to develop the multi-key methods. This paper presents a discussion of FHE and MKFHE with a specific focus on the current techniques and three implementations, comprising the first in the multi-key setups, to the extent of our understanding.