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

The density peaks clustering algorithm (DPC) has been widely concerned since it was proposed in 2014. There is no need to specify in advance and only one parameter required. However, some disadvantages are still witnessed in DPC: (1) Requiring repeated experiments for choosing a suitable calculation method of the local density due to the variations in the scale of the dataset, which will lead to additional time cost. (2) Difficulty in finding an optimal cutoff distance threshold, since different parameters not only impact the selection of cluster centers but also directly affect the quality of clusters. (3) Poor fault tolerance of the allocation strategy, especially in manifold datasets or datasets with uneven density distribution. Targetting solutions to these problems, a density peaks clustering based on local fair density and fuzzy k-nearest neighbors membership allocation strategy (LF-DPC) is proposed in this paper. First, to obtain a more balanced local density, two classic local density calculation methods are combined in the algorithm to calculate the local fair density through the optimization function with the smallest local density difference. Second, a robust two stage remaining points allocation strategy is designed. In the first stage, k-nearest neighbors are used to quickly and accurately allocate points from the cluster center. In the second stage, to further improve the accuracy of allocation, a fuzzy k-nearest neighbors membership method is designed to allocate the remaining points. Finally, the LF-DPC algorithm has been experimented based on several synthetic and real-world datasets. The results prove that the proposed algorithm has obvious advantages compared with the other five ones.

This paper aims to select the appropriate node(s) to effectively destabilize the terrorist network in order to reduce the terrorist group’s effectiveness. Considerations are introduced in this literature as fuzzy soft sets. Using the weighted average combination rule and the D–S theory of evidence, we created an algorithm to determine which node(s) should be isolated from the network in order to destabilize the terrorist network. The paper may also prove that if its power and foot soldiers simultaneously decrease, terrorist groups will collapse. This paper also proposes using entropy-based centrality, vote rank centrality, and resilience centrality to neutralize the network effectively. The terrorist network considered for this study is a network of the 26/11 Mumbai attack created by Sarita Azad.

Most of the research in fuzzy rough sets and fuzzy topological structures have been studied on the basis of fuzzy partially ordered sets. Instead of fuzzy partially ordered sets, the concept of distance functions in complete co-residuated lattices is introduced. Using distance functions, we define Alexandrov pretopology, Alexandrov precotopology and fuzzy interior (fuzzy closure) operators in complete co-residuated lattices, and we investigate their properties. Moreover, we prove that there exist isomorphic categories and Galois correspondence between topological categories.

The occlusion in the real feedlot environment is ubiquitous, and the current research based on the cattle face recognition under occlusion conditions is almost non-existent. Thus, an attention mechanism module with high accuracy and low model complexity is designed to incorporate into MobileNet so that the cattle face under occlusion can be identify accurately, which is the RGB images captured in the ranch environment. In this paper, we also construct a Simmental cattle face image dataset for data modeling and method evaluation, which contains 10,239 images of 103 cattle. The experimental results show that when the occluder is in the upper left and lower right corner, if the occlusion rate is less than 30%, the value of Top_1 reaches more than 90%; if it is less than 50%, the value of Top_1 is more than 80%. Even if the middle part occludes lots of important information, the occlusion rate of 40% has an accuracy of more than 80%. Furthermore, comparing the proposal model with MobileNet, the parameter and model size are equal, and the amount of calculation as a cost increase a little. Therefore, the proposal model is suitable to transplant to the embedded system in the future.

Over the past decade, the computer vision community has given increased attention to the development of age estimation systems. Several approaches to more accurate and robust facial age estimation have been introduced. Apparent age datasets are typically collected from uncontrolled environments, leading to a number of challenges. In this paper, a cascade model system, which we called the ‘Integrated Classification and Regression with Landmark Ratios (ICRL), is introduced. Our system uses a classification model in order to learn the age label distribution, then uses this knowledge as an auxiliary input to a regression model. ICRL is based on context facial information and label distribution analysis. Facial context information is introduced through the extraction of precise facial landmark ratios. Extracted landmark ratios allow the system to distinguish each age label. The ICRL system uses a classification model to train the CNN network to learn the in-between relation of age labels. ICRL sufficiently models the aging process in the form of ordered and continuous imagery. The ICRL system minimizes the number of parameters needed as well as overall computational costs whilst maintaining robust and accurate results. Despite its simplicity, our system has outperformed other state-of-the-art approaches when applied onto the MORPH II, CLAP2015, AFAD and UTKFace datasets. ICRL achieved an overall superior predictive performance, reaching 99.67% with MORPH II, 99.51% with AFAD, 96.52 with CLAP2015, and 96.28% with UTKFace.

Effectively identifying self-admitted technical debt (SATD) from project source code comments helps developers quickly find and repay these debts, thereby reducing its negative impact. Previous studies used techniques based on patterns, text mining, natural language processing, and neural networks to detect SATD. Compared with these above, Convolutional Neural Networks (CNN) have the strong feature extraction ability. Deep network ensembles are demonstrated great potential for the task of sentences classification. In order to boost the performance of CNN-based SATD detecting, we propose a deep neural network ensemble contribute to ensemble learning in a simple yet effective way. Specifically, CNN, CNN-LSTM (convolutional neural network and long short-term memory), and DPCNN (Deep Pyramid Convolutional Neural Networks) are used as individual classifiers to diversify the deep network ensembles. In order to improve the explainability, we introduce attention to measure the contribution of feature words to SATD classification. 62,285 source code comments from 10 projects were used in our experiments. The results show that our approach can effectively reduce misjudgment and detect more SATD, especially for cross-project, so as to greatly improve the detection accuracy.

The refining of information from the immense amount of unstructured data on the internet can be a critical issue in identifying public opinion. It is difficult to extract relevant concepts from huge amounts of data. Concept level semantic parsing is improved over word-based investigation as it conserves the semantical data relevant to many-word articulations. The semantic proposals offer a superior comprehension of textual data and serve to altogether precision the exactness of numerous mining operations in text assignments. The extraction of concepts from textual data is a significant step forward in content analysis at the concept stage. We present a CLSA-CapsNet method that extracts concepts from natural language text. Then the extracted concepts are applied in Capsule networks (CapsNet). Moreover, the integration of Concept Level Sentiment Analysis (CLSA) and Capsule Networks (CapsNet) has not yet been implemented on the hotel review dataset. This is the first attempt, which we researched and embraced by the capsule network, to develop classification models for hotel reviews. The developed results demonstrated excellent performance with a prediction accuracy of 86.6% for CLSA-CapsNet models, respectively. Various similarities have also been made across our techniques and they are implemented by some other deep learning algorithms, such as rnn-lstm. Overall, the outstanding success obtained by CLSA-CapsNet in this investigation highlights its ability in the hotel review dataset. We likewise show exploratory outcomes, in which the proposed system outpaced the state-of-the-art CLSA-CapsNet model.

The development of advanced technologies in variety of domains such as health care, sensor measurements, intrusion detection, motion capture, environment monitoring have directed to the emergence of large scale time stamped data that varies over time. These data are influenced by complexities such as missing values, multivariate attributes, time-stamped features. The objective of the paper is to construct temporal classification framework using stacked Gated Recurrent Unit (S-GRU) for predicting ozone level. Ozone level prediction plays a vital role for accomplishing healthy living environment. Temporal missing value imputation and temporal classification are two functions performed by the proposed system. In temporal missing value imputation, the temporal correlated k-nearest neighbors (TCO-KNN) approach is presented to address missing values. Using attribute dependency based KNN, the nearest significant set is identified for each missing value. The missing values are imputed using the mean values from the determined closest significant set. In temporal classification, the classification model is build using stacked gated recurrent unit (S-GRU). The performance of the proposed framework investigated using ozone multivariate temporal data sets shows improvement in classification accuracy compared to other state of art methods.

Caption generation using an encoder-decoder approach has recently been extensively studied and implemented in various domains, including image captioning and code captioning. In this research article, we propose one particular approach for completing a capture generation task using an “attention”-based sequence-to-sequence framework that, when combined with a conventional encoder-decoder model, generates captions in an attention-based manner. ResNet-152 is a Convolutional Neural Network (CNN) based encoder that generates a comprehensive representation of an input image while embedding that into a fixed size length vector. To predict the next sentence, the decoder uses LSTM, a Recurrent Neural Network (RNN), and an attention-based mechanism to concentrate attention on certain sections of an image selectively. Define a set of epochs to 69, which should be enough for training the model to generate informative descriptions, and the validation loss has reached its minimum limit and no longer decreases. We present the datasets as well as the evaluation metrics, as well as quantitative and qualitative analysis. Experiments on the MSCOCO and Flickr8k benchmark datasets illustrate the model’s efficacy in comparison to the baseline techniques. On MSCOCO, evaluation scores included BLEU-1 0.81, BLEU-2 0.61, BLEU-3 0.47, and 0.33 METEOR. For Flickr8k BLEU-1 0.68, BLEU-2 0.49, BLEU-3 0.41, METEOR 0.23, and 0.86 on SPICE. The proposed approach is comparable with several state-of-the-art methods in terms of standard evaluation metric, demonstrating that it can produce more accurate and richer captions.

This paper is devoted to discussing the reverse triple I method based on the Pythagorean fuzzy set (PFS). We first propose the concepts of Pythagorean t-norm, Pythagorean t-conorm, residual Pythagorean fuzzy implication operator (RPFIO) and Pythagorean fuzzy biresiduum. The reverse triple I methods for Pythagorean fuzzy modus ponens (PFMP) and Pythagorean fuzzy modus tollens (PFMT) are also established. In addition, some interesting properties of the reverse triple I method of PFMP and PFMT inference models are analysed, including the robustness, continuity and reversibility. Finally, a practical problem is provided to illustrate the effectiveness of the reverse triple I method for PFMP in decision-making problems. The advantages of the new method over existing methods are also expounded. Overall, compared with the existing methods, the proposed methods are based on logical reasoning rather than using aggregation operators, so the novel methods are more logical, can better deal with the uncertain problems in complex decision-making environments and can completely reflect the decision-making opinions of decision-makers.

This paper aims to further study the new kind of ordered fuzzy group named ordered L-group, which is put forward in literature [20]. Some algebraic properties of ordered L-groups, such as the relationship between elements, the equivalent characterizations and the products of these groups are discussed. Following that, the properties of substructures including characterization theorems, the convexity, the products of (normal) subgroups maintain the original substructure, along with the properties of ordered L-group homomorphisms are explored. The discussion of ordered fuzzy groups in this paper is from the perspective of fuzzy binary operation, which is different from the commonly method that just discuss the fuzzification of substructures in the research of fuzzy algebra. It can better reflect the essence of fuzzy groups logically just like that of classical groups.

Internet of Things (IoT) services are directly deployed on resource-constrained smart devices. Smart devices are characteristic by spatial and temporal constraints and energy limitations. A single IoT service cannot meet the complex requirements of users, so multiple IoT services need to be combined to provide services to users. As more and more smart devices are deployed in IoT, how to select IoT services with lower energy consumption and better quality of service (QoS) for service composition becomes a challenging problem. Combined with the characteristics that the data information of IoT is closely related to geographical location, the GeoHash algorithm is used to locally screen services based on geographical location, so as to narrow the range of candidate services. For smart devices with energy constraints, this paper proposes a combined optimization model. The model considers not only the transmission energy consumption and switching energy consumption, but also the execution energy consumption when the device provides services. In order to balance QoS attributes and energy consumption, the composition problem is regarded as a multi-objective optimization problem and solved using a genetic algorithm (GA). The simulation results show that service composition scheme selected by this service composition optimization model has lower energy consumption and higher service quality.

In this research, a timely diagnosis and prediction mechanism for drill failure are provided to improve the maintenance process in drilling through fuzzy inference systems. Failures and decisions are based on information and reliability as well, and that affects the quality of decision-making. We apply the potential of if-then rules and a new approach called Z-number that considers fuzzy constraints and reliability at the same time. Exerting Z-number in this research took maximum advantage of reducing uncertainty for predicting failures. Additionally, this research has a practical aspect in maintenance systems by using if-then rules that rely on Z-number. The proposed approach can cover the expert idea during drill operation time simultaneously. This approach also helps experts encounter ambiguous situations and formulate uncertainties. Experts or drill operators can consider key factors of drilling collapse along with the reliability of these factors. The proposed approach can be applied to a real-life situation of human inference with probability for the purpose of predicting failures during drilling. Hence, this method has excellent flexibility for implementation in various maintenance systems.

An important feature of the outbreak of systemic financial risk is that the linkage and contagion of risk amongst the various sub-markets of the financial system have increased significantly. In addition, research on the prediction of systemic financial risk plays a significant role in the sustainable development of the financial market. Therefore, this paper takes China’s financial market as its research object, considers the risks co-activity among major financial sub-markets, and constructs a financial composite indicator of systemic stress (CISS) for China, describing its financial systemic stress based on 12 basic indicators selected from the money market, bond market, stock market, and foreign exchange market. Furthermore, drawing on the decomposition and integration technology in the TEI@I complex system research methodology, this paper introduces advanced variational mode decomposition (VMD) technology and extreme learning machine (ELM) algorithms, constructing the VMD-DE-ELM hybrid model to predict the systemic risk of China’s financial market. According to e _RMSE , e _MAE , and e _MAPE , the prediction model’s multistep-ahead forecasting effect is evaluated. The empirical results show that the China’s financial CISS constructed in this paper can effectively identify all kinds of risk events in the sample range. The results of a robustness test show that the overall trend of China’s financial CISS and its ability to identify risk events are not affected by parameter selection and have good robustness. In addition, compared with the benchmark model, the VMD-DE-ELM hybrid model constructed in this paper shows superior predictive ability for systemic financial risk.

Monitoring the diversity of wild animals is a core part of the research and protection of wild animals. Due to the harsh outdoor environment, researchers cannot squat in the deep forest for a long time. Therefore, designing a sensor network system for wildlife monitoring is of great value to wildlife research, protection, and management. When deploying a wildlife monitoring network in the wild environment, it is necessary to solve the problem of the effective use of energy. To this end, this paper proposes an energy-saving optimization method for node scheduling and a wake-up scheme based on a cultural genetic algorithm. This method achieves the purpose of energy saving by making redundant nodes fall asleep and waking up sleep nodes to repair the coverage blind area caused by dead nodes. Simulation results show that this method can activate fewer sensor nodes to monitor the required sensing area, and its performance is better than other known solutions.

Time series forecasting (TSF) is significant for many applications, therefore the exploration and study for this problem has been proceeding. With the advances of computing power, deep neural networks (DNNs) have shown powerful performance on many machine learning tasks when considerable amounts of data can be used. However, sufficient data may be unavailable in some scenarios, which leads to performance degradation or even not working of DNN-based models. In this paper, we focus on few-shot time series forecasting task and propose to employ meta-learning to alleviate the problems caused by insufficient training data. Therefore, we propose a meta-learning-based prediction mechanism for few-shot time series forecasting task, which mainly consists of meta-training and meta-testing. The meta-training phase uses first-order model-agnostic meta-learning algorithm (MAML) as a core component to conduct cross-task training, and thus our method also inherits the advantages of the MAML, i.e., model-agnostic, in the sense that our method is compatible with any model trained with gradient descent. In the meta-testing phase, the DNN-based models are fine-tuned by the small number of time series data from an unseen task in the meta-training phase. We design two groups of comparison models to validate the effectiveness of our method. The first group, as the baseline models, is trained directly on specific time series dataset from target task. The second group, as comparison models, is trained by our proposed method. Also, we conduct data sensitivity study to validate the robustness of our method. The experimental results indicate the second group models outperform the first in different degrees in terms of prediction accuracy and convergence speed, and our method has strong robustness for forecast horizons and data scales.

The new wave of industry 4.0 has made battery-based automated guided vehicles (AGVs) an essential tool for material handling in manufacturing systems. However, many challenges related to battery management and machines and AGVs energy consumption. To handle these challenges an efficient battery management strategy is designed. The proposed approach supports multispeed operating modes for machines and AGVs, which offers a high flexibility to the manufacturing system. The aim of the proposed approach is to keep the minimal residual electric charge above the critical level, while enhancing the global performance of the manufacturing system. As a consequence, it increases the AGVs production hours and guarantees batteries safety.

The developed approach can bring economic benefits for industry 4.0, by increasing the productivity and avoiding AGVs batteries damage. Extended literature benchmark instances related to the manufacturing 4.0 are used to evaluate the efficiency of the suggested approach.

The face is a dominant biometric for recognizing a person. However, face recognition becomes challenging when there are severe changes in lighting conditions, i.e., illumination variations, which have been shown to have a more severe effect on recognition performance than the inherent differences between individuals. Most of the existing methods for tackling the problem of illumination variation assume that illumination lies in the large-scale component of a facial image; as such, the large-scale component is discarded, and features are extracted from small-scale components. Recently, it has been shown that large-scale component is also important; in addition, small-scale component contains detrimental noise features. Keeping this in view, we introduce a method for illumination invariant face recognition that exploits large-scale and small-scale components by discarding the illumination artifacts and detrimental noise using ContourletDS. After discarding the unwanted components, local and global features are extracted using a convolutional neural network (CNN) model; we examined three widely employed CNN models: VGG-16, GoogLeNet, and ResNet152. To reduce the dimensions of local and global features and fuse them, we employ linear discriminant analysis (LDA). Finally, ridge regression is used for recognition. The method was evaluated on three benchmark datasets; it achieved accuracies of 99.7%, 100%, and 79.76% on Extended Yale B, AR, and M-PIE, respectively. The comparison reveals that it outperforms the state-of-the-art methods.

Due to the fact that the real manufacturing processes are often constrained by many kinds of resources and the trend that the energy consumption of factories is regulated more and more strictly, this paper studies the energy-efficient multi-resource flexible job shop scheduling problem (EE-MRFJSP). The goal is to minimize the energy consumption and completion time for all of the jobs’ production. Firstly, a general mathematic model for EE-MRFJSP is set up, in which the unit energy consumptions of the main resource’s different states are varied, and a constraint formula to ensure no crossover working periods for any resource is included. Then, a non-dominated sorting teaching-learning-based optimization(NSTLBO) algorithm is proposed to solving the problem, the details of NSTLBO include the real encoding method, Giffler Thompson rule for decoding, non-dominated sorting rule to rank the pareto sets and crowding distance of solution for maintaining the population’s diversity, and the traditional two evolving stages: teacher education and student mutual study. Finally, comparative experiments are made based on some new designed instances, and the results verify our proposed NSTLBO algorithm can effectively solve the EE-MMFJSP, and has obvious advantages by comparing with NSGA-II, NRGA, and MOPSO.

The substitutability between products or the intensity of market competition is the key parameter affecting the supplier’s pricing decision. However, the parameter cannot be accurately measured in real life. This paper provides a method based on prior information to solve this issue. First, compared to classical concept lattice theory, the interval concept lattice theory can deal with uncertain information more accurately. It is used to extract the objects within the interval parameters [α, β], and then interval concepts and lattice structure are built. Second, based on the interval concepts and lattice structure, the association rule mining algorithm is designed to further extract the association rules under different interval parameters. Third, to obtain the effective association degree between two objects, the rule optimization algorithm is put forward by comparing the update of rules. Finally, the association degree can indirectly reflect the substitutability between products. Then the price of a new product can be determined. Our paper provides some implication on pricing for suppliers in competitive supply chain.

In the era of big data, recommender systems (RSs) have become growing essential tools. They represent important machine learning solutions that mainly contribute to keeping users engaged with personalized content in e-platforms. Several RSs have been proposed in the literature, and most of them have focused on English content. However, for content in other languages like Arabic, very restricted works have been done to develop RSs. In recent times, the Arabic content on the Web has increased significantly because of the growing number of Arabic web users. This highlights the need for building RSs for Arabic content. To better handle this challenge, we decided to provide the research community with a novel deep learning (DL)-based RS devoted to Arabic content. The main goal of the proposed RS is to predict user preferences from textual reviews written in the Arabic language. This is achieved by combining two independent DL techniques into one system: a convolutional neural network (CNN)-text processor for representing users and items; and a neural network, in particular, a multi-layer perceptron (MLP) to estimate interactions between user-item pairs. Extensive experiments on four large-scale Arabic datasets demonstrate that our proposed system can achieve better prediction accuracy than other state-of-the-art alternatives. Notably, it improves the MSE between 0.84% and 16.96%, and the MAE between 0.14% and 13.71%. This work is the first attempt designed to deal with a large volume of data in the Arabic context, opening up new research possibilities for future developments of Arabic RSs.

Uncertain delay differential system is an important mathematical model. Stability is a basic problem of uncertain delay differential system. Delay and uncertain interference often lead to changes in the stability of the system. Establishing the judgment of the stability of uncertain delay differential system conditions is very important. Based on the strong Lipschitz condition, the judgment of p-th moment stability for uncertain delay differential equations (UDDEs) has been investigated. Actually, the strong Lipschitz condition is assumed that it only relates to the current state, it is difficult to be employed to determine the stability in p-th moment for the UDDEs. In this paper, we consider two kinds of new Lipschitz conditions containing the current state and the past state, which are more weaker than the strong Lipschitz condition. Meanwhile, new sufficient theorems and corollaries under the new Lipschitz conditions as the tools to judge the p-th moment stability for the UDDEs are proved. Some examples explain the rationality of the corresponding theorems and corollaries.

Automatic Text Summarization(ATS) is distinctly beneficial due to a vast amount of textual data and time-consuming manual summarization. In order to enhance ATS for single document in huge datasets, a new extractive graph framework - text extractive SUMmarization framework based on EDge information with COreference resolution EDCOSUM is proposed in this paper that relies on coreference resolution, adding edge information in word-level graph and a sentence-ranking strategy. EDCOSUM combines the graph-based and statistical-based extractive summarization methods. It is a general method for any document (not limited to a specific domain). Moreover, two ranking strategies(sentence and LSA ranking strategy) are proposed for sentence selection. A set of extensive experiments on CNN/Daily Mail and NEWSROOM are conducted for investigating the proposed method. The widely used automatic evaluation tool: Recall-Oriented Understudy for Gisting Evaluation(ROUGE) is utilized to evaluate EDCOSUM. Compared to the state-of-the-art ATS methods, EDCOSUM achieves a competitive result by improvements of over the highest scores in the literature for metrics ROUGE-1, ROUGE-2 and ROUGE-L respectively.

This paper deals with the design and development of a novel approach, centered on the creation and development of a fuzzy controller to analyze electroencephalogram (EEG) data. The fuzzy controller makes use of the functions associated with the different regions of the brain to correlate multiple Brodmann areas to several outputs, where a normal analysis would associate only one region to one output. This controller was designed to quickly adapt to any data imported into it. The current implemented framework supports a math study. The math subjects’ outputs were attuned to their related study which involved transcranial direct current stimulation (tDCS), which is a form of neurostimulation. Anode affinity, cathode affinity, calculation, memory, and decision making were the outputs focused on for the math study. This task is best suited to a fuzzy controller since interactions between Brodmann areas can be analyzed and the contributions of each area accounted for by indicating which regions have stronger and weaker effects on any given output.

 The aim of this paper is to investigate pricing and production decisions of a monopoly firm that operates a co-product technology with two grades. A novel mathematical model that embeds a utility-maximizing customer choice model is developed to solve this problem. The closed-form expressions for the optimal solutions are derived and the results suggest that the distribution of customer valuations, yield rate and demand uncertainties have a vital influence on the firm’s optimal prices and profits. We then extend our study by allowing stockout-based substitution where a customer may be willing to purchase a substitute if his most preferred product is not available but the substitute provides him with non-negative utility. The results indicate that disregarding stockout-based substitution (i) results in severe supply-demand mismatches for the product line in two directions; (ii) leads to higher or lower profit margins for both products; (iii) may not cause profit loss when the prices of both products are exogenous; however, this result does not hold when the prices are endogenous.

With the increasing complexity of decision making (DM) problems, powerful mathematical tools are needed to represent and process fuzzy and uncertain DM information, and Pythagorean fuzzy set (PFS) is such a mathematical tool. PFS has been successfully applied in the field of fuzzy multiple criteria decision making (MCDM). Correlation coefficient is an information measure of PFS, and plays an important role in the application of PFS. At present, there is a problem that the existing correlation coefficients cannot moderately measure the correlation degree between PFSs, so this paper proposes the new correlation coefficients of PFS. The TODIM method has been proved to be effective in dealing with MCDM problems that consider the psychological behavior of decision makers. This paper extends the TODIM method with the new correlation coefficients of PFS, and the extended TODIM method is called Pythagorean fuzzy CC-TODIM method. By numerical examples, it is verified that the new correlation coefficients of PFS are more reasonable and valid. By case analysis, it is verified that the Pythagorean fuzzy CC-TODIM method can effectively solve the MCDM problems, and the Pythagorean fuzzy CC-TODIM method based on the new correlation coefficients is more accurate and reliable.

As an effective tool for three-way decisions (3WD) problems, decision-theoretic rough sets (DTRSs) have raised increasing attention recently. In view of the advantages of q-rung orthopair uncertain linguistic variables (q-ROULVs) in depicting uncertain information, a new DTRSs model based on q-ROULVs is proposed to solve three-way group decision-making (3WGDM) problems. Firstly, the loss function of DTRSs is depicted by q-ROULVs and a q-rung orthopair uncertain linguistic DTRSs model is constructed subsequently. Secondly, to aggregate different experts’ evaluation results on loss function in group decision-making (GDM) scenario, the q-rung orthopair uncertain linguistic geometric Heronian mean (q-ROULGHM) operator and the q-rung orthopair uncertain linguistic weighted geometric Heronian mean (q-ROULWGHM) operator are presented. Related properties of the proposed operators are investigated. Thirdly, to compare the expected loss of each alternative, a new score function of q-ROULVs is defined and the corresponding decision rules for 3WGDM are deduced. Finally, an illustrative example of venture capital in high-tech projects is provided to verify the rationality and effectiveness of our method. The influence of different conditional probabilities and parameter values on decision results is comprehensively discussed.

We increase the power of the Artificial Neural Networks with the help of the Activation Function (AF). The tansig and logsig are widely used AF. But there is still requires some improvement in the AF. So, in this paper, we have proposed a NewSigmoid AF in the neural network. NewSigmoid is also as powerful as tansig and logsig. In multiple cases, the NewSigmoid function gives a better or equivalent performance as compared with both these AF. Like these AF, NewSigmoid is also a smooth S-shape, bounded, continuously differentiable, and zero-centered function. Therefore the NewSigmoid is also suitable for solving non-linear problems. We have tested this AF on iris, cancer, glass, chemical, bodyfat, wine, and ovarian datasets. We use Scaled Conjugate Gradient (SCG), Levenberg-Marquardt (LM), and Bayesian Regularization (BR) algorithms during the optimization of the neural network. Maximum 100% accuracy in the iris dataset while using LM, and BR; 99.9% accuracy in the cancer dataset using BR; 100% accuracy in the glass dataset using BR; 100% accuracy in the chemical and bodyfat dataset using SCG, LM, and BR; 100% accuracy in the wine dataset using LM, and BR; and 99.1% accuracy in the ovarian dataset using BR has been found while working with multilayer neural networks. The NewSigmoid also achieves 100% training and validation accuracy on the mathework-cap image dataset using SCG.

This study presents a fault diagnosis method for rolling bearing based on multi-scale deep subdomain adaptation network (MSDSAN). The proposed MSDSAN, as improvement of deep subdomain adaptation network (DSAN), is an unsupervised transfer learning method. MSDSAN reduces the subdomain distribution discrepancy between domains rather than marginal distribution discrepancy, and so better domain invariant fault features are derived to avoid misalignment between domains. Aiming at avoiding fault information loss by fixed receptive fields feature extraction, selective kernel convolution module is introduced into feature extraction of MSDSAN, by which multiple receptive fields are applied to ensure an optimal receptive field for each working condition. Moreover, contribution rates are adaptively assigned to all receptive fields, and the disturbing information extracted by inappropriate receptive fields is further eliminated. As a result, more comprehensive and effective fault information is derived for bearing fault diagnosis. Fault diagnosis experiment of bearings is performed to verify the superiority of the proposed method, and the experimental results demonstrate that MSDSAN achieves better transfer effects and higher accuracy than SOTA methods under varying working conditions.

Exponential Euler differences for semi-linear differential equations of first order have got rapid development in the past few years and a variety of exponential Euler difference methods have become very significant researching topics. In allusion to fuzzy genetic regulatory networks of fractional order, this paper firstly establishes a novel difference method called Mittag-Leffler Euler difference, which includes the exponential Euler difference. In the second place, the existence of a unique global bounded solution and equilibrium point, global exponential stability and synchronization of the derived difference models are investigated. Compared with the classical fractional Euler differences, fuzzy Mittag-Leffler discrete-time genetic regulatory networks can better depict and retain the dynamic characteristics of the corresponding continuous-time models. What’s more important is that it starts a new avenue for studying discrete-time fractional-order systems and a set of theories and methods is constructed in studying Mittag-Leffler discrete models.

The rapid development of the Internet has accelerated the expansion of e-commerce sacle of fresh agricultural products. The actual audience of smart logistics distribution of fresh agricultural products is customers, and customers enjoy the process and results of distribution services. However, the current research mainly selects indicators from the aspects of enterprise performance, cost and technical level based on the perspective of managers and technicians, which make it difficult to truly reflect customers’ feelings in the evaluation results. At the same time, the evaluation methods mainly focus on the comprehensive evaluation method and fuzzy evaluation method. These evaluation methods are greatly affected by subjective factors in the evaluation grade distribution, and the assignment is often relatively complete and inaccurate. To solve these problems, this paper constructs the evaluation index system of intelligent logistics distribution of fresh agricultural products from the perspective of customers, so that the selection of indicators is more in line with the real wishes of customers. And we use the extension function to construct the correlation function for multi-level extension evaluation to ensure the accuracy of the evaluation results. Taking X logistics enterprise as an example, this paper verifies the scientificity of the evaluation index system of intelligent logistics distribution of fresh agricultural products through empirical research, which has reference significance for further improving the intelligent logistics distribution of fresh agricultural products.

Cardio vascular disease threatens human life with higher mortality rate. Therefore it is quite important to monitor. An arrhythmia is an abnormal heart beat and rhythm which causes the disease. The best tool to find the heart rhythm of heart is Electro Cardiogram (ECG) which provides information about the different types of arrhythmias. This paper aims at proposing an automatic framework by employing multi-domain features to classify ECG signals. Proposed work uses optimum method of feature selection to improvise the efficiency of the classification process. A hybrid optimization algorithm is used for feature selection and proposed to optimize the parameters of the existing Support Vector Machine (SVM) classifier. Proposed hybrid optimization algorithm was developed using Particle Swarm Optimization (PSO) and Migration Modified Biogeography Based Optimization (MMBBO) algorithm. Algorithm provides an improved solution to the optimizing the parameters of ECG signals. Results are evaluated by implementing in MATLAB software and the performance is justified with comparative analysis. The proposed framework enhances the process of automatic prediction of various arrhythmias or rhythm abnormalities which performs in gaining better accuracy. For data sets, the average classification accuracy of this method is 97.89%. This result is an improvement of 4–5% over the comparison of other methods.

With the continuous development of sensor and computer technology, human-computer interaction technology is also improving. Gesture recognition has become a research hotspot in human-computer interaction, sign language recognition, rehabilitation training, and sports medicine. This paper proposed a method of hand gestures recognition which extracts the time domain and frequency domain features from surface electromyography (sEMG) by using an improved multi-channels convolutional neural network (IMC-CNN). The 10 most commonly used hand gestures are recognized by using the spectral features of sEMG signals which is the input of the IMC-CNN model. Firstly, the third-order Butterworth low-pass filter and high-pass filter are used to denoise the sEMG signal. Secondly, effective sEMG signal segment from denoised signal is applied. Thirdly, the spectrogram features of different channels’ sEMG signals are merged into a comprehensive improved spectrogram feature which is used as the input of IMC-CNN to classify the hand gestures. Finally, the recognition accuracy of IMC-CNN model, three single channel CNN of IMC-CNN model, SVM, LDA, LCNN and EMGNET are compared. The experiment was carried out on the same dataset and the same computer. The experimental results showed that the recognition accuracy, sensitivity and accuracy of the proposed model reached 97.5%, 97.25% and 96.25% respectively. The proposed method not only has high average recognition accuracy on MYO collected dataset, but also has high average recognition accuracy on NinaPro DB5 dataset. Overall, the proposed model has more advantages in accuracy and efficiency than that of the comparison models.

Learning Management Systems is a challenge of implementing information technology (IT) in the higher educational field. This paper introduces a framework for assessing an LMS by integrating partial last squares-structural equation modeling (PLS-SEM) and fuzzy analytic hierarchic process with Z-numbers (Fuzzy Z-AHP). The objective is to propose the combination of the two approaches via results of PLS-SEM for the construction of the decision matrix for Fuzzy Z-AHP. The PLS-SEM method was used firstly to evaluate the conceptual model Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) and extracting the significant connections between the independent constructs and the behavioral intention to use an LMS. Secondly is adapted the Fuzzy Z-AHP method to rank the independent significant constructs initializing from the PLS-SEM results. Using a questionnaire survey, the study sampled 530 users of LMS in 4 Albanian universities as respondents. To the best of our knowledge this paper is among the first that combines PLS-SEM with Fuzzy Z-AHP for the UTAUT2 model while using an LMS. This combination showed that the most important construct of UTAUT2 affecting behavioral intention to use an LMS was habit. This study assist the decision makers and policy makers to provide the means to obtain better managerial conclusions for the improvement and progress of an LMS.

Distributed Generating (DG) units, Energy Storage Systems (ESS), Distributed Reactive Sources (DRS), and resilient loads make up the microgrid (MG), which can operate in both connected and isolated modes. Because the amount of power generated by Renewable Energy Sources (RES) such as Wind Energy Systems (WES) and Photovoltaic Energy Systems (PVES) is unpredictable, it becomes difficult for MGs planners to make judgments. In this article, the uncertainties caused by RES are resolved through the successful application of a hybrid optimization approach and the integration of hybrid DGs. The Teaching Learning Algorithm (TLA) is used in this study to determine the best site for DGs and reconfiguration, and heuristic fuzzy has been merged with TLA to handle multi-objectives such as total generation and emission cost minimization, and bus voltage deviation. In addition, the impact of replacing RES with hybrid DGs on RES performance is investigated. The ideal structures are determined by solving four different scenarios with the suggested approach, allowing DSO to make decisions with greater flexibility. The proposed technique is validated using a benchmark IEEE 33 bus system that has been converted into a microgrid. WES, PVES, and hybrid DGs are validated using a 24-hour daily load pattern with 24-hour load dispatching characteristic behaviors.

Thyroid nodule segmentation is an indispensable part of the computer-aided diagnosis of thyroid nodules from ultrasound images. However, it remains challenging to segment the nodules from ultrasound images due to low contrast, high noise, diverse appearance, and complex thyroid nodules structure. So, it requires high clinical experience and expertise for proper detection of nodules. To alleviate the doctor’s tremendous effort in the diagnosis stage, we utilized several convolutional neural network architectures based on Encoder-Decoder architecture, U-Net architecture, Res-UNet architecture. To handle the complexity of the residual blocks, we also proposed three hybrid Res-UNet architectures by reducing the number of residual connections. The experimental analysis of the segmentation models proves the viability of residual learning in the U-Net architecture. Hybrid models which use minimum residual connections provide efficient segmentation frameworks similar to Res-UNet architecture with a minimum computational requirement. The experimental results indicate that all the segmentation models based on residual learning and U-Net can accurately delineate nodules without human intervention. This model helps to reduce dependencies on operators and acts as a decision tool for the radiologist.

The electric vehicle market has surged the consideration of charging station requirements in the commercial and residential areas of the urban regions. The addition of charging stations at the existing power network introduces a greater challenge on voltage stability and losses. The effect of the charging station can be addressed through the optimal integration of Distributed Generation (DG) units into the network. The improper placement of DG units can jeopardize the network stability. These issues are addressed by optimal placement of DG units and charging stations in the network to improve voltage, reduce transmission loss and maximize the charging station capacity. Here the objectives are considered as a multi-objective problem and solved using an enhanced Ant-lion optimization algorithm. The proposed method is implemented and tested over IEEE – 33, 69 and 94 radial bus system in MATLAB R2020a version. In IEEE – 33 bus system, the total loss reduction of 67.63% and the minimum voltage of 0.981 is attained with 2909.2 kW of DG and 1770.7 kW of charging station. The voltage stability index is improved to 0.92. The efficacy of the proposed method is evaluated through comparison with existing methods such as Genetic Algorithm (GA) with VRP method, Harris Hawks Optimization (HHO) and Particle Swarm Optimization (PSO). It is evident that the proposed method gives improved performance than other methods.

Finding efficient solutions for the multi-objective linear fractional programming problem (MOLFPP) is a challenging issue in optimization because more than one target has to be taken into account. For the problem, we face the concept of efficient solutions which is an infinite set especially when the objectives are in conflict. Since a classical method generally comes out with only one efficient solution, thus introducing new efficient approaches is helpful and beneficial for the decision makers to make their decisions according to more possibilities. In this paper, we aim to consider the MOLFPP with fuzzy coefficients (FMOLFPP) where the concept of α - cuts is utilized so as to transform the fuzzy numbers into closed intervals and rank the fuzzy numbers as well. Consequently, the fuzzy problem is changed into an interval valued multi-objective linear fractional programming problem (IV-MOLFPP). Subsequently, the IV-MOLFPP is further changed into linear programming problems (LPPs) using a parametric approach, weighted sum and max-min methods. It is demonstrated that the solution obtained is at least a weakly ɛ - efficient solution, where the value of ɛ helps a decision maker (DM) to make his decision appropriately i.e. DMs chose more likely the solutions with the lowest value of ɛ. Numerical examples are solved to illustrate the method and comparison are made to show the accuracy, and the reliability of the proposed solutions.

Soil Tillage serious game designed as a training media has been researched based on the plowing forces using polynomial functions. However, the learning process is rare; hence the players in Serious Games (SG) are less engaged and tend to be more static in their games. The effects of vertical cutting angle, plowshare depth, and motor speed affect the soil plowing force in soil tillage. Therefore it is expected that a plow force model with a learning function will generate more actual conditions, engage the player and eventually affect the player’s behavior. The serious game design uses a Hierarchical Finite State Machine (HFSM) in this study. HFSM state is motor speed, vertical cutting angle, and plowing depth. The learning function is based on Neural Network (NN), with a multilayer feed-forward neural network (FFNN) is chosen to estimate plowing forces. The Levenberg-Marquardt algorithm is used by NN to approach second-order training speed without computing the Hessian matrix and is the fastest backpropagation algorithm. The result of the research is a plowing force model values closer to the actual by giving players feedback as they learn. In the transition, HFSM has a feedback value to the initial state, which is helpful as part of measuring one game cycle that is run, thus providing a learning experience in a serious game.

The problem of bilateral matching of teams and scientific and technical talents is studied in new R&D institutions with different forms of uncertain assessment information. A decision method is proposed based on a combination of grey correlation and cloud model. The method firstly applies interval grey numbers to characterize uncertain assessment score information and cloud models to characterize uncertain linguistic assessment information; secondly, the two different pieces of information are converted into grey correlation coefficients by applying grey correlation analysis methods to the assessment values, so as to solve indicator weights, and assemble assessment data based on indicator weights and cloud models; finally, the bilateral matching model is constructed and the matching results are solved based on the cloud model data features and the dual objectives of maximum satisfaction and minimum uncertainty. The case analysis and method comparison show that the method is feasible and effective.

The cubic set, introduced as a combination of a fuzzy set and an interval-valued fuzzy set, provided researchers with more flexibility than the previous two sets in dealing with complex and uncertain problems. Fuzzy graphs, based on this type of set, are among the emerging fuzzy graphs that have a great potential to model the surrounding phenomena. Consistent with the special role that cubic graphs play in decision-making and selecting superior options, dominating these graphs is of great importance and value. In this paper, we introduce the domination of the cubic graphs in terms of strong edges and examine their properties. In addition, we examine domination in terms of independent sets and since many of the phenomena surrounding us are hybrid, we also discuss the domination concept on its fuzzy operations. Finally, we present an application of this graph on the subject of domination.

 Clear images are generally desirable in high-level computer vision algorithms which are mostly deployed outdoors. However, affected by the changeable weather in the real world, images are inevitably contaminated by rain streaks. Deep convolutional neural networks (CNNs) have shown significant potential in rain streaks removal. The performance of most existing CNN-based deraining methods is often enhanced by stacking vanilla convolutional layers and some other methods use dilated convolution which can only model local pixel relations to provide the necessary but limited receptive field. Therefore, long-range contextual information is rarely considered for this specific task, thus, deraining a single image remains challenging problem. To address the above problem, an effective residual deep attention network (RDANet) for single image rain removal is proposed. Specifically, we design a strong basic unit that contains dilated convolution, spatial and channel attention module (SCAM) simultaneously. As contextual information is very important for rain removal, the proposed basic unit can capture global long-distance dependencies among pixels in feature maps and model feature relations across channels. Compared with a single dilated convolution, the spatial and channel attention enhance the feature expression ability of the network. Moreover, some previous works have proven that the no-rain information in a rain image will be missing during deraining. To enrich the detailed information in the clean images, we present a residual feature processing group (RFPG) that contains several source skip connections to inject rainy shallow source information into each basic unit. In summary, our model can effectively handle complicated long rain streaks in spatial and the outputs of the network can retain most of the details of the original rain images. Experiments demonstrate the superiority of our RDANet over state-of-the-art methods in terms of both quantitative metrics and visual quality on both synthetic and real rainy images.

Although smart grids are characterized by self-healing, economy, high efficiency, and security, many hidden dangers exist in the development of smart grids due to a gradually expanding power grid and the continuous access of new energy to the power grid. Therefore, the development of smart grids, especially their reliability, security, and vulnerability, warrants further investigation. In this study, the vulnerability of smart grids is identified, and the vulnerability elements of smart grids are selected. Based on relevant theories, such as credibility and the combination of the credibility-based moment-generating function and the distortion function, a calculation model and framework of the vulnerability index of a smart grid are constructed. An empirical analysis is also conducted. This study provides a scientific basis for analyzing the vulnerability of smart grids and suggesting reasonable preventive measures and auxiliary decision-making information for relevant planning, design, and operation personnel, which contributes to the sustainable and healthy development of smart grids.

 In this paper, to reduce the redundant attractions and incorrect directions of firefly algorithm (FA), a distance-guided selection approach (DSFA) is proposed, which consists of a distance-guided mechanism and selection strategy. Where the designed distance-guided mechanism reduces the attractions and plays as a classifier for global search and local search, the suggested selection strategy can avoid local search falling into traps, thereby increasing the probability of correct direction. With the good cooperation of these two approaches, DSFA obtains a good balance of exploration and exploitation. To confirm the performance of the proposed algorithm, excessive experiments are conducted on CEC2013 benchmark functions, large-scale optimization problems CEC2008, and software defect prediction (SDP). In the comparison with the 5 advanced FA variants, DSFA provides the optimal solutions to most CEC2013 problems. Besides, when facing the problems of class imbalance and the dimensional explosion of datasets, DSFA greatly improves the performance of machine learning classifiers employed by SDP. It can be concluded that DSFA is an effective method for global continuous optimization problems.

In this paper, we introduce the notion of amplitude interval-valued complex Pythagorean fuzzy sets (AIVCPFSs). The motivation for this extension is the utility of interval-valued complex fuzzy sets in membership and non-membership degree which can express the two dimensional ambiguous information as well as the interaction among any set of parameters when they are in the form of interval-valued. The principle of AIVCPFS is a mixture of the two separated theories such as interval-valued complex fuzzy set and complex Pythagorean fuzzy set which covers the truth grade (TG) and falsity grade (FG) in the form of the complex number whose real part is the sub-interval of the unit interval. We discuss some set-theoretic operations and laws of the AIVCPFSs. We study some particular examples and basic results of these operations and laws. We use AIVCPFSs in signals and systems because its behavior is similar to a Fourier transform in certain cases. Moreover, we develop a new algorithm using AIVCPFSs for applications in signals and systems by which we identify a reference signal out of the large number of signals detected by a digital receiver. We use the inverse discrete Fourier transform for the membership and non-membership functions of AIVCPFSs for incoming signals and a reference signal. Thus a method for measuring the resembling values of two signals is provided by which we can identify the reference signal.

A robust collaborative system of active products (a product is called active when its ownership does not get transferred from provider to requestor at the time of its usage) should have an in-built mechanism which can make entities (service provider(s) and requestor(s)) to decide with whom to collaborate. In the absence of such a mechanism, the system is bound to have high job failure rate, resulting in wastage of resources. This paper proposes a Trust based Multi-Agent Framework (TbMAF) for collaborative systems of active products which enable only trustworthy entities to collaborate, safeguarding both users’ sensitive applications and providers’ resources. The trustworthiness of service provider(s) and requestor(s) is computed using Fuzzy Inference System (FIS) and Radial Basis Function Neural Network (RBFNN) methodologies, respectively. A prototype based on the proposed system has been tested using real time data of a collaborative system namely, EGEE (Enabling Grids for E-science). This paper finds evidence that the job failure rate is lower when collaborations take place only between trustworthy entities. Further, the proposed framework is found to be robust against malicious entities and can capture the evolving behavior of entities as well.

Because of the advantages of deep learning and information fusion technology, it has drawn much attention for researchers to combine them to achieve target recognition, positioning, and tracking. However, when the existing neural network process multichannel images (e.g., color images), multiple channels as a whole input into neural networks, which makes it hard for networks to fully learn information in R, G, and B channels of images. Therefore, it is not conducive to the final learning effect of the networks. To solve the problem, using different combinations of R, G, and B channels of color images for feature-level fusion, this paper proposes three fusion types as “R/G/B”, “R+G/G+B/B+R”, and “R+G+B/R+G+B/R+G+B” multichannel concat-fusional convolutional neural networks. Experimental results show that multichannel concat-fusional convolutional neural networks with fusional types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” achieve better performance than the corresponding non-fusional convolutional neural networks on different datasets. It shows that networks with fusion types of “R+G/G+B/B+R” and “R+G+B/R+G+B/R+G+B” can learn more fully information of R, G, and B channels of color images and improve the learning performance of networks.

The evolving new and modern technologies raise the risks in the network which will be affected by several attacks and thus give rise to developing efficient network attack detection and classification methods. Here in this article for predicting and classifying the network attacks, the LSTM neural network with XGBoost is suggested in which the NSL-KDD dataset was utilized to train the LSTM in the study. In the beginning, the unnecessary data and the noisy data will be eliminated using the dataset and the feature subset with the most compelling features will be selected using the feature selection. By utilizing the essential data, the proposed system will be trained and the training parameter values will be modified for maximizing the functionality of the proposed system. Then, the result of the proposed system will be evaluated with some of the existing machine learning and deep learning algorithms such as SVM, LR, RF, DNN, and CNN with the performance metrics like Accuracy, F1 score, Recall, and Precision. It was found that the proposed model outperforms better than the other algorithms as this model is trained with the most important features and due to this, the training time and overfitting of the learning model was reduced thereby increasing the model effectiveness

 Machine learning and deep learning methods have become exponentially more accurate. These methods are now as precise as experts of respective fields, so it is being used in almost all areas of life. Nowadays, people have more faith in machines than men, so, in this vein, deep learning models with the concept of transfer learning of CNN are used to detect and classify diabetic retinopathy and its different stages. The backbone of various CNN-based models such as InceptionResNetV2, InceptionV3, Xception, MobileNetV2, VGG19, and DenceNet201 are used to classify this vision loss disease. In these base models, transfer learning has been applied by adding some layers like batch normalization, dropout, and dense layers to make the model more effective and accurate for the given problem. The training of the resulting models has been done for the Kaggle retinopathy 2019 dataset with about 3662 fundus fluorescein angiography colored images. Performance of all six trained models have been measured on the test dataset in terms of precision, recall, F1 score, macro average, weighted average, confusion matrix, and accuracy. A confusion matrix is based on maximum class probability prediction that is the incapability of the confusion matrix. The ROC-AUC of different classes and the models are analyzed. ROC-AUC is based on the actual probability of different categories. The results obtained from this study show that InceptionResNetV2 is proven the best model for diabetic retinopathy detection and classification, among other models considered here. It can work accurately in case of less training data. Thus, this model may detect and classify diabetic retinopathy automatically and accurately at an early stage. So it would be beneficial for humans to reduce the effects of diabetes. As a result of this, the impact of diabetes on vision loss can be minimized, and that would be a blessing in the medical field.

With technological advancement, visual search has become an effective tool for searching important information by providing images. We propose a practical medical equipment recognition that can be used in visual search through deep transfer learning. We evaluated three deep learning models, i.e., VGG-16, ResNet-50, and Inception-v3, to recognise ten different classes of medical equipment. A data set consisting of 2,666 images had been collected and augmented to measure the models’ effectiveness. The models pre-trained with the ImageNet data set were transferred to the final models, and the last layers were replaced and trained with the collected data set. A grid search method was then used to find the best combination of hyperparameters, such as optimiser, batch size, epoch number, dropout rate, and learning rate. We tested the models using photos captured using smartphones. The results showed that Inception-v3 outperformed the other two models with the highest accuracy of 0.9454. This is the first study that uses deep transfer learning for recognising medical equipment to our best knowledge. Such recognition technology can potentially be implemented in visual search for helping consumers to check the validity of medical equipment.

Cervical cancer can be cured if it is initially screened and giving timely treatment to the patients. This paper proposes an optimization technique for exposing and segmenting the cancer portion in cervical images using transform and windowing technique. The image processing steps are preprocessing, transformation, feature extraction, feature optimization, classification, and segmentation involved in the proposed work. Initially, Gabor transform is enforced on the cervical test image to modify the pixels associated with the spatial domain into multi-resolution domain. Subsequently, the parameters of the multi-level features are extracted from the Gabor transformed cervical image. Then, the extracted features are optimized using the Genetic Algorithm (GA), and the optimistic prominent part is classified by the Convolutional Neural Networks (CNN). Finally, the Finite Segmentation Algorithm (FSA) is used to detect and segment the cancer region in cervical images. The proposed GA based CNN classification method describes the effectual detection and classification of cervical cancer by the parameters such as sensitivity, specificity and accuracy. The experimental results are shown 99.37% of average sensitivity, 98.9% of average specificity and 99.21% of average accuracy, 97.8% of PPV, 91.8% of NPV, 96.8% of FPR and 90.4% of FNR.

To the best of author’s knowledge, only one approach is proposed in the literature to solve fuzzy linear fractional minimal cost flow problems (minimal cost flow problems in which each known arc cost is represented either by a triangular fuzzy number or a trapezoidal fuzzy number). In this paper, the mathematical incorrect assumptions, considered in the existing approach to solve fuzzy linear fractional minimal cost flow problems, are pointed out. Also, by generalizing an existing approach for solving fuzzy linear fractional programming problems, an approach (named as Mehar approach) is proposed to solve fuzzy linear fractional minimal cost flow problems. Furthermore, two numerical examples are solved to illustrate the proposed Mehar approach.

Due to the limitation of positioning devices, there is a certain error between GPS positioning data and the real location on the map, and the positioning data needs to be processed to have better usability. For example, accurate location is needed for traffic flow control, automatic driving navigation, logistics tracking, etc. There are few studies specifically for circular road sections. In addition, many existing map matching methods based on Hidden Markov model (HMM) also have the problem that GPS points are easily to be matched to tangent or non-adjacent road sections at circular road sections. Therefore, the contextual voting map matching method for circular road sections (STDV-matching) is proposed. The method proposes multiple subsequent point direction analysis methods based on STD-matching to determine entry into the circular section, and adds candidate section frequency voting analysis to reduce matching errors. The effectiveness of the proposed method is verified at the circular section by comparing it with three existing HMM methods through experiments using two real map and trajectory datasets.

In the modern industrial process, a complete production process is achieved by requiring a variety of equipment to cooperate with each other. The abnormality in any equipment will have a large or small impact on process safety or product quality, resulting in increased risk. In recent years, many data-driven early-warning methods have been developed in academia. However, most of the methods need to be implemented on the support of normal and fault data. In order to overcome the problem, this paper establishes a new early-warning model based on negative selection algorithm (NSA) for centrifugal compressor unit without fault data. Firstly, a nearest neighbor fixed boundary negative selection algorithm (NFB-NSA) is proposed by optimizing detector generation mechanism and matching rules for test samples. Secondly, the performance of NFB-NSA is tested by Iris dataset. The experimental results among NFB-NSA, V-detector, and other anomaly detection methods for Iris dataset shows that NFB-NSA can achieve the highest detection accuracy and the lowest false alarm rate in most cases. Finally, the early-warning of centrifugal compressor unit under normal samples is carried on by NFB-NSA in this paper. Validated by field data, NFB-NSA is demonstrated to be of excellent accuracy and robustness by results of experiments. Moreover, the influence of size of training sample on performance of NFB-NSA is obtained.

The numbers of Helly, Carathéodory and Radon are a central theme in classic convex spaces and each of them is invariant under isomorphism. The theory of M-fuzzifying convex spaces is an active research field since it is presented. This paper focus on convex invariants of M-fuzzifying convex spaces. The degrees of Helly independent, Carathéodory independent and Radon independent of non-empty set are defined in the framework of M-fuzzifying convex spaces. By those definitions, we introduce the Helly number, Carathéodory number and Radon number of M-fuzzifying convex spaces. Finally, we inspect M-fuzzifying topology and M-fuzzifying JHC which are characterized by convex invariants of M-fuzzifying convex spaces.

Bonferroni means (BM) operator is the extended form of the arithmetic mean operator, used for simplifying non-dominant and non-feasible problems diagnosed in genuine life scenarios. A lot of aggregation operators are the specific parts of the BM operators under the consideration of different values of parameters which are the main parts of the BM operators. In the presence of the BM operator and a very well-known conception in the scenario of fuzzy set, called complex Pythagorean fuzzy (CPF) setting, the objective of this scenario is to diagnose the CPF power BM (CPFPBM) operator and utilize their beneficial results with important properties. Moreover, a multi-attribute decision-making (MADM) technique is evaluated in the presence of invented operators for CPF settings. In the last of this study, we diagnosed the superiority and efficiency of the invented works with the help of sensitive analysis and graphical illustrations to enhance the gap of the research works.

Starting with an approximation space as the underlying structure, we look at the rough uniformity of a topological rough group. Next, taking L as a complete residuated lattice, we consider L-subgroup and normal L-subgroup of a group to create the L-fuzzy upper rough subgroup, and the L-fuzzy lower rough subgroup within the framework of the L-fuzzy approximation spaces. Here we particularly focus on a category of L-fuzzy upper rough subgroups, and a special kind of category of L-closure groups that arises naturally. We introduce the notion of the L-fuzzy approximation group, and study some of its properties including the usual function space structure for the L-fuzzy approximation spaces. Furthermore, using the notion of an L-fuzzy upper approximation operator, we investigate some categorical connection between the L-fuzzy approximation groups, and the L-closure groups. In a similar fashion, using an L-fuzzy lower approximation operator, we investigate the categorical connection between the L-fuzzy approximation groups, and the L-interior groups.

Pseudo EQ-algebras were introduced by X.L. Xin as possible algebraic semantics for fuzzy type theory. The main goal of this paper is to investigate pseudo EQ-algebras with internal states. To begin with, we introduce the notion of pseudo EQ-algebras with internal state(simplify, ISPEQ-algebra) and study its properties. Moreover, we discuss the relation between ISPEQ-algebras and states on pseudo EQ-algebras. In the following, we study state filters(simplify S-fliters) and state prefilters(simplify S-prefliters) of ISPEQ-algebras. We construct ISPEQ-algebras from S-fliters and derive congruence relation θ of ISPEQ-algebras. In the end, we give the generating formula of prefilters on residuated pseudo EQ-algebras and based on that we get the generating formula of S-prefilters on residuated pseudo EQ-algebras.

Grey Wolf Optimizer (GWO) is competitive to other population-based algorithms. However, considering that the conventional GWO has inadequate global search capacity, a GWO variant based on multiple strategies, i.e., adaptive Evolutionary Population Dynamics (EPD) strategy, differential perturbation strategy, and greedy selection strategy, named as ADGGWO, is proposed in this paper. Firstly, the adaptive EPD strategy is adopted to enhance the search capacity by updating the position of the worst wolves according to the best ones. Secondly, the exploration capacity is extended by the use of differential perturbation strategy. Thirdly, the greedy selection improves the exploitation capacity, contributing to the balance between exploration and exploitation capacity. ADGGWO has been examined on a suite from CEC2014 and compared with the traditional GWO as well as its three latest variants. The significance of the results is evaluated by two non-parametric tests, Friedman test and Wilcoxon test. Furthermore, constrained portfolio optimization is applied in this paper to investigate the performance of ADGGWO on real-world problems. The experimental results demonstrate that the proposed algorithm, which integrates multiple strategies, outperforms the traditional GWO and other GWO variants in terms of both accuracy and convergence. It can be proved that ADGGWO is not only effective for function optimization but also for practical problems.

Hyperspectral Image (HSI) is usually composed of hundreds of capturing wavelength bands, which not only increase the size of the HSI rapidly but also impose various obstacles in classifying the objects accurately. Moreover, the traditional machine learning schemes utilize only the spectral features for HSI classification, which, therefore, neglect the spatial features that have a significant impact on the classification improvement. To address the aforementioned issues, in this paper, we propose to employ the principal component analysis (PCA), the baseline feature extraction method, and a thoughtfully designed stacked autoencoder, a deep learning-based feature extraction approach, for reducing the high dimensionality of the HSI and then propose a novel lightweight 3D-2D convolutional neural network (CNN) framework to concurrently exploit both spatial and spectral features from the dimensionality-reduced HSI for classification. In particular, PCA and stacked autoencoder are applied to reduce the high dimensionality of the original HSI and then the proposed 3D-2D CNN provides a combination of 3D and 2D convolution operations to extract the subtle spatial and spectral features for efficient classification. We well-adjust the proposed 3D-2D CNN architecture, and perform extensive experiments on three benchmark HSI datasets and compare our approach with the state-of-the-art classical and deep learning methods. Experimental results illustrate that we have achieved an overall accuracy of 99.73%, 99.90%, and 99.32% on Indian Pines, Pavia University, and Kennedy Space Center datasets, respectively, which outperform the classical machine learning and independent 2D and 3D CNN-based state-of-the-art methods.

In this paper, the authors introduce catalyzed LM-G-filter spaces, a special case of weakly inspired LM-G-filter spaces and identify certain properties of these spaces. It is proved that CLM-G, the category of catalyzed LM-G-filter spaces, is isomorphic to ILM-G, the category of inspired LM-G-filter spaces. Moreover, the categorical connection between WILM-G, the category of weakly inspired LM-G-filter spaces, and CLM-G is investigated through interior and exterior catalyzation of weakly inspired LM-G-filter spaces. It is proved that CLM-G is an isomorphism-closed, bireflective and bicoreflective full subcategory of WILM-G and LM-G.

This research explores indicators and methods for an enterprise to measure and evaluate user satisfaction with enterprise social media for knowledge management. This paper presents qualitative indicators, including three service levels of enterprise social media for knowledge management (KM) from a techno-social perspective. This research puts forward a synthetic evaluation model mixed with linguistic variables, consistent fuzzy preference relations (CFPR) and cloud model for measuring and evaluating user satisfaction. The synthetic evaluation model can transform linguistic variables into quantitative data to obtain user satisfaction levels and determine the distance between the expected satisfaction level and actual performance. This research can help an enterprise to improve the service ability of its social media to meet users’ requirements for knowledge management.

 Semantic alignment is a key component in Cross-Language Text Matching (CLTM) to facilitate matching (e.g., query-document matching) between two languages. The current solutions for semantic alignment mainly perform word-level translation directly, without considering the contextual information for the whole query and documents. To this end, we propose a Dual-Level Collaborative Rough-to-Fine Filter Alignment Network (DLCCFA) to achieve better cross-language semantic alignment and document matching. DLCCFA is devised with both a coarse-grained filter in word-level and a fine-grained filter in sentence-level. Concretely, for the query in word-level, we firstly extract top-k translation candidates for each token in the query through a probabilistic bilingual lexicon. Then, a Translation Probability Attention (TPA) mechanism is proposed to obtain coarse-grained word alignment, which generates the corresponding query auxiliary sentence. Afterwards, we further propose a Bilingual Cross Attention and utilize Self-Attention to achieve fine-grained sentence-level filtering, resulting in the cross-language representation of the query. The idea is that each token in the query works as an anchor to filter the semantic noise in the query auxiliary sentence and accurately align semantics of different languages. Extensive experiments on four real-world datasets of six languages demostrate that our method can outperform the mainstream alternatives of CLTM.

In the era of big data for exploring attribute reduction/rough set-based feature selection related problems, to design efficient strategies for deriving reducts and then reduce the dimensions of data, two fundamental perspectives of Granular Computing may be taken into account: breaking up the whole into pieces and gathering parts into a whole. From this point of view, a novel strategy named label-specific guidance is introduced into the process of searching reduct. Given a formal description of attribute reduction, by considering the corresponding constraint, we divide it into several label-specific based constraints. Consequently, a sequence of these label-specific based constraints can be obtained, it follows that the reduct related to the previous label-specific based constraint may have guidance on the computation of that related to the subsequent label-specific based constraint. The thinking of this label-specific guidance runs through the whole process of searching reduct until the reduct over the whole universe is derived. Compared with five state-of-the-art algorithms over 20 data sets, the experimental results demonstrate that our proposed acceleration strategy can not only significantly accelerate the process of searching reduct but also offer justifiable performance in the task of classification. This study suggests a new trend concerning the problem of quickly deriving reduct.

Congestion not only affects the power flow, but also leads certain issues, like market power, market inefficiency and security. When the transmission line exceeds their limits congestion is occurred (voltage, thermal, stability). Congestion management is a technique that helps to deal the issue corresponding to congestion. Many methods have been developed to manage congestion, and also several countries execute various strategies for the smooth functioning of their network. In this manuscript, the rescheduling of congestion management in a deregulated environment using DA-MRFO is proposed. The proposed hybrid technique is the combined execution of both the dragonfly algorithm (DA) and manta ray foraging optimization (MRFO). Dragonfly algorithm is enhanced using Manta ray Foraging optimization (MRFO), hence it is named DA-MRFO technique. The proposed method is used to alleviate transmission grid congestion on group-based electricity market via reprogramming active power of generators and also to reprogram the generator power. Congestion is the major Independent System Operator (ISO) concern on deregulated electricity market that is traditionally controlled by reprogramming generator output power. However, the effects of changes in the generator output power on the overloaded line flow are not identical. All the generators do not represent a desirable approach for congestion management. Here, a generator sensitivity factor is adapted for supporting the optimal generator selection in a congestion management (CM). In a congestion relief process, it is provided at the lowest possible cost. The reduction of power flow with collection of congested lines is probable through coordinated response of reactive energy dispatch as wind farms. The proposed approach is executed in modified IEEE 30 bus system and IEEE 57 bus system, then the efficiency is compared with the various existing optimization approaches.

Breast cancer diagnosis utilizes histopathological images to get best results as per standards. For detailed diagnosis of breast cancer, microscopic analysis is necessary. During analysis, pathologists examine breast cancer tissues under different magnification levels and it takes a long time, can be hampered by human interpretation and requires expertise of different magnifications. A single patient usually requires dozens of such images during examination. Since, labelling the data is a computationally expensive task, it is assumed that the images for all patients have the same label in conventional image-based classification and is not usually tested practically. In this study, we are intending to investigate the significance of machine learning techniques in computer aided diagnostic systems based on analysis of histopathological breast cancer images. Publicly available BreakHis data set containing around 8,000 histopathological images of breast tumours is used for conducting experiments. The recently proposed non-parametric approach is proven to show interesting results when compared in detail with machine learning approaches. Our proposed model ’Deep-Hist’ is magnification independent and achieves > 92.46% accuracy with Stochastic Gradient Descent (SGD) which is better than the pretrained models for image classification. Hence, our approach can be used in processing data for use in research and clinical environments to provide second opinions very close to the experts’ intuition.

 A computational method for detecting pineapple ripening could lead to increased agricultural productivity. It is possible to predict fruit maturity before harvesting to increase agricultural productivity. A ripe fruit’s quality, its standard content of physical and chemical properties will increase the value of a good when traded outside the market. This paper studies and improves the Tiny YOLO-v4 model for identifying the pineapple ripening period. Researchers studied pineapples in a pineapple garden in Vietnam’s central region. They wanted to determine when pineapples were ripe. The API and the website are based on the YOLO innovation model. Apps and website APIs will be available for mobile devices so that people can monitor fruits. Technology transfer and academic research are combined in this study. We prepared the pineapple data set by using 5,000,000 pineapples harvested from the pineapple farm at different stages of growth. To make the measurements, we improved the YOLO-v4 algorithm. This results in a more accurate training model and reduced train-ing time. A 98.26% recognition accuracy is quite impressive. Research takes place at large-scale plantations, so the models are created from the data collected at the plantations and are used as labels; training takes a long time for the tiniest details about pineapples, and finding pineapple-growing regions takes a long time. The deep learning classifier was able to process pineapple plantation photos by using the camera on the mobile phone.

 The regularly issued low frequency data, such as the change of fund position (weekly), and Producer Price Index (monthly), can affect the subsequent trend of stock returns. However, the forecasting effect of low frequency data on high frequency has not been discussed amply. This paper proposes a new mixed frequency neural network that helps to fill this research gap. The original time series is decomposed into several components through ensemble empirical mode decomposition, then the frequency alignment method is applied to integrate the high frequency component with low frequency variable as inputs, and the CNN-BiLSTM-Attention network completes the remaining forecasting work. The empirical results show that compared with other benchmark models, the proposed procedures perform better when predicting the high frequency components and obtain a smaller statistical error in the final ensemble results. The proposed model has great potential for the forecasting of reverse mixed time series.

 The main purpose of this paper is to introduce invariant convergence in intuitionistic fuzzy normed space. Following which we present some characteristics of this notion with respect to intuitionistic fuzzy norm. We also define strongly invariant convergence, ideal invariant convergence and invariant ideal convergence in intuitionistic fuzzy normed space. After that, we establish the relationship between these notions with respect to intuitionistic fuzzy norm. Lastly, we define ideal invariant Cauchy and invariant ideal Cauchy criteria for sequences in intuitionistic fuzzy normed space and relate it to their convergence notion.

Multi-objective optimization is an emerging field concerning optimization problems associated with more than one objective function, each of them has to be optimized simultaneously. Multi-objective optimization is widely used in logistics and supply chains to reduce the cost and time involved in transportation. With the increase in Global Supply Chains, many organizations are facing the challenges of delivering products to their customers at a fast pace, low cost, and high reliability. There are numerous factors that may affect the goal of an organization to optimize the cost, time, and effort during the transportation of their products to the end customers. For instance, in the existing transportation problems, the type of vehicles used for the movement of the products is not focused. Transportation of the goods is considered to utilize any type of vehicle irrespective of the nature of the goods. However, in real-life scenarios, there are certain constraints in the vehicle used to transport the finished goods or raw materials from a source to a destination. Vehicles such as tanker trucks, top open trucks, closed trucks, etc. need to be booked based on the nature of goods to be transported. Also, the cost and time of transportation are uncertain in nature. In this paper, we formulate the Multi-Objective Solid Transportation Problem (MOSTP) by considering the above issue. The uncertain parameters of the problem are considered as Pentagonal Intuitionistic Fuzzy Numbers (PIFN). Magnitude method is used for defuzzification. An algorithm to find the solution of formulated Intuitionistic Fuzzy Multi-Objective Solid Transportation problem (IFMOSTP) is provided. The proposed model is illustrated by a numerical example which is solved with the help of LINGO software.

In this manuscript, a hybrid technique is proposed for Torque Ripple (TR) minimization of Switched Reluctance Motor (SRM). The proposed technique is the consolidation of Wingsuit flying search (WFS) optimization and Gradient Boosting Decision Tree (GBDT) algorithm, hence it is known as WFS-GBDT technique. The control mechanisms consists of fractional order proportional integral derivative (FOPID) speed controller on external loop as well as current controller on internal loop with controlling turn activate and deactivate angles for SRM. The complexity of acquiring the ideal evaluation of proportional, integral and derivative gains for speed and current controller including turn activate and deactivate angles are deemed as a multi-objective optimization issue. Here, the WFS optimize the gain parameters of external speed loop along internal current loop with commutation angles for turn activate and deactivate switches. The WFS optimization processing is used to productive machine learning dataset under the types of SRM parameter. By using the satisfied dataset, the GBDT is predicted and mandatory forecasting is implemented in the entire machine operating stage. The optimized gain parameters based, the fractional order proportional integral derivative controller is tuned exactly. The proposed WFS-GBDT control technique lessens the torque ripple and quick settling time with this proper control, because of its systematic random search capabilities, thereby enhancing the dynamic execution of SRM drive. Finally, the proposed technique is activated in MATLAB/Simulink site, its performance is analyzed with existing techniques, like Base, ALO and WFS. The best, worst, mean, standard deviation for ISEspeed using proposed technique attains 230.5364, 231.5934, 230.952 and 0.05314. The best, worst, mean and standard deviation for torque ripple using proposed technique attains 0.4571, 0.6548, 0.585 and 0.472. The best, worst, mean, standard deviation for ISEcurrent using proposed technique attains 3.1257, 3.9754, 3.5783 and 0.0472.

Statistical lifetime distributions play a very important role in modeling data sets in various fields. Extending the existing distributions is of great interest in statistical research. The modification of the distributions provides more flexible model as compared to existing one. In this article, we propose a new probability model using Quadratic Rank Transmutation Map technique, named as Transmuted Lomax Exponential Distribution (TLED). The new distribution can model data sets with increasing, decreasing and bathtub shape hazard rates. Various statistical properties of the proposed distribution such as moments, order statistics, quantile function, mean residual life function and characteristic function are derived. Further, the parameter estimates are obtained through Maximum Likelihood method along with asymptotic confidence intervals. The utility of the new model is evaluated by analyzing two real data sets. In order to access the performance of the new model, several goodness of fit measures is used. The results indicate that the new model best fits the data as compared to the other extensions of the Lomax distribution.

As a result of the advancements in Industry 4.0, the amount of data collected within industries are continuously expanding to achieve an innovative environment within the industry by maximizing asset usage. Meanwhile, the redundancy rate is increasing in cloud storage, which has an impact on data storage and analysis. To lower the rate of redundancy, the proposed system comprises a Time series-based deduplication technique. In the Time series-based deduplication technique, the Adaptive Multi-Pattern Boyer Moore Horspool (AM-BMH) algorithm, and Merkle tree were used to produce time-series data. Another significant challenge is that the geographically distributed cloud system has encountered that the data placement methodology with high-priced transportation costs for data transmission. To overcome this issue, an optimal data placement strategy using Modified Distribution is proposed. Thus the proposed Time Series-based Deduplication and Optimal Data Placement Strategy (TDOPS) is found to be effective when compared with the existing system. The various parameters like space reduction, efficient retrieval, data transportation costs, and data transmission time are taken into the account in the cloud environment for an evaluation. The proposed scheme saves 98 percent of storage space, 55 percent computation overhead, and improves 60% of cloud storage efficacy.

Taking advantage of dredged sediments as lightweight materials is a useful solution to protect the environment and save natural materials in the field of construction. In which unconfined compression strength is an important criterion to determine the application in the construction project. It is difficult to find the optimal mixing ratio based on design standards or construction conditions because the unconfined compression strength (UCS) is affected by the mixing ratio of the materials and additives. In this study, the Machine Learning (ML) models consisting of Extreme Gradient Boosting (XGB) model and Linear regression models are investigated to design components for reinforced lightweight soil based on the influence of unconfined compression strength of the test sample which is water content, cement content, air foam content, waste fishing net. To evaluate the effectiveness of the proposed ML models, several evaluation criteria including Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and coefficient of determination (R²) are proposed. The results show that the predictions of the XGB model have high accuracy with R² = 0.9695, RMSE = 5.5849 kPa and MAE = 4.1583 kPa for the testing dataset. Sensitivity analysis evaluates the influence of input variables on UCS and the interaction between input variables to help design RLS components optimally.