Journal of Intelligent & Fuzzy Systems - Volume 44, issue 3

Authors: Nguyen, Hoa Cuong | Xuan, Cho Do | Nguyen, Long Thanh | Nguyen, Hoa Dinh

Article Type: Research Article

Abstract: Advanced Persistent Threat (APT) attack detection and monitoring has attracted a lot of attention recently when this type of cyber-attacks is growing in both number and dangerous levels. In this paper, a new APT attack model, which is the combination of three different neural network layers including: Multi-layer Perceptron (MLP), Inference (I), and Graph Convolutional Networks (GCN) is proposed. The new model is named MIG for short. In this model, the MLP layer is in charge of aggregating and extracting properties of the IPs based on flow network in Network traffic, while the Inference layer is responsible for building IP …information profiles by grouping and concatenating flow networks generated from the same IP. Finally, the GCN layer is used for analyzing and reconstructing IP features based on the behavior extraction process from IP information records. The APT attacks detection method based on network traffic using this MIG model is new, and has yet been proposed and applied anywhere. The novelty and uniqueness of this method is the combination of many different data mining techniques in order to calculate, extract and represent the relationship and the correlation between APT attack behaviors based on Network traffic. In MIG model, many meaningful anomalous properties and behaviors of APT attacks are synthesized and extracted, which help improve the performance of APT attack detection. The experimental results showed that the proposed method is meaningful in both theory and practice since the MIG model not only improves the ability to correctly detect APT attacks in network traffic but also minimizes false alarms. Show more

Keywords: APT attacks, behavior profile, inference, graph convolutional neural network, graph analysis

DOI: 10.3233/JIFS-221055

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3459-3474, 2023

Authors: Liu, Yuyang | Ma, Tinghuai | Huang, Xuejian | Li, Ting

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219329 .

DOI: 10.3233/JIFS-221671

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3475-3500, 2023

Authors: Nguyen-Trong, Khanh | Nguyen-Hoang, Khoi

Article Type: Research Article

Abstract:  COVID-19 (Coronavirus Disease of 2019) is one of the most challenging healthcare crises of the twenty-first century. The pandemic causes many negative impacts on all aspects of life and livelihoods. Although recent developments of relevant vaccines, such as Pfizer/BioNTech mRNA, AstraZeneca, or Moderna, the emergence of new virus mutations and their fast infection rate yet pose significant threats to public health. In this context, early detection of the disease is an important factor to reduce its effect and quickly control the spread of pandemic. Nevertheless, many countries still rely on methods that are either expensive and time-consuming (i.e., Reverse-transcription polymerase …chain reaction) or uncomfortable and difficult for self-testing (i.e., Rapid Antigen Test Nasal). Recently, deep learning methods have been proposed as a potential solution for COVID-19 analysis. However, previous works usually focus on a single symptom, which can omit critical information for disease diagnosis. Therefore, in this study, we propose a multi-modal method to detect COVID-19 using cough sounds and self-reported symptoms. The proposed method consists of five neural networks to deal with different input features, including CNN-biLSTM for MFCC features, EfficientNetV2 for Mel spectrogram images, MLP for self-reported symptoms, C-YAMNet for cough detection, and RNNoise for noise-canceling. Experimental results demonstrated that our method outperformed the other state-of-the-art methods with a high AUC, accuracy, and F1-score of 98.6%, 96.9%, and 96.9% on the testing set. Show more

Keywords: COVID-19 diagnostics, multi-modal classification, Convolutional neural network (CNN), bidirectional-LSTM, Cough classification

DOI: 10.3233/JIFS-222863

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3501-3513, 2023

Authors: Zhao, Hu | Jia, Li-Yan | Chen, Gui-Xiu

Article Type: Research Article

Abstract: Notice that there’s a one-to-one correspondence between between (L , M )-fuzzy hull operators and (L , M )-fuzzy convex structures. So, it is necessary to consider the product of (L , M )-fuzzy convex structures through the product structures of (L , M )-fuzzy hull operators. In this paper, we construct the product structures of (L , M )-fuzzy hull operators to characterize the product of (L , M )-fuzzy convex structures. On the other hand, we construct the coproduct structures of (L , M )-fuzzy hull operators to give a reasonable definition with respect to the coproduct of …(L , M )-fuzzy convex structures. Show more

Keywords: (L, M)-fuzzy convex spaces, (L, M)-fuzzy hull operators, Base, Product, Coproduct

DOI: 10.3233/JIFS-222911

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3515-3526, 2023

Authors: Li, Xu-Dong | Wang, Jie-Sheng | Hao, Wen-Kuo | Song, Hao-Ming | Zhao, Xiao-Rui

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-221098

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3527-3559, 2023

Authors: Liu, Yao | Shen, Hao | Shi, Lei

Article Type: Research Article

Abstract: Social networks have accelerated the speed and scope of information dissemination. However, the lack of regulation and freedom of speech on social platforms has resulted in the widespread dissemination of the unverified message. Therefore, rapid and effective detection of social network rumors is essential to purify the network environment and maintain public security. Currently, the defects of rumor detection technology are that the detection time is too long and the timeliness is poor. In addition, the differences based on specific regions or specific fields will lead to deviations in the training dataset. In this paper, firstly, the definition of rumor …is described, and the current problems and detection process of rumor detection are described; Secondly, introduce different data acquisition methods and analyze their advantages and disadvantages; Thirdly, according to the development of rumor detection technology, the existing rumor detection methods of artificial, machine learning and deep learning are analyzed and compared; Finally, the challenges of social network rumor detection technology are summarized. Show more

Keywords: Rumor, rumor detection, machine learning, deep learning, social networks

DOI: 10.3233/JIFS-221894

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3561-3578, 2023

Authors: Xu, Le | Mo, Yuanbin | Lu, Yanyue

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-211855

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3579-3594, 2023

Authors: Jin, Xu | Jin, LeSheng | Chen, Zhen-Song | Mesiar, Radko | Yager, Ronald

Article Type: Research Article

Abstract: Interval basic uncertain information is a generalization of basic uncertain information. Due to their special structures, the induced aggregation and induced OWA operators have diversified inducing aggregation modes for them. In order to provide both normative paradigms and special ways to perform reasonable induced aggregation with vectors of interval basic uncertain information, this work systematically analyzes some substantial ways of performing induced aggregation by special means of non-induced aggregation. Numerous inducing posets are suggested to use which can help automatically generate weight vectors. Some special weights generation methods based on complex inducing information with numerical examples are also proposed and …presented. Show more

Keywords: Aggregation operators, basic uncertain information, decision making, induced aggregation operators, interval basic uncertain information, preference aggregation

DOI: 10.3233/JIFS-220528

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3595-3602, 2023

Authors: Li, Shugang | Ji, Xiaoru | Zhang, Beiyan | Liu, Ying | Lu, Hanyu | Yu, Zhaoxu

Article Type: Research Article

Abstract: The maintenance and strategy operation after patent licensing can bring great market competitiveness and benefits to enterprises. But the large time span from patent licensing to market application makes it challenging to discern the benefits of patent competition strategy. Besides, artificial intelligence (AI) is an emerging industry without ready-to-use experience to formulate patent competition strategy, and particularly current researches have not designed patent competition strategy from the micro patent management perspective of AI enterprises to solve the uncertainty caused by the lag of market application relative to patent licensing. This research builds an expert group discriminant system based on the …system dynamics method to address this problem. It integrates expert tacit knowledge to determine the fuzzy variable value and the fuzzy relationship. The patent competition strategy subsystem in national dimension, industry dimension and enterprise dimension for capturing the market from the perspective of enterprise technology competitiveness are constructed. By combining the three subsystems, the enterprise patent competition strategy system dynamics model with evolution analysis is established. Finally, taking typical Chinese AI enterprise iFLYTEK as an example, the multi-scenario simulation is carried out and the results under four different scenarios can provide effective decision supports for managers to formulate reasonable patent competition strategy and gain high market share. This research sheds light on modeling and evolution analysis of the patent competition strategy which comprehensively and systematically considers the operation mechanism of patent management and contributes to dealing with the uncertainty and ambiguity in the system dynamics model effectively. Show more

Keywords: Patent competition strategy, system dynamics method, expert group discrimination, artificial intelligence

DOI: 10.3233/JIFS-220572

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3603-3619, 2023

Authors: Akram, Muhammad | Zahid, Kiran | Kahraman, Cengiz

Article Type: Research Article

Abstract: The striking theory of ELECTRE III approach, being a marvelous strategy to deal with pseudo criterion, prevails over the traditional variants of ELECTRE method and other decision-making approaches for veracious decision-making. The noticeable efficiency and broader space of complex Pythagorean fuzzy model make it more significant and dominant for modeling two dimensional imprecise knowledge. The remarkable contribution of this study is to present a high aptitude variant of ELECTRE method by taking the advantage of the flexible structure of complex Pythagorean fuzzy sets closely following the outranking principles of ELECTRE III method. The proposed complex Pythagorean fuzzy ELECTRE III method …is accredited to employ the theory of ELECTRE III technique to excellently deal with pseudo criterion as well as the two dimensional imprecise data for authentic decision-making. The proposed methodology uses three different threshold values, including preference, indifference and veto threshold values, to check the preference relation between alternatives. The presented strategy is applied to a case study for material selection to get the befitting decision. The comparative study with Pythagorean fuzzy ELECTRE III method is also included in this article to verify its decision-making aptitude. Show more

Keywords: Group decision-making, ELECTRE III method, Pseudo criteria, Complex Pythagorean fuzzy set, Threshold values

DOI: 10.3233/JIFS-220764

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3621-3645, 2023

Authors: Sharmila Devi, J. | Balasubramanian, P.

Article Type: Research Article

Abstract: Milling seems to be the most extensively utilized production technology in modern manufacturing industries, and it plays a significant role. Chatter is a type of disturbance in the form of vibration that has a negative impact on machining operation. Chatter recognition utilizing sensor outputs is a hot topic in academia. Although some progress has indeed been documented utilizing various featurization techniques and ml techniques, conventional approaches have a number of limitations, including manual preparation and a huge dataset need. Although, these are widely being used to evaluate milling operations in terms of production efficiency & work piece surface quality,.they are …not suited for real applications due to their computing duration and require large data for training process. Therefore, in this study, three well-performing deep learning approaches such as LSTM, DTW, and Bi-LSTM are used to provide an effective way for monitoring and managing chatter in the milling processes with the Duplex 2205 material. Here, some of the parameters like acceleration is measured while the milling operation is taking place, and the measured acceleration value is processed using selected three DL techniques for identifying the presence of chatter and are tested to see which one performs the best. The Bi-LSTM outperformed other approaches in detecting chatter present, according to the data. Show more

Keywords: Bi-directional long short term memory, long short term memory, dynamic time warping, deep learning, acceleration, milling chatter detection

DOI: 10.3233/JIFS-221091

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3647-3666, 2023

Authors: Wang, Yongguo | Bi, Xuewen | Zhang, Xinxin

Article Type: Research Article

Abstract: The high power generation growth by photovoltaic systems needs to forecast the power generation profile during a day. It is also required to evolve the high-efficient and optimal on-grid/off-grid photovoltaic power generation units. Furthermore, some advantages can be achieved by integrating photovoltaic systems with storage devices such as battery energy storage systems. Thus, optimizing the hybrid systems comprising photovoltaic and battery energy storage systems is needed to evaluate the best capacity. In the present work, a novel control and sizing scheme is proposed for the battery energy storage system in a photovoltaic power generation plant in one-hour ahead and one-day …ahead during the dispatching phase. Then, the proposed prediction strategy is recommended for solar irradiation and power utilization. The control approach comprises a predictive control method concerning a Radial Basis Function network optimized by Levenberg-Marquardt back-propagation learning algorithm. Using the RBF network for simulation leads to a WAPE % =1.68 %. Show more

Keywords: Photovoltaic systems, battery energy storage system, control method, prediction method, RBF neural network, experimental dataset

DOI: 10.3233/JIFS-221123

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3667-3680, 2023

Authors: Nuhoho, Raphael Elimeli | Wenyu, Chen | Baffour, Adu Asare

Article Type: Research Article

Abstract:  As digital image acquisition becomes ubiquitous in recent years, the need for indoor scene recognition becomes more pronounced. Existing methods leverage the features of composing objects in a scene and overlook the adverse impacts of the common objects reoccurring in other scenes. This drawback decreases the feature discrimination between scenes (e.g., living room, dining room, and bedroom) due to reoccurring objects (e.g., tables, chairs, and toys). We propose a method of training convolutional networks by punishing or discounting the local object representations’ predictive ability and encouraging the network to learn global scene layout representations. To retain more vital information for …the scene feature representation, we introduce an activation function (with unbounded above, bounded below, smooth, and non-monotonic properties) to allow more low-negative values to flow through the network, discarding high negative values. We evaluate the proposed methods on MIT Indoor 67 and Scene 15 datasets. The experiment findings show that the proposed methods capture global scene concepts and improve performance. Show more

Keywords: Indoor scene recognition, feature representation, activation functions, convolutional neural network

DOI: 10.3233/JIFS-221975

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3681-3693, 2023

Authors: Meziani, Ahlem | Bourouis, Abdelhabib | Chebout, Mohamed Sedik

Article Type: Research Article

Abstract: Effective risk management reaction improves the absorption of critical impacts on supply chains. Supply chain risk (SCR) sources, like control, process, demand, and supply, need to be identified, assessed, and mitigated to make rational decisions immediately. Late detection of a disruptive event can cause delays in handling risk. Since SCRs consist of complex, uncertain, and incomplete information, most of the provided risk assessment mechanisms cannot handle it in real-time. Hence, in this paper, we introduce NeutroMAS4SCRM, a framework incorporating real-time Multi-Agent Systems (MAS) with Neutrosophic Data Analytic Hierarchy Processes to best deal with the complexity, uncertainty, and vagueness of SCR …management-related issues and which can hence help decision-makers adopt less risky decisions. In addition, the MAS technology contribution to SCR management is outlined through a comparative study among the most recent studies. In contrast, the proposed MAS for the supply chain is implemented under the JADE agent platform, where the FIPA-ACL-based message content is specified using a dedicated ontology. A simulation-based decision support system is used to assess the cost risk and its harmful effects and determine how well the proposed framework can help companies manage risks efficiently. The simulation has proven to reduce risk costs by about 85%. Show more

Keywords: Supply chain risk management, single-valued neutrosophic set, neutrosophic DAHP, multi agent system, simulation

DOI: 10.3233/JIFS-222305

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3695-3716, 2023

Authors: Lakshmi Narayanan, S. | Ignatia, K. Majella Jenvi | Alfurhood, Badria Sulaiman | Bhat, Nagaraj

Article Type: Research Article

Abstract: A Gaussian Curvature-based Local Tetra Descriptor (GCLTrP) is proposed in this paper to incorporate geometric discriminative feature extraction using a hybrid combination of Gaussian Curvature (GC) and Local Terta Pattern (LTrP). The texture of an image is locally discriminant, capturing the equivalent binary response from the gaussian curvature. The extracted feature value is fed into the Enhanced Grey Wolf Optimization (EGWO), a lightweight metaheuristic searching algorithm that selects the best optimal textural features. The proposed GCLTrP with EGWO method’s effective performance is validated using the benchmarks dataset, and the results are tested using the performance evaluation metric. In comparison to …other cutting-edge methods, the proposed method achieves the highest overall classification accuracy of 100% on the Brodatz and RS datasets. In terms of computational redundancy and noise reduction, the proposed technique outperforms the other existing techniques. Show more

Keywords: Feature extraction, feature selection, classification, texture analysis

DOI: 10.3233/JIFS-222481

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3717-3731, 2023

Authors: Huong, Trieu Thu | Lan, Luong Thi Hong | Giang, Nguyen Long | Binh, NguyenThi My | Vo, Bay | Son, Le Hoang

Article Type: Research Article

Abstract:  Transfer learning (TL) is further investigated in computer intelligence and artificial intelligence. Many TL methodologies have been suggested and applied to figure out the problem of practical applications, such as in natural language processing, classification models for COVID-19 disease, Alzheimer’s disease detection, etc. FTL (fuzzy transfer learning) is an extension of TL that uses a fuzzy system to pertain to the vagueness and uncertainty parameters in TL, allowing the discovery of predicates and their evaluation of unclear data. Because of the system’s increasing complexity, FTL is often utilized to further infer proper results without constructing the knowledge base and environment …from scratch. Further, the uncertainty and vagueness in the daily data can arise and modify the process. It has been of great interest to design an FTL model that can handle the periodicity data with fast processing time and reasonable accuracy. This paper proposes a novel model to capture data related to periodical phenomena and enhance the quality of the existing inference process. The model performs knowledge transfer in the absence of reference or predictive information. An experimental stage on the UCI and real-life dataset compares our proposed model against the related methods regarding the number of rules, computing time, and accuracy. The experimental results validated the advantages and suitability of the proposed FTL model. Show more

Keywords: Complex fuzzy set, mamdani complex fuzzy inference system, transfer learning, fuzzy transfer learning, complex fuzzy transfer learning

DOI: 10.3233/JIFS-222582

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3733-3750, 2023

Authors: Wu, Guanghua | Li, Hongsheng | Li, Hongyu | Guo, Shiping | Ma, Wenjian | Dong, Jing

Article Type: Research Article

Abstract: The business expansion installation can only simply record the most basic business information, which leads to the problems of complex power supply procedures and low efficiency. Therefore, a study on the optimal power supply parameters of the business expansion installation based on grey correlation degree and fuzzy C-means clustering algorithm is proposed. Firstly, the grey correlation degree is used to process the optimal power supply parameter data of industrial expansion and installation, and the parameters of fuzzy C-means clustering algorithm are set. On this basis, an intelligent management system for the optimal power supply process of industrial expansion and installation …is constructed, and the system development conditions are set up; According to the four business links of project reserve, business acceptance, collaborative operation and performance evaluation, the customer business expansion and installation function module is constructed, so as to realize the calculation of the optimal power supply line of the business expansion and installation and complete the research on the optimal power supply parameters. The experimental results show that the output stability, output throughput performance and parameter optimization ability of this method for the line impedance characteristic control of the power supply of the industrial expansion device are good and are always on the rise. At 3 cm, the output throughput reaches 1.9%, and the parameter analysis ability can reach 350 pixels, which has certain application value. Show more

Keywords: Grey correlation degree, fuzzy C-means clustering algorithm, business expansion newspaper installation, Optimal power supply parameters

DOI: 10.3233/JIFS-222926

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3751-3762, 2023

Authors: Zhang, Shasha | Liu, Xiaodi | Garg, Harish | Zhang, Shitao

Article Type: Research Article

Abstract: With the implementation and steady progress of the Belt and Road (B&R) initiative, China’s investment in countries along the B&R has maintained a high growth trend. Generally speaking, investment problems are often accompanied by high risk and uncertainty, and how to make the suitable investment decision is a difficult issue. This paper investigates an investment decision approach under the probabilistic hesitant fuzzy environment. Firstly, a new probabilistic hesitant fuzzy distance and correlation coefficient are defined to overcome the defects of the existing probabilistic hesitant fuzzy information measures. Secondly, an attribute weight integrated model is constructed by combining the maximum deviation …method, the CRITIC method and the maximum entropy principle, which is able to take into account the correlation between attributes and make full use of the decision information. In addition, a disappointment theory-based probabilistic hesitant fuzzy multi-attribute decision making (PHFMADM) method is proposed to solve the investment decision problem, which can integrate the psychological behavior of decision makers into the decision making process and make the decision results more authentic and reliable. Finally, the rationality and validity of the method are verified by comparing with the existing methods. Show more

Keywords: Investment decision making, Distance, Correlation coefficient, Disappointment theory, Probabilistic hesitant fuzzy sets

DOI: 10.3233/JIFS-223059

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3763-3786, 2023

Authors: Zhou, Tong | Zhang, Shuai | Zhang, Dongping | Chan, Verner | Yang, Sihan | Chen, Mengjiao

Article Type: Research Article

Abstract: With the increasing demand for express delivery and enhancement of sustainable logistics, the collaborative multi-depot delivery based on electric vehicles has gradually attracted the attention of logistics industry. However, most of the existing studies assumed that the products required by different customers could be delivered from any homogeneous depot, ignoring the limitations in facilities and environment of depots in reality. Thus, this study proposed a novel collaborative multi-heterogeneous-depot electric vehicle routing problem with mixed time windows and battery swapping, which not only involves the multi-heterogeneous-depot to meet different customer demands, but also considers the constraints of mixed time windows to …ensure timely delivery. Furthermore, a customer-oriented multi-objective optimization model minimizing both travel costs and time window penalty costs is proposed to effectively improve both delivery efficiency and customer satisfaction. To solve this model, an extended non-dominated sorting genetic algorithm-II is proposed. This combines a new coding scheme, a new initial population generation method, three crossover operators, three mutation operators, and a particular local search strategy to improve the performance of the algorithm. Experiments were conducted to verify the effectiveness of the proposed algorithm in solving the proposed model. Show more

Keywords: Electric vehicle routing problem, multi-objective optimization, collaborative multi-heterogeneous-depot, mixed time windows, nondominated sorting genetic algorithm-II

DOI: 10.3233/JIFS-223298

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3787-3805, 2023

Authors: Li, Shiyong | Li, Wenzhe | Sun, Wei | Liu, Jia

Article Type: Research Article

Abstract: The advantages of cloud computing attract a large number of enterprises to deploy their applications into the cloud, thereby reducing their own operating costs. This paper considers deploying inelastic applications into the cloud and proposes an optimal resource allocation model. The deployment functions for inelastic applications are nonconvex (e.g., sigmoidal), then the resource allocation model becomes a hard nonconvex optimization problem. The traditional gradient-based resource allocation algorithm cannot effectively achieve the global optimum. Therefore, this paper applies particle swarm optimization (PSO) method to design a resource allocation scheme. This scheme can not only effectively solve the resource allocation problem of …deploying inelastic enterprise applications into the cloud, but also solve the hard problem of deploying multi-class applications into the cloud when the enterprise can support both elastic and inelastic applications. We also compare the performance of the proposed PSO-based resource allocation scheme with some other methods and illustrate some numerical examples to verify the effectiveness and superiority of the proposed resource allocation scheme. Show more

Keywords: Cloud deployment, inelastic applications, resource allocation, nonconvex optimization, PSO

DOI: 10.3233/JIFS-201239

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3807-3823, 2023

Authors: Khan, Indadul | Dutta, Prasanta | Maiti, Manas Kumar | Basuli, Krishnendu

Article Type: Research Article

Abstract: In this study, Bat algorithm (BA) is modified along with K -opt operation and one newly proposed perturbation approach to solve the well known covering salesman problem (CSP). Here, along with the restriction of the radial distances of the unvisited cities from the visited cities another restriction is imposed where a priority is given to some cities for the inclusion in the tour, i.e., some clusters to be created where the prioritised cities must be the visiting cities and the corresponding CSP is named as Prioritised CSP (PCSP). In the algorithm, 3-opt and 4-opt operations are used for two different …purposes. The 4-opt operation is applied for generating an initial solution set of CSP for the BA and the 3-opt operation generates some perturbed solutions of a solution. A new perturbation approach is proposed for generating neighbour solutions of a potential solution where the exchange of some cities in the tour is made and is named as K -bit exchange operation. The proposed solution approach for the CSP and PCSP is named as the modified BA embedded with K -bit exchange and K -opt operation (MBAKEKO). It is a two-stage algorithm where in the first stage of the algorithm the clustering of the cities is done with respect to a fixed visiting city of each cluster in such a manner that the distances of the other cities of the cluster must lie with in the fixed covering distance of the problem and in the second stage the BA is applied to find the minimum cost Hamiltonian circuit by passing through the visiting cities of the clusters. MBAKEKO is tested with a set of benchmark test problems with significantly large sizes from the TSPLIB. To measure the performance of MBAKEKO, its results are compared with the results of different well-known approaches for CSPs available in the literature. It is observed from the comparison studies that MBAKEKO searches the minimum cost tour for any of the considered instances compared to all other well-known algorithms in the literature. It can be concluded from the numerical studies that the performance of MBAKEKO is better with respect to the state-of-the-art algorithms available in the literature. Show more

Keywords: Combinatorial optimization, covering salesmen problem, priority based covering salesman problem, K-bit exchange operation, K-opt, Bat Algorithm

DOI: 10.3233/JIFS-220396

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3825-3849, 2023

Authors: Kanimozhi Selvi, C.S. | Jayaprakash, D. | Poonguzhali, S.

Article Type: Research Article

Abstract: Autism spectrum disorder is a neuro-developmental disorder that affects communication and social skills in individuals. Screening and diagnosis of autism using conventional methods, such as interviews with parents or caregivers and observational assessments takes a long time. The accurate diagnosis of autism by physicians and healthcare professionals seems to be challenging. By analyzing data on autistic children, medical professionals can learn about autism screening assessment decision making. The present study aims to develop a parental autism screening tool termed the Indian Autism Grading Tool (IAGT) for early screening of autism. Data are collected using the Indian Autism Parental Questionnaire and …assigned with grades. This dataset is employed to test five supervised machine learning models, which compare classification performance based on accuracy, precision and recall. The most effective model should be used to implement the autism screening application. MLR is known to be more robust and to support fewer data sets, so it can be employed for the implementation of ML-powered mobile applications. MLR achieves the overall accuracy of 97.85%, which equates to 0.72%, 2.37%, 0.84% and 1.54% better than SVM, DT, KNN and GNB respectively. The proposed tool is developed in both Tamil and English. The pilot study is conducted with 30 children and the predictability of the tool is compared with the clinician. Therefore, the tool consistently achieves the same level of accuracy as clinicians. Show more

Keywords: Artificial intelligence, machine learning techniques, autism spectrum disorder, Indian autism parental questionnaire, mobile application

DOI: 10.3233/JIFS-221087

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3851-3865, 2023

Authors: Amanullah, M. | Thanga Ramya, S. | Sudha, M. | Gladis Pushparathi, V.P. | Haldorai, Anandakumar | Pant, Bhaskar

Article Type: Research Article

Abstract: On the basis of quality estimate, early prediction and identification of software flaws is crucial in the software area. Prediction of Software Defects SDP is defined as the process of exposing software to flaws through the use of prediction models and defect datasets. This study recommended a method for dealing with the class imbalance problem based on Improved Random Synthetic Minority Oversampling Technique (SMOTE), followed by Linear Pearson Correlation Technique to perform feature selection to predict software failure. On the basis of the SMOTE data sampling approach, a strategy for software defect prediction is given in this paper. To address …the class imbalance, the defect datasets were initially processed using the Improved Random-SMOTE Oversampling technique. Then, using the Linear Pearson Correlation approach, the features were chosen, and using the k-fold cross validation process, the samples were split into training and testing datasets. Finally, Heuristic Learning Vector Quantization is used to classify data in order to predict software problems. Based on measures like sensitivity, specificity, FPR, and accuracy rate for two separate datasets, the performance of the proposed strategy is contrasted with the approaches to classification that presently exist. Show more

Keywords: Index Terms: Software defect prediction, improved random-SMOTE oversampling technique, linear pearson correlation, heuristic learning vector quantization (LVQ), training and test datasets

DOI: 10.3233/JIFS-220480

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3867-3876, 2023

Authors: Suganthi, M. | Arun Prakash, R.

Article Type: Research Article

Abstract: Everything becomes smart in the modern era, for everything we need a better plan or arrangements. In the olden days, essential information was noted as a document with the help of paper and pen or printed texts. But the intelligent world needs a paperless environment by converting handwritten or printed text documents into software copies. This can be achieved by the electronic data conversion concept called Optical Character Recognition (OCR). OCR of some documents is complex because of different writing styles and quality of scanned image issues, which can be solved by adopting a deep learning technique for better accuracy. …We employed Long Short Term Memory (LSTM) for English Optical Character Recognition for paperless and effortless data storage and fast access in this work. Still, the records may contain the entities like names, contact details, drug details, diseases, educational qualifications, dates, etc. These entities cannot be separated by employing OCR alone; we need an entity recognition framework for deeper and faster data analysis. For efficient Named Entity Recognition, we utilize the Adaptive Fuzzy Inference System (ANFIS) powered by the algorithms CRF and BERT to automatically label each entity by training the vast amount of unlabeled text data. The ANFIS model is equipped with both linguistic and numerical knowledge. It is more accurate than the ANN when it comes to identifying patterns and classification data. Also, it is more transparent to the user. Our proposed framework aims to improve the performance of the character recognition system by using a feed-forward network. One of the main issues that have been identified in the development of this system is noise. Through this network, we can provide a single input and one output layer. The main components of the system are the training and recognition sections. These two sections are mainly focused on image acquisition and feature extraction. Besides these, they also include training and simulation of the classifier. The first step in the process of image recognition is to extract the features from the normalized image matrix. We then train the network using a proposed training algorithm. Experimentation on medical records attains a higher accuracy value of 0.9637, recall value of 0.9627, and f1 score of 0.9627, respectively. Show more

Keywords: Paperless environment, Optical Character Recognition, Named Entity Recognition, faster data analysis, accuracy

DOI: 10.3233/JIFS-221486

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3877-3890, 2023

Authors: Hovorushchenko, Tetiana | Medzatyi, Dmytro | Voichur, Yurii | Lebiga, Mykyta

Article Type: Research Article

Abstract: The paper develops the method for forecasting the level of software quality based on quality attributes. This method differs from the known ones in that it provides forecasting the quality level of future software based on the processing the software quality attributes’ values, which are available in the software requirements specification (SRS). So, the proposed method makes it possible to compare the SRSs, to immediately refuse the realization of a software based on unsuccessful SRS (saving money and time, reducing the probability of failed and challenged projects), and to make a reasonable choice of the specification for the further implementation …of a software with the highest quality (of course, if errors will not be introduced at subsequent stages of the software life cycle). During the experiments, 4 SRS were analyzed, which were fulfilled by different IT firms of Khmelnytskyi (Ukraine) for the solution of the same task. Taking into account the forecasted quality level of the future software, which will have developed according to each of the analyzed SRS, a comparison of the 4 analyzed SRS was made, and a reasoned choice of the specification was made for the further realization of the highest quality software. Show more

Keywords: Software quality, software quality attributes, software quality characteristics, software quality level, artificial neural network (ANN)

DOI: 10.3233/JIFS-222394

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3891-3905, 2023

Authors: Ma, Hongdong | Li, Gang | Liu, Rongyue | Shen, Mengdi | Liu, Xiaohui

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-212780

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3907-3925, 2023

Authors: Ferrari, Allan Christian Krainski | Leandro, Gideon Villar | Coelho, Leandro dos Santos | Delgado, Myriam Regattieri De Biase Silva

Article Type: Research Article

Abstract: The rat swarm optimizer is one of the most recent metaheuristics focused on global optimization. This work proposes a fuzzy mechanism that aims to improve the convergence of this algorithm, adjusting the amplitude of the parameter that directly affects the chasing mechanism of the behavior of rats. The proposed fuzzy model uses the normalized fitness of each individual and the population diversity as input information. For evaluation criteria, the fuzzy mechanism proposed, was implemented in the optimization of third-three single objective problems. For comparison criteria, the proposed fuzzy variant is compared with other algorithms, such as GWO (Grey Wolf Optimizer), …SSA (Salp Swarm Algorithm), WOA (Whale Optimization Algorithm), and also with two proposed alternative fuzzy variants. One of the simpler fuzzy variants uses only population diversity as input information, while the other uses only the normalized fitness value of each rat. The results show that the proposed fuzzy system improves the convergence of the conventional version of the rat algorithm and is also competitive with other metaheuristics. The Friedman test shows statistically the results obtained. Show more

Keywords: Rat swarm optimizer, metaheuristics, fuzzy system, optimization, friedman test

DOI: 10.3233/JIFS-222522

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3927-3942, 2023

Authors: Ranjeeth Kumar, C. | Kalaiarasu, M.

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-222795

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3943-3958, 2023

Authors: Paramasivam Thuraipandi, Sivagurunathan | Nagarajan, Sathish Kumar

Article Type: Research Article

Abstract: The spectrum scarcity problem in today’s wireless communication network is addressed through the use of a cognitive radio network (CRN). Detection in the spectrum is made easier by cooperative spectrum sensing (CSS), which is a tool developed by the military. The fusion centre receives the sensing information from each secondary user and uses it to make a global conclusion about the presence of the principal user. Literature has offered several different methods for decision making that lack scalability and robustness. CSS censoring is inspected in the attendance of faded settings in the current study. Rayleigh fading, which affects reporting channels …(R), is examined in detail. Multiple antennae and an energy detector (ED) are used by each secondary user (SU). A selection combiner (SC) combines the ED outputs with signals from the primary user (PU), which are established by several antennas on SU, before the joint signal is utilised to make a local result. SUs are expurgated at the fusion centre (FC) using a hybrid Support Vector Machine (SVM) that significantly improves detection performance and reduces the number of false positives. With a minimum false alarm probability of 0.1, error rate of 0.04, spectrum utilization of 99%, throughput of 2.9kbps and accuracy of 99%, proposed model attains better performance than standard SVM and Artificial Neural Network (ANN) models. Show more

Keywords: Energy detector, primary user, cognitive radio network, secondary user, cooperative spectrum sensing

DOI: 10.3233/JIFS-222983

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3959-3971, 2023

Authors: Wang, Jing

Article Type: Research Article

Abstract: Before neural networks, image style transfer procedures had a common idea: analyze images with a certain style, build a mathematical or statistical model for the style, and then change the image to be transferred, so that it better fits the established model. In this paper, k-means and semantic closed natural matting algorithm is combined for image segmentation, the style and content in the image are extracted based on neural network, and the resulting image is synthesized by image reconstruction technology to realize the migration of national costume styles. Due to the serious artifacts of the output image, an improved image …style transfer algorithm is adopted to constrain the transformation from the input image to the output image in the local affine transformation of the color space, and this constraint is expressed as a completely differentiable parameter term, image distortion is suppressed effectively. In the process of real photo style transfer, there is also space inconsistency. Smoothing is done to ensure that the space style is consistent after style processing, it greatly speeds up the operation speed. On NVIDIA GTX1080TI graphics card, algorithm is tested with 256×256 resolution images. It includes three indicators of average running time, memory usage and the number of styles generated by a single model, which are 0.06 s, 136.06 MB and 1 respectively. These indicators can reflect the efficiency and flexibility of the algorithm. Show more

Keywords: Garment feature extraction, deep learning, closed form natural image matting algorithm, K-means, image segmentation, image style transfer

DOI: 10.3233/JIFS-220761

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3973-3986, 2023

Authors: Sreenivasulu, A. | Subramanian, S. | Sangameswara Raju, P.

Article Type: Research Article

Abstract: The world’s energy offer has been beneath an incredible pressure because of the speedy depletion of fossil resources, energy security, environmental issues and therefore the ever-increasing fashionable living sophistication. The problem of persistent hikes in oil costs, climate threats and soaring energy demand has pleased the worldwide interest to exploiting and investment in renewable sorts of energy (RE), alternative energy specially. A electrical phenomenon, PV system is simple to put in, has no moving components, is sort of freed from maintenance, reduced vulnerability to power loss and is expandable. Despite these benefits, PV energy prices significantly on top of fossil …fuels. This can be because of its lower effectiveness and better prices. In PV systems tracking MPPT in effective manner is still the problem. In this paper, the 1000 W grid connected PV system has been taken for analysis of various MPPT techniques. Grid connected PV system modeled, tested under totally different irradiation conditions and conjointly for partial shading conditions. additional it’s enforced under partial shading condition for early MPPT ways, improvement methodology,at finally adopted deep learning methodology for the system and therefore the obtained results were compared with different methods. Show more

Keywords: Maximum power point tracking, deep learning, partial shading conditions, efficiency, power

DOI: 10.3233/JIFS-221465

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3987-3998, 2023

Authors: Deepa, K. | Ranjeeth Kumar, C.

Article Type: Research Article

Abstract: The remarkable developments in biotechnology as well as the health sciences have resulted in the production of an enormous amount of data, including high-throughput screening genomics information and clinical information obtained through extensive electronic health records (EHRs). The application of data mining and machine learning techniques in the biosciences is today more vital than ever to achieving this objective as attempts are made to intelligently translate all readily available data into knowledge. Diabetes mellitus (DM), a group of metabolic disorders, is well known to have a serious detrimental effect on population lives all over the world. Large-scale research into all …aspects of diabetic has resulted in the production of enormous amounts of data (detection, etiopathophysiology, therapy, etc.). The goal of the current study is to conduct a thorough examination of the use of machine learning, data mining methods and tools in the field of diabetes research, with the first classification making an appearance to be the most popular. These applications relate to a Statistical model and Diagnosis, b) Diabetic Complications, c) Multiple genes Background and Environment, and e) Free Healthcare and Management. Numerous machine learning algorithms were applied. 85% of the methods used were supervised learning approaches, whereas 15% were uncontrolled ones, including association rules. Developed on improved support vector machines, the most successful and widely used algorithm (SVM). Medical datasets were predominantly used in terms of data kind. Show more

Keywords: Diabetes mellitus, data mining, machine learning techniques, medical datasets, screening genomics information and early diagnosis

DOI: 10.3233/JIFS-222574

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 3999-4011, 2023

Authors: Yu, Jianping | Yuan, Laidi | Zhang, Tao | Fu, Jilin | Cao, Yuyang, | Li, Shaoxiong | Xu, Xueping

Article Type: Research Article

Abstract: The development of natural language processing promotes the progress of general linguistic studies. Based on the selected features and the extracted rules for word sense disambiguation (WSD), some valuable knowledge of the relations between linguistic features and word sense classes may be discovered, which may provide theoretical and practical evidence and references for lexical semantic study and natural language processing. However, many available approaches of feature selection for WSD are in the end to end operation, they can only select the optimal features for WSD, but not provide the rules for WSD, which makes knowledge discovery impossible. Therefore, a new …Filter-Attribute partial ordered structure diagram (Filter-APOSD) approach is proposed in this article to fulfill both feature selection and knowledge discovery. The new approach is a combination of a Filter approach and an Attribute Partial Ordered Structure Diagram (APOSD) approach. The Filter approach is designed and used for filtering the simplest rules for WSD, and the APOSD approach is used to provide the complementary rules for WSD and visualize the structure of the datasets for knowledge discovery. The features occurring in the final rule set are selected as the optimal features. The proposed approach is verified by the benchmark data set from the SemEval-2007 preposition sense disambiguation corpus with around as the target word for WSD. The test result shows that the accuracy of WSD of around is greatly improved comparing with the one by the state of the art, and 17 out of 22 features are finally selected and ranked according to their contribution to the WSD, and some knowledge on the relations between the word senses and the selected features is discovered. Show more

Keywords: Filter-APOSD approach, feature selection, word sense disambiguation, knowledge discovery, English preposition

DOI: 10.3233/JIFS-222715

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4013-4028, 2023

Authors: Huang, Bogang | Chen, Fu

Article Type: Research Article

Abstract: The physical education teaching quality evaluation is a very important part of the current physical education teaching reform in colleges and universities, and many experts and scholars have achieved fruitful results in this area, which has played a role in promoting the development of physical education teaching evaluation theory and practice. But at the same time, it should be soberly recognized that, with the deepening reform of physical education teaching in colleges and universities, the current teaching quality evaluation system can no longer meet the needs of the current education situation, and there are still many problems that need to …be further studied and improved. The teaching quality decision evaluation of college volleyball training is looked as the MAGDM. Thus, a useful MAGDM process is needed to cope with it. The information entropy is used for determination of target weight. Based on the grey relational analysis (GRA) and probabilistic double hierarchy linguistic term sets (PDHLTSs), this paper constructs the PDHLTS-GRA for MAGDM issues. Finally, an example for teaching quality evaluation of college volleyball training is used to illustrate the designed method. Show more

Keywords: Multiple attribute group decision making (MAGDM), probabilistic double hierarchy linguistic term sets (PDHLTSs), GRA method, teaching quality evaluation

DOI: 10.3233/JIFS-222945

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4029-4039, 2023

Authors: Pandey, Mamta | Litoriya, Ratnesh | Pandey, Prateek

Article Type: Research Article

Abstract: Massive open online courses (MOOCs) are a recent e-learning programme that has received widespread acceptance among several colleges. Student dropout from MOOCs is a big worry in higher education and policy-making circles, as it occurs frequently in colleges that offer these types of courses. The majority of student dropouts are caused by causes beyond the institution’s control. Using an IF-DEMATEL (Intuitive Fuzzy Decision-making Trial and Evaluation Laboratory) approach, the primary factors and potential causal relationships for the high dropout rate were identified. The most effective aspects of massive open online courses (MOOCs) are identified using IF-DEMATEL and CIFCS. Moreover, it …explains the interconnectedness of the various MOOC components. As an added measure, a number of DEMATEL techniques are used to conduct a side-by-side comparison of the results. Decisions made by the educational organisation could benefit from the findings. According to the research, there are a total of twelve indicators across four dimensions that are related to online course withdrawal amongst students. Then, experienced MOOC instructors from various higher education institutions were invited to assess the level of influence of these characteristics on each other. Academic skills and talents, prior experience, course design, feedback, social presence, and social support were identified as six primary characteristics that directly influenced student dropout in MOOCs. Interaction, course difficulty and length, dedication, motivation, and family/work circumstances have all been found to play a secondary part in student dropout in massive open online courses (MOOCs). The causal connections between the major and secondary factors were traced and discussed. The results of this study can help college professors and administrators come up with and implement effective ways to reduce the high number of students who drop out of massive open online courses (MOOCs). Show more

Keywords: Massive open online courses, lifelong learning, intuinistic fuzzy DEMATEL, online learning environments

DOI: 10.3233/JIFS-190357

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4041-4058, 2023

Authors: Peng, Lijuan | Xu, Dongsheng

Article Type: Research Article

Abstract: The MULTIMOORA (multiple multi-objective optimization by ratio analysis) method is useful for multiple criteria decision-making method. It is based on expected utility theory and assumes that decision makers are completely rational. However, some studies show that human beings are usually bounded rational, and their regret aversion behaviors play an important role in the decision-making process. Interval neutrosophic sets can more flexibly depict uncertain, incomplete and inconsistent information than single-valued neutrosophic sets. Therefore, this paper improves the traditional MULTIMOORA method by combining the regret theory under interval neutrosophic sets. Firstly, the regret theory is used to calculate the utility value and …regret-rejoice value of each alternatives. Secondly, the criteria weights optimization model based on the maximizing deviation is constructed to obtain the weight vector. Then, the MULTIMOORA method is used to determine the order of the alternatives. Finally, an illustrative example about school selection is provided to demonstrate the feasibility of the proposed method. Sensitivity analysis shows the validity of the regret theory in the proposed method, and the ranking order change with different regret avoidance parameter. Comparisons are made with existing approaches to illustrate the advantage of the proposed method in reflecting decision makers’ psychological preference. Show more

Keywords: Interval neutrosophic set, regret theory, multiple criteria decision making, MULTIMOORA

DOI: 10.3233/JIFS-212903

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4059-4077, 2023

Authors: Venkata Lakshmi, S. | Sujatha, K. | Janet, J.

Article Type: Research Article

Abstract: In recent years, speech processing resides a major application in the domain of signal processing. Due to the audibility loss of some speech signals, people with hearing impairment have difficulty in understanding speech, which reintroduces a crucial role in speech recognition. Automatic Speech Recognition (ASR) development is a major challenge in research in the case of noise, domain, vocabulary size, and language and speaker variability. Speech recognition system design needs careful attention to challenges or issues like performance and database evaluation, feature extraction methods, speech representations and speech classes. In this paper, HDF-DNN model has been proposed with the hybridization …of discriminant fuzzy function and deep neural network for speech recognition. Initially, the speech signals are pre-processed to eliminate the unwanted noise and the features are extracted using Mel Frequency Cepstral Coefficient (MFCC). A hybrid Deep Neural Network and Discriminant Fuzzy Logic is used for assisting hearing-impaired listeners with enhanced speech intelligibility. Both DNN and DF have some problems with parameters to address this problem, Enhanced Modularity function-based Bat Algorithm (EMBA) is used as a powerful optimization tool. The experimental results show that the proposed automatic speech recognition-based hybrid deep learning model is effectively-identifies speech recognition more than the MFCC-CNN, CSVM and Deep auto encoder techniques. The proposed method improves the overall accuracy of 8.31%, 9.71% and 10.25% better than, MFCC-CNN, CSVM and Deep auto encoder respectively. Show more

Keywords: Speech recognition, adaptive filter, feature extraction, deep learning, discriminant fuzzy function, deep neural networks, Mel-frequency

DOI: 10.3233/JIFS-212945

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4079-4091, 2023

Authors: Yang, Can | Li, Ping

Article Type: Research Article

Abstract: Mobile game providers benefit by selling virtual items in the game. Each event is described as an example in the player log data, and the player indicates the purchase status of the various game props as a plurality of tags, the game props recommendation question is abstractd into a multi-instance multi-label learning problem. On this basis, the fast multi-instance multi-label learning algorithm is designed for recommendation of mobile online game props, and semi-supervised learning is used to improve the recommendation performance. Off-line data sets and the online game experimental results of the actual online mobile phone show that the game …props based on multi-instance multi-tagging learning technology brings a significant increase in game revenue. Show more

Keywords: Machine learning, Multi-Instance Multi-Label Learning (MIML), semi-supervised learning, recommendation

DOI: 10.3233/JIFS-220703

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4093-4102, 2023

Authors: Yang, Feifei | Zhang, Pengfei

Article Type: Research Article

Abstract:  Multi-source information fusion is a sophisticated estimating technique that enables users to analyze more precisely complex situations by successfully merging key evidence in the vast, varied, and occasionally contradictory data obtained from various sources. Restricted by the data collection technology and incomplete data of information sources, it may lead to large uncertainty in the fusion process and affect the quality of fusion. Reducing uncertainty in the fusion process is one of the most important challenges for information fusion. In view of this, a multi-source information fusion method based on information sets (MSIF) is proposed in this paper. The information set …is a new method for the representation of granularized information source values using the entropy framework in the possibilistic domain. First, four types of common membership functions are used to construct the possibilistic domain as the information gain function (or agent). Then, Shannon agent entropy and Shannon inverse agent entropy are defined, and their summation is used to evaluate the total uncertainty of the attribute values and agents. Finally, an MSIF algorithm is designed by infimum-measure approach. The experimental results show that the performance of Gaussian kernel function is good, which provides an effective method for fusing multi-source numerical data. Show more

Keywords: Multi-source information fusion, information sets, Shannon entropy, uncertainty, fuzzy membership degree

DOI: 10.3233/JIFS-222210

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4103-4112, 2023

Authors: Gowthami, S. | Harikumar, R.

Article Type: Research Article

Abstract: Melanoma is one of the widespread skin cancers that has affected millions in past decades. Detection of skin cancer at preliminary stages may become a source of reducing mortality rates. Hence, it is required to develop an autonomous system of reliable type for the detection of melanoma via image processing. This paper develops an independent medical imaging technique using Self-Attention Adaptation Generative Adversarial Network (SAAGAN). The entire processing model involves the process of pre-processing, feature extraction using Scale Invariant Feature Transform (SIFT), and finally, classification using SAAGAN. The simulation is conducted on ISIC 2016/PH2 datasets, where 10-fold cross-validation is undertaken …on a high-end computing platform. The simulation is performed to test the model efficacy against various images on several performance metrics that include accuracy, precision, recall, f-measure, percentage error, Matthews Correlation Coefficient, and Jaccard Index. The simulation shows that the proposed SAAGAN is more effective in detecting the test images than the existing GAN protocols. Show more

Keywords: Autonomous, melanoma, generative adversarial network, scale invariant feature transform, synthetic datasets

DOI: 10.3233/JIFS-220015

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4113-4122, 2023

Authors: Bensoltane, Rajae | Zaki, Taher

Article Type: Research Article

Abstract: Aspect-based sentiment analysis (ABSA) is a challenging task of sentiment analysis that aims at extracting the discussed aspects and identifying the sentiment corresponding to each aspect. We can distinguish three main ABSA tasks: aspect term extraction, aspect category detection (ACD), and aspect sentiment classification. Most Arabic ABSA research has relied on rule-based or machine learning-based methods, with little attention to deep learning techniques. Moreover, most existing Arabic deep learning models are initialized using context-free word embedding models, which cannot handle polysemy. Therefore, this paper aims at overcoming the limitations mentioned above by exploiting the contextualized embeddings from pre-trained language models, …specifically the BERT model. Besides, we combine BERT with a temporal convolutional network and a bidirectional gated recurrent unit network in order to enhance the extracted semantic and contextual features. The evaluation results show that the proposed method has outperformed the baseline and other models by achieving an F1-score of 84.58% for the Arabic ACD task. Furthermore, a set of methods are examined to handle the class imbalance in the used dataset. Data augmentation based on back-translation has shown its effectiveness through enhancing the first results by an overall improvement of more than 3% in terms of F1-score. Show more

Keywords: Aspect-based sentiment analysis, aspect category detection, deep learning, BERT, data augmentation, arabic language

DOI: 10.3233/JIFS-221214

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4123-4136, 2023

Authors: Aruna, K. | Pradeep, G.

Article Type: Research Article

Abstract: Container technology is highly significant in Information and Communication Technology (ICT) systems. To maximize container effectiveness, scaling plays a significant part. Therefore, in the fog computing framework, containers are an ideal solution for hosting and scaling services. Fog networks help to increase the number of connected devices by connecting to external gateways through the Fog of Things (FoT). It is a new approach to designing and implementing fog computing systems for the IoT. The research article aims on a novel Container with a Fog-based Scalable Self-organizing Network (CFSSN) framework and use a Self-Organizing Network based Light Weight Container (SON-LWC) algorithm …for moving container services for scaling expansion. This work focuses on how to transfer service or data from container to fog and self-group network. It goes over the most recent container migration methodologies, covering both live and cold migration services. Using intelligent container improves high bandwidth efficiency and provides a solution for a scalable network. Show more

Keywords: Docker, container, ICT, CFSSN, FoT, DevOps, SON-LWC

DOI: 10.3233/JIFS-221524

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4137-4148, 2023

Authors: Weng, Ling | Lin, Jian | Lv, Shujie | Huang, Yan

Article Type: Research Article

Abstract: As the increasingly serious water pollution problem affects the sustainable development of the ecological environment, the research of water pollution treatment engineering cannot be delayed. Among them, the performance evaluation of water pollution treatment engineering is a major focus. After reading the existing studies, it is found that most of the existing performance evaluation indicators of water pollution treatment engineering have qualitative indicators and there is an unbalanced preference representation. Intuitionistic multiplicative linguistic sets can be a good representation of the qualitative preference and non-preference of decision-makers in the context of decision-making containing unbalanced phenomena. Therefore, to better solve the …problem of water pollution treatment engineering, this paper introduces intuitionistic multiplicative linguistic sets to the problem of water pollution treatment engineering and proposes an effective theory for it. First, considering the multiplicative nature of the intuitionistic multiplicative linguistic set, a new score function and accuracy function are defined, and on this basis, the priority rules of intuitionistic multiplicative linguistic set are given to prepare for the subsequent water pollution treatment engineering performance ranking. And the distance measure of intuitionistic multiplicative linguistic set is introduced and a CRITIC attribute weight determination model under intuitionistic multiplicative linguistic set is obtained on this basis. Secondly, the Choquet integral operator is applied to better represent the correlation between elements. However, the nature of membership degree and non-membership degree shows that it is not reasonable to aggregate the information of intuitionistic multiplicative linguistic sets with a single increasing and decreasing transformation. Therefore, in this paper, we propose the IMLS bi-direction exponent Choquet integral operator, which is inspired by the bi-direction Choquet integral. Lastly, we improve the original preference function of the classical PROMETHEE II method to obtain the bi-directional PROMETHEE II method in intuitionistic multiplicative linguistic information. Finally, a numerical case is also provided to illustrate the scientific and rational application of the bi-directional PROMETHEE II method in intuitionistic multiplicative linguistic information for the performance evaluation of water pollution treatment engineering. Show more

Keywords: Intuitionistic multiplicative linguistic sets, bi-direction Choquet integral, performance evaluation, water pollution treatment, PROMETHEE II method

DOI: 10.3233/JIFS-223373

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4149-4173, 2023

Authors: Rawshdeh, Amani A. | Al-jarrah, Heyam H. | Tiwari, Surabhi | Tallafha, Abdalla A.

Article Type: Research Article

Abstract: In this paper, we use the soft set theory and the concept of semi-linear uniform spaces to introduce the notion of soft semi-linear uniform spaces with its generalization, briefly soft-GSL US . We investigate some properties of soft topology that induced by soft-GSL US . Also, we use the members of soft-GSL US to define a soft proximity space and a soft filter then we establish the relationships between them. Finally, we give the perceptual application of soft semi-linear uniform structures by employing the natural transformation of a soft semi-linear uniform space to a soft proximity.

Keywords: Soft set, soft point, soft topology, soft semi-linear uniform spaces, soft proximity

DOI: 10.3233/JIFS-220587

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4175-4184, 2023

Authors: Lin, Jiaoqing | Yu, Rui | Xu, Xinrui

Article Type: Research Article

Abstract: The construction of real estate projects is a large and complex system project, and the completion of the construction goals on time and with quality is the key to the sustainable development of construction enterprises. In the process of real estate project construction, the management performance of building decoration material suppliers will directly affect the efficiency of real estate enterprises. How to correctly evaluate the building material suppliers (BMSs) of real estate enterprises and establish a good partnership affects the economic benefits of the enterprise and the possibility of subsequent cooperation between the two sides, which has become one of …the issues of importance to real estate enterprises. The selection and application of BMSs is the MAGDM. In this defined paper, the defined 2-tuple linguistic neutrosophic number (2TLNN) grey relational analysis (2TLNN-GRA) decision method is generated based on GRA and 2-tuple linguistic neutrosophic sets (2TLNSs). The 2TLNN-GRA method is generated for MAGDM. Finally, the decision example for BMSs selection is generated and some comparisons is generated. Show more

Keywords: Multiple attribute group decision making (MAGDM), 2TLNSs, GRA method, building material suppliers (BMSs)

DOI: 10.3233/JIFS-221410

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4185-4196, 2023

Authors: Du, Weidong

Article Type: Research Article

Abstract: Nowadays, the model compression method of knowledge distillation has drawn great attentions in Recommender systems (RS). The strategy of bidirectional distillation performs the bidirectional learning for both the teacher and the student models such that these two models can collaboratively improve with each other. However, this strategy cannot effectively exploit representation capabilities of each item and lack of the interpretability for the importance of items. Thus, how to develop an effective sampling scheme is still valuable for us to further study and explore. In this paper, we propose an improved rank discrepancy-aware item sampling strategy to enhance the performance of …bidirectional distillation learning. Specifically, by employing the distillation loss, we train the teacher and student models to reflect the fact that a user has partiality for the unobserved items. Then, we propose the improved rank discrepancy-aware sampling strategy based on feedback learning mechanism to transfer just the useful information which can effectively enhance each other. The key part of the multiple distillation training aims to select valuable items which can be re-distilled in the network for training. The proposed technique can effectively solve the problem of high ambiguity in nature for recommender system. Experimental results on several real-world recommender system datasets well demonstrate that the improved bidirectional distillation strategy shows better performance. Show more

Keywords: Bidirectional distillation, student-teacher learning, rank discrepancy aware items selection, recommender system

DOI: 10.3233/JIFS-222063

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4197-4206, 2023

Authors: Li, Qiyu | Langari, Reza

Article Type: Research Article

Abstract: Human-computer interaction(HCI) has broad range of applications. One particular application domain is rehabilitation devices. Several bioelectric signals can potentially be used in HCI systems in general and rehabilitation devices in particular. Surface ElectroMyoGraphic(sEMG) signal is one of the more important bioelectric signals in this context. The sEMG signal is formed by muscle activation although the details are rather complex. Applications of sEMG are referred is commonly referred to as myoelectric control since the dominant use of this signal is to activate a device even if (as the term control may imply) feedback is not always used in the process. With …the development of deep neural networks, various deep learning architectures are used for sEMG-based gesture recognition with many researchers having reported good performance. Nevertheless, challenges remain in accurately recognizing sEMG patterns generated by gestures produced by hand or the upper arm. For instance one of the difficulties in hand gesture recognition is the influence of limb positions. Several papers have shown that the accuracy of gesture classification decreases when the limb position changes even if the gesture remains the same. Prior work by our team has shown that dynamic gesture recognition is in principle more reliable in detecting human intent, which is often the underlying idea of gesture recognition. In this paper, a Convolutional Neural Network (CNN) with Long Short-Term Memory or LSTM (CNN-LSTM) is proposed to classify five common dynamic gestures. Each dynamic gesture would be performed in five different limb positions as well. The trained neural network model is then used to enable a human subject to control a 6 DoF (Degree of Freedom) robotic arm with 1 DoF gripper. The results show a high level of accurate performance achieved with the proposed approach. In particular, the overall accuracy of the dynamic gesture recognition is 84.2%. The accuracies vary across subjects but remain at approximately 90%for some subjects. Show more

Keywords: Human-computer interaction, sEMG signal, neural network, gesture recognition

DOI: 10.3233/JIFS-222985

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4207-4221, 2023

Authors: Wang, Jing

Article Type: Research Article

Abstract: The clothing images on the Internet is growing rapidly, and there is an increasing demand for the clothing images’ intelligent classification. In this paper, Region-Based Fully Convolutional Networks (R-FCN) is introduced into the clothing image recognition. In the clothing image classification, because the network training time is long and the recognition rate of deformed clothing images is low, an improved framework HSR-FCN is proposed. The regional suggestion network and HyperNet network in R-FCN are integrated in the new framework, the learning approach of image features is changed in HSR-FCN, the higher accuracy can be achieved in a shorter training time. …A spatial transformation network is introduced into the model, the input clothing image and feature map are spatially transformed and aligned, the feature learning is strengthened for multi-angle clothing and deformed clothing. The experimental results show that the improved HSR-FCN model is used to strengthen effectively the learning of deformed clothing images, and with a shorter training time, the average accuracy rate of the original network model R-FCN is increased by about 3%, it reachs 96.69%. Show more

Keywords: Garment images, deep learning, image classification, region-based fully convolutional networks (R-FCN), HyperNet, region proposal networks, spatial transformation networks

DOI: 10.3233/JIFS-220109

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4223-4232, 2023

Authors: Song, Tao

Article Type: Research Article

Abstract: The quality of physical education (PE) teaching in colleges and universities is the basis for the development of PE disciplines in colleges and universities, so currently thinking about how to effectively improve the quality of PE teaching in colleges and universities has become the first and foremost problem for many college and university PE departments to solve. In order to solve this problem, it is necessary to build a reasonable and scientific evaluation and monitoring system of PE teaching quality, because only by establishing an effective evaluation and monitoring system of teaching quality can we evaluate and supervise all the …PE operation properly and scientifically, and then give feedback in the process of evaluation and supervision, such evaluation and monitoring system can greatly promote the continuous improvement of PE teaching quality in colleges and universities. This is also one of the most effective means to improve the quality of PE and achieve the goal of PE in colleges and universities. The PE teaching quality evaluation in Colleges and Universities is frequently viewed as the multiple attribute group decision making (MAGDM) issue. In this paper, the 2-tuple linguistic neutrosophic number grey relational analysis (2TLNN-GRA) method is built based on the traditional grey relational analysis (GRA) and 2-tuple linguistic neutrosophic sets (2TLNNSs). Then, a numerical example for PE teaching quality evaluation in Colleges and Universities has been given and some comparisons is used to illustrate advantages of 2TLNN-GRA method. Show more

Keywords: Multiple attribute group decision making (MAGDM) problems, 2-tuple linguistic neutrosophic sets (2TLNSs), GRA method, teaching quality evaluation

DOI: 10.3233/JIFS-221857

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4233-4244, 2023

Authors: Reji, M. | Joseph, Christeena | Nancy, P. | Lourdes Mary, A.

Article Type: Research Article

Abstract: Intrusion detection systems (IDS) can be used to detect irregularities in network traffic to improve network security and protect data and systems. From 2.4 times in 2018 to three times in 2023, the number of devices linked to IP networks is predicted to outnumber the total population of the world. In 2020, approximately 1.5 billion cyber-attacks on Internet of Things (IoT) devices have been reported. Classification of these attacks in the IoT network is the major objective of this research. This research proposes a hybrid machine learning model using Seagull Optimization Algorithm (SOA) and Extreme Learning Machine (ELM) classifier to …classify and detect attacks in IoT networks. The CIC-IDS-2018 dataset is used in this work to evaluate the proposed model. The SOA is implemented for feature selection from the dataset, and the ELM is used to classify attacks from the selected features. The dataset has 80 features, in the proposed model used only 22 features with higher scores than the original dataset. The dataset is divided into 80% for training and 20% for testing. The proposed SOA-ELM model obtained 94.22% accuracy, 92.95% precision, 93.45% detection rate, and 91.26% f1-score. Show more

Keywords: Intrusion detection, IoT, SOA, ELM, feature selection, attack classification, machine learning

DOI: 10.3233/JIFS-222427

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 3, pp. 4245-4255, 2023