Journal of Intelligent & Fuzzy Systems - Volume 44, issue 2

Authors: Yao, Linjie | Zhang, Guidong | Sheng, Yuhong

Article Type: Research Article

Abstract: Multi-dimensional uncertain differential equations (MUDEs) are often used to describe complex systems that vary with time. In this paper, the generalized moment estimation method is employed to estimate the MUDEs’ unknown parameters. A method to optimize parameters with multiple estimation results is proposed. The hypothesis test and α-path are proposed to verify the feasibility of the parameter results. Several examples of parameter estimation for MUDEs are given, as well as two numerical examples to verify the feasibility of the method.

Keywords: Uncertainty theory, multi-dimensional uncertain differential equation, generalized moment estimation, parameter estimation

DOI: 10.3233/JIFS-213503

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2427-2439, 2023

Authors: Sathish, S. | Kavitha, K. | Poongodi, J.

Article Type: Research Article

Abstract: The industrial world including the merits of Internet of Things (IoT) paradigm has wide opened the evolution of new digital technology to facilitate promising and revolutionizing dimensions in diversified industrial application. However, handling the deployment challenges of security awareness, energy consumption, resource optimization, service assurance and real-time big data analytics in Industrial IoT Networks is a herculean task. In this paper, Dantzig Wolfe Decomposition Algorithm-based Service Assurance and Parallel Optimization Algorithm (DWDA-SAPOA) is proposed for guaranteeing QoS in energy efficient Software-Defined Industrial IoT Networks. This DWDA-SAPOA is proposed for achieving minimized energy consumption on par with the competitive network routing …algorithms which fails in satisfying the strict requirements of heterogeneous Quality of Service (QoS) during the process of optimizing resources under industrial communications. It is proposed as a service assurance and centralized route optimization strategy using the programmability and flexibility characteristics facilitating by the significant Software Defined Networking (SDN) paradigm which is implemented over a multi-layer programmable industrial architecture. It supports bandwidth-sensitive service and ultra-reliable low-latency communication type of heterogeneous flows that represents a routing optimization problem which could be potentially modelled as a multi-constrained shortest path problem. It further adopts Dantzig Wolfe Decomposition Algorithm (DWDA) to handle the complexity of NP-hard involved in solving the multi-constrained shortest path problems. The simulation experiments of the proposed DWDA-SAPOA prove its predominance in minimizing energy consumption by 24.28%, flow violation by 19.21%, packet loss by 21.28%, and end-to-end delay by 29.82%, and bandwidth utilization by up to 26.22% on par with the benchmarked QoS provisioning and energy-aware routing problem. Show more

Keywords: Software defined networking, Dantzig Wolfe Decomposition algorithm, industrial internet of things networks, multi-constrained shortest path problem, centralized route optimization

DOI: 10.3233/JIFS-221776

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2441-2454, 2023

Authors: Akalya devi, C. | Karthika Renuka, D. | Pooventhiran, G. | Harish, D. | Yadav, Shweta | Thirunarayan, Krishnaprasad

Article Type: Research Article

Abstract: Emotional AI is the next era of AI to play a major role in various fields such as entertainment, health care, self-paced online education, etc., considering clues from multiple sources. In this work, we propose a multimodal emotion recognition system extracting information from speech, motion capture, and text data. The main aim of this research is to improve the unimodal architectures to outperform the state-of-the-arts and combine them together to build a robust multi-modal fusion architecture. We developed 1D and 2D CNN-LSTM time-distributed models for speech, a hybrid CNN-LSTM model for motion capture data, and a BERT-based model for text …data to achieve state-of-the-art results, and attempted both concatenation-based decision-level fusion and Deep CCA-based feature-level fusion schemes. The proposed speech and mocap models achieve emotion recognition accuracies of 65.08% and 67.51%, respectively, and the BERT-based text model achieves an accuracy of 72.60%. The decision-level fusion approach significantly improves the accuracy of detecting emotions on the IEMOCAP and MELD datasets. This approach achieves 80.20% accuracy on IEMOCAP which is 8.61% higher than the state-of-the-art methods, and 63.52% and 61.65% in 5-class and 7-class classification on the MELD dataset which are higher than the state-of-the-arts. Show more

Keywords: Emotion recognition, time-distributed models, CNN-LSTM, BERT, DCCA

DOI: 10.3233/JIFS-220280

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2455-2470, 2023

Authors: Han, Meng | Li, Ang | Gao, Zhihui | Mu, Dongliang | Liu, Shujuan

Article Type: Research Article

Abstract: In reality, the data generated in many fields are often imbalanced, such as fraud detection, network intrusion detection and disease diagnosis. The class with fewer instances in the data is called the minority class, and the minority class in some applications contains the significant information. So far, many classification methods and strategies for binary imbalanced data have been proposed, but there are still many problems and challenges in multi-class imbalanced data that need to be solved urgently. The classification methods for multi-class imbalanced data are analyzed and summarized in terms of data preprocessing methods and algorithm-level classification methods, and the …performance of the algorithms using the same dataset is compared separately. In the data preprocessing methods, the methods of oversampling, under-sampling, hybrid sampling and feature selection are mainly introduced. Algorithm-level classification methods are comprehensively introduced in four aspects: ensemble learning, neural network, support vector machine and multi-class decomposition technique. At the same time, all data preprocessing methods and algorithm-level classification methods are analyzed in detail in terms of the techniques used, comparison algorithms, pros and cons, respectively. Moreover, the evaluation metrics commonly used for multi-class imbalanced data classification methods are described comprehensively. Finally, the future directions of multi-class imbalanced data classification are given. Show more

Keywords: Classification, multi-class imbalance data, data preprocessing method, algorithm-level classification method

DOI: 10.3233/JIFS-221902

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2471-2501, 2023

Authors: Xiao, Yanjun | Zhao, Churui | Qi, Hao | Liu, Weiling | Meng, Zhaozong | Peng, Kai

Article Type: Research Article

Abstract: In the control system of a lithium battery rolling mill, the correction system was crucial. This was because the correction system had a significant impact on the performance of the lithium battery rolling mill, including high precision and efficient rolling quality. However, the non-linearity of the correction system and the uncertainty of the correction system made it a challenging problem to achieve a high precision correction control. The contribution and innovation of this paper was a genetic fuzzy PID control strategy based on Kalman filter, which was proposed and applied to the control of lithium battery rolling mill correction technology. …In order to achieve intelligent control of a high-precision electrode rolling mill correction system, an algorithm fusion control scheme was proposed. Firstly, a novel and detailed correction system model was presented. Next, the initial PID parameters of the correction were optimized by means of a genetic algorithm so that the PID parameters could be adapted to the correction control process and then optimized again by adding an extended Kalman filter. Finally, the lithium battery rolling mill correction control system was validated, tested and commissioned in the field. The results showed that the designed algorithm could meet the working requirements of the lithium battery rolling mill and that it improved the accuracy of the correction system. In the actual lithium battery rolling mill production process, the algorithm was compared with a conventional PID. Compared with the common single algorithm, the fusion algorithm proposed in this paper was a complete set of high precision correction control system algorithm to solve the high precision problem faced by the correction system in the actual lithium battery rolling mill correction system. Show more

Keywords: Pole piece rolling mill, deviation correction system, fuzzy PID, genetic algorithm, algorithm fusion, extended kalman filter

DOI: 10.3233/JIFS-221028

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2503-2523, 2023

Authors: Vo, Tham

Article Type: Research Article

Abstract: The wind power is considered as a potential renewable energy resource which requires less management cost and effort than the others like as tidal, geothermal, etc. However, the natural randomization and volatility aspects of wind in different regions have brought several challenges for efficiently as well as reliably operating the wind-based power supply grid. Thus, it is necessary to have centralized monitoring centers for managing as well as optimizing the performance of wind power farms. Among different management task, wind speed prediction is considered as an important task which directly support for further wind-based power supply resource planning/optimization, hence towards …power shortage risk and operating cost reductions. Normally, considering as traditional time-series based prediction problem, most of previous deep learning-based models have demonstrated significant improvement in accuracy performance of wind speed prediction problem. However, most of recurrent neural network (RNN) as well as sequential auto-encoding (AE) based architectures still suffered several limitations related to the capability of sufficient preserving the spatiotemporal and long-range time dependent information of complex time-series based wind datasets. Moreover, previous RNN-based wind speed predictive models also perform poor prediction results within high-complex/noised time-series based wind speed datasets. Thus, in order to overcome these limitations, in this paper we proposed a novel integrated convolutional neural network (CNN)-based spatiotemporal randomization mechanism with transformer-based architecture for wind speed prediction problem, called as: RTrans-WP. Within our RTrans-WP model, we integrated the deep neural encoding component with a randomized CNN learning mechanism to softy align temporal feature within the long-range time-dependent learning context. The utilization of randomized CNN component at the data encoding part also enables to reduce noises and time-series based observation uncertainties which are occurred during the data representation learning and wind speed prediction-driven fine-tuning processes. Show more

Keywords: Wind speed prediction, deep learning, transformer, randomization, nomenclatures

DOI: 10.3233/JIFS-222446

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2525-2541, 2023

Authors: Yu, Wenmei | Xia, Lina | Cao, Qiang

Article Type: Research Article

Abstract: With the development of big data, Internet finance, the digital economy is developing rapidly and has become an important force to drive the continuous transformation of the global economy and society. China has put forward plans for the development of digital economy from 2021 to 2025, requiring the number of core industries of digital economy to reach 10% of GDP by 2025, while continuously improving China’s digital economy to achieve high-quality development of China’s digital economy. Aiming at China’s digital economy, we use the adaptive lasso method and select feature variables based on quantitative and qualitative perspectives, so as to …predict the development trend of China’s digital economy from 2021 to 2025 based on the TDGM (1, 1, r) grey model optimized by the particle swarm algorithm. Meanwhile, we have added the comparative analyses with TDGM(1,1), Grey Verhulst, GM(1,1) models and evaluate the prediction results both Ex-ante and Ex-post, demonstrating the feasibility of the proposed model and the accuracy. Finally, we find that the future of China’s digital economy will meet the planned objectives in terms of quantity and quality, but the trend of digital economy development in quantity is faster, thanks to the development of digital technology application industry. Show more

Keywords: Digital economy development, adaptive lasso grey model, TDGM(1, 1, r) model, quantity and quality

DOI: 10.3233/JIFS-222520

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2543-2560, 2023

Authors: Muthumanickam, Arunkumar | Balasubramanian, Gomathy | Chakrapani, Venkatesh

Article Type: Research Article

Abstract: The field of self-driving cars is one that is rapidly growing in popularity. The goal of autonomous vehicles has always been to avoid accidents. It has long been argued that human errors while driving are the primary cause of traffic accidents, and autonomous cars have the potential to remove this. An intelligent transportation system based on the Internet of Things (IoT) is required at some point for the vehicle to make an instant choice to evade accidents, regardless of the competence of a decent driver Mishaps on the road and in the weather are those that occur due to unfavourable …weather circumstances such as fog, gusts, snow, rain, slick pavement, sleet, etc. There are many factors that might cause a vehicle to lose control, including speed, weight, momentum, poor fleet maintenance. It has the potential to lessen the number of collisions caused by poor weather and deteriorating road circumstances. An IoT-based intelligent accident escaping system for poor weather and traffic circumstances is presented here. A variety of sensors are used to check the health of the vehicle. Data from sensors is processed by a microcontroller and displayed on the dashboard of a car after it has been received. The proposed model combines both an IoT system that monitors weather and road conditions and an intelligent system based on deep learning that learns the adverse variables that impact an accident in order to anticipate and prescribe a harmless speed to the driver. The experimental results show that the proposed deep learning technique achieved 94% of accuracy, where the existing LeNet model achieved 80% of accuracy for the prediction process. The proposed ResNet is more effective than LeNet, because identity mapping is used to solve the vanishing gradient problems. Show more

Keywords: Accidents-free driving, autonomous vehicles, deep learning, fleet management, internet of things, microcontroller, sensors

DOI: 10.3233/JIFS-222719

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2561-2576, 2023

Authors: Little Flower, X. | Poonguzhali, S.

Article Type: Research Article

Abstract: For real-time applications, the performance in classifying the movements should be as high as possible, and the computational complexity should be low. This paper focuses on the classification of five upper arm movements which can be provided as a control for human-machine interface (HMI) based applications. The conventional machine learning algorithms are used for classification with both time and frequency domain features, and k-nearest neighbor (KNN) outplay others. To further improve the classification accuracy, pretrained CNN architectures are employed which leads to computational complexity and memory requirements. To overcome this, the deep convolutional neural network (CNN) model is introduced with …three convolutional layers. To further improve the performance which is the key idea behind real-time applications, a hybrid CNN-KNN model is proposed. Even though the performance is high, the computation costs of the hybrid method are more. Minimum redundancy maximum relevance (mRMR), a feature selection method makes an effort to reduce feature dimensions. As a result, better performance is achieved by our proposed method CNN-KNN with mRMR which reduces computational complexity and memory requirement with a mean prediction accuracy of about 99.05±0.25% with 100 features. Show more

Keywords: Empirical mode decomposition, minimum redundancy maximum relevance, spectrogram representation, k-nearest neighbor, deep learning

DOI: 10.3233/JIFS-220811

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2577-2591, 2023

Authors: Annapandi, P. | Ramya, R. | Kotaiah, N.C. | Rajesh, P. | Subramanian, Arun

Article Type: Research Article

Abstract: This manuscript proposes an efficient hybrid strategy to obtain the optimal solution of operational cost reduction, size reduction of hybrid renewable energy sources and optimal power flow control for off-grid system. Here, off-grid is incorporated with photovoltaic array, wind turbine, Diesel generator, and battery energy storage system. The hybrid method is joint execution of Giza Pyramids Construction (GPC) and Billiards-inspired optimization algorithm (BOA) hence it is named GPC-BOA technique. The major purpose of proposed method is minimizing the operational cost as well as size of hybrid renewable energy sources and improves the power flow of system. In this energy management …system of off-grid provides cost reduction which includes the generation, replacement, operating and maintenance, cost of fuel consumption, cost of exchanged power with grid, and the penalty for emissions. Here, the GPC method is employed for forecasting the load requirement of system. The BOA technique optimizes the off-grid system through the deliberation of forecasted load requirement. At last, the proposed approach is performed on MATLAB platform and the performance is assessed using existing techniques. Show more

Keywords: Energy management system, cost, power flow, photovoltaic array, wind turbine, Diesel generator, battery energy storage system

DOI: 10.3233/JIFS-221176

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2593-2614, 2023

Authors: Cisneros, Luis | Rivera, Gilberto | Florencia, Rogelio | Sánchez-Solís, J. Patricia

Article Type: Research Article

Abstract: Business analytics refers to the application of sophisticated tools to obtain valuable information from a large dataset that is generated by a company. Among these tools, fuzzy optimisation stands out because it helps decision-makers to solve optimisation problems considering the uncertainty that commonly occurs in application domains. This paper presents a bibliometric analysis following the PRISMA statement on the Dimensions database to obtain publications related to fuzzy optimisation applied to business domains. The purpose of this analysis is to gather useful information that can help researchers in this area. A total of 2,983 publications were analysed using VOSviewer to identify …the trend in the number of publications per year, relationships in terms in both the title and abstract of these publications, most influential publications, and relationships among journals, authors, and institutions. Show more

Keywords: PRISMA statement, VOSviewer, bibliometric insights, scientific landscape, fuzzy optimisation, prescriptive analytics

DOI: 10.3233/JIFS-221573

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2615-2630, 2023

Authors: Duman, Ekrem

Article Type: Research Article

Abstract: The use of the social media (SM) has become more and more widespread during the last two decades, the companies started looking for insights for how they can improve their businesses using the information accumulating therein. In this regard, it is possible to distinguish between two lines of research: those based on anonymous data and those based on customer specific data. Although obtaining customer specific SM data is a challenging task, analysis of such individual data can result in very useful insights. In this study we take up this path for the customers of a bank, analyze their tweets and …develop three kinds of analytical models: clustering, sentiment analysis and product propensity. For the latter one, we also develop a version where, besides the text information, the structural information available in the bank databases are also used in the models. The result of the study is a considerably more efficient set of analytical CRM models. Show more

Keywords: Social media, banking, CRM, NLP, sentiment analysis

DOI: 10.3233/JIFS-221619

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2631-2642, 2023

Authors: Han, Yongguang | Zhang, Shanshan | Deng, Dexue

Article Type: Research Article

Abstract: Aiming at the multi-attribute group decision-making (MAGDM) problem with unclear index weights values, and thinking about the bounded rational behavior of decision makers (DMs), we proposed a new improved CPT-VIKOR decision method under intuitionistic fuzzy (IF-CPT-VIKOR). Due to the emergence of special cases in IFSs, a new IFS score function and distance formula are defined. Meanwhile, the use of entropy weight method to obtain the weight information of indicators enhances the objectivity of the model. Furthermore, CPT is integrated into the IFS environment, which fully reflects the psychological behavior of DMs, and take advantage of the VIKOR method to determine …the final sorting of the scheme. Finally, through the application cases of the commercial concrete supplier selection (CCSS) and the comparison with the existing authoritative methods to verify the feasibility and validity of the method. Show more

Keywords: Multiple attribute group decision making (MAGDM), cumulative prospect theory (CPT), VIKOR method, intuitionistic fuzzy sets (IFSs), Commercial concrete supplier selection (CCSS)

DOI: 10.3233/JIFS-221780

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2643-2654, 2023

Authors: Peng, Jinghong | Zhou, Jun | Liang, Guangchuan | Qin, Can | Peng, Cao | Chen, YuLin | Hu, Chengqiang

Article Type: Research Article

Abstract: Gas gathering pipeline network system is an important process facility for gas field production, which is responsible for collecting, transporting and purifying natural gas produced by wells. In this paper, an optimization model for the layout of star-tree gas gathering pipeline network in discrete space is established to find the most economical design scheme. The decision variables include valve set position, station position and pipeline connection relation. A series of equality and inequality constraints are developed, including node flow balance constraints, pipeline hydraulic constraints and pipeline structure constraints. A global optimization strategy is proposed and an improved genetic algorithm is …used to solve the model. To verify the validity of the proposed method, the optimization model is applied to a coalbed methane field gathering pipeline network in China. The results show that the global optimization scheme saves 1489.74×104 RMB (26.36%) in investment cost compared with the original scheme. In addition, the comparison between the global and hierarchical optimization scheme shows that the investment cost of the global optimization scheme is 567.22×104 RMB less than that of the hierarchical optimization scheme, which further proves the superiority of the global optimization method. Finally, the study of this paper can provide theoretical guidance for the design and planning of gas field gathering pipeline network. Show more

Keywords: Natural gas, pipeline network, layout design, global optimization, genetic algorithm

DOI: 10.3233/JIFS-222199

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2655-2672, 2023

Authors: Zhang, Qi | Su, Qian | Liu, Baosen | Pei, Yanfei | Zhang, Zongyu | Chen, De

Article Type: Research Article

Abstract: Effectively evaluating high-embankment deformation and stability is important for heavy-haul railway safety. An improved extension model with an attribute reduction algorithm was proposed for the comprehensive evaluation method. First, a hierarchical evaluation system for high embankments in heavy-haul railways was established using the attribute reduction algorithm, which includes the principal component analysis, maximum information coefficient, coefficient of variation, and improved Dempster-Shafer evidence theory. Furthermore, the improved extension model was used to evaluate high-embankment performance in heavy-haul railways. In this improved extension model, the combination weighting method, an asymmetric proximity function, and the maximum membership principle effectiveness verification were used. Finally, …three high embankments in a Chinese heavy-haul railway were studied. The results illustrate that the main influencing factors for high-embankment performance in a heavy-haul railway are annual rainfall, annual temperature, and 21 other indicators. The performance of the three embankments is level III (ordinary), level II (fine), and level III (ordinary), respectively, indicating that these embankments have generally unfavourable performance. The three embankments’ performance matches field measurements, and the proposed method outperforms the Fuzzy-AHP method, cloud model, and gray relational analysis. This study demonstrates the feasibility of the proposed method in assessing the high-embankment performance under heavy axle loads. Show more

Keywords: Heavy-haul railway, high embankment, comprehensive evaluation, improved extension model, attribute reduction

DOI: 10.3233/JIFS-222562

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2673-2692, 2023

Authors: Cetinkaya, Suleyman | Demir, Ali

Article Type: Research Article

Abstract: The purpose of this research is to establish the solution to the time-fractional initial value problem (TFIVP) in Caputo- Fabrizio sense by implementing a new integral transform called ARA transform together with the iterative method. The existence of the ARA transform is investigated. Moreover, it is shown that the ARA integral transform of order n of a continuous function well defined. First, TFIVP is reduced into a simpler problem by utilizing the ARA transform. Secondly, the truncated solution of the reduced problem is obtained through the iterative method. Finally, the application of inverse ARA transform allows us to construct …a truncated solution of TFIVP. The novelty of this study is that the first time the ARA transform is applied to obtain the solution of TFIVP in the Caputo-Fabrizio sense. Illustrative examples with the Fokker-Planck equation present that this method works better than other methods which is one of the strong points of this research. Show more

Keywords: Caputo-Fabrizio derivative, ARA transform, iterative method, time fractional initial value problem, Fokker-Planck equation

DOI: 10.3233/JIFS-223237

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2693-2701, 2023

Authors: Dai, Qinglong | Qin, Guangjun | Li, Jianwu | Zhao, Jun | Cai, Jifan

Article Type: Research Article

Abstract: Flink is regarded as a promising distributed data processing engine for unifying bounded data and unbounded data. Unbalanced workloads upon multiple workers/task managers/servers in the Flink bring congestion, which will lead to the quality of service (QoS) decreasing. The balanced load distribution could efficiently improve QoS. Besides, existing works are lagging behind the current Flink version. To distribute workloads upon workers evenly, a resource-oriented load balancing task scheduling (RoLBTS) mechanism for Flink is proposed. The capacities of CPU, memory, and bandwidth are taken into consideration. Based on the barrel principle, the memory, and the bandwidth are respectively selected to model …the resource occupancy ratio of the physical node and that of the physical link. On the based of modeled resource occupancy ratio, the data processing of load-balancing resource usage in Flink is formulated as a quadratic programming problem. Based on the self-recursive calling, a RoLBTS algorithm for scheduling task-needed resources is presented. Trough the numerical simulation, the superiority of our work is evaluated in terms of resource score, the number of possible scheduling solutions, and resource usage ratio. Show more

Keywords: Unbounded data, bounded data, integrated stream processing, Flink, load balancing

DOI: 10.3233/JIFS-222524

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2703-2713, 2023

Authors: Lina, Ma | Hao, Ma | Yang, Zhang | Iqbal, Najaf

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-213565

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2715-2727, 2023

Authors: Qiu, Yutan | Zhou, Qing

Article Type: Research Article

Abstract: Role-oriented network embedding aims to preserve the structural similarity of nodes so that nodes with the same role stay close to each other in the embedding space. Role-oriented network embeddings have wide applications such as electronic business and scientific discovery. Anonymous walk (AW) has a powerful ability to capture structural information of nodes, but at present, there are few role-oriented network embedding methods based on AW. Our main contribution is the proposal of a new framework named REAW, which can generate the role-oriented embeddings of nodes based on anonymous walks. We first partition a number of anonymous walks starting from …a node into the representative set and the non-representative set. Then, we leverage contrastive learning techniques to learn AW embeddings. We integrate the learned AW embeddings with AW’s empirical distribution to obtain the structural feature of the node, and finally we generate the node’s embedding through message passing operations. Extensive experiments on real network datasets demonstrate the effectiveness of our framework in capturing the role of nodes. Show more

Keywords: Network embedding, network structure, role-oriented, anonymous walk

DOI: 10.3233/JIFS-222712

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2729-2739, 2023

Authors: Song, Xudong | Wan, Xiaohui | Yi, Weiguo | Cui, Yunxian | Li, Changxian

Article Type: Research Article

Abstract: In recent years, the lack of thermal images and the difficulty of thermal feature extraction have led to low accuracy and efficiency in the fault diagnosis of circuit boards using thermal images. To address the problem, this paper presents a simple and efficient intelligent fault diagnosis method combined with computer vision, namely the bag-of-SURF-features support vector machine (BOSF-SVM). Firstly, an improved BOF feature extraction based on SURF is proposed. The preliminary fault features of the abnormally hot components are extracted by the speeded-up robust features algorithm (SURF). In order to extract the ultimate fault features, the preliminary fault features are …clustered into K clusters by K-means and substituted into the bag-of-features model (BOF) to generate a bag-of-SURF-feature vector (BOSF) for each image. Then, all of the BOSF vectors are fed into SVM to train the fault classification model. Finally, extensive experiments are conducted on two homemade thermal image datasets of circuit board faults. Experimental results show that the proposed method is effective in extracting the thermal fault features of components and reducing misdiagnosis and underdiagnosis. Also, it is economical and fast, facilitating savings in labour costs and computing resources in industrial production. Show more

Keywords: Thermal images, circuit boards, fault diagnosis, bag-of-features, support vector machine

DOI: 10.3233/JIFS-223093

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2741-2752, 2023

Authors: Rajalakshmi, R. | Sivakumar, P. | Prathiba, T. | Chatrapathy, K.

Article Type: Research Article

Abstract: In healthcare (HC), Internet of Things (IoT) integrated cloud computing provides various features and real-time applications. However, owing to the nature of IoT architecture, their types, various modes of communication and the density of data transformed in the network, security is currently a critical issue in the IoT healthcare (IoT-HC) field. This paper proposes a deep learning (DL) model, namely Adaptive Swish-based Deep Multi-Layer Perceptron (ASDMLP) that identifies the intrusions or attacks in the IoT healthcare (IoT-HC) platform. The proposed model starts by clustering the patients’ sensor devices in the network using the Probability-based Fuzzy C-Means (PFCM) model. After clustering …the devices, the cluster heads (CHs) among the cluster members are selected based on the energy, distance and degree of the sensor devices for aggregating the data sensed by the medical sensor devices. The base station (BS) sends the patient’s data collected by the CHs to the cloud server (CS). At the cloud end, the proposed model implements an IDS by applying training of the DL model in publicly available databases. The DL approach first performs preprocessing of the data and then selects optimal features from the dataset using the Opposition and Greedy Levy mutation-based Coyotes Optimization Algorithm (OGCOA). The ASDMLP trains these optimal features for the detection of HC data intrusions. The outcomes confirm that the proposed approach works well on real-time IoT datasets for intrusion detection (ID) without compromising the energy consumption (EC) and lifespan of the network. Show more

Keywords: Smart healthcare, Internet of Things (IoT), intrusion detection system, deep learning, healthcare security

DOI: 10.3233/JIFS-223166

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2753-2768, 2023

Authors: Lovelyn Rose, S. | Ravitha Rajalakshmi, N. | Sabari Nathan, M. | Suraj Subramanian, A. | Harishkumar, R.

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-220705

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2769-2778, 2023

Authors: Xu, Juan | Ma, Zhen Ming | Xu, Zeshui

Article Type: Research Article

Abstract: Heronian mean (HM) operators, which can capture the interrelationship between input arguments with the same importance, have been a hot research topic as a useful aggregation technique. In this paper, we propose the generalized normalized cross weighted HM operators on the unit interval which can not only capture the interrelationships between input arguments but also aggregate them with different weights, some desirable properties are derived. Then, generalized cross weighted HM operators are extended to real number set and applied to binary classification. We list the detailed steps of binary classification with the developed aggregation operators, and give a comparison of …the proposed method with the existing ones using the Iris dataset with 5-fold cross-validation (5-f cv), the accuracy of the proposed method for the training sets and the testing sets are both 100%. Show more

Keywords: Generalized cross weighted HM operator, cross weight vector, binary classification

DOI: 10.3233/JIFS-221152

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2779-2789, 2023

Authors: Osman, Mawia | Xia, Yonghui

Article Type: Research Article

Abstract: This paper proposes a method for solving fuzzy linear and nonlinear partial q -differential equations by the fuzzy q -differential transform. Further, we implemented the fuzzy fractional q -differential transform for solving some types of fuzzy fractional q -differential equations . The technique investigated is based on gH -differentiability, fuzzy q-derivative, and fuzzy q-fractional derivative. Various concrete problems have been tested by implementing the new method, and the results show great performance. The results also reveal that the method is a very effective and quite accurate mathematical tool for solving fuzzy fractional and integer q -differential equations. Finally, we …have provided some examples illustrating our method. Show more

Keywords: Fuzzy numbers, fuzzy-valued functions, fuzzy q-derivative; fuzzy q-fractional derivative, gH-differentiability, fuzzy q-differential transform method

DOI: 10.3233/JIFS-222567

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2791-2846, 2023

Authors: Wang, Biao | Wei, Hongquan | Li, Ran | Liu, Shuxin | Wang, Kai

Article Type: Research Article

Abstract: Spotting rumors from social media and intervening early has always been a daunting challenge. In recent years, Deep neural networks have begun to discover rumors by exploring the way of rumor propagation. The existing static graph models either only focus on the spatial structure information of rumor propagation or on time series propagation information but do not effectively combine them. This paper proposes the Static Spatiotemporal Model (SSM), which first extracts the textual semantic information and constructs undirected and directed propagation trees. Then obtains spatial structure information of rumor propagation through Graph Convolutional Network and extracts time series propagation information …through the Recurrent Neural Network. The extracted spatiotemporal information is enhanced using different source node information hopping. Finally, SSM uses a weighted connection ensemble to rumor classification. Experimentally validated on datasets such as Weibo and Twitter, the results show that the proposed method outperforms several state-of-the-art static graph models. To better apply SSM in early detection and characterize early concepts, this paper presents a new data collection index for early detection, which can detect events that spread faster and have more significant influence in a targeted manner. The experimental results on the new indicators further verify the superiority of SSM as it can extract sufficient information in early detection or events with fewer participants. Show more

Keywords: Rumor detection, deep learning, SSM, spatiotemporal information, early detection, data collection index

DOI: 10.3233/JIFS-220417

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2847-2862, 2023

Authors: Ramkumar, N. | Sadasivam, G. Sudha | Renuka, D. Karthika

Article Type: Research Article

Abstract: Multimodal analysis focuses on the internal and external manifestations of cancer cells to provide physicians, oncologists and surgeons with timely information on personalized diagnosis and treatment for patients. Decision fusion in multimodal analysis reduces manual intervention, and improves classification accuracy facilitating doctors to make quick decisions. Genetic characteristics extracted on biopsies do not, however, provide details on adjacent cells. Images can only provide external observable details of cancer cells. While mammograms can detect breast cancer, region wise details can be obtained from ultrasound images. Hence, different types of imaging techniques are used. Features are extracted using the SelectKbest method in …the Wisconsin Breast Cancer, Clinical and gene expression datasets. The features are extracted using Gray Level Co-occurrence Matrix from Histology, Mammogram and Sonogram images. For image datasets, the Convolution Neural Network (CNN) is used as a classifier. The combined features from clinical, gene expression and image datasets are used to train an Integrated Stacking Classifier. The integrated multimodal system’s effectiveness is shown by experimental findings. Show more

Keywords: Convolution neural networks, multimodal analysis, gray level co-occurrence matrix, histopathological, mammogram, sonogram and integrated stacking classifier

DOI: 10.3233/JIFS-220633

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2863-2880, 2023

Authors: Xie, Ying | Zhu, Yuan | Lu, Zhenjie

Article Type: Research Article

Abstract: In view of the large-scale and high-dimensional problems of industrial data and fault-tracing problems, a fault detection and diagnosis method based on multi-block probabilistic kernel partial least squares (MBPKPLS) is proposed. First, the process variables are divided into several blocks in a decentralized manner to address the large-scale and high-dimensional problems. The probabilistic characteristics and relationship between the corresponding process variables and the quality variables of each block are analyzed using latent variables, and the PKPLS model of each block is established separately. Second, the MBPKPLS model is applied to process monitoring, statistics of each block are established in a …high-dimensional space, and the monitoring indicators in each block are used to detect faults. Third, based on fault detection, the multi-block concept is further used to locate the cause of fault, thereby solving the problem of fault tracing. Finally, a numerical example and the penicillin fermentation process (PFP) are used to test the effectiveness of the MBPKPLS method. The results demonstrate that the proposed method is suitable for processing large-scale, high-dimensional data with strong nonlinear characteristics, and the MBPKPLS process monitoring method is effective for improving the performance of fault detection and diagnosis. Show more

Keywords: Large-scale industrial process, multi-block probabilistic kernel partial least squares, fault detection, fault diagnosis

DOI: 10.3233/JIFS-220605

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2881-2894, 2023

Authors: Ma, Yizhe | Yu, Long | Lin, Fangjian | Tian, Shengwei

Article Type: Research Article

Abstract:  In increasingly complex scenes, multi-scale information fusion becomes more and more critical for semantic image segmentation. Various methods are proposed to model multi-scale information, such as local to global, but this is not enough for the scene changes more and more, and the image resolution becomes larger and larger. Cross-Scale Sampling Transformer is proposed in this paper. We first propose that each scale feature is sparsely sampled at one time, and all other features are fused, which is different from all previous methods. Specifically, the Channel Information Augmentation module is first proposed to enhance query feature features, highlight part of …the response to sampling points and enhance image features. Next, the Multi-Scale Feature Enhancement module performs a one-time fusion of full-scale features, and each feature can obtain information about other scale features. In addition, the Cross-Scale Fusion module is used for cross-scale fusion of query feature and full-scale feature. Finally, the above three modules constitute our Cross-Scale Sampling Transformer(CSSFormer). We evaluate our CSSFormer on four challenging semantic segmentation benchmarks, including PASCAL Context, ADE20K, COCO-Stuff 10K, and Cityscapes, achieving 59.95%, 55.48%, 50.92%, and 84.72% mIoU, respectively, outperform the state-of-the-art. Show more

Keywords: Multi-scale fusion, Segmentation, Transformer

DOI: 10.3233/JIFS-220976

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2895-2907, 2023

Authors: Xu, Huili | Li, Bing

Article Type: Research Article

Abstract: In this paper, a class of Clifford-valued neutral fuzzy neural-type networks with proportional delay and D operator and whose self feedback coefficients are also Clifford numbers are considered. By using the Banach fixed point theorem and some differential inequality techniques, we directly study the existence and global asymptotic stability of pseudo almost periodic solutions by not decomposing the considered Clifford-valued systems into real-valued systems. Finally, two examples are given to illustrate our main results. Our results of this paper are new.

Keywords: Clifford-valued neural network, fuzzy neural network, proportional delay, D operator, pseudo almost periodic solution, global asymptotic stability.

DOI: 10.3233/JIFS-221017

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2909-2925, 2023

Authors: Deepa, S. | Sridhar, K.P. | Baskar, S. | Mythili, K.B. | Reethika, A. | Hariharan, P.R.

Article Type: Research Article

Abstract: A smart healthcare network can use sensors and the Internet of Things (IoT) to enhance patient care while decreasing healthcare expenditures. It has become more difficult for healthcare providers to keep track and analyze the massive amounts of data it generates. Health care data created by IoT devices and e-health systems must be handled more efficiently. A wide range of healthcare industries can benefit from machine learning (ML) algorithms in the digital world. However, each of these algorithms has to be taught to anticipate or solve a certain problem. IoT-enabled healthcare data and health monitoring-based machine learning algorithms (IoT-HDHM-MLA ) …have been proposed to solve the difficulties faced by healthcare providers. Sensors and IoT devices are vital for monitoring an individual’s health. The proposed IoT-HDHM-MLA aims to deliver healthcare services via remote monitoring with experts and machine learning algorithms. In this system, patients are monitored in real-time for various key characteristics using a collection of small wireless wearable nodes. The health care business benefits from systematic data collection and efficient data mining. Thus, the experimental findings demonstrate that IoT-HDHM-MLA enhances efficiency in patient health surveillance. Show more

Keywords: Health monitoring, machine learning algorithms, IoT, smart healthcare

DOI: 10.3233/JIFS-221274

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2927-2941, 2023

Authors: Abolpour, Kh. | Zahedi, M.M. | Shamsizadeh, M.

Article Type: Research Article

Abstract:  The current study aims to investigate the L-valued tree automata theory based on t-norm/t-conorm and it further examines their algebraic and L-valued topological properties. Specifically, the concept of L-valued operators with t-norm/t-conorm is introduced and the existing relationships between them are also studied. Interestingly, we associate L-valued co-topologies/topologies for a given L-valued tree automaton, using them to characterize some algebraic concepts. Further, we introduce the concepts of Alexandroff L-graded co-topologies and Alexandroff L-graded topologies which correspond to the L-valued operators with t-norm and L-valued operators with t-conorm/implicator, respectively. In addition, we aim to specify the relationship between the L-graded co-topologies/topologies, …showing that the introduced L-graded co-topologies/topologies have some interesting consequences under homomorphism. Show more

Keywords: L-valued tree automaton, operator, L-valued topology, homomorphism

DOI: 10.3233/JIFS-221960

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2943-2955, 2023

Authors: Chhabra, Megha | Sharan, Bhagwati | Kumar, Manoj

Article Type: Research Article

Abstract:  The users of mobile phone are exponentially increasing. The applications are developed every day in a variety of domains to enhance the Quality of User Experience (QoUE) along with utility determinants. The design of the mobile application impacts the QoUE. QoUE in mobile applications is a measure that describes the appropriateness of the purpose of the application and the need for user retention. However, the challenge is to identify, understand, focus and interconnect the variety of determinants influencing the QoUE based on mobile application design. These determinants are based on the diversity of users and the related functional needs, user-specific …needs, and background functioning of the application. The modelling and analysis help mobile application developers to improve, increase and retain user engagement on the app based on improved QoUE. To do so, a qualitative analytical method is employed in the following steps. The first ever Fuzzy Cognitive Map (FCM) is proposed to show the causal-effect links of the interdependent determinants in mobile applications based on QoUE. In our model, the existence of relationships between determinants relies on a thorough literature review. The weight of these links is estimated by users of different ages and lines of work. This is performed by an empirical study based on a questionnaire filled by experts. The questionnaire is based on the formal utility and perceived QoUE-based topics. Finally, scenario-based analysis on formed FCM based on these inputs is performed. We show that small changes in cases using different direct determinants can be used to enhance QoUE. These changes can be studied before launching an application for the user, thereby limiting the need to rework the improvements based on QoUE and providing useful guidance for the possible increase in user base and behaviour change. Show more

Keywords: User experience, fuzzy cognitive maps, modelling, quality experience, mobile applications

DOI: 10.3233/JIFS-222111

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2957-2979, 2023

Authors: Tian, Xiaoyan | Chen, Xinzhang | Feng, Linlin

Article Type: Research Article

Abstract: As the latest and hottest concept in the international arena, the metaverse concept has attracted the attention of various industries including information, economy, art, management, education and teaching for its application and technology integration research, but whether to define metaverse as a technology or a scenario has not yet reached a unified understanding in the academic and scientific communities. We believe that metaverse should be used as a key concept and emerging theory in building the future intelligent field. Therefore, we introduce the concept of metaverse in future film and animation teaching as a novel, strategic and disruptive teaching field …with great potential, and the constructed metaverse self-directed learning field will become an important part of school education resource optimization. In this study, we focus on the quality improvement path of film and animation teaching in the context of metaverse, and conduct a study on the assessment method of teaching quality after the introduction of metaverse concept. Specifically, we discuss the quality improvement measures in the future teaching of film and animation, construct a teaching field of film and animation based on the metaverse, and propose a related teaching quality assessment model and establish an index system for the quality assessment of film and animation teaching in the context of the metaverse. The index system is composed of 3 primary indicators, 9 secondary indicators and 27 tertiary indicators, and the quantitative calculation is carried out by the Analytic Hierarchy Process (AHP) in fuzzy mathematics, and the weighting results of the indicators are calculated. The research goal of combining quantitative analysis and qualitative research was achieved. What can be seen through our research is that the metaverse online classroom built with virtual reality and other technologies will have more advantages than the traditional teaching classroom. In the future, similar learning devices can be introduced in film and animation teaching, and diversified learning modules can be established. Not only can the learning efficiency of offline classroom be improved, but also more learning space can be opened for online classroom. This study bridges the gap in the theory of quality assessment of film and animation teaching after the introduction of the future metaverse concept, innovates the analysis of the new concept and the improvement of the old method, builds a new scenario of organic combination of new technology and traditional education teaching, and provides a new idea for international and domestic future education research. Show more

Keywords: Teaching quality assessment, teaching film and animation, metaverse, metaverse field architecture, fuzzy mathematical theory

DOI: 10.3233/JIFS-222779

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2981-2997, 2023

Authors: Gokiladevi, M. | Santhoshkumar, Sundar

Article Type: Research Article

Abstract: Early identification of chronic kidney disease (CKD) becomes essential to reduce the severity level and mortality rate. Since medical diagnoses are equipped with latest technologies such as machine learning (ML), data mining, and artificial intelligence, they can be employed to diagnose the disease and aid decision making process. Since the accuracy of the classification model greatly depends upon the number of features involved, the feature selection (FS) approaches are developed which results in improved accuracy. With this motivation, this study designs a novel chaotic binary black hole based feature selection with classification model for CKD diagnosis, named CBHFSC-CKD technique. The …proposed CBHFSC-CKD technique encompasses the design of chaotic black hole based feature selection (CBH-FS) to choose an optimal subset of features and thereby enhances the diagnostic performance. In addition, the bacterial colony algorithm (BCA) with kernel extreme learning machine (KELM) classifier is applied for the identification of CKD. Moreover, the design of BCA to optimally adjust the parameters involved in the KELM results in improved classification performance. A comprehensive set of simulation analyses is carried out and the results are inspected interms of different aspects. The simulation outcome pointed out the supremacy of the CBHFSC-CKD technique compared to other recent techniques interms of different measures. Show more

Keywords: Chronic kidney disease, data classification, feature selection, machine learning, metaheuristics, disease diagnosis

DOI: 10.3233/JIFS-220994

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 2999-3010, 2023

Authors: Öztunç, Simge | İhtiyar, Sultan

Article Type: Research Article

Abstract: In this paper the concept of soft continuity is focused on for digital images by using soft sets which is defined on κ - adjacent digital images. Also the definitions of digital soft isomorphism and digital soft retraction are given. Some theorems are obtained deal with soft isomorphism and soft retraction for digital images and some numerical examples are presented in dimension 2. Finally digital soft retraction is obtained as a soft topological invariant.

Keywords: Digital image, soft set, soft continuous function, soft retraction

DOI: 10.3233/JIFS-221213

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3011-3021, 2023

Authors: Zhao, Zhengwei | Yang, Genteng | Li, Zhaowen

Article Type: Research Article

Abstract: Outlier detection is a process to find out the objects that have the abnormal behavior. It can be applied in many aspects, such as public security, finance and medical care. An information system (IS) as a database that shows relationships between objects and attributes. A real-valued information system (RVIS) is an IS whose information values are real numbers. A RVIS with missing values is an incomplete real-valued information system (IRVIS). The notion of inner boundary comes from the boundary region in rough set theory (RST). This paper conducts experiments directly in an IRVIS and investigates outlier detection in an IRVIS …based on inner boundary. Firstly, the distance between two information values on each attribute of an IRVIS is introduced, and the parameter λ to control the distance is given. Then, the tolerance relations on the object set are defined according to the distance, by the way, the tolerance classes, the λ-lower and λ-upper approximations in an IRVIS are put forward. Next, the inner boundary under each conditional attribute in an IRVIS is presented. The more inner boundaries an object belongs to, the more likely it is to be an outlier. Finally, an outlier detection method in an IRVIS based on inner boundary is proposed, and the corresponding algorithm (DE) is designed, where DE means degree of exceptionality. Through the experiments base on UCI Machine Learning Repository data sets, the DE algorithm is compared with other five algorithms. Experimental results show that DE algorithm has the better outlier detection effect in an IRVIS. It is worth mentioning that for comprehensive comparison, ROC curve and AUC value are used to illustrate the advantages of the DE algorithm. Show more

Keywords: RST, IRVIS, Outlier detection, Inner boundary

DOI: 10.3233/JIFS-222777

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3023-3041, 2023

Authors: Azimifar, Maryam | Nejatian, Samad | Parvin, Hamid | Bagherifard, Karamollah | Rezaei, Vahideh

Article Type: Research Article

Abstract: We introduce a semi-supervised space adjustment framework in this paper. In the introduced framework, the dataset contains two subsets: (a) training data subset (space-one data (SOD )) and (b) testing data subset (space-two data (STD )). Our semi-supervised space adjustment framework learns under three assumptions: (I) it is assumed that all data points in the SOD are labeled, and only a minority of the data points in the STD are labeled (we call the labeled space-two data as LSTD ), (II) the size of LSTD is very small comparing to the size of SOD , and (III) …it is also assumed that the data of SOD and the data of STD have different distributions. We denote the unlabeled space-two data by ULSTD , which is equal to STD  - LSTD . The aim is to map the training data, i.e., the data from the training labeled data subset and those from LSTD (note that all labeled data are considered to be training data, i.e., SOD  ∪ LSTD ) into a shared space (ShS ). The mapped SOD , ULSTD , and LSTD into ShS are named MSOD , MULSTD , and MLSTD , respectively. The proposed method does the mentioned mapping in such a way that structures of the data points in SOD and MSOD , in STD and MSTD , in ULSTD and MULSTD , and in LSTD and MLSTD are the same. In the proposed method, the mapping is proposed to be done by a principal component analysis transformation on kernelized data. In the proposed method, it is tried to find a mapping that (a) can maintain the neighbors of data points after the mapping and (b) can take advantage of the class labels that are known in STD during transformation. After that, we represent and formulate the problem of finding the optimal mapping into a non-linear objective function. To solve it, we transform it into a semidefinite programming (SDP ) problem. We solve the optimization problem with an SDP solver. The examinations indicate the superiority of the learners trained in the data mapped by the proposed approach to the learners trained in the data mapped by the state of the art methods. Show more

Keywords: Semi-supervised domain adaptation, non-linear optimization, local-preserving domain adaptation, semidefinite programming, kernel learning, principal component analysis

DOI: 10.3233/JIFS-200224

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3043-3057, 2023

Authors: Dhamodharavadhani, S. | Rathipriya, R.

Article Type: Research Article

Abstract: This paper aims to develop the methodology for enhancing the regression models using Cluster based sampling techniques (CST) to achieve high predictive accuracy and can also be used to handle large datasets. Hard clustering (KMeans Clustering) or Soft clustering (Fuzzy C-Means) to generate samples called clusters, which in turn is used to generate the Local Regression Models (LRM) for the given dataset. These LRMs are used to create a Global Regression Model. This methodology is known as Enhanced Regression Model (ERM). The performance of the proposed approach is tested with 5 different datasets. The experimental results revealed that the proposed …methodology yielded better predictive accuracy than the non-hybrid MLR model; also, fuzzy C-Means performs better than the KMeans clustering algorithm for sample selection. Thus, ERM has potential to handle data with uncertainty and complex pattern and produced a high prediction accuracy rate. Show more

Keywords: Clustering, KMeans, fuzzy c-means, multiple linear regression, regression, sampling methods

DOI: 10.3233/JIFS-211736

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3059-3069, 2023

Authors: Lekha, A. | Parvathy, K.S.

Article Type: Research Article

Abstract:  Let G  = (V , μ , σ ) be a fuzzy graph on a finite set V . A fuzzy subset μ ′ of μ is called a fuzzy dominating set of G  if, μ ′ ( v ) + ∑ x ∈ V ( σ ( x , v ) ∧ μ ′ ( x ) ) ≥ μ ( v ) for every v ∈ V . Fuzzy domination number γ fz is defined accordingly. In this paper we …initiate a study of this parameter. Some properties of fuzzy dominating sets are studied and fuzzy domination number γ fz is determined for some graphs. Show more

Keywords: Fuzzy Graph, Fuzzy Dominating Sets, Fuzzy Domination Number

DOI: 10.3233/JIFS-220987

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3071-3077, 2023

Authors: Ayidzoe, Mighty Abra | Yu, Yongbin | Mensah, Patrick Kwabena | Cai, Jingye | Baagyere, Edward Yellakuor | Bawah, Faiza Umar

Article Type: Research Article

Abstract: Colorectal cancer is the third most diagnosed malignancy in the world. Polyps (either malignant or benign) are the primary cause of colorectal cancer. However, the diagnosis is susceptive to human error, less effective, and falls below recommended levels in routine clinical procedures. In this paper, a Capsule network enhanced with radon transforms for feature extraction is proposed to improve the feasibility of colorectal cancer recognition. The contribution of this paper lies in the incorporation of the radon transforms in the proposed model to improve the detection of polyps by performing efficient extraction of tomographic features. When trained and tested with …the polyp dataset, the proposed model achieved an overall average recognition accuracy of 94.02%, AUC of 97%, and an average precision of 96%. In addition, a posthoc analysis of the results exhibited superior feature extraction capabilities comparable to the state-of-the-art and can contribute to the field of explainable artificial intelligence. The proposed method has a considerable potential to be adopted in clinical trials to eliminate the problems associated with the human diagnosis of colorectal cancer. Show more

Keywords: Capsule network, colorectal polyp, convolutional neural network, explainable artificial intelligence

DOI: 10.3233/JIFS-212168

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3079-3091, 2023

Authors: Li, Zepeng | Huang, Rikui | Zhang, Yufeng | Zhu, Jianghong | Hu, Bin

Article Type: Research Article

Abstract:  Knowledge Graph Embedding (KGE), which aims to embed the entities and relations of a knowledge gxraph into a low-dimensional continuous space, has been proven to be an effective method for completing a knowledge graph and improving the quality of the knowledge graph. The translation-based models represented by TransE, TransH, TransR and TransD have achieved great success in this regard. There is still potential for improvement in dealing with complex relations. In this paper, we find that the lack of flexibility in entity embedding limits the model’s ability to model complex relations. Therefore, we propose single-directional-flexible (sdf) models and multi-directional-flexible (mdf) …models to increase the flexibility and expressiveness of entity embeddings. These two methods can be applied to the TransD model and its variant models without increasing any time cost and space cost. We conduct experiments on benchmarks such as WN18 and FB15k. The experimental results show that the models significantly surpasses the classical translation models in both tasks of triplet classification and link prediction. In particular, for Hits@1 of link prediction of WN18, we get 71.7% after applying our method to TransD, which is much better than 24.1% of TransD. Show more

Keywords: Knowledge graph embedding, translation model, complex relation, single-directional-flexible model, multi-directional-flexible model

DOI: 10.3233/JIFS-211553

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3093-3105, 2023

Authors: Wan, Chenxia | Fang, Liqun | Cao, Shaodong | Luo, Jiaji | Jiang, Yijing | Wei, Yuanxiao | Lv, Cancan | Si, Weijian

Article Type: Research Article

Abstract: The investigation on brain magnetic resonance imaging (MRI) of cerebral small vessel disease (CSVD) classification algorithm based on deep learning is particularly important in medical image analyses and has not been reported. This paper proposes an MRI classification algorithm based on convolutional neural network (MRINet), for accurately classifying CSVD and improving the classification performance. The working method includes five main stages: fabricating dataset, designing network model, configuring the training options, training model and testing performance. The actual training and testing datasets of MRI of CSVD are fabricated, the MRINet model is designed for extracting more detailedly features, a smooth categorical-cross-entropy …loss function and Adam optimization algorithm are adopted, and the appropriate training parameters are set. The network model is trained and tested in the fabricated datasets, and the classification performance of CSVD is fully investigated. Experimental results show that the loss and accuracy curves demonstrate the better classification performance in the training process. The confusion matrices confirm that the designed network model demonstrates the better classification results, especially for luminal infarction. The average classification accuracy of MRINet is up to 80.95% when classifying MRI of CSVD, which demonstrates the superior classification performance over others. This work provides a sound experimental foundation for further improving the classification accuracy and enhancing the actual application in medical image analyses. Show more

Keywords: Cerebral small vessel disease, brain magnetic resonance imaging, convolutional neural network, feature extraction, classification accuracy

DOI: 10.3233/JIFS-213212

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3107-3114, 2023

Authors: Zhang, Xinyu | Yu, Long | Tian, Shengwei

Article Type: Research Article

Abstract: In today’s social media and various frequently used lifestyle applications, the phenomenon that people express their sentiment via comments or instant barrage is common. People not only show their joys and sorrows in the process of expression but also present their opinions to one thing in many aspects which include. Nowadays, aspect-based sentiment analysis has become a mature and wildly-used technology. There are many public datasets considered as a benchmark to test model performance, such as Laptop2014, Restaurant2014, Twitter, etc. In our work, we also use these public datasets as the test criteria. Current mainstream models generally use the methods …of stacking multi-RNNs layers or combining neural networks and BERT or other pre-trained models. On account of the importance displayed by the dependence between aspect words and sentiment words, we investigate a novel model (BGAT) blending bidirectional gated recurrent unit (BiGRU) and relational graph attention network (RGAT) to learn dependencies information. Extensive experiments have been conducted on five datasets, the results demonstrate the great capability of our model. Show more

Keywords: Aspect-based sentiment analysis, graph attention network, BiGRU, dependency information, natural language processing

DOI: 10.3233/JIFS-213020

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3115-3126, 2023

Authors: Mythrei, S. | Singaravelan, S.

Article Type: Research Article

Abstract: In this web era, entity linking plays a major role. In the web the information’s are associated with different kinds of data and objects. Heterogeneous information networks (HIN) involved multi composed interlinked interconnected objects with various types of connections which is more prominent in this real world. Most of the research work focused towards processing homogeneous networks as well as linking entities with Wikipedia as knowledge base. In this paper we proposed a probabilistic based domain specific entity linking system that will link named entity mentions detected from unstructured web text corpus with corresponding entity in the existing domain specific …Heterogeneous information networks as knowledge base. This work is most challenging due to entity name ambiguity as well as knowledge in the network that are limited one. The proposed model framework presents a model that will link named entity from unstructured web text with domain specific Heterogeneous information network mainly focuses on to learn the weight of meta path. The experiments are done over real world dataset such as DBLP and IMDB dataset. Show more

Keywords: DBLP, IMDB dataset, homogeneous networks

DOI: 10.3233/JIFS-220331

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3127-3135, 2023

Authors: Xu, Huiyan

Article Type: Research Article

Abstract: The diagnosis cycle of schizophrenia is long, there is no objective diagnostic basis. The over-energy entropy product of the speech fluency rectangular parameter is designed in the paper, the fuzzy clustering is used to double locate speech pause areas and to assist in the diagnosis of schizophrenia. The pause area of speech is located based on the low speech fluency and flat energy in schizophrenia patients, an extraction algorithm is given for speech fluency quantification parameters, support vector machine (SVM) classifier is used in the approach. The fluency acoustic features of speech are taken from 28 schizophrenia patients and 28 …normal controls, these are used to verify the effect of the method in schizophrenia recognition, there is a correct rate of over 85%. The automatic schizophrenia identification based on energy entropy product and fuzzy clustering can provide objective, effective and non-invasive auxiliary for clinical diagnosis of schizophrenia. Show more

Keywords: Schizophrenia, speech fluency rectangle parameter, fuzzy clustering, hyperenergy entropy product, speech pauses in schizophrenia

DOI: 10.3233/JIFS-220248

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3137-3151, 2023

Authors: Purohit, Amit | Patheja, Pushpinder Singh

Article Type: Research Article

Abstract: Sentiment analysis is a natural language processing (NLP) technique for determining emotional tone in a body of text. Using product reviews in sentiment analysis and opinion mining various methods have been developed previously. Although, existing product review analyzing techniques could not accurately detect the product aspect and non-aspect. Hence a novel Detach Frequency Assort is proposed to detect the product aspect term using TF-ISF (Term frequency-inverse sentence frequency) with Part of Speech (POS) tags for sentence segmentation and additionally using Feedback Neural Network to combine product aspect feedback loop. Furthermore, decision-making problem occurs during classification of sentiments. Hence, to solve …this problem a novel technique named, Systemize Polarity Shift is proposed in which flow search based Support Vector Machine (SVM) with Bag of Words model classifies pre-trained review comments as positive, negative, and neutral sentiments. Moreover, the identification of specific products is not focused in sentiment analysis. Hence, a novel Revival Extraction is proposed in which a specific product is extracted based on thematic analysis method to obtain accurate data. Thus, the proposed Product Review Opinion framework gives effective optimized results in sentiment analysis with high accuracy, specificity, recall, sensitivity, F1-Score, and precision. Show more

Keywords: Sentiment analysis, opinion mining, support vector machine, thematic analysis

DOI: 10.3233/JIFS-213296

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3153-3169, 2023

Authors: Hernández, Sergio | López, Juan Luis | López-Cortés, Xaviera | Urrutia, Angelica

Article Type: Research Article

Abstract: Recommendations analysis of road safety requires decision-making tools that accommodate weather uncertainties. Operation and maintenance of transport infrastructure have been one of the sub-areas that require attention due to its importance in the quality of the road. Several investigations have proposed artificial neural networks and Bayesian networks to assess the risk of the road. These methods make use of historic accident records to generate useful road safety metrics; however, there is less information on how climatic factors and road surface conditions affect the models that generate recommendations for safe traffic. In this research, Bayesian Network, as a Hidden Markov Models, …and Apriori method are proposed to evaluate the open and closed state of the road. The weather and road surface conditions are explicitly written as a sequence of latent variables from observed data. Different weather variables were studied in order to evaluate both road states (open or close) and the results showed that the Hidden Markov Model provides explicit insight into the sequential nature of the road safety conditions but does not provide a directly interpretable result for human decision making. In this way, we complement the study with the Apriori algorithm using categorical variables. The experimental results show that combining the Hidden Markov Model and the Apriori algorithm provides an interpretable rule for decision making in recommendations of road safety to decide an opening or closing of the road in extreme weather conditions with a confidence higher than 90%. Show more

Keywords: Road safety analysis, hidden markov models, apriori methods

DOI: 10.3233/JIFS-211746

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3171-3187, 2023

Authors: Kannan, Sridharan

Article Type: Research Article

Abstract: In today’s world, mining and learning applications play an essential role in healthcare sectors and intend to transform all the data into an understandable form. However, the healthcare sectors require an automated disease prediction system for better medical analysis and emphasize better prediction accuracy for evaluation purposes. In this paper, a new automated prediction model based on Linearly Support Vector Regression and Stacked Linear Swarm Optimization (LSVR-SLSO) has been proposed to predict heart disease accurately. Primarily, the features are analyzed in a linear and non-linear manner using LSVR feature learning approaches. The extracted features are then fed into the SLSO …model in order to extract the global optimal solutions. These global solutions will reduce the data dimensionality and computational complexity during the evaluation phase. Moreover, the optimal solution facilitates the proposed model to predict heart disease appropriately. The simulation can be carried out through the MATLAB environment by utilizing a publicly available benchmark heart disease dataset. The performance results evident that the proposed LSVR-SLSO model can efficiently predict heart disease with superior accuracy of 98%, precision of 98.76%, and recall of 99.7% when compared with conventional approaches. The better performance of the proposed model will pave the way to act as an effective clinical decision support tool for physicians during an emergency. Show more

Keywords: Heart disease prediction, feature selection, optimization, automated system, mining and learning

DOI: 10.3233/JIFS-212772

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3189-3202, 2023

Authors: Wang, Kaixiang | Yang, Ming | Yang, Wanqi | Wang, Lei

Article Type: Research Article

Abstract: Deep neural networks have been adopted in multi-label classification for their excellent performance, however, existing methods fail to comprehensively utilize the high-order correlations between instances and the high-order correlations between labels, and these methods are difficult to deal with label noise effectively. We propose a novel end-to-end deep framework named Robust Fused Hypergraph Neural Networks for Multi-Label Classification (RFHNN), which can effectively utilize the two kinds of high-order correlations and adopt them to mitigate the impact of label noise. In RFHNN, Hypergraph Neural Networks (HNNs) are adopted to mine and utilize the high-order correlations of the instances in the feature …space and the label space respectively. The high-order correlations of the instances can not only improve the accuracy of the classification and the discrimination of the proposed model, but also lay the foundation for the subsequent noise correction module. Meanwhile, a hypergraph construction method based on the Apriori algorithm is proposed to realize Hypergraph Neural Networks (HNNs), which can mine robust second-order and high-order label correlations effectively. Effective classifiers are learned based on the correlations between the labels, which will not only improve the accuracy of the model, but can also enhance the subsequent noise correction module. In addition, we have designed a noise correction module in the networks. With the help of the high-order correlations among the instances and the effective classifier, the framework can effectively correct the noise and improve the robustness of the model. Extensive experimental results on datasets demonstrate that our proposed approach is better than the state-of-the-art multi-label classification algorithms. When dealing with the multi-label training datasets with noise in the label space, our proposed method also has great performance. Show more

Keywords: Multi-label classification, fused hypergraph neural network, high-order label correlations, noise correction, robust classification framework

DOI: 10.3233/JIFS-212844

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3203-3218, 2023

Authors: Jie, Zheng | Daijun, Wei | Liming, Tang

Article Type: Research Article

Abstract: For D numbers theory, there are some drawbacks in the D numbers’ integration rule. For example, the missing information is ignored in the final decision judgment for multi-attribute decision (MADM). For this problem, some researchers have improved the D numbers’ integration rules based on optimistic criterion for overcoming the shortcoming of D numbers’ integration rule. However, optimistic and pessimistic criterion are two sides of the coin for fuzzy environment. Therefore, in this article, a new D numbers’ integration rules based on pessimistic criterion is proposed. We improve the D numbers’ integration rules to redefine the missing information distribution rules based …on pessimistic criterion. The missing information is distributed in inverse proportion to each D number according to the size of the original evidence credibility. Two examples of MADM is applied by the proposed method, the results show that the proposed method can be applied to MADM. Show more

Keywords: Uncertainty, multiple attributes decision making, D numbers, integration representation, pessimistic criterion

DOI: 10.3233/JIFS-211533

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 2, pp. 3219-3231, 2023