Journal of Intelligent & Fuzzy Systems - Volume 43, issue 5

Authors: Yu, Jianping | Fu, Jilin | Bai, Tana | Zhang, Tao | Li, Shaoxiong

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Abstract: This article has been retracted.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-220388

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6383-6393, 2022

Authors: Gopinath, P. | Shivakumar, R.

Article Type: Research Article

Abstract: Recognition of finger vein patterns is essential technique that analyses the finger vein patterns to enable accurate authentication of an individual. A proper, accurate and quick learning of patterns is essentially required for improving the classification pattern. It is essential in developing an intelligent algorithm to effectively study and classify the patterns. In this paper, we develop an improved deep learning hybrid model for feature extraction and classification. A dimensional reduction deep neural network (DR-DNN) model has included a dimensional reduction model for extracting the essential features by reducing the dimensionality of feature datasets. A convolutional neural network (CNN) helps …in classifying the benign vein patterns from the malignant vein patterns. The effectiveness is compared against existing deep learning classifiers to measure how effective the deep learning model is used for classifying finger vein patterns for biometric authentication. The results shows that the proposed method achieves an accuracy rate of 97.16% for the proposed method, where the other existing methods including CNN, Recurrent Neural Network (RNN) and Deep Neural Nets (DNN) has an accuracy rate of 86%, 80.66% and 88.31%, respectively. Show more

Keywords: Deep neural networks, Deep Convolutional Neural Network, feature extraction, classification, finger vein patterns

DOI: 10.3233/JIFS-220423

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6395-6403, 2022

Authors: Lin, Ting-Yu | Hung, Kuo-Chen | Lin, Kuo-Ping | Hon, Jau-Shin | Chiu, Anthony Shun Fung

Article Type: Research Article

Abstract: With the economic growth of the world, sustainable development is a popular issue in recent years. Sustainable assessment is an important part of sustainable development. There are many previous scholars have used multiple-criteria decision-making (MCDM) to develop different evaluation frameworks in different fields. Elimination et Choix Traduisant la Realite II (ELECTRE II) is one of the most commonly used methods for MCDM. ELECTRE II uses alternatives, criteria, and criteria weighting from decision-makers to calculate the concordance and discordance indices. These two indices are used to rank the alternatives. The concordance and discordance indices in ELECTRE II are important because they …are the key to make accurate decisions. Previous scholars have failed to make comprehensive calculations for these indices, nor make their units of measure comparable, which negatively affected their results. This study improved the approach in calculating these indices and illustrated it using three case studies: (1) university examination results, (2) a sustainability assessment of groundwater remediation and (3) an assessment of power generation technologies. This improved ELECTRE II method offers decision-makers an objective basis for decision-making. Show more

Keywords: Sustainability assessment, multiple-criteria decision-making, ELECTRE II, decision analysis

DOI: 10.3233/JIFS-220441

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6405-6418, 2022

Authors: Manjula, P. | Priya, S. Baghavathi

Article Type: Research Article

Abstract: In today’s world, a Network Intrusion Detection System (NIDS) plays a vital role in order to secure the Wireless Sensor Network (WSN). However, the traditional NIDS model faced critical constraints with network traffic data due to growth in the complexity of modern attacks. These constraints have a direct impact on the overall performance of the WSN. In this paper, a new robust network intrusion classification framework based on the enhanced Visual Geometry Group (VGG-19) pre-trained model has been proposed to prolong the performance of WSN. Primarily, the pre-trained weights from the ImageNet dataset are utilized to train the parameters of …the VGG-19. Afterward, a Hybrid Deep Neural Network based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) will be employed to extract the influential features from network traffic data to enlarge the intrusion detection accuracy. The proposed VGG-19 + Hybrid CNN-LSTM model exploits both binary classification and multi-classification to classify attacks as either normal or attacked. A network intrusion benchmark dataset is used to assess the performance of the suggested system. The results reveal that the proposed VGG-19 + Hybrid CNN-LSTM learning system surpasses other pre-trained models with a superior accuracy of 98.86% during the multi-classification test. Show more

Keywords: Intrusion detection, classification, deep neural network, convolutional neural network, machine learning

DOI: 10.3233/JIFS-220444

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6419-6432, 2022

Authors: Suresh Kumar, K. | Helen Sulochana, C. | Radhamani, A.S. | Ananth Kumar, T.

Article Type: Research Article

Abstract:  Many websites are attempting to offer a platform for users or customers to leave their reviews and comments about the products or services in their native languages. The cross-domain adaptation (CDA) analyses sentiment across domains. The sentiment lexicon falls short resulting in issues like feature mismatch, sparsity, polarity mismatch and polysemy. In this research, an augmented sentiment dictionary is developed in our native regional language (Tamil) that intends to construct the contextual links between terms in multi-domain datasets to reduce problems like polarity mismatch, feature mismatch, and polysemy. Data from the source domain and target domain both labeled and unlabeled …are used in the proposed dictionary. To be more specific, the initial dictionary uses normalised pointwise mutual information (nPMI) to derive contextual weight, whereas the final dictionary uses the value of terms across all reviews to compute the accurate rank score. Here, a deep learning model called BERT is used for sentiment classification. For cross-domain adaptation, a modified multi-layer fuzzy-based convolutional neural network (M-FCNN) is deployed. This work aims to build a single dictionary using large number of vocabularies for classifying the reviews in Tamil for several target domains. This extendible dictionary enhances the accuracy of CDA greatly when compared to existing baseline techniques and easily handles a large number of terms in different domains. Show more

Keywords: Cross-domain adaptation (CDA), BERT classification, modified multi-layer fuzzy convolutional neural networks (M-FCNN)

DOI: 10.3233/JIFS-220448

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6433-6450, 2022

Authors: Titus, P. | Ajitha Fancy, J. | Joshi, Gyanendra Prasad | Amutha, S.

Article Type: Research Article

Abstract: A set S  ⊆ V in a graph G is a MED -set if every vertex in V  - S has a monophonic eccentric vertex in S . The MED -number γme  (G ) is the cardinality of a minimum MED -set of G . A set S  ⊆ V in a graph G is a CMED -set if S is a MED -set and the induced subgraph is connected. The CMED -number γcme  (G ) is the cardinality of a minimum CMED -set of G . We investigate some properties of the CMED …-sets. Also, we determine the bounds of the CMED -number and find the same for some standard graphs. The CMED -number has applications in security based communication networks in real life situations. This motivated us to introduce and investigate CMED -set in a graph. Show more

Keywords: Monophonic eccentric vertex, MED-set, MED-number, CMED-set, CMED-number

DOI: 10.3233/JIFS-220463

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6451-6460, 2022

Authors: Menekse, Akin | Akdag, Hatice Camgoz

Article Type: Research Article

Abstract: Combinative distance-based assessment (CODAS) is a multi-criteria decision-making (MCDM) method that is based on the Euclidean and Hamming distances of alternatives from the average scores of attributes. Spherical fuzzy sets, as the recent extensions of ordinary fuzzy sets, were developed based on Pythagorean and neutrosophic sets and enable decision-makers to express their membership, non-membership, and hesitancy degrees independently and in a larger domain than most other fuzzy extensions. This paper proposes a new interval-valued spherical fuzzy CODAS method and provides extra space for catching the vagueness in the nature of the problem. The feasibility and practicality of the proposed model …are illustrated with an application for evaluating the reopening readiness of academic units for campus education in the era of COVID-19. Three decision-makers from a higher education institution evaluate four academic units with respect to five strategic criteria and prioritize them according to their readiness levels for the campus type of education. Sensitivity and comparative analyses, theoretical and practical contributions, limitations, and future research avenues are also presented in the study. Show more

Keywords: CODAS, interval-valued spherical fuzzy, COVID-19, higher education institution, reopening readiness

DOI: 10.3233/JIFS-220468

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6461-6476, 2022

Authors: Rajnish, Kumar | Bhattacharjee, Vandana

Article Type: Research Article

Abstract: Software defect prediction is used to assist developers in finding potential defects and allocating their testing efforts as the scale of software grows. Traditional software defect prediction methods primarily concentrate on creating static code metrics that are fed into machine learning classifiers to predict defects in the code. To achieve the desired classifier performance, appropriate design decisions are required for deep neural network (DNN) and convolutional neural network (CNN) models. This is especially important when predicting software module fault proneness. When correctly identified, this could help to reduce testing costs by concentrating efforts on the modules that have been identified …as fault prone. This paper proposes a CONVSDP and DNNSDP (cognitive and neural network) approach for predicting software defects. Python Programming Language with Keras and TensorFlow was used as the framework. From three NASA system datasets (CM1, KC3, and PC1) selected from PROMISE repository, a comparative analysis with machine learning algorithms (such as Random Forest (RF), Decision Trees (DT), Nave Bayes (NF), and Support Vector Machine (SVM) in terms of F-Measure (known as F1-score), Recall, Precision, Accuracy, Receiver Operating Characteristics (ROC) and Area Under Curve (AUC) has been presented. We extract four dataset attributes from the original datasets and use them to estimate the development effort, development time, and number of errors. The number of operands, operators, branch count, and executable LOCs are among these attributes. Furthermore, a new parameter called cognitive weight (Wc) of Basic Control Structure (BCS) is proposed to make the proposed cognitive technique more effective, and a cognitive data set of 8 features for NASA system datasets (CM1, KC3, and PC1) selected from the PROMISE repository to predict software defects is created. The experimental results showed that the CONVSDP and DNNSDP models was comparable to existing classifiers in both original datasets and cognitive data sets, and that it outperformed them in most of the experiments. Show more

Keywords: Machine learning, software defect prediction, CNN model, cognitive weight, basic control structures, neural network

DOI: 10.3233/JIFS-220497

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6477-6503, 2022

Authors: Singh, Upendra | Gupta, Puja | Shukla, Mukul

Article Type: Research Article

Abstract: Image Incorporation concerns, including background confusion, uneven population distribution, and variations in scale and familiarity, can make group counting difficult. Pre-existing information and multi-level contextual representations are required to handle these problems effectively with deep neural networks and Mask-RCNN. Numerous studies on crowd counting use density maps without segmentation, which treat a group of individuals as a single entity. This article offers a hybrid method for crowd counting that combines Mask-RCNN (MRCNN) and a bidirectional convolutional long-term memory network (ConvLSTM), dubbed (CC: MRCNN-biCLSTM). The CC: MRCNN-biCLSTM is based on the Mask-RCN; it first segments instances and generates density maps, which …are passed into adversarial learning during the training phase. Finally, the bidirectional convolutional LSTM is being used to return metrics and counts for individuals within a group of individuals. Following that, the suggested activity detection technique based on the Bayesian non-linear filter AD-BNF is used to identify a person’s activity. Additionally, the suggested approach resolves human grouping and enhances metric performance. Extensive studies demonstrate that the suggested method outperforms more sophisticated techniques on four frequently used difficult criteria for density map precision and quality. Show more

Keywords: Mask-RCNN, bidirectional ConvLSTM, cluster counting, adversarial learning, activity detection

DOI: 10.3233/JIFS-220503

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6505-6520, 2022

Authors: Khan, Madad | Anis, Saima | Zuev, Sergei | Ullah, Hikmat | Zeeshan, Muhammad

Article Type: Research Article

Abstract:  In this paper, we have discussed some new operations and results of set theory for complex fuzzy sets (CFSs). Moreover, we developed the basic results of CFSs under the basic operations such as complex fuzzy simple difference, bounded sum, bounded difference, dot product, bounded product, union, intersection, and Cartesian product. We explored the CFSs and discussed the related properties with examples such as complex fuzzy bounded sum over the intersection, complex fuzzy dot product over the union, etc. Identifying the reference signals under the environment of CFSs have always been a challenging. Many algorithms based on set theoretic operations and …distance measures have been proposed for identifying a reference signal using any common system. But linear time invariant (LTI) system is considered easy to analyze the linear and time-varying signals. We used CFSs in signals and systems. We developed an algorithm based on convolution product and LTI system under the complex fuzzy environment. We identified a high degree of resemblance (reference signal) of the received signals to the reference signal in a linear time-invariant (LTI) system that receives an input signal and produces an output signal. Show more

Keywords: Complex fuzzy sets, inverse discrete Fourier transform, signals and systems, linear-time invariant (LTI) system

DOI: 10.3233/JIFS-220517

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6521-6548, 2022

Authors: Yang, Jing | Su, Wei

Article Type: Research Article

Abstract: Interval-valued neutrosophic set (IVNS) plays an important role in dealing with imprecise judgment information. For a multi-attribute decision making problem, the information of alternatives under different attributes is given in the form of interval valued neutrosophic number(IVNN). The objective of the presented paper is to develop a multiple-attribute decision making (MADM) method under interval-valued neutrosophic sets(IVNSs) using the new similarity measurement. The similarity measurement of IVNSs has always been a research hotspot. A new similarity measurement of IVNSs is first proposed in this paper based on Chebyshev distance. The proposed method enriches the existing similarity measurement methods. It can be …applied to not only IVNSs, but also single-valued neutrosophic sets(SVNSs). The influence of each attribute on the decision-making result can be described by the weight. How to formulate the weight scientifically is vital as well. In this paper, the objective weight is calculated by normalizing the grey correlation coefficient obtained by a score function which can be applied to IVNSs. The objective weight is then combined with the subjective one by considering an adjustment factor with the weighted summation method. The adjustment factor is determined by the importance of subjective weight. Finally, an example is used to illustrate the comparison results of the proposed algorithm and other three ones. The comparison shows that the proposed algorithm is effective and can identify the optimal scheme quickly. Show more

Keywords: Fuzzy multi-attribute decision making, similarity measure, chebyshev distance, interval-valued neutrosophic sets

DOI: 10.3233/JIFS-220534

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6549-6559, 2022

Authors: Tan, Guimei | Yu, Xichang

Article Type: Research Article

Abstract: As an important tool to measure the degree of difficulty of predicting the realization of an uncertain set, entropy theory of uncertain set has been investigated by many scholars. In order to measure the uncertainty associated with some uncertain sets, this paper first proposes the arc entropy for an uncertain set. Then a computational arc entropy formula via inverse membership function is introduced to calculate the arc entropy more quickly, and some properties of arc entropy are studied. Furthermore, some applications are also provided to illustrate the superiority of the arc entropy.

Keywords: Uncertainty theory, uncertain set, arc entropy, portfolio selection

DOI: 10.3233/JIFS-220564

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6561-6574, 2022

Authors: Tang, Jianfei | Zhao, Hui

Article Type: Research Article

Abstract: The focus of a large amount of research on malware detection is currently working on proposing and improving neural network structures, but with the constant updates of Android, the proposed detection methods are more like a race against time. Through the analysis of these methods, we found that the basic processes of these detection methods are roughly the same, and these methods rely on professional reverse engineering tools for malware analysis and feature extraction. These tools generally have problems such as high time-space cost consumption, difficulty in achieving concurrent analysis of a large number of Apk, and the output results …are not convenient for feature extraction. Is it possible to propose a general malware detection process implementation platform that optimizes each process of existing malware detection methods while being able to efficiently extract various features on malware datasets with a large number of APK? To solve this problem, we propose an automated platform, AmandaSystem, that highly integrates the various processes of deep learning-based malware detection methods. At the same time, the problem of over privilege due to the openness of Android system and thus the problem of excessive privileges has always required the accurate construction of mapping relationships between privileges and API calls, while the current methods based on function call graphs suffer from inefficiency and low accuracy. To solve this problem, we propose a new bottom-up static analysis method based on AmandaSystem to achieve an efficient and complete tool for mapping relationships between Android permissions and API calls, PerApTool. Finally, we conducted tests on three publicly available malware datasets, CICMalAnal2017, CIC-AAGM2017, and CIC-InvesAndMal2019, to evaluate the performance of AmandaSystem in terms of time efficiency of APK parsing, space occupancy, and comprehensiveness of extracted features, respectively, compared with existing methods were compared. Show more

Keywords: Cybersecurity, android malware analysis, static analysis, dynamic analysis, least privilege

DOI: 10.3233/JIFS-220567

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6575-6589, 2022

Authors: Cypto, J. | Karthikeyan, P.

Article Type: Research Article

Abstract: With the growth in vehicular traffic, there is a greater risk of road accidents. Over speeding, intoxicated driving, driver distractions, red-light runners, ignoring safety equipment such as seat belts and helmets, non-adherence to lane driving, and improper overtaking are the leading causes of accidents. Speed violation, in particular, has a significant influence on today’s transportation. Also, detecting this speed violation and punishing this violator are more time-consuming tasks. For that reason, a novel automatic speed violation detection in traffic based on Deep learning is proposed in this paper. This proposed method is separated into two working modules: object detection and …license plate recognition. The object detection module uses the most efficient PP YOLO neural networks. It utilizes open ALPR (Automatic License Plate Recognition) for the vehicle’s number plate identification, which passes the traffic above maximum speed. With the number plate details, the authorities can take action against the rule violator with less time and effort. The simulation results show that the proposed automatic speed violation detection system also has an accuracy rate of 98.8% for speed violation detection and 99.3% for license plate number identification, demonstrating that the approach described in this work has a higher performance in terms of accuracy. Furthermore, the proposed technique was compared to recent existing results. Show more

Keywords: Speed violation, intoxicated driving, deep learning, PP YOLO, object detection, license plate recognition

DOI: 10.3233/JIFS-220577

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6591-6606, 2022

Authors: Shi, Xuecheng | Lin, Zhichao | Zhou, Ligang | Bao, Hengjia

Article Type: Research Article

Abstract: Linguistic q-rung orthopair fuzzy numbers (Lq-ROFNs) are an effective tool for representing fuzzy linguistic information, and they can obtain a wider expression scope than linguistic intuitionistic fuzzy numbers and linguistic Pythagorean fuzzy numbers by increasing the value of parameter q . In this paper, we propose a new similarity measure called the grey similarity degree between any two Lq-ROFNs based on the concept of the grey correlation degree. Considering the significance of determining unknown weights, we also propose a grey correlation method to determine each expert’s weight under different alternatives and attributes, and we construct an optimization model to determine …incompletely known attribute weights. Furthermore, an approach to linguistic q-rung orthopair fuzzy multiple-attribute group decision making is proposed that combines the grey similarity degree with the PROMETHEE II method. Finally, a numerical example is given to illustrate the effectiveness of the proposed method, and a sensitivity analysis and comparison analysis are also performed. Show more

Keywords: Linguistic q-rung orthopair fuzzy numbers, grey correlation degree, grey similarity degree, PROMETHEE, group decision making

DOI: 10.3233/JIFS-220579

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6607-6625, 2022

Authors: An, Qing | Tang, Ruoli | Li, Xueyan | Zhang, Xiaodi | Li, Xin

Article Type: Research Article

Abstract: In order to optimally control the marine hybrid power system (HPS) under increasingly complex regulation constraints or hardware constraints, an efficient power-flow scheduling model and optimization algorithm are of great importance. This work focuses on the optimal power-flow scheduling of marine HPS, especially on the efficiency improvement of the penalty functions for satisfying complex constraints. To be specific, an optimal operation model of marine HPS is discussed, and the complex model constraints are described as various penalty functions. Secondly, a novel optimization algorithm, namely adaptive multi-context cooperatively coevolving differential evolution algorithm with random topology and mutated context vector (AMCCDE - rt - mcv ) …is developed to optimize the aforementioned model. In order to ensure the satisfaction of the complex model constraints, the detailed forms for penalty functions are researched and the optimal parameters for penalty functions are comprehensively compared, analysed and tested by a set of numerical experiments. Finally, the developed methodologies are tested by simulation experiments. Experimental results show that the damping factor, exponent parameter and punish strength constant effect the efficiency of penalty functions a lot, and the developed penalty functions can effectively satisfy all the model constraints with fast response speed. With the integration of penalty functions, the developed methodology can obtain promising performance on the optimal scheduling of the evaluated marine HPS. Show more

Keywords: Hybrid power system, optimal energy management, penalty function, optimization algorithm, differential evolution

DOI: 10.3233/JIFS-220645

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6627-6649, 2022

Authors: Suresh, K. | Jagatheeswari, P.

Article Type: Research Article

Abstract: Renewable energy has seen a substantial increase in deployment as an alternative to traditional power sources. However, two fundamental constraints exist that preclude widespread adoption: the availability of the generated power and the expense of the equipment. One of the most critical difficulties with this sort of hybrid system is to appropriately design the Hybrid Renewable Energy System (HRES) elements so that they fulfill all load requirements while requiring the least amount of investment and running expenditures. This research proposes a novel technique for evaluating the optimal smart grid linking Hybrid Renewable Energy (Solar photovoltaic and wind) with battery, to …increase profitability, dependability, and feasibility. A multiobjective function is suggested and constructed to be optimized utilizing two optimization algorithms: Enhanced Particle Swarm Optimization (EPSO) and Harris Hawks Optimization (HHO) algorithm with Fuzzy-Extreme Learning Machine (ELM). The primary goal for the HRES is to operate optimally to reduce the cost of energy generat ion through hourly day-ahead. Here, the Fuzzy-ELM is utilized to predict the required load of the smart grid-connected system and hybrid EPSO-HHO, which are introduced to solve the problem of HRES economic analysis. Finally, the suggested EPSO-EHO method is implemented in the MATLAB software, and its performance comparison is made with other existing methods such as PSO, WOA, and HHO. The simulation result shows that the cost of the newly suggested EPSO-HHO technique-based Hybrid Renewable Energy System is less than PSO, WOA, and HHO by 4.89 %, 4.51 %, and 4.05 %, respectively. Show more

Keywords: Harris Hawks’ Optimization, economic analysis, renewable energy sources, Extreme Learning Machine, smart grid

DOI: 10.3233/JIFS-220726

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6651-6662, 2022

Authors: Durmaz, Nida | Budak, Ayşenur

Article Type: Research Article

Abstract: This study aims to define the adoption barriers to Industry 4.0 for sustainable supply chain and define their causalities and, dependencies, hierarchical levels of these barriers. Firstly, a framework for critical barriers to Industry 4.0 for sustainable supply chain management is created with literature review and experts for the first time. Then an integrated approach of Grey DEMATEL – ANP is proposed to analyze the adoption barriers to Industry 4.0 in sustainable supply chain management. The proposed method determines the cause-effect relationship among barriers, the strength of interactions, and the relative weights of critical barriers to Industry 4.0 in a …sustainable supply chain. The results show that uncertainty about economic benefits, resistance to change, and lack of infrastructure and tools for Industry 4.0 in the Sustainable supply chain are crucial barriers to implementing Industry 4.0 technologies in SSC. This study can help decision-makers and managers define the barriers and provide the theoretical guideline to implement Industry 4.0 technologies across the sustainable supply chain successfully. Show more

Keywords: Sustainable supply chain management, Grey DEMATEL, ANP, Industry 4.0 adoption barriers

DOI: 10.3233/JIFS-220732

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6663-6682, 2022

Authors: Jiang, Ruiyang

Article Type: Research Article

Abstract: The Pile motion seems to be one of the most critical in pile failure that requires appraisal before installing piles. The variables to estimate the Pile Settlement parameter, there are several methods. Among existing theoretical ways to investigate the pile movement mathematically, most studies have tried to model the piles’ settlement overloading period using artificial intelligence. Thus, this research has used the Artificial Neural Network to have the actual status of pile motion vertically over the loading periods dynamically and statically. Therefore, the present research has utilized the Radial Basis Function Neural Network joint with Equilibrium Optimizer Algorithm and Grasshopper …Optimization Algorithm to figure out the optimum number of neurons within the hidden layer. Kuala Lumpur’s Klang Valley Mass Rapid Transit transportation network, Malaysia, opted to model the piles’ settlement and earth properties via the proposed hybrid RBF-GOA and RBF-EOA frameworks. By modeling both frameworks, the error index of RMSE for RBF-GOA and HRBF-EOA were gained to 0.6312 and 0.5947, respectively. However, the VAF indicator showed identical results of the rates 96.98 and 97.33, respectively. Overly, the RBF-EOA represented better than RBF-GOA by little efficiency. Show more

Keywords: Pile in rock, settlement, prediction, radial basis function, equilibrium optimizer algorithm, grasshopper optimization, R-value correlation

DOI: 10.3233/JIFS-220741

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6683-6695, 2022

Authors: Kalaichelvi, V. | Vimala Devi, P. | Meenakshi, P. | Swaminathan, S. | Suganya, S.

Article Type: Research Article

Abstract: The billions of bits of information are transferred each second through the internet every day. The information may be text, image, audio or video etc, accordingly, we need some protection mechanism while sharing confidential data. Generally, RSA algorithm is used for encrypting the Secret images. However, the security provided by Elliptic Curve Cryptography (ECC) is higher with lower sized key than the RSA algorithm. So, this article proposes an extended Elliptic Curve encryption approach for encrypting the secret images. In this system, the secret image is partitioned into three color image planes such as Red, Green and Blue. By applying …Radix-64 encoding and Mapping table, these planes are converted into elliptic curve points and then these points are encrypted using ECC algorithm. Again, these points are applied to the Radix-64 decoding and the mapping table to get ciphered-image. At last, the key parameters such as a, b, p and Generator point (G) are embedded in the last four pixel positions of the ciphered-image. In order to get the original secret image, the recipient must extract these key parameters from the encrypted image and then apply the remaining processes to the encrypted image in the opposite order. Experimental results tested using MATLAB R2021b and it shows that the NPCR and UACI values are 99.54% and 28.73 % and better quality feature is attained since the entropy value is almost closer to eight. So, the proposed image encryption has robust capacity to fight against the differential attack. Show more

Keywords: ECC, Radix-64 conversion, image encryption, image decryption, security

DOI: 10.3233/JIFS-220767

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6697-6708, 2022

Authors: Mishra, Anju | Singh, Laxman | Pandey, Mrinal | Lakra, Sachin

Article Type: Research Article

Abstract: Diabetic Retinopathy (DR) is a disease that damages the retina of the human eye due to diabetic complications, resulting in a loss of vision. Blindness may be avoided If the DR disease is detected at an early stage. Unfortunately, DR is irreversible process, however, early detection and treatment of DR can significantly reduce the risk of vision loss. The manual diagnosis done by ophthalmologists on DR retina fundus images is time consuming, and error prone process. Nowadays, machine learning and deep learning have become one of the most effective approaches, which have even surpassed the human performance as well as …performance of traditional image processing-based algorithms and other computer aided diagnosis systems in the analysis and classification of medical images. This paper addressed and evaluated the various recent state-of-the-art methodologies that have been used for detection and classification of Diabetic Retinopathy disease using machine learning and deep learning approaches in the past decade. Furthermore, this study also provides the authors observation and performance evaluation of available research using several parameters, such as accuracy, disease status, and sensitivity. Finally, we conclude with limitations, remedies, and future directions in DR detection. In addition, various challenging issues that need further study are also discussed. Show more

Keywords: Retinal fundus images, machine learning, deep learning, classification, Diabetic retinopathy

DOI: 10.3233/JIFS-220772

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6709-6741, 2022

Authors: Niu, Guo | Ma, Zhengming | Liu, Xi

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-220785

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6743-6754, 2022

Authors: Aras, Cigdem G. | Al-shami, Tareq M. | Mhemdi, Abdelwaheb | Bayramov, Sadi

Article Type: Research Article

Abstract: A bipolar soft set is given by helping not only a chosen set of “parameters” but also a set of oppositely meaning parameters called “not set of parameters”. It is known that a structure of bipolar soft set is consisted of two mappings such that F  : E  → P  (X ) and G  :⌉ E  → P  (X ), where F explains positive information and G explains opposite approximation. In this study, we first introduce a new definition of bipolar soft points to overcome the drawbacks of the previous definition of bipolar soft points given in [34]. Then, we explore …the structures of bipolar soft locally compact and bipolar soft paracompact spaces. We investigate their main properties and illuminate the relationships between them. Also, we define the concept of a bipolar soft compactification and investigate under what condition a bipolar soft topology forms a bipolar soft compactification for another bipolar soft topology. To elucidate the presented concepts and obtained results, we provide some illustrative examples. Show more

Keywords: bipolar soft set, bipolar soft topology, bipolar soft locally compactness, bipolar soft paracompactness

DOI: 10.3233/JIFS-220834

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6755-6763, 2022

Authors: Xu, Qin | Xu, Shumeng | Wang, Dongyue | Yang, Chao | Liu, Jinpei | Luo, Bin

Article Type: Research Article

Abstract: Representing features at multiple scales is of great significance for hyperspectral image classification. However, the most existing methods improve the feature representation ability by extracting features with different resolutions. Moreover, the existing attention methods have not taken full advantage of the HSI data, and their receptive field sizes of artificial neurons in each layer are identical, while in neuroscience, the receptive field sizes of visual cortical neurons adapt to the neural stimulation. Therefore, in this paper, we propose a Res2Net with spectral-spatial and channel attention (SSCAR2N) for hyperspectral image classification. To effectively extract multi-scale features of HSI image at a …more granular level while ensuring a small amount of calculation and low parameter redundancy, the Res2Net block is adopted. To further recalibrate the features from spectral, spatial and channel dimensions simultaneously, we propose a visual threefold (spectral, spatial and channel) attention mechanism, where a dynamic neuron selection mechanism that allows each neuron to adaptively adjust the size of its receptive fields based on the multiple scales of the input information is designed. The comparison experiments on three benchmark hyperspectral image data sets demonstrate that the proposed SSCAR2N outperforms several state-of-the-art deep learning based HSI classification methods. Show more

Keywords: Hyperspectral image classification, deep learning, convolutional neural networks (CNNs), Res2Net, visual attention mechanism

DOI: 10.3233/JIFS-220863

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6765-6781, 2022

Authors: Sanjana, R. | Ramesh, G.

Article Type: Research Article

Abstract: This paper is concerned with the solution mechanism to solve the transportation problem under unpredictability by using interval valued intuitionistic fuzzy parameters. The parameters are chosen as intervals in which costs are modeled by intuitionistic fuzzy numbers, whereas source and destination are taken as crisp values. Various methods of transportation problem like VAM, Monalisha’s Approximation method, Zero point method are used to illustrate the cost in interval numbers by using the interval arithmetic operations. For each method, a solution is derived without converting into crisp expression followed by a graphical representation.

Keywords: Interval valued intuitionistic fuzzy numbers, inteval valued intuitionistic fuzzy transportation problem, interval arithmetic, interval VAM, interval ZPM

DOI: 10.3233/JIFS-220946

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6783-6792, 2022

Authors: Lakkshmanan, Ajanthaa | Anbu Ananth, C. | Tiroumalmouroughane, S.

Article Type: Research Article

Abstract: Pancreatic tumor is the deadliest disease which needs earlier identification to reduce the mortality rate. With this motivation, this study introduces a Multi-Objective Metaheuristics with Intelligent Deep Learning Model for Pancreatic Tumor Diagnosis (MOM-IDL) model. The proposed MOM-IDL technique encompasses an adaptive Weiner filter based pre-processing technique to enhance the image quality and get rid of the noise. In addition, multi-level thresholding based segmentation using Kapur’s entropy is employed where the threshold values are optimally chosen by the barnacles mating optimizer (BMO). Besides, densely connected network (DenseNet-169) is employed as a feature extractor and fuzzy support vector machine (FSVM) is …utilized as a classifier. For improving the classification performance, the BMO technique was implemented for fine-tuning the parameters of the FSVM model. The design of MOBMO algorithm for threshold selection and parameter optimization processes shows the novelty of the work. A wide range of simulations take place on the benchmark dataset and the experimental results highlighted the enhanced performance of the MOM-IDL technique over the recent state of art techniques. Show more

Keywords: Pancreatic tumor, computer aided diagnosis, deep learning, image classification, parameter optimization

DOI: 10.3233/JIFS-221171

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6793-6804, 2022

Authors: Qiu, Chenye | Fang, Huixing | Liu, Ning

Article Type: Research Article

Abstract: Microgrid (MG) systems are growing at a rapid pace since they can accommodate the high amount of renewable energy. Since the MG consists of small distributed generators (DG) with volatile characteristics, an efficient energy management system is the main requisite in MG. In this paper, a chaotic sine cosine algorithm with crossover operator (CSCAC) is proposed for the day-ahead MG optimal energy scheduling problem. CSCAC includes a novel non-linear transition parameter based on the chaos system which can help the algorithm escape from local optima. A chaotic search operator is proposed to enhance the local search ability. Furthermore, a crossover …operator is devised to combine the advantages of different search strategies and achieve a comparatively better balance of exploration and exploitation. First, the effectiveness of CSCAC is validated on several benchmark functions. Then, it is applied to the day-ahead energy scheduling in a MG with three wind power plants, two photovoltaic power plants and a combined heat and power plant (CHP). Furthermore, it is implemented in two more cases considering the uncertainty and stochastic nature of the renewable power sources. Experimental results demonstrate the superiority of CSCAC over other comparative algorithms in the optimal MG energy management problem. Show more

Keywords: Sine cosine algorithm, microgrid, chaotic system, energy scheduling, uncertainty

DOI: 10.3233/JIFS-221178

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6805-6819, 2022

Authors: Zhang, Taoyun | Zhang, Yugang | Zhang, Guangdong | Xue, Ling | Wang, Jin

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-221185

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6821-6830, 2022

Authors: Li, Xiang | Yu, Junqi | Wang, Qian | Dong, Fangnan | Cheng, Renyin | Feng, Chunyong

Article Type: Research Article

Abstract: Short-term energy consumption prediction of buildings is crucial for developing model-based predictive control, fault detection, and diagnosis methods. This study takes a university library in Xi’an as the research object. First, a time-by-time energy consumption prediction model is established under the supervised learning approach, which uses a long short-term memory (LSTM) network and a Multi-Input Multi-Output (MIMO) strategy. The experimental results validate the model’s validity, which is close enough to physical reality for engineering purposes. Second, the potential of the people flows factor in energy consumption prediction models is explored. The results show that people flow has great potential in …predicting building energy consumption and can effectively improve the prediction model performance. Third, a diagnostic method, which can recognize abnormal energy consumption data is used to diagnose the unreasonable use of the building during each hour of operation. The method is based on differences between actual and predicted energy consumption data derived from a short-term energy consumption prediction model. Based on actual building operation data, this work is enlightening and can serve as a reference for building energy efficiency management and operation. Show more

Keywords: Deep learning, energy consumption prediction, energy consumption diagnosis, people flows

DOI: 10.3233/JIFS-221188

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6831-6848, 2022

Authors: Senthil, P. | Selvakumar, S.

Article Type: Research Article

Abstract: Digital evidence is an integral part of any trial. Data is critical facts, encrypted information that requires explanation in order to gain meaning and knowledge. The current process of digital forensic research cannot effectively address the various aspects of a complex infrastructure. Therefore, digital forensics requires the optimal processing of a complex infrastructure that differs from the current process and structure. For a long time, digital forensic research has been utilized to discuss these issues. In this research, we offer a forensic investigation hybrid deep learning approach based on integrated multi-model data fusion (HDL-DFI). First, we concentrate on digital evidence …collection and management systems, which can be achieved by an integrated data fusion model with the help of an improved brain storm optimization (IBSO) algorithm. Here, we consider several multimedia data’s for evidence purposes, i.e. text, image, speech, physiological signals, and video. Then, we introduce a recurrent multiplicative neuron with a deep neural network (RM-DNN) for data de-duplication in evidence collection, which avoids repeated and redundant data. After that, we design a multistage dynamic neural network (MDNN) for sentimental analysis to decide what type of crime has transpired and classify the action on it. Finally, the accuracy, precision, recall, F1-score, G-mean, and area under the curve of our proposed HDL-DFI model implemented with the standard benchmark database and its fallouts are compared to current state-of-the-art replicas (AUC). The results of our experiments show that the computation time of the proposed model HDL-DFI is 20% and 25% lower than the previous model’s for uploading familiar and unfamiliar files, 22% and 29% lower for authentication generation, 23% and 31% lower for the index service test scenario, and 24.097% and 32.02% lower for familiarity checking . Show more

Keywords: Digital forensics, evidence collection, evidence protection, deep learning, multi model fusion

DOI: 10.3233/JIFS-221307

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6849-6862, 2022

Authors: Muruganandham, R. | Sheik Abdullah, A. | Selvakumar, S.

Article Type: Research Article

Abstract: The primary goal of this study is to optimize web content for a positive user experience and to develop a data-driven methodology to assess the success of visitor flow on a website for school children. Through Vision-Based Page Segmentation, the suggested study work intends to broaden the stated web approach’s reach and statistical inference. The improvisation has been made accordingly with the semantic structure observed from each node with the designated degree of coherence to indicate the content in spatial and block based on visual perception for each event. The click count (number of clicks) is calculated for all the …possibilities of Quest Software. The most frequently accessed event is displayed at the top to enhance usability and visibility with an accuracy of about 92.80%. From the experimental analysis, it has been observed that most of the students preferred events corresponding to drawing, rhymes, and rangoli with a willingness rate of above 80%, respectively. Statistical analysis has been made using chi-square analysis, and it has been found that the levels from A to D are significant for three years with a P -value < 0.001. Sentimental analysis of feedback collected from the participants about the events is also done, and the most preferred event is suggested for the upcoming years. Show more

Keywords: Data driven model, event analysis, optimization, page segmentation, web analytics

DOI: 10.3233/JIFS-221392

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6863-6875, 2022

Authors: Mohana Sundaram, K.D. | Shankar, T. | Sudhakar Reddy, N.

Article Type: Research Article

Abstract: Computer vision functions like object detection, image segmentation, and image classification were recently getting advance due to Convolutional Neural Networks (CNNs). In the food and agricultural industries, image classification plays a critical role in quality control. CNNs are made up of layers that alternate between convolutional, nonlinearity, and feature pooling. In this article, we proposed Fuzzy Pooling, a novel pooling approach that works based on fuzzy logic, that can increase the accuracy of the CNNs by replacing the conventional pooling layer. This proposed Fuzzy Pooling was put to the test with CIFAR-10 and SVHN data sets on single layer CNN, …and it outperformed previous pooling strategies by achieving 92% and 97% classification accuracy. This proposed Fuzzy Pooling layer was replaced the Max Pooling layer in the ThinNet architecture, and it was trained using the back propagation method. It was demonstrated experimentally on the Lemon fruit data set to classify the fruits into three categories such as Good, Medium, and Poor. In order to classify the lemon fruit into three categories, the 1000 Fully Connected layer in ThinNet architecture was replaced with three Fully Connected layers. The Modified ThinNet architecture called ThinNet_FP was trained with a learning rate of 0.001 and achieved 97% accuracy in classifying the images and outperformed previous CNN architectures when trained on the same data set. Show more

Keywords: Convolutional neural network (CNN), fuzzy logic, fuzzy pooling, back propagation, fruit classification

DOI: 10.3233/JIFS-221550

Citation: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 5, pp. 6877-6891, 2022