Journal of Intelligent & Fuzzy Systems - Volume 46, issue 1

Authors: Zhang, Zhi-Hao | Wang, Jie-Sheng | Chen, Lin

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Abstract: This article has been retracted.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-233769

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2665-2691, 2024

Authors: Wang, Bing | Yue, Wei | Zhang, Lu

Article Type: Research Article

Abstract: The California Bearing Ratio (CBR) holds significant importance in the design of flexible pavements and airport runways, serving as a critical soil parameter. Moreover, it offers a means to gauge the soil response of subgrades through correlation, an aspect pivotal in soil engineering, particularly in shaping subgrade design for rural road networks. The CBR value of soil is influenced by numerous factors, encompassing variables like maximum dry density (MDD), optimum moisture content (OMC), liquid limit (LL), plastic limit (PL), plasticity index (PI), soil type, and soil permeability. The condition of the soil, whether soaked or unsoaked, also contributes to this …value. It is worth noting that determining CBR is time-consuming and extensive. Acknowledging the gravity of this determination, the study introduces a pioneering approach employing machine learning. This innovative technique uses a foundational multi-layer perceptron model, harnessing the algorithm’s robust capabilities in addressing regression challenges. A hybridization approach enhances the multi-layer perceptron’s performance and achieves optimal results. This approach integrates the Bonobo Optimizer (BO), Smell Agent Optimization (SAO), Prairie Dog Optimization (PDO), and Gold Rush Optimizer (GRO). The hybrid models proposed in this study exhibit promising results in predicting CBR values. The MLAO3 hybrid model is particularly noteworthy, emerging as the most accurate predictor among the range of models, with an impressive R2 value of 0.994 and an RMSE value of 2.80. Show more

Keywords: California bearing ratio, multi-layer perceptron, meta-heuristic algorithms, hybrid machine learning

DOI: 10.3233/JIFS-233794

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2693-2711, 2024

Authors: Zhang, Benfei | Huang, Lijun | Wang, Jie | Zhang, Li | Wu, Yue | Jiang, Yizhang | Xia, Kaijian

Article Type: Research Article

Abstract: In this paper, a novel semi-supervised fuzzy clustering algorithm, MFM-SFCM, based on a membership fusion mechanism is proposed for Diffusion-weighted imaging (DWI) brain infarction lesion segmentation. The proposed MFM-SFCM algorithm addresses the issue of weakened constraints and insufficient influence of labeled samples on the clustering process that arises in the semi-supervised fuzzy C-means clustering (SFCM) when emphasizing supervised information. By using a new membership fusion mechanism, MFM-SFCM eliminates this issue, greatly improving the accuracy of clustering results and accelerating convergence speed. This allows fuzzy clustering to achieve good results in the segmentation of DWI brain infarction lesions using a small …amount of labeled information. The effectiveness of the MFM-SFCM algorithm is demonstrated through experiments conducted on a real-world dataset of DWI brain images. Show more

Keywords: Semi-supervised clustering, supervised information, FCM, membership fusion mechanism, medical image segmentation

DOI: 10.3233/JIFS-234148

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2713-2726, 2024

Authors: Zhang, Ju | Zhang, Tao | Xiang, Yanpeng | Liu, Jiahao | Zhang, Yu

Article Type: Research Article

Abstract: Information hiding is a crucial technology in the field of information security. Embedding capacity and stego-image quality are two key performance metrics in information hiding. In recent years, many information-hiding methods have been proposed to enhance embedding capacity and stego-image quality. However, through the study of these methods, we found that there is still room for improvement in terms of performance. This paper proposes a high-capacity information-hiding method based on a chunking matrix (CM). CM divides a 256×256 matrix into blocks, where each block contains k ×k corresponding secret numbers. A pair of pixels is extracted from the original …image and used as the coordinates for the matrix. In the search domain at that coordinate position, the corresponding secret number is found, and the matrix coordinates of the secret information are used as the pixel value for the stego-image. This paper evaluates the security and effectiveness of CM through measures such as embedding capacity, peak signal-to-noise ratio (PSNR), and bit-plane analysis. CM achieves a maximum embedding capacity of 4.806 bits per pixel (bpp ) and maintains a PSNR value of more than 30 dB. Furthermore, the bit-plane analysis fails to detect the presence of the information hidden using CM method. Show more

Keywords: Information hiding, security, chunking matrix, block, stego-image

DOI: 10.3233/JIFS-234236

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2727-2741, 2024

Authors: Wang, Ling | Ni, Zhiyun

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-234582

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2743-2757, 2024

Authors: Sun, Haibin | Li, Zheng

Article Type: Research Article

Abstract: Millions of traffic accidents occur worldwide each year, resulting in tens of thousands of deaths. The primary cause is the distracted behavior of drivers during the driving process. If the distracted behaviors of drivers during driving can be detected and recognized in time, drivers can regulate their driving and the goal of reducing the number of traffic fatalities can be achieved. A deep learning model is proposed to detect driver distractions in this paper. The model can identify ten behaviors including one normal driving behavior and nine distracted driving behaviors. The proposed model consists of two modules. In the first …module, the cross-domain complementary learning (CDCL) algorithm is used to detect driver body parts in the input images, which reduces the impact of environmental factors in vehicles on the convolutional neural network. Then the output images of the first module are sent to the second module. The Resnet50 and Vanilla networks are ensembled in the second module, and then the driver behavior can be classified. The ensemble architecture used in the second module can reduce the sensitivity of only a single network on the data, and then the detection accuracy can be improved. Through the experiments, it can be seen that the proposed model in this paper can achieve an average accuracy of 99.0%. Show more

Keywords: Deep learning, neural networks, distracted behavior, ensemble learning, semantic segmentation

DOI: 10.3233/JIFS-234593

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2759-2773, 2024

Authors: Wang, Fang

Article Type: Research Article

Abstract: The rapid development of cultural tourism in recent years refers to a process of cultural experience of tourist objects with cultural characteristics. It can not only vigorously carry forward the rich and colorful history and cultural deposits, but also combine the huge economic and cultural benefits generated by tourism, and promote the rapid development of cultural construction. Cultural tourism is a kind of way that all kinds of social groups enjoy, and it is a deep and lasting way of communication, which can promote the communication between people of different social strata. The existing literature has explored the influence of …tourists’ psychological carrying capacity, but failed to explain the process and degree of influence. Based on behavioral and experience theories, this paper proposes that culture has a positive impact on tourists’ psychological carrying capacity through tourist experience, and tests relevant hypotheses. The primary psychological traits of historical and cultural tourists include curiosity about historical mysteries, the desire for historical knowledge, motivation to collect spiritual enrichment, academic interest in cultural heritage exploration, and an aesthetic appreciation for classical history. Key determinants include the scale and conservation of historical and cultural resources, their combination with natural attractions, and the personal qualities of tourists and the cultural competence of tour guides. The mental health care model combines tourism and psychology to facilitate both physical and mental well-being through professional psychological counseling services, aiding tourists in their recovery and self-healing. This integrated approach offers a broad scope and potential as an effective tool for addressing negative emotions, with demonstrated therapeutic effects focusing on psychological and social factors. Show more

Keywords: Role of psycho-occupational therapy, cultural tourism, tourists, mode of physical and mental recovery

DOI: 10.3233/JIFS-235010

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2775-2788, 2024

Authors: Zhaoxian, Ren | Min, Qu

Article Type: Research Article

Abstract: People’s demands for a higher quality of life are increasing, and furniture remains an essential part of daily life. In traditional furniture design methods, designers typically rely on their experience, leading to significant disparities between design solutions and user expectations. A comprehensive model is proposed with combination of Fuzzy KANO (FKANO) method, the Criteria Importance through Intercriteria Correlation (CRITIC) method, and the Coupling Coordination Degree (CCD) method for furniture design and evaluation, using desk design as an example. Firstly, FKANO model is applied to classify and filter user requirements, identifying crucial user needs as the basis for subsequent design. Secondly, …three desk design proposals that align with user requirements are formulated. Thirdly, the CRITIC method is introduced, using the filtered user requirements to construct an evaluation system and calculate the weights of various indicators. Lastly, the CCD method is applied to select the optimal desk design from five samples, including three designed by this study and two existing on the market. This comprehensive approach contains critical stages such as requirement identification, weight determination, and solution selection, achieving comprehensive research objectives. Besides, sensitivity analysis was conducted to validate the effectiveness of this integrated model, demonstrating its ability to balance different user requirements under different weight settings. The results indicate that the proposed approach enhances the scientific rigor, systematization, and user satisfaction of the furniture design and decision-making process. It offers valuable guidance for furniture manufacturers and designers, allowing furniture products to more effectively align with market demands, thus enhancing their competitiveness. Show more

Keywords: FKANO model, CRITIC method, CCD technique, design and evaluation, furniture design

DOI: 10.3233/JIFS-235272

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2789-2810, 2024

Authors: Tran-Anh, Dat | Nguyen Huu, Quynh | Nguyen Thi Phuong, Thao | Dao Thi Thuy, Quynh

Article Type: Research Article

Abstract: The wilting of leaves caused by disease poses risks to both harvest yield and the environment. Therefore, the timely detection of disease signs on leaves is crucial to enable farmers to prevent disease outbreaks and safeguard their crops. However, manually observing all diseased leaves on a large scale demands substantial time and human effort. In this study, we propose an effective method for automated disease detection on leaves. Specifically, this method utilizes images captured from mobile phones. The proposed technique combines four models (ensemble of models) with distinct features: (1) ResNeXt50 model with a high-quality image processing, (2) ViT model …with a low-quality image processing, (3) Efficientnet B5 model combines a self-learning with noisy input, and (4) Mobilenet V3 model with image segmentation. Experimental results demonstrate that the proposed method outperforms some of the state-of-the-art methods on TLU-Leaf dataset (ours) with F1-score of 90% and Cassava Leaf Disease dataset with F1-score of 87%. Show more

Keywords: Convolutional neural network, deep learning, multiple-model, leaf disease classification

DOI: 10.3233/JIFS-235940

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2811-2823, 2024

Authors: Hu, Huixian | Wang, Xiu | Li, Tian

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-236094

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2825-2834, 2024

Authors: Awodutire, Phillip Oluwatobi | Sule, Ibrahim

Article Type: Research Article

Abstract: In this work, a new family of distribution, which generalizes the Beta Weibull-G family by the introduction of a shape parameter to enhance better fit and flexibility, called the Modified Beta Weibull-G family of distributions is obtained. The mixture representation of the derived family of distributions was discussed, with the results effective in studying moments, moment generating functions, order statistics. Parameters of the family of distributions were estimated using the maximum likelihood estimation method. By utilizing this modified class of distributions, we build a new distribution called the modified beta Weibull Weibull and applied it to engineering datasets. Application revealed …a better performance in model fit, compared to some other distributions. Show more

Keywords: Modified Beta-G Distribution, Weibull-G, Modified Beta Weibull G distribution, estimation, real life data

DOI: 10.3233/JIFS-223042

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2835-2850, 2024

Authors: Che, Gaofeng | Yu, Zhen

Article Type: Research Article

Abstract: This work investigates trajectory-tacking control problem for underactuated autonomous underwater vehicles (AUV) with unknown dynamics. Due to the unknown dynamics, an action-critic networks based adaptive dynamic programming (ADP) scheme combined with backstepping approach is designed, which can achieve high-level system stability and tracking control accuracy. Firstly, the backstepping approach is introduced into the kinematic model of underactuated AUV and produces a virtual velocity control which is taken as the desired velocity input of the dynamic model of underactuated AUV. Secondly, the error tracking system is constructed according to the dynamic model of underactuated AUV. Thirdly, the critic neural network and …the action neural network are employed to transform the trajectory-tracking control problem into optimal control problem based on policy iteration algorithm. At last simulation results are given to verify the effectiveness of the proposed control scheme. Show more

Keywords: Adaptive dynamic programming (ADP), backstepping approach, tracking control, autonomous underwater vehicle (AUV)

DOI: 10.3233/JIFS-230232

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2851-2863, 2024

Authors: Xie, Tian-Tian | Wang, Rui-Ying

Article Type: Research Article

Abstract: Connectivity is one of the most essential notions in general topology. Convex structures are topological-like structures. Many properties in topological spaces have been generalized to convex structures, such as separation. However, connectivity has not been studied in convex structures yet. In this paper, firstly, based on the consideration to hull operators, separatedness is defined in classical convex structures, and then we provide the concept of connectivity. Secondly, some equivalent characterizations of connectivity are discussed, and we investigate the related properties of connectivity. In additional, through (L , M )-fuzzy convex hull operators, we propose the separatedness degrees of (L , …M )-fuzzy convex structures. Furthermore, the notion of connectedness degrees of (L , M )-fuzzy convex structures is introduced. Finally, many properties of connectivity in general convex structures can be generalized to (L , M )-fuzzy convex structures. Show more

Keywords: Convex structure, connectivity, (L, M)-fuzzy convex structure, separatedness degree, connectedness degree

DOI: 10.3233/JIFS-232309

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2865-2876, 2024

Authors: Yan, Guangzhou | Ni, Yaodong

Article Type: Research Article

Abstract: This paper studies the pricing and low-carbon decision problems in a supply chain containing a manufacturer and a downstream retailer. The manufacturer produces a single product under the cap-and-trade scheme. We formulate the price and carbon-concerned demand function. To maximize their revenue, the manufacturer and the retailer determine their selling prices and carbon emission reduction rates separately. Due to the fast product updates speed, some parameters do not have enough historical data. For example, the sales cost of the retailer, the demand of consumers, and the total carbon emissions of manufacturers are far from frequency stability. This fact makes the …distribution function obtained in practice usually deviate from the frequency. They are all uncertain variables whose distributions are estimated from the empirical data of experts or managers. In this paper, we give three decentralized game models to explore the equilibrium behaviors in the corresponding decision environment under an uncertain environment. Corresponding analytical solutions are offered under different game scenarios. Finally, numerical experiments are performed to illustrate the effectiveness of the established models and yield some remarkable insights. Show more

Keywords: Supply chain management, Pricing decision, Cap-and-trade, Low-carbon, Stackelberg game

DOI: 10.3233/JIFS-232607

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2877-2897, 2024

Authors: Li, Shi | Zhang, Yongkang

Article Type: Research Article

Abstract: Entity linking is an important task for information retrieval and knowledge graph construction. Most existing methods use a bi-encoder structure to encode mentions and entities in the same space, and learn contextual features for entity linking. However, this type of system still faces some problems: (1) the entity embedding part of the model only learns from the local context of the target entity, which is too unique for entity linking model to learn the context commonality of information; (2) the entity disambiguation part only uses similarity calculation once to determine the target entity, resulting in insufficient interaction between the mentions …and candidate entities, and ineffective recall of real entities. We propose a new entity linking model based on graph neural network. Different from other bi-encoder retrieval systems, this paper introduces a fine-grained semantic enhancement information into the entity embedding part of the bi-encoder to reduce the specificity of the model. Then, the cross-attention encoder is used to re-rank the target mention and each candidate entity after the entity retrieval model. Experimental results show that although the model is not optimal in inference speed, it outperforms all baseline methods on the AIDA-CoNLL dataset, and has good generalization effects on four datasets in different fields such as MSNBC and ACE2004. Show more

Keywords: Entity linking, semanic reinforcement, cross-attention mechanism, graph convolutional network

DOI: 10.3233/JIFS-233124

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2899-2910, 2024

Authors: Dineshkumar, R. | Alphy, Anna | Kalaivanan, C. | Bashkaran, K. | Pattanaik, Balachandra | Logeswaran, T. | Saranya, K. | Deivasikamani, Ganeshkumar | Johny Renoald, A.

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-233263

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2911-2927, 2024

Authors: Jiang, Jianming | Ban, Yandong | Li, Jiayi | Zhou, Yane

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-234205

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2929-2939, 2024

Authors: Sri Vinitha, V. | Renuka, D. Karthika

Article Type: Research Article

Abstract: Spam Email is a serious concern which can steal user’s personal information and cause huge financial loss due to the increasing rate of internet users. Therefore, the demand for accurate spam filtering has become more sophisticated for the Email spam detection. In the existing techniques, it is difficult to intricate the relationship between words in the Email using certain word embedding techniques and learning rate tuning is one of the greatest challenges of stochastic optimization. To overcome this difficulty, the proposed framework uses diverse ensemble based Email spam classification by incorporating multiple word embedding’s with Continuous Coin Betting optimizer. Word2Vec …is used to produce the first set of 200D, next set of 200D word embedding is produced by Glove and 768D is produced by using Bidirectional Encoder Representations from Transformers (BERT) respectively. After generating word embedding, then it is classified through diverse ensemble based classifier with base level classifier consists of Long Short Term Memory (LSTM) Networks, Gated Recurrent Unit (GRU) and Bi-directional Gated Recurrent Unit (Bi-GRU) and LSTM as Meta-classifier using COCOB optimizer. Experiments were conducted on 3 benchmark Email dataset and result shows that the proposed system outperforms well with a low false positive rate. Show more

Keywords: Word2Vec, bidirectional encoder representations from transformers, global vectors, gated recurrent unit, bi-directional gated recurrent unit, long short term memory, continuous coin betting

DOI: 10.3233/JIFS-235464

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2941-2954, 2024

Authors: Hu, Kuang-Hua | Chen, Fu-Hsiang | Zeng, Jhih-Hong | Lin, Sin-Jin

Article Type: Research Article

Abstract: Blockchain technology holds considerable amount of potential for all types of industries by executing transactions in a verifiable, efficient, and permanent channel. It has been widely viewed as a standard requirement for making industry ready for the future, but when it comes to practical applications, it still arouses numerous risks/challenges that need to be addressed. Therefore, it is essential to address this gap and establish a comprehensive and effective practical framework to align the information technology revolution with sustainable value creation. The purpose of this research is to realize to what extent an enterprise legacy system’s transformation benefits a blockchain-based …system and to minimize its specific risk through a hybrid fuzzy MRDM (multiple rule-based decision making) model that integrates data envelopment analysis with rough set theory (DEA-RST) and the fuzzy DEMATEL approach grounded on a questionnaire derived from domain experts. We aim to point out the inherent risks of blockchain-based technology adoption and to assist senior engineers in designing or adopting a suitable architecture for practical operation and planning of any future integration and development. The potential risk evaluation of business blockchain adoption reveals that the priority improvement sequence based on dimensions is smart contract risk, value transfer risk, and standard risk. Furthermore, law and regulation are the most critical criteria. Show more

Keywords: Blockchain-based technology adoption risk, decision making, multiple rule-based decision making, data envelopment analysis, risk management

DOI: 10.3233/JIFS-223381

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2955-2969, 2024

Authors: Li, Dan | Chen, Ming | Peng, Kaixiang | Wu, Libing

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-231664

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2971-2979, 2024

Authors: Khatun, Jasminara | Amanathulla, Sk | Pal, Madhumangal

Article Type: Research Article

Abstract: In the realm of handling imprecise information, picture fuzzy cubic sets have emerged as a more versatile tool compared to cubic sets, cubic intuitionistic fuzzy sets, and similar models. These sets offer better adaptability, precision and compatibility with the system than existing fuzzy models. This paper extends the concept of picture fuzzy cubic sets to the domain of graph theory, introducing the novel concept of picture fuzzy cubic graphs that surpasses previous results in terms of generality. The paper explores various essential operations, including composition, the Cartesian product, P -join, R -join, P -union, R -union of picture fuzzy cubic …graphs. It also investigates the order and degree of picture fuzzy cubic graphs. Furthermore, this work presents two practical applications of picture fuzzy cubic graphs. The first application involves computing the impact of other companies on a specific company and the second application focuses on evaluating the overall impact within a group of companies. Show more

Keywords: Picture fuzzy cubic set, picture fuzzy cubic graph, R-union, R-join

DOI: 10.3233/JIFS-232523

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2981-2998, 2024

Authors: Mutar, Emad Kareem

Article Type: Research Article

Abstract: In reliability analysis, the structure-function is a commonly used mathematical representation of the studied system. A signature vector is used for systems with independently and identically distributed (i.i.d.) component lifetimes. Each element in the signature represents the probability that the failure of the corresponding component will fail the entire system. This paper aims to provide a comprehensive understanding of assessing the performance of two complex systems for optimal communication design. The study compares two systems with the same components using signatures, expected cost rate, survival signature, and sensitivity to determine which system is preferred. It also provides several sufficient conditions …for comparing the lifetimes of two systems based on the usual stochastic order. The results are applied to two communication systems that have the same components. The mathematical properties presented in the study have been proven to enable efficient weighting of the optimal design. Show more

Keywords: Coherent system, signature, survival signature, sensitivity, stochastic order

DOI: 10.3233/JIFS-234456

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 2999-3011, 2024

Authors: Peng, Yaxin | Yang, Keni | Zhao, Fangrong | Shen, Chaomin | Zhang, Yangchun

Article Type: Research Article

Abstract: Domain adaptation solves the challenge of inadequate labeled samples in the target domain by leveraging the knowledge learned from the labeled source domain. Most existing approaches aim to reduce the domain shift by performing some coarse alignments such as domain-wise alignment and class-wise alignment. To circumvent the limitation, we propose a coarse-to-fine unsupervised domain adaptation method based on metric learning, which can fully utilize more geometric structure and sample-wise information to obtain a finer alignment. The main advantages of our approach lie in four aspects: (1) it employs a structure-preserving algorithm to automatically select the optimal subspace dimension on the …Grassmannian manifold; (2) based on coarse distribution alignment using maximum mean discrepancy, it utilizes the smooth triplet loss to leverage the supervision information of samples to improve the discrimination of data; (3) it introduces structure regularization to preserve the geometry of samples; (4) it designs a graph-based sample reweighting method to adjust the weight of each source domain sample in the cross-domain task. Extensive experiments on several public datasets demonstrate that our method achieves remarkable superiority over several competitive methods (more than 1.5% improvement of the average classification accuracy over the best baseline). Show more

Keywords: Domain adaptation, metric learning, triplet loss, structure regularization, sample reweighting

DOI: 10.3233/JIFS-235912

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 3013-3027, 2024

Authors: Zekrifa, Djabeur Mohamed Seifeddine | Saravanakumar, R. | Nair, Sruthi | Pachiappan, Krishnagandhi | Vetrithangam, D. | Kalavathi Devi, T. | Ganesan, T. | Rajendiran, M. | Rukmani Devi, S.

Article Type: Research Article

Abstract: The increasing need for effective energy storage solutions has led to the prominence of lithium-ion batteries as a crucial technology across multiple industries. The proficient administration of these batteries is imperative in order to guarantee maximum efficiency, prolong their longevity, and uphold safety measures. This study presents a novel methodology for enhancing battery management systems (BMS) through the integration of cloud-based solutions, artificial intelligence (AI), and machine learning approaches. In this study, we present a conceptual framework that utilises cloud computing to augment the practical functionalities of battery management systems (BMS) specifically in the context of lithium-ion batteries. The incorporation …of cloud computing facilitates the implementation of scalable data storage, remote monitoring, and processing resources, hence enabling the execution of real-time analysis and decision-making processes. By leveraging the capabilities of machine learning and artificial intelligence, our methodology focuses on addressing crucial battery metrics, including the state of charge (SoC) and state of health (SoH). Through the ongoing collection and analysis of data obtained from battery systems that are deployed in real-world settings, the framework iteratively improves its predictive models, hence facilitating precise assessment of battery states. Ensuring safety is a crucial element in the management of batteries. The solution we propose utilises anomaly detection algorithms driven by artificial intelligence to detect potential safety issues, facilitating prompt responses and mitigating dangerous circumstances. In order to showcase the efficacy of our methodology, we offer practical implementations in several industries, encompassing the integration of renewable energy, use of electric vehicles, and optimisation of industrial processes. Through the utilisation of cloud-based machine learning techniques, we are able to enhance the efficiency of energy storage and consumption, while simultaneously enhancing the dependability and security of battery systems. This study highlights the potential of the proposed framework to revolutionise battery management paradigms, thereby guaranteeing secure and efficient energy prospects for a sustainable future. Show more

Keywords: Battery management system, state of health, state of charge, artificial intelligence, machine learning, cloud-based solutions

DOI: 10.3233/JIFS-236391

Citation: Journal of Intelligent & Fuzzy Systems, vol. 46, no. 1, pp. 3029-3043, 2024