International Journal of Intelligent Systems最新文献

{"title":"A Protecting-Privacy Path Query Supporting Semantic-Based Multikeyword Search Over Ciphertext Graph Data in Cloud Computing","authors":"Bin Wu,&nbsp;Zhuolin Mei,&nbsp;Jiaoli Shi,&nbsp;Zongmin Cui,&nbsp;Zhiqiang Zhao,&nbsp;Jinzhou Huang","doi":"10.1155/int/8819489","DOIUrl":"https://doi.org/10.1155/int/8819489","url":null,"abstract":"<div>\u0000 <p>With the rapid development of information technology and intelligence, there are more and more usage scenarios of graph data. Path queries have always been a hot topic of research for scholars. There are already many mature methods and ideas in the study of the path query on the plaintext graph. For the path query on graph data in the case of cloud outsourcing, it is necessary to consider both the construction of query algorithms and the protection of privacy information. The processing of graph privacy information through encryption, and then outsourcing to the cloud platform, is a common measure. The semantic-based path query supporting multikeyword search is an extended path query method, which can improve the query function. For users, it is very troublesome to access and process the encrypted graph data. In this article, we propose a protecting-privacy semantic-based multikeyword path query scheme on the ciphertext graph (PSMP). Firstly, based on the principle of searchable encryption and vector operation, a secure index is constructed, and then the cloud server uses the secure index to implement path queries. This article demonstrates its security through formal analysis and verifies its effectiveness through experimental comparison and analysis. The work of this article has a certain promoting effect on the query processing and analysis of ciphertext graph data.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/8819489","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143949974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Consensus Mechanisms in Blockchain: A Comprehensive Review","authors":"Ali Ahmed Al-awamy,&nbsp;Nagi Al-shaibany,&nbsp;Axel Sikora,&nbsp;Dominik Welte","doi":"10.1155/int/5821997","DOIUrl":"https://doi.org/10.1155/int/5821997","url":null,"abstract":"<div>\u0000 <p>Blockchain technology, renowned for its foundational attributes of decentralization, security, and immutability, offers substantial potential for diverse applications. At the heart of blockchain functionality are consensus mechanisms, crucial for preserving the decentralized integrity of the network. However, traditional consensus algorithms like Proof of Work (PoW), Proof of Stake (PoS), and Byzantine Fault Tolerance (BFT) typically require significant computational and communication resources, which may not be feasible for resource-limited environments. The purpose of this paper is to explore hybrid consensus algorithms that integrate conventional consensus mechanisms with advanced nonlinear data structures. We comprehensively analyze a wide range of hybrid consensus mechanisms, emphasizing their architectural design, operational efficiencies, and ability to address both consensus-specific vulnerabilities and network-level threats, such as Sybil attacks, double-spending, and partitioning attacks. To achieve this, we employ a set of comprehensive evaluation criteria for blockchain technologies, namely, validation, IoT, real-time processing, application suitability, security, and implementation. These criteria help assess the adaptability and efficacy of each mechanism in diverse operational contexts. Through this examination, the paper seeks to illuminate the significant contributions and implications of hybrid consensus mechanisms, guiding stakeholders, researchers, and developers toward making informed decisions about optimizing blockchain technology for their specific needs and inspiring the development of innovative solutions.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5821997","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143930291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Collaborative Integration of Vehicle and Roadside Infrastructure Sensor for Temporal Dependency-Aware Task Offloading in the Internet of Vehicles","authors":"Kaiyue Luo,&nbsp;Yumei Wang,&nbsp;Yu Liu,&nbsp;Konglin Zhu","doi":"10.1155/int/8064086","DOIUrl":"https://doi.org/10.1155/int/8064086","url":null,"abstract":"<div>\u0000 <p>With advancements of in-vehicle computing and Multi-access Edge Computing (MEC), the Internet of Vehicles (IoV) is increasingly capable of supporting Vehicle-oriented Edge Intelligence (VEI) applications, such as autonomous driving and Intelligent Transportation Systems (ITSs). However, IoV systems that rely solely on vehicular sensors often encounter limitations in forecasting events beyond current roadways, which are critical for regional transportation management. Moreover, the inherent temporal dependency in VEI application data poses risks of interruptions, impeding the seamless tracking of incremental information. To address these challenges, this paper introduces a joint task offloading and resource allocation strategy within an MEC environment that collaboratively integrates vehicles and Roadside Infrastructure Sensors (RISs). The strategy carefully considers the Doppler shift from vehicle mobility and the Tolerance for Interruptions of Incremental Information (T3I) in VEI applications. We establish a decision-making framework that actively balances delay, energy consumption, and the T3I metric by formulating the task offloading as a stochastic network optimization problem. Utilizing Lyapunov optimization, we dissect this complex problem into three targeted subproblems that include optimizing local computational capacity, MEC computational capacity and comprehensive offloading decisions. To tackle the efficient offloading, we develop algorithms that separately optimize offloading scheduling, channel allocation and transmission power control. Notably, we incorporate a Potential Minimum Point (PMP) algorithm to boost parallel processing and simplify computational scale through matrix decomposition. Evaluations of our algorithm show that it excels in both complexity and accuracy, with accuracy improvements ranging from 74.3% to 114.0% in asymmetric resource environments. Simulation and experimental studies on offloading performance validate the effectiveness of our framework, which significantly balances network performance, reduces latency, and improves system stability.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/8064086","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143930294","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Attack and Defense Researches on the Dual-Layer Network of Multivariable Anomaly Causes","authors":"Jiaxin Han,&nbsp;Rui Zhang,&nbsp;Zhonglin Ye,&nbsp;Xuanrong Huo,&nbsp;Yuzhi Xiao,&nbsp;Yuhui Zheng","doi":"10.1155/int/1522150","DOIUrl":"https://doi.org/10.1155/int/1522150","url":null,"abstract":"<div>\u0000 <p>Multivariate anomaly causes interpretation provides insight into the root cause of information system anomalies, identifying the direct factors that trigger anomalies and revealing potential systemic flaws. However, current research generally focuses on two directions: on the one hand, anomaly diagnosis research for nodes with high anomaly degree; on the other hand, single-layer anomaly causes interpretation graph construction based on explicit features capturing anomaly locations and their neighborhood structures. These approaches pay insufficient attention to the attack defense of anomaly causes interpretation graph, thereby weakening the credibility and reliability of anomaly causation interpretation. Therefore, we systematically explore the attack strategy and defense mechanism of the multivariate anomaly causes interpretation graph. Firstly, we propose an adaptive learning method for constructing a dual-layer anomaly causes interpretation graph. The method reduces the dependence on artificial a priori assumptions by introducing an adaptive mechanism and realizes the dynamic decoupling of the spatiotemporal coupling relationships of multivariate data, thus providing a diversified perspective for the multivariate anomaly causes interpretation. Second, considering the vulnerability of the multivariate spatiotemporal correlation after decoupling and the structural characteristics of the dual-layer anomaly causes interpretation graph, we further propose a structural protection mechanism based on dual-layer complex networks to improve the structural robustness and resistance to the interference of anomaly causes interpretation graph. Finally, we verify the effectiveness of the proposed model by testing various attack defense scenarios such as noise attack, gradient attack, and structure attack. The experimental results show that the model in this paper can effectively defend against multiple attack methods and ensure the integrity and reliability of the anomaly causes interpretation graph.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1522150","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143904901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Evolutionary Game Model for Green Production Decisions of Supply Chain Enterprises Considering Supply Chain Break Risk","authors":"Fulei Shi,&nbsp;Chuansheng Wang,&nbsp;Zhenfang Qin","doi":"10.1155/int/4329215","DOIUrl":"https://doi.org/10.1155/int/4329215","url":null,"abstract":"<div>\u0000 <p>The problem of environmental pollution has been extensively discussed, especially in the production phase of the supply chain. Many enterprises seek innovation and strive to achieve a win-win situation of economic and environmental benefits. However, the cooperation and competition between enterprises are likely to cause the interruption of the supply chain. Therefore, by combining the green production strategy with supply chain risk management, this paper builds an evolutionary game model between suppliers and manufacturers, to deeply understand the impact of supply chain disruption on the choice of the green production strategy by suppliers and manufacturers and reveal the conditions under which the system evolves into different stability strategies. The results show that (1) under different conditions, the system will have an evolutionarily stable strategy. When the total revenue of green production alone by the supplier or manufacturer is greater than the expenditure and the cost of supply chain disruption is greater than the difference between the investment cost of green production and the total revenue of green production alone, the system will produce two different evolution results. (2) The cooperation willingness of the supplier and manufacturer, the investment cost of green production, and the risk coefficient of supply chain break will all affect the evolution trajectory of the system, and the greater the absolute difference between these factors and the threshold, the faster the system convergence speed. By formulating relevant policies, the system can meet the conditions of evolutionary stability strategy (1, 1), which can promote the upstream and downstream enterprises of the supply chain to realize cooperative green production faster. This paper contributes to the understanding of green supply chain management and evolutionary game theory, while providing insights into how companies along the supply chain can achieve cooperative green production for the benefit of society and the environment.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/4329215","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143897221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced Multidimensional Nonlinear Correlation via Phase Reconstruction and Broad Learning for Distributed Fusion Detection of Weak Pulse Signals","authors":"Liyun Su,&nbsp;Xuelian Long","doi":"10.1155/int/8827255","DOIUrl":"https://doi.org/10.1155/int/8827255","url":null,"abstract":"<div>\u0000 <p>Due to the intricate chaotic environments encountered in distributed sensor applications, such as sea monitoring, machinery fault diagnosis, and EEG weak signal detection, neural networks often face insufficient data to effectively carry out detection tasks. In contrast to traditional machine learning models, a statistical approach employing multidimensional nonlinear correlation (MNC) exhibits an unparalleled signal pattern prediction capability and possesses a streamlined yet robust framework for signal processing. However, the direct application of MNC to weak pulse signal detection remains constrained. To surmount these challenges and achieve high-precision signal detection, we explore a novel MNC approach, integrating phase reconstruction and manifold broad learning, specifically tailored for distributed sensor fusion detection amidst chaotic noise. Initially, the distributed observational data undergoes phase space reconstruction, transforming it into fixed-size arrays. These reconstructed tuples are then processed through the high-dimensional sequence of manifold broad learning, serving as inputs for the nonlinear correlation module to extract spatiotemporal features. Subsequently, a MNC system augmented with a QRS detector layer is devised to predict and classify the presence of a weak pulse signal. This integrated MNC approach, combining phase reconstruction and broad learning, operates within an enhanced feature space of the source domain, realizing detection fusion across distributed sensors through a majority voting principle. Simulation studies and experiments conducted on sea clutter datasets demonstrate the efficacy and robustness of the proposed MNC method, leveraging phase reconstruction and manifold broad learning strategies, for distributed sensor weak pulse signal fusion detection within chaotic backgrounds.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/8827255","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143900955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable Deep Learning for Classifying Skin Lesions","authors":"Mojeed Opeyemi Oyedeji,&nbsp;Emmanuel Okafor,&nbsp;Hussein Samma,&nbsp;Motaz Alfarraj","doi":"10.1155/int/2751767","DOIUrl":"https://doi.org/10.1155/int/2751767","url":null,"abstract":"<div>\u0000 <p>The global prevalence of skin cancer necessitates the development of AI-assisted technologies for accurate and interpretable diagnosis of skin lesions. This study presents a novel deep learning framework for enhancing the interpretability and reliability of skin lesion predictions from clinical images, which are more inclusive, accessible, and representative of real-world conditions than dermoscopic images. We comprehensively analyzed 13 deep learning models from four main convolutional neural network architecture classes: DenseNet, ResNet, MobileNet, and EfficientNet. Different data augmentation strategies and model optimization algorithms were explored to access the performances of the deep learning models in binary and multiclass classification scenarios. In binary classification, the DenseNet-161 model, initialized with random weights, obtained a top accuracy of 79.40%, while the EfficientNet-B7 model, initialized with pretrained weights from ImageNet, reached an accuracy of 85.80%. Furthermore, in the multiclass classification experiments, DenseNet121, initialized with random weights and trained with AdamW, obtained the best accuracy of 65.1%. Likewise, when initialized with pretrained weights, the DenseNet121 model attained a top accuracy of 75.07% in multiclass classification. Detailed interpretability analyses were carried out leveraging the SHAP and CAM algorithms to provide insights into the decision rationale of the investigated models. The SHAP algorithm was beneficial in understanding the feature attributions by visualizing how specific regions of the input image influenced the model predictions. Our study emphasizes using clinical images for developing AI algorithms for skin lesion diagnosis, highlighting the practicality and relevance in real-world applications, especially where dermoscopic tools are not readily accessible. Beyond accessibility, these developments also ensure that AI-assisted diagnostic tools are deployed in diverse clinical settings, thus promoting inclusiveness and ultimately improving early detection and treatment of skin cancers.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2751767","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analyzing and Detecting Abnormal Behaviors of Drug Abuse and Addiction Users in School Environments Based on Deep Learning Approaches","authors":"Salma Kammoun Jarraya,&nbsp;Marwa Masmoudi,&nbsp;Fahad Abdullah Alqurashi,&nbsp;Sultanah M. Alshammari","doi":"10.1155/int/9722173","DOIUrl":"https://doi.org/10.1155/int/9722173","url":null,"abstract":"<div>\u0000 <p>Drug abuse and addiction problems are one of the most serious health, social, and psychological problems facing the world. Many international studies indicate that the start of drug abuse occurs mostly in adolescence, which is the period that young people spend in schools, institutes, and universities. Drugs in the student community have become a scourge that raises increasing concern, whether among families or educators, over the fate of school children and educational attainment. Regarding their behaviors, an addicted student often exhibits abnormal behaviors such as permanent lethargy, anxiety, tremors, and aggressive behavior toward others. Moreover, to obtain drugs, the addicted student becomes compelled to resort to various means and ways, and they gradually become criminal addicts. To this endeavor, a detector of abnormal behaviors in schools has become a necessity. In this paper, we built an automatic system able to analyze and detect abnormal behaviors of addicted students and inform the educational staff and parents to know how to manage and treat them. On a technical level, we used deep learning and the recent computer vision techniques in the suggested solution due to their contributions to human behavior and emotion recognition fields. The best-recorded result (97.5%) is obtained with fused handcrafted features based on skeleton joints and deep features extracted with the MobileNet pretrained model and forwarded to a deep proposed network based on two TimeDistributed layers, one BiLSTM layer, and several Dense layers.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/9722173","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143884038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MalFSLDF: A Few-Shot Learning-Based Malware Family Detection Framework","authors":"Wenjie Guo,&nbsp;Jingfeng Xue,&nbsp;Yuxin Lin,&nbsp;Wenbiao Du,&nbsp;Jingjing Hu,&nbsp;Ning Shi,&nbsp;Weijie Han","doi":"10.1155/int/7390905","DOIUrl":"https://doi.org/10.1155/int/7390905","url":null,"abstract":"<div>\u0000 <p>The evolution of malware has led to the development of increasingly sophisticated evasion techniques, significantly escalating the challenges for researchers in obtaining and labeling new instances for analysis. Conventional deep learning detection approaches struggle to identify new malware variants with limited sample availability. Recently, researchers have proposed few-shot detection models to address the above issues. However, existing studies predominantly focus on model-level improvements, overlooking the potential of domain adaptation to leverage the unique characteristics of malware. Motivated by these challenges, we propose a few-shot learning-based malware family detection framework (MalFSLDF). We introduce a novel method for malware representation using structural features and a feature fusion strategy. Specifically, our framework employs contrastive learning to capture the unique textural features of malware families, enhancing the identification capability for novel malware variants. In addition, we integrate entropy graphs (EGs) and gray-level co-occurrence matrices (GLCMs) into the feature fusion strategy to enrich sample representations and mitigate information loss. Furthermore, a domain alignment strategy is proposed to adjust the feature distribution of samples from new classes, enhancing the model’s generalization performance. Finally, comprehensive evaluations of the MaleVis and BIG-2015 datasets show significant performance improvements in both 5-way 1-shot and 5-way 5-shot scenarios, demonstrating the effectiveness of the proposed framework.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/7390905","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Emotion Recognition System for Human–Robot Interaction (HRI) Using Deep Ensemble Classification","authors":"Khalid Zaman,&nbsp;Gan Zengkang,&nbsp;Sun Zhaoyun,&nbsp;Sayyed Mudassar Shah,&nbsp;Waqar Riaz,&nbsp;Jiancheng (Charles) Ji,&nbsp;Tariq Hussain,&nbsp;Razaz Waheeb Attar","doi":"10.1155/int/6611276","DOIUrl":"https://doi.org/10.1155/int/6611276","url":null,"abstract":"<div>\u0000 <p>Human emotion recognition (HER) has rapidly advanced, with applications in intelligent customer service, adaptive system training, human–robot interaction (HRI), and mental health monitoring. HER’s primary goal is to accurately recognize and classify emotions from digital inputs. Emotion recognition (ER) and feature extraction have long been core elements of HER, with deep neural networks (DNNs), particularly convolutional neural networks (CNNs), playing a critical role due to their superior visual feature extraction capabilities. This study proposes improving HER by integrating EfficientNet with transfer learning (TL) to train CNNs. Initially, an efficient R-CNN accurately recognizes faces in online and offline videos. The ensemble classification model is trained by combining features from four CNN models using feature pooling. The novel VGG-19 block is used to enhance the Faster R-CNN learning block, boosting face recognition efficiency and accuracy. The model benefits from fully connected mean pooling, dense pooling, and global dropout layers, solving the evanescent gradient issue. Tested on CK+, FER-2013, and the custom novel HER dataset (HERD), the approach shows significant accuracy improvements, reaching 89.23% (CK+), 94.36% (FER-2013), and 97.01% (HERD), proving its robustness and effectiveness.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6611276","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}