Expert Systems最新文献

{"title":"Accelerated Artificial Bee Colony Optimization for Cost-Sensitive Neural Networks in Multi-Class Problems","authors":"Hilal Hacilar,&nbsp;Bilge Kagan Dedeturk,&nbsp;Mihrimah Ozmen,&nbsp;Mehlika Eraslan Celik,&nbsp;Vehbi Cagri Gungor","doi":"10.1111/exsy.70045","DOIUrl":"https://doi.org/10.1111/exsy.70045","url":null,"abstract":"<p>Metaheuristics are advanced problem-solving techniques that develop efficient algorithms to address complex challenges, while neural networks are algorithms inspired by the structure and function of the human brain. Combining these approaches enables the resolution of complex optimization problems that traditional methods struggle to solve. This study presents a novel approach integrating the ABC algorithm with ANNs for weight optimization. The method is further enhanced by vectorization and parallelization techniques on both CPU and GPU to improve computational efficiency. Additionally, this study introduces a cost-sensitive fitness function tailored for multi-class classification to optimize results by considering relationships between target class levels. It validates these advancements in two critical applications: network intrusion detection and earthquake damage estimation. Notably, this study makes a significant contribution to earthquake damage assessment by leveraging machine learning algorithms and metaheuristics to enhance predictive models and decision-making in disaster response. By addressing the dynamic nature of earthquake damage, this research fills a critical gap in existing models and broadens the understanding of how machine learning and metaheuristics can improve disaster response strategies. In both domains, the ABC-ANN implementation yields promising results, particularly in earthquake damage estimation, where the cost-sensitive approach demonstrates satisfactory outcomes in macro-F1 and accuracy. The best results for macro-F1, weighted-F1, and overall accuracy provides best results with the UNSW-NB15 and earthquake datasets, showing values of 64%, 72%, 68%, and 60%, 80%, and 79%, respectively. Comparative performance evaluations reveal that the proposed parallel ABC-ANN model, incorporating the novel cost-sensitive fitness function and enhanced by vectorization and parallelization techniques, significantly reduces training time and outperforms state-of-the-art methods in terms of macro-F1 and accuracy in both network intrusion detection and earthquake damage estimation.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70045","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143809524","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"HiSum: Hierarchical Topic-Driven Approach for Role-Oriented Dialogue Summarisation","authors":"Keyan Jin,&nbsp;Yapeng Wang,&nbsp;Xu Yang,&nbsp;Sio Kei Im","doi":"10.1111/exsy.70043","DOIUrl":"https://doi.org/10.1111/exsy.70043","url":null,"abstract":"<div>\u0000 \u0000 <p>As the volume of information on online communication platforms continues to grow, the task of dialogue summarisation becomes increasingly critical for understanding and extracting key information from diverse conversations. Traditional approaches often struggle to cope with the dynamic nature of dialogues, such as managing perspectives from multiple speakers and seamlessly transitioning between different topics. We propose a novel hierarchical topic-driven approach to generate role-oriented dialogue summarisation (HiSum) to address these challenges. First, we utilise VarGMM clustering technology for in-depth topic segmentation, which enables the model to capture the key topics in a dialogue. Second, we employ a LayerAttn hierarchical attention mechanism to dynamically adjust the focus of dialogue content based on participants' importance and the topics' relevance. Experimental results on three public dialogue summarisation data sets (CSDS, MC and SAMSUM) demonstrate that our method significantly outperforms most existing strong baseline methods across various evaluation metrics and surpasses the current state-of-the-art methods in certain metrics. Detailed analysis demonstrates that HiSum can perform more precise topic segmentation and effectively identify critical information. Our code is publicly available at: https://github.com/kjin0119/HiSum.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143818397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Continual Learning and Adaptive Sensing State Response-Based Target Recognition and Long-Term Tracking Framework for Smart Industrial Applications","authors":"Lu Chen,&nbsp;Gun Li,&nbsp;Jie Tan,&nbsp;Yang Li,&nbsp;Shenbing Fu,&nbsp;Haoyuan Ma,&nbsp;Yu Liu,&nbsp;Yuhao Yang,&nbsp;Weizhong Qian,&nbsp;Qinsheng Zhu,&nbsp;Amir Hussain","doi":"10.1111/exsy.70037","DOIUrl":"https://doi.org/10.1111/exsy.70037","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Purpose</h3>\u0000 \u0000 <p>With the rapid development of artificial intelligence technology, highly intelligent and unmanned factories have become an important trend. In the complex environments of smart factories, the long-term tracking and inspection of specified targets, such as operators and special products, as well as comprehensive visual recognition and decision-making capabilities throughout the whole production process, are critical components of automated unmanned factories. However, challenges such as target occlusion and disappearance frequently occur, complicating long-term tracking. Currently, there is limited research specifically focused on developing robust and comprehensive long-term visual tracking frameworks for unmanned factories, particularly those designed to integrate with embedded platforms and overcome various challenges.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We first construct three new benchmark datasets in the complex workshop environment of a smart factory (referred to as SF-Complex3 data), which include challenging conditions such as complete occlusion and partial occlusion of targets. A brain memory-inspired approach is used to determine uncertainty estimation parameters, including confidence, peak-to-sidelobe ratio and average peak-to-correlation energy, to develop a continual learning-based adaptive model update method. Additionally, we design a lightweight target detection model to automatically detect and locate targets in the initial frame and during re-detection. Finally, we integrate the algorithm with ground mobile robots and unmanned aerial vehicles-based imaging and processing equipment to build a new visual detection and tracking framework, smart factory complex recognition and tracking.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>We conducted extensive tests on the benchmark UAV20L and SF-Complex3 datasets. The proposed algorithm demonstrates an average performance improvement of 6% when addressing key challenging attributes, compared to state-of-the-art tracking methods. Additionally, the algorithm was capable of running efficiently on embedded platforms, including mobile robots and UAVs, at a real-time speed of 36.4 frames per second.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>The proposed SFC-RT framework effectively addresses the challenges of target loss and occlusion in long-term tracking within complex smart factory environments. The framework meets the requirements for real-time performance, robustness and lightweight design, making it well suited for practical deployment.</p>\u0000 </section>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143793496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Improved Grid Clustering Algorithm for Geographic Data Mining","authors":"Honglei He","doi":"10.1111/exsy.70042","DOIUrl":"https://doi.org/10.1111/exsy.70042","url":null,"abstract":"<div>\u0000 \u0000 <p>Grid clustering is a classical clustering algorithm with the advantage of lower time complexity, which is suitable for the analysis of large geographic data. However, it is sensitive to the grid division parameter <i>M</i> and density threshold <i>R</i>, and the clustering accuracy is poor. The article proposes a hybrid clustering algorithm HCA-BGP based on grid and division. the algorithm first uses grid clustering to obtain the core part of the class family, and then uses the division-based method to obtain the edge part of the class family. Through experiments on simulated datasets and real geographic datasets, it is proved to have better results than the existing grid clustering as well as some other classical algorithms. In terms of clustering accuracy, compared with the classical grid clustering algorithm Clique, the clustering F-value of this paper's algorithm is improved by 20.3% on dataset S1, 81.8% on dataset R15, and 7.6% on average on the eight geographic datasets. In terms of the sensitivity of parameters <i>M</i> and <i>R</i>, compared with Clique, the variance of the clustered F-value of this paper's algorithm is reduced by 89.3% on dataset S1; the variance of the clustered ARI is reduced by 99.9% on the real geographic dataset Data8. Compared to another grid-based clustering algorithm, GDB, HCA-BGP also demonstrates significant advantages.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143740975","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Dual Indicator Ranking Method for Complexly Constrained Multi-Objective Optimization","authors":"Qian Zeng,&nbsp;Hai-Lin Liu","doi":"10.1111/exsy.70046","DOIUrl":"https://doi.org/10.1111/exsy.70046","url":null,"abstract":"<div>\u0000 \u0000 <p>Addressing multi-objective optimization problems (MOPs) with complex constraints presents a significant challenge due to their diverse nature. While existing algorithms can effectively handle specific types of complex constraints, they often struggle with a variety of such constraints. To address this issue, we propose an innovative evolutionary algorithm for constrained multi-objective optimization. A key feature is the integration of a novel differential operator that generates offspring based on the presence of feasible solutions within the main population. This strategy is particularly effective for handling complex constraints characterised by small feasible spaces and deceptive infeasible regions. Additionally, the algorithm employs a dual-indicator ranking mechanism to evaluate and select individuals from the auxiliary population based on the quality and quantity of feasible solutions generated by the main population. Promising individuals are then migrated back to the main population, thereby enhancing the exploration of the solution space. This approach demonstrates significant superiority in solving MOPs with discontinuous feasible regions or extensive infeasible areas. Empirical comparisons across a range of benchmark problems show that the proposed algorithm outperforms current state-of-the-art methods in evolutionary constrained multi-objective optimization, underscoring its potential as a robust tool for handling MOPs with complex constraints.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143741570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EFNet: An Effective Facial Expression Recognition Network for Infants","authors":"Lei Geng,&nbsp;Tingting Qi,&nbsp;Zhitao Xiao,&nbsp;Yuelong Li,&nbsp;Wei Wang,&nbsp;Mei Wei","doi":"10.1111/exsy.70040","DOIUrl":"https://doi.org/10.1111/exsy.70040","url":null,"abstract":"<div>\u0000 \u0000 <p>Facial expression plays a crucial role during interactions with people. Previous studies on facial expression recognition (FER) have mainly focused on adults, while there are few studies on FER for infants. Due to the apparent differences in facial proportions and facial contours between infants and adults, the FER studies for infants could not be conducted on existing expression datasets. In order to study infant facial expressions in-depth, we create the infant facial expression recognition (IFER) dataset by collecting 10,240 infant images. Since infants' faces have smooth facial lines and weak sharpness, the inter-class similarity of facial expressions is higher than adults, and the existing networks for facial expression recognition lack attention to inter-class similarity. To address the above problems, we propose an effective infant facial expression recognition network named EFNet. In the first stage, the convolutional neural network (CNN) branch and the self-attention branch extract the overall features of infants' faces. In the second stage, we propose the self-adaptive attentional centre loss (SACL). The SACL uses the extracted feature maps as contexts to estimate the weights by an attention mechanism and then applies the attentional weights to guide the centre loss. Overall, the SACL facilitates inter-class separateness and intra-class compressiveness of related information in an embedding space. The state-of-the-art results on the IFER dataset confirm the remarkable effectiveness of the EFNet.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143741452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A BERT-Based Multi-Embedding Fusion Method Using Review Text for Recommendation","authors":"Haebin Lim,&nbsp;Qinglong Li,&nbsp;Sigeon Yang,&nbsp;Jaekyeong Kim","doi":"10.1111/exsy.70041","DOIUrl":"https://doi.org/10.1111/exsy.70041","url":null,"abstract":"<p>Collaborative filtering is a widely used method in recommender systems research. However, contrary to the assumption that it relies solely on rating data, many contemporary models incorporate review information to address issues such as data sparsity. Although previous recommender systems utilised review texts to capture user preferences and item features, they often rely on a single-embedding model to represent these features, which may limit the richness of the extracted information. Recent advancements suggest that combining multiple pre-trained embedding models can enhance text representation by leveraging the strengths of different encoding methods. In this study, we propose a novel recommender system model, the Multi-embedding Fusion Network for Recommendation (MFNR), which employs a multi-embedding approach to effectively capture and represent user and item features in review texts. Specifically, the proposed model integrates Bidirectional Encoder Representations from Transformers (BERT) and its optimised variant, RoBERTa, both of which are pre-trained transformer-based models designed for natural language understanding. By leveraging their contextual embeddings, our model extracts enriched feature representations from review texts. Extensive experiments conducted on real-world review datasets from Amazon.com and Goodreads.com demonstrate that MFNR significantly outperforms existing baseline models, achieving an average improvement of 9.18% in RMSE and 14.81% in MAE. These results highlight the efficacy of the multi-embedding approach, indicating its potential for broader application in complex recommendation scenarios.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70041","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143717396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 Survey on Internet of Medical Things (IoMT): Enabling Technologies, Security and Explainability Issues, Challenges, and Future Directions","authors":"Mert Melih Ozcelik,&nbsp;Ibrahim Kok,&nbsp;Suat Ozdemir","doi":"10.1111/exsy.70010","DOIUrl":"https://doi.org/10.1111/exsy.70010","url":null,"abstract":"<p>Internet of Medical Things (IoMT) paradigm refers to the process of collection, transmission and analysis of healthcare data using communication and information systems over the internet. IoMT consist of medical devices that can link to the internet or other networks, including wearables, sensors, monitoring tools and other medical appliances. IoMT data can be utilised to lower costs, increase the effectiveness of healthcare delivery and improve the patient health status. In addition to the potential benefits IoMT may provide, the impact of COVID19 pandemic has also strengthened the desire to collect patient data remotely and pushed a lot of medical professionals to utilise IoMT applications such as telemedicine, telehealth, remote patient monitoring, remote patient diagnostics and distant consultations etc. The expectation is that IoMT market size and the usage will increase dramatically and IoMT will change the conventional healthcare systems significantly in the upcoming years. Motivated with that growth expectation, this study aims to analyse the IoMT, its components, enabling technologies and applications by emphasising the fundamental pillars (sensing, communication, data analytics, and security) essential for developing a reliable, dependable, and secure IoMT ecosystem. Furthermore, this study conducts a detailed analysis of recent major cyberattacks targeting the healthcare industry, evaluating their impact and discussing the key lessons derived from these incidents by employing DOTMLPFI approach. Additionally, this survey offers a concise overview of the emerging technologies that complement IoMT in the development of smart healthcare systems and explores potential future directions within this evolving field.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70010","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689936","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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":"Recommendation of Learning Resources for MOOCs Based on Historical Sequential Behaviours","authors":"Wei Song,&nbsp;Qihao Zhang,&nbsp;Simon Fong,&nbsp;Tengyue Li","doi":"10.1111/exsy.70034","DOIUrl":"https://doi.org/10.1111/exsy.70034","url":null,"abstract":"<div>\u0000 \u0000 <p>Learning path recommendation is crucial for guiding learners through a series of courses in a logical sequence based on their previous learning experiences. This is particularly important for improving learning outcomes in massive open online courses (MOOCs) for diverse learners. Because both the historical learning courses and recommended learning paths can be represented as sequential patterns (SPs); it is reasonable to approach this problem through SP mining (SPM). In addition to support, we incorporate three factors, that is, course learning days, grades and engagement, to model frequent high-utility SPs (FHUSPs). When recommending a learning path, FHUSPs that align with the target user's learning history and are common among successful learners, while rare among less successful ones, are prioritised. If there are insufficient matching FHUSPs, we address this by recommending additional courses based on the joint competency and complementarity of learners similar to the target learner. Experimental results on a real-world dataset demonstrate that our method provides highly accurate and relevant recommendations.</p>\u0000 </div>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Arabic Short-Text Dataset for Sentiment Analysis of Tourism and Leisure Events","authors":"Seham Basabain,&nbsp;Ahmed Al-Dubai,&nbsp;Erik Cambria,&nbsp;Khalid Alomar,&nbsp;Amir Hussain","doi":"10.1111/exsy.70030","DOIUrl":"https://doi.org/10.1111/exsy.70030","url":null,"abstract":"<p>The focus of this study is to present the detailed process of collecting a dataset of Arabic short-text in the tourism context and annotating this dataset for the task of sentiment analysis using an automatic zero-shot labelling technique utilising transformer-based models. This is benchmarked against a baseline manual annotation approach utilising native Arab human annotators. This study also introduces an approach exploiting both manual/handcrafted and automatically generated annotations of the dataset tweets for the task of sentiment analysis as part of a cross-domain approach using a model trained on sarcasm labels and vice versa. The total collected corpus size is 2293 tweets; after annotation, these tweets were labelled in a three-way classification approach as either positive, negative or neutral. We run different experiments to provide benchmark results of Arabic sentiment classification. Comparative results on our dataset show that the highest performing baseline model when utilising manual labels was MARBERT, with an accuracy of up to 87%, which was pre-trained for Arabic on a massive amount of data. It should be noted that this model enhanced its performance additionally after pre-training on a dialectical Arabic and modern standard Arabic corpus. On the other hand, zero-shot automatically generated labels achieved an 84% accuracy rate in predicting sarcasm classes from sentiment labels.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":"42 5","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.70030","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143689466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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}