Artificial Intelligence Review最新文献

{"title":"Image-based deep learning for smart digital twins: a review","authors":"Md Ruman Islam,&nbsp;Mahadevan Subramaniam,&nbsp;Pei-Chi Huang","doi":"10.1007/s10462-024-11002-y","DOIUrl":"10.1007/s10462-024-11002-y","url":null,"abstract":"<div><p>Smart Digital Twins (<i>SDTs</i>) are being increasingly used to virtually replicate and predict the behaviors of complex physical systems through continual data assimilation, enabling the optimization of the performance of these systems by controlling the actions of systems. Recently, the Deep Learning (<i>DL</i>) models have significantly enhanced the capabilities of <i>SDTs</i>, particularly for tasks such as predictive maintenance, anomaly detection, and optimization. In many domains, including medicine, engineering, and education, <i>SDTs</i> use image data (image-based <i>SDTs</i>) to observe, learn, and control system behaviors. This paper focuses on various approaches and associated challenges in developing image-based <i>SDTs</i> by continually assimilating image data from physical systems. The paper also discusses the challenges in designing and implementing <i>DL</i> models for <i>SDTs</i>, including data acquisition, processing, and interpretation. In addition, insights into the future directions and opportunities for developing new image-based <i>DL</i> approaches to develop robust <i>SDTs</i> are provided. This includes the potential for using generative models for data augmentation, developing multi-modal <i>DL</i> models, and exploring the integration of <i>DL</i> models with other technologies, including Fifth Generation (<i>5 G</i>), edge computing, and the Internet of Things (<i>IoT</i>). In this paper, we describe the image-based <i>SDTs</i>, which enable broader adoption of the Digital Twins (<i>DTs</i>) paradigms across a broad spectrum of areas and the development of new methods to improve the abilities of <i>SDTs</i> in replicating, predicting, and optimizing the behavior of complex systems.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11002-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475224","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":"Multi-strategy fusion mayfly algorithm on task offloading and scheduling for IoT-based fog computing multi-tasks learning","authors":"Xiao-Fei Sui,&nbsp;Jie-Sheng Wang,&nbsp;Shi-Hui Zhang,&nbsp;Si-Wen Zhang,&nbsp;Yun-Hao Zhang","doi":"10.1007/s10462-025-11145-6","DOIUrl":"10.1007/s10462-025-11145-6","url":null,"abstract":"<div><p>The rapid development of Internet of Things (IoT) technology has accumulated a large amount of data, which needs to be stored, processed and deeply analyzed to meet the specific goals and needs of users. As an emerging computing model, Fog computing can allocate a large number of computing resources reasonably. In order to solve the problem of insufficient population diversity and low algorithm efficiency, Aiming at the task scheduling problem of Bag-of-Tasks(BoT) application in cloud and fog environment, a multi-strategy fusion Mayfly Algorithm was proposed. The method of improving the individual learning coefficient and the global learning coefficient is used to significantly improve the convergence speed, local search ability, and global search ability, and then the method of improving the social positive attraction coefficient is used to balance the development and exploration ability of the algorithm and help the algorithm to get rid of the local optimum. The main goal of the logarithm Mayfly Algorithm (lMA) is to complete the tasks of the IoT task package in the fog system efficiently with low cost in terms of reducing execution time and operating costs. The improved algorithms were compared with Mayfly Algorithm (MA), Genetic Algorithm (GA), Grey Wolf Optimizer (GWO), Tyrannosaurus Optimization Algorithm (TROA), Harris Hawks Optimization (HHO), Reptile Search Algorithm (RSA) and Red-Tailed Hawk Algorithm (RTH), and the results showed that lMA was significantly improved in terms of reducing processing time and operating cost. The performance of lMA is verified, and the results show that the model can not only save transmission energy consumption but also have good convergence.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11145-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475226","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":"Interval-valued intuitionistic fuzzy generator based low-light enhancement model for referenced image datasets","authors":"Chithra Selvam,&nbsp;Dhanasekar Sundaram","doi":"10.1007/s10462-025-11138-5","DOIUrl":"10.1007/s10462-025-11138-5","url":null,"abstract":"<div><p>Image processing is a rapidly evolving research field with diverse applications across science and technology, including biometric systems, surveillance, traffic signal control and medical imaging. Digital images taken in low-light conditions are often affected by poor contrast and pixel detail, leading to uncertainty. Although various fuzzy based techniques have been proposed for low-light image enhancement, there remains a need for a model that can manage greater uncertainty while providing better structural information. To address this, an interval-valued intuitionistic fuzzy generator is proposed to develop an advanced low-light image enhancement model for referenced image datasets. The enhancement process involves a structural similarity index measure (SSIM) based optimization approach with respect to the parameters of the generator. For experimental validation, the Low-Light (LOL), LOLv2-Real and LOLv2-Synthetic benchmark datasets are utilized. The results are compared with several existing techniques using quality metrics such as SSIM, peak signal-to-noise ratio, absolute mean brightness error, mean absolute error, root mean squared error, blind/referenceless image spatial quality evaluator and naturalness image quality evaluator, demonstrating the superiority of the proposed model. Ultimately, the model’s performance is benchmarked against state-of-the-art methods, highlighting its enhanced efficiency.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11138-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475221","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 three-way decision model for multi-granular support intuitionistic fuzzy rough sets based on overlap functions","authors":"Peng Yu,&nbsp;Xiyue Zhao","doi":"10.1007/s10462-025-11139-4","DOIUrl":"10.1007/s10462-025-11139-4","url":null,"abstract":"<div><p>Three-way decision-making provides an effective framework for addressing uncertainty, aligning closely with human cognitive decision patterns. This paper proposes a novel three-way decision model based on multi-granular support intuitionistic fuzzy rough sets, integrating <i>n</i>-dimensional overlap and grouping functions. The model constructs optimistic and pessimistic upper and lower approximations to optimize decision rules and introduces score and precision functions for ranking. To validate the model, a consumer decision-making algorithm was developed and applied to empirical data. The results demonstrate that the proposed model effectively narrows decision boundary regions, enhances decision-making precision, and supports decision-making in complex multi-attribute scenarios. This study not only advances rough set theory but also offers practical tools for addressing real-world uncertainty in decision-making.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11139-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475222","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 reinforcement learning-based multi-operator differential evolution with cubic spline for the path planning problem","authors":"Mohamed Reda,&nbsp;Ahmed Onsy,&nbsp;Amira Y. Haikal,&nbsp;Ali Ghanbari","doi":"10.1007/s10462-025-11129-6","DOIUrl":"10.1007/s10462-025-11129-6","url":null,"abstract":"<div><p>Path planning in autonomous driving systems remains a critical challenge, requiring algorithms capable of generating safe, efficient, and reliable routes. Existing state-of-the-art methods, including graph-based and sampling-based approaches, often produce sharp, suboptimal paths and struggle in complex search spaces, while trajectory-based algorithms suffer from high computational costs. Recently, meta-heuristic optimization algorithms have shown effective performance but often lack learning ability due to their inherent randomness. This paper introduces a unified benchmarking framework, named Reda’s Path Planning Benchmark 2024 (RP2B-24), alongside two novel reinforcement learning (RL)-based path-planning algorithms: Q-Spline Multi-Operator Differential Evolution (QSMODE), utilizing Q-learning (Q-tables), and Deep Q-Spline Multi-Operator Differential Evolution (DQSMODE), based on Deep Q-networks (DQN). Both algorithms are integrated under a single framework and enhanced with cubic spline interpolation to improve path smoothness and adaptability. The proposed RP2B-24 library comprises 50 distinct benchmark problems, offering a comprehensive and generalizable testing ground for diverse path-planning algorithms. Unlike traditional approaches, RL in QSMODE/DQSMODE is not merely a parameter adjustment method but is fully utilized to generate paths based on the accumulated search experience to enhance path quality. QSMODE/DQSMODE introduces a unique self-training update mechanism for the Q-table and DQN based on candidate paths within the algorithm’s population, complemented by a secondary update method that increases population diversity through random action selection. An adaptive RL switching probability dynamically alternates between these Q-table update modes. DQSMODE and QSMODE demonstrated superior performance, outperforming 22 state-of-the-art algorithms, including the IMODEII. The algorithms ranked first and second in the Friedman test and SNE-SR ranking test, achieving scores of 99.2877 (DQSMODE) and 93.0463 (QSMODE), with statistically significant results in the Wilcoxon test. The practical applicability of the algorithm was validated on a ROS-based system using a four-wheel differential drive robot, which successfully followed the planned paths in two driving scenarios, demonstrating the algorithm’s feasibility and effectiveness for real-world scenarios. The source code for the proposed benchmark and algorithm is publicly available for further research and experimentation at: https://github.com/MohamedRedaMu/RP2B24-Benchmark and https://github.com/MohamedRedaMu/QSMODEAlgorithm.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11129-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143475223","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":"Deep crowd anomaly detection: state-of-the-art, challenges, and future research directions","authors":"Md. Haidar Sharif,&nbsp;Lei Jiao,&nbsp;Christian W. Omlin","doi":"10.1007/s10462-024-11092-8","DOIUrl":"10.1007/s10462-024-11092-8","url":null,"abstract":"<div><p>Crowd anomaly detection is one of the most popular topics in computer vision in the context of smart cities. A plethora of deep learning methods have been proposed that generally outperform other machine learning solutions. Our review primarily discusses algorithms that were published in mainstream conferences and journals between 2020 and 2022. We present datasets that are typically used for benchmarking, produce a taxonomy of the developed algorithms, and discuss and compare their performances. Our main findings are that the heterogeneities of pre-trained convolutional models have a negligible impact on crowd video anomaly detection performance. We conclude our discussion with fruitful directions for future research.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11092-8.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446432","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":"Musical heritage historical entity linking","authors":"Arianna Graciotti,&nbsp;Nicolas Lazzari,&nbsp;Valentina Presutti,&nbsp;Rocco Tripodi","doi":"10.1007/s10462-024-11102-9","DOIUrl":"10.1007/s10462-024-11102-9","url":null,"abstract":"<div><p>Linking named entities occurring in text to their corresponding entity in a Knowledge Base (KB) is challenging, especially when dealing with historical texts. In this work, we introduce Musical Heritage named Entities Recognition, Classification and Linking (<span>mhercl</span>), a novel benchmark consisting of manually annotated sentences extrapolated from historical periodicals of the music domain. <span>mhercl</span> contains named entities under-represented or absent in the most famous KBs. We experiment with several State-of-the-Art models on the Entity Linking (EL) task and show that <span>mhercl</span> is a challenging dataset for all of them. We propose a novel unsupervised EL model and a method to extend supervised entity linkers by using Knowledge Graphs (KGs) to tackle the main difficulties posed by historical documents. Our experiments reveal that relying on unsupervised techniques and improving models with logical constraints based on KGs and heuristics to predict <span>NIL</span> entities (entities not represented in the KB of reference) results in better EL performance on historical documents.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11102-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446433","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 actor-critic based recommender system with context-aware user modeling","authors":"Maryam Bukhari,&nbsp;Muazzam Maqsood,&nbsp;Farhan Adil","doi":"10.1007/s10462-025-11134-9","DOIUrl":"10.1007/s10462-025-11134-9","url":null,"abstract":"<div><p>Recommendation systems empower users with tailored service assistance by learning about their interactions with systems and recommending items based on their preferences and interests. Typical recommender systems view the recommendation process as a static procedure disregarding the fact that users’ preferences are changed over time. Reinforcement learning (RL) approaches are the most advanced and recent techniques used by researchers to handle challenges where the user’s interest is captured by their most recent interactions with the system. However, most of the recent research on RL-based recommender systems focuses on simply the user’s recent interactions to generate the recommendations without taking into account the context of the user in which these interactions occur. The context has a great impact on users’ interests, behaviors, and ratings e.g., user mood, time, day type, companion, social circle, and location. In this paper, we propose a context-aware deep reinforcement learning-based recommender system focusing on context-specific state modeling methods. In this approach, states are designed based on the user’s most recent context. In parallel, a list-wise version of the context-aware recommender agent is also proposed, in which a list of items is recommended to users at each step of interaction based on their context. The findings of the study indicate that modeling users’ preferences in combination with contextual variables improves the performance of RL-based recommender systems. Furthermore, we evaluate the proposed method on context-based datasets in an offline environment. The performance in terms of evaluation measures optimally indicates the worth of the proposed method in comparison with existing studies. More precisely, the highest Presicion@5, MAP@10, and NDCG@10 of the context-aware recommender agent are 77%, 76%, and 74% respectively.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11134-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446534","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 synergetic intuitionistic fuzzy model combining AHP, entropy, and ELECTRE for data fabric solution selection","authors":"Fang Zhou,&nbsp;Ting-Yu Chen","doi":"10.1007/s10462-025-11128-7","DOIUrl":"10.1007/s10462-025-11128-7","url":null,"abstract":"<div><p>Amidst the ongoing digital transformation, enterprises face the challenge of managing ever-expanding volumes of data from multiple sources and diverse structures. Semantic data fabric emerges as a promising solution, offering an innovative approach to integrate data resources from various channels and produce meaningful insights. The selection of an appropriate data fabric solution has become a focal point amidst burgeoning data lakes and silos, garnering international attention. This research aims to precisely evaluate potential data fabric solutions using an innovative synergetic intuitionistic fuzzy evaluation model. We propose a hybrid approach, IF-AHP-Entropy-ELECTRE, which integrates the analytic hierarchy process (AHP), entropy, and elimination et choix traduisant la réalité (ELECTRE) techniques within the framework of intuitionistic fuzzy (IF) sets. This model is utilized to a data fabric solution selection (DFSS) issue for an appliance company, identifying the optimal solution based on its superior performance in foundational technology, real-time analytics, and customizable features. The effectiveness and adaptability of this approach stem from a novel hierarchical evaluative criteria system encompassing technology, capability, cost, and security. The criteria weights, derived from IF-AHP-Entropy, reflect both subjective and objective judgments of decision-makers, while the ranking generated by IF-ELECTRE employs a piecewise scoring function and a unique distance measure, factoring in optimistic perspectives and cross-information. Through sensitivity and comparative analyses, our approach demonstrates enhanced robustness, precision, and adaptability in dynamic DFSS contexts when compared to traditional multicriteria decision-making methods, such as IF-WSM, IF-TOPSIS, and IF-ELECTRE. Specifically, our model provides a decision support system that combines extensive functionality with a user-friendly design, making it highly effective for DFSS challenges. This approach not only establishes a solid foundation for data integration in data management but also enhances business competitiveness and supports sustained growth in the digital economy.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11128-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446491","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":"Psychological and physiological computing based on multi-dimensional foot information","authors":"Shengyang Li,&nbsp;Huilin Yao,&nbsp;Ruotian Peng,&nbsp;Yuanjun Ma,&nbsp;Bowen Zhang,&nbsp;Zhiyao Zhao,&nbsp;Jincheng Zhang,&nbsp;Siyuan Chen,&nbsp;Shibin Wu,&nbsp;Lin Shu","doi":"10.1007/s10462-024-11087-5","DOIUrl":"10.1007/s10462-024-11087-5","url":null,"abstract":"<div><p>As the population ages, utilizing foot information to continuously monitor the physiological and psychological health status of the elderly is emerging as a pivotal tool for meeting this crucial societal demand. However, few reviews explored how multi-dimensional foot data has been integrated into physiological and psychological computing. This review is essential as it fills a critical knowledge gap in understanding the connections between physiological and psychological disorders and various components of foot information. To identify relevant literature, a thorough search was conducted across IEEE, DBLP, Elsevier, Springer, Google Scholar, and PubMed, initially yielding 2386 publications. After multiple rounds of systematic filtering, 404 publications were selected for in-depth analysis. This review examines (1) the mechanisms linking foot information to human physiological and psychological conditions, (2) the monitoring devices that collect diverse foot-based data, (3) the datasets correlating diseases with multiple foot data, (4) the prevalent feature engineering of different foot data, and (5) the cutting-edge machine and deep learning algorithms for diseases analysis. It also provides insights into future developments in foot information health monitoring for psychological and physiological computing.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11087-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423248","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}