Artificial Intelligence Review最新文献

{"title":"Neural combinatorial optimization with reinforcement learning in industrial engineering: a survey","authors":"K. T. Chung,&nbsp;C. K. M. Lee,&nbsp;Y. P. Tsang","doi":"10.1007/s10462-024-11045-1","DOIUrl":"10.1007/s10462-024-11045-1","url":null,"abstract":"<div><p>In recent trends, machine learning is widely used to support decision-making in various domains and industrial operations. Because of the increasing complexity of modern industries, industrial engineering aims not only to increase cost-effectiveness and productivity but also to consider sustainability, resilience, and human centricity, resulting in many-objective, constrained, and stochastic operations research. Based on the above stringent requirements, combinatorial optimization (CO) problems are thus developed to support the complicated decision-making process in operations research. Due to the computational complexity of exact algorithms and the uncertain solution quality of heuristic methods, there is a growing trend to leverage the power of machine learning in solving CO problems, known as neural combinatorial optimization (NCO), where reinforcement learning (RL) is the core to achieve the sequential decision support. This survey study provides a comprehensive investigation of the theories and recent advancements in applying RL to solve hard CO problems, such as vehicle routing, bin packing, assignment, scheduling, and planning problems, and, in addition, summarizes the applications of neural combinatorial optimization with reinforcement learning (NCO-RL). The detailed review found that although the research domain of NCO-RL is still under-explored, its research potential has been proven to address environmental sustainability, adaptability, and human factors. Last but not least, the technical challenges and opportunities of the NCO-RL to embrace the industry 5.0 paradigm are discussed.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11045-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423100","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 review on EEG-based multimodal learning for emotion recognition","authors":"Rajasekhar Pillalamarri,&nbsp;Udhayakumar Shanmugam","doi":"10.1007/s10462-025-11126-9","DOIUrl":"10.1007/s10462-025-11126-9","url":null,"abstract":"<div><p>Emotion recognition from electroencephalography (EEG) signals is crucial for human–computer interaction yet poses significant challenges. While various techniques exist for detecting emotions through EEG signals, contemporary studies have explored the combination of EEG signals with other modalities. However, the field is still rapidly evolving, and new advancements are constantly being made. Comprehensive research is essential by distilling all factors in one manuscript to stay up-to-date with the latest research findings. This review offers an overview of multimodal leaning in EEG-based emotion recognition and discusses current literature in this domain from 2017 to 2024. Three primary challenges addressed are the fusion algorithm, representation of different modalities, and classification scheme. The review thoroughly explores the challenges of fusion algorithms, representation of different modalities, and classification schemes through empirical studies, offering a detailed analysis of their effectiveness. The approach of fusion algorithms is compared and evaluated based on convention and deep learning fusion methods. The research results show that poor performance is attributed to a lack of rigor and inadequate methods to identify correlated patterns across modalities to create a unified representation for experiments. This indicates a need for more thorough analysis and integration of data in future studies. When more than two modalities are involved, it becomes increasingly important to consider different aspects of classification schemes, such as the number of features and model selection. However, designing a classification scheme without considering the number of parameters and emotional categories may compromise the accuracy of classification. To aid readers in understanding the findings better, the results of different classification schemes and their corresponding accuracies are summarized. The tables in this draft display the fusion algorithms researchers utilize and evaluate the effectiveness of selected modalities, providing valuable insights for decision-making. Key contributions include a systematic survey of EEG features, an exploration of EEG integration with behavioral modalities, an investigation of fusion methods, and an overview of key challenges and future research directions in implementing multimodal emotion recognition systems.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11126-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423101","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":"AI-based bridge maintenance management: a comprehensive review","authors":"Farham Shahrivar,&nbsp;Amir Sidiq,&nbsp;Mojtaba Mahmoodian,&nbsp;Sanduni Jayasinghe,&nbsp;Zhiyan Sun,&nbsp;Sujeeva Setunge","doi":"10.1007/s10462-025-11144-7","DOIUrl":"10.1007/s10462-025-11144-7","url":null,"abstract":"<div><p>Over recent decades, the implementation of Artificial Intelligence (AI) across various industrial fields from automation to cybersecurity has been transformative. Whilst the implementations of linking AI and data sciences remain complex and thus limited, they both aim to harness data for actionable insights and future predictions. A research focal point in the application of AI in maintenance is crucial for the sustainability and efficiency of assets. Typically, in the civil infrastructure, there are significant benefits to be gained from AI-driven applications. This study reviews the implementation of the AI in bridge maintenance decision-making by conducting a review of literature on major works undertaken by researchers and analysing 102 scientific articles published from 2010 to 2023. Our literature review revealed an emerging trend in recent studies, focusing on the exploration of defect prognosis in bridge maintenance. However, upon further analysis, it becomes evident that there is a notable gap in the existing literature, in the studies related to performance-based prognostic maintenance strategies for bridges. This gap presents an opportunity for future research, one that could yield valuable insights in the field of bridge maintenance and asset management. The review also reveals the focus of the existing literature on defect identification by using the bridge imagery processing. While the AI’s potential in damage detection using bridge imagery is evident, challenges persist including the computational processing and data availability. This review of the literature includes a comprehensive overview of the current implementation of AI in bridge maintenance, highlighting limitations, challenges, and prospective directions.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11144-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423097","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":"Quantum deep learning in neuroinformatics: a systematic review","authors":"Nabil Anan Orka,&nbsp;Md. Abdul Awal,&nbsp;Pietro Liò,&nbsp;Ganna Pogrebna,&nbsp;Allen G. Ross,&nbsp;Mohammad Ali Moni","doi":"10.1007/s10462-025-11136-7","DOIUrl":"10.1007/s10462-025-11136-7","url":null,"abstract":"<div><p>Neuroinformatics involves replicating and detecting intricate brain activities through computational models, where deep learning plays a foundational role. Our systematic review explores quantum deep learning (QDL), an emerging deep learning sub-field, to assess whether quantum-based approaches outperform classical approaches in brain data learning tasks. This review is a pioneering effort to compare these deep learning domains. In addition, we survey neuroinformatics and its various subdomains to understand the current state of the field and where QDL stands relative to recent advancements. Our statistical analysis of tumor classification studies (n = 16) reveals that QDL models achieved a mean accuracy of 0.9701 (95% CI 0.9533–0.9868), slightly outperforming classical models with a mean accuracy of 0.9650 (95% CI 0.9475–0.9825). We observed similar trends across Alzheimer’s diagnosis, stroke lesion detection, cognitive state monitoring, and brain age prediction, with QDL demonstrating better performance in metrics such as F1-score, dice coefficient, and RMSE. Our findings, paired with prior documented quantum advantages, highlight QDL’s promise in healthcare applications as quantum technology evolves. Our discussion outlines existing research gaps with the intent of encouraging further investigation in this developing field.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11136-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423098","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":"Metaheuristic optimization algorithms for multi-area economic dispatch of power systems: part II—a comparative study","authors":"Yang Wang,&nbsp;Guojiang Xiong","doi":"10.1007/s10462-025-11125-w","DOIUrl":"10.1007/s10462-025-11125-w","url":null,"abstract":"<div><p>Multi-Area Economic Dispatch (MAED) plays an important role in the operation and planning of power systems. In Part I of this series, we have summarized various optimization techniques to the MAED problem comprehensively, showing clearly that metaheuristic optimization algorithms (MOAs) have become the dominant approach for solving this problem due to their ease of application and powerful search capability. Although many different types of MOAs have been proposed, there is no study on the comprehensive evaluation, comparison and recommendation of different MOAs for the MAED problem. In this part, we selected 32 algorithms including differential evolution, particle swarm optimization, teaching–learning based algorithm, JAYA algorithm, and their advanced variants to evaluate and compare their performance on the eleven reported MAED cases summarized in Part I of this series. The comparative study was comprehensively conducted based on various performance criteria including solution quality, convergence, robustness, computational efficiency, and statistical analysis. The comparisons reveal that the DE series is the most competitive overall. Nevertheless, there is no single algorithm that ranks in the top three on all cases. This study can provide a practical reference and applicability recommendation for the selection of MOAs for solving the MAED problem.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11125-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423102","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":"Evaluation of belief entropies: from the perspective of evidential neural network","authors":"Kun Mao,&nbsp;Yanni Wang,&nbsp;Wen Zhou,&nbsp;Jiangang Ye,&nbsp;Bin Fang","doi":"10.1007/s10462-025-11130-z","DOIUrl":"10.1007/s10462-025-11130-z","url":null,"abstract":"<div><p>In Dempster-Shafer’s theory, the belief entropy for total uncertainty measure of mass function has attracted the interest of many researchers in recent years. Although various belief entropies can meet some basic requirements, how to judge the performance of belief entropies is still an open issue. This paper proposes a novel evidential neural network (ENN) classifier to evaluate different belief entropies in practical application. Driven by the least commitment principle (LCP), the maximum entropy is integrated into the traditional divergence-based loss function. The proposed loss function consists of divergence and maximum entropy parts, which considers not only the distribution difference but also the degree of approaching the maximum entropy. Some classification experiments are conducted in 7 real-world datasets to validate the effectiveness of the proposed evaluation method.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11130-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143423099","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 review on persian question answering systems: from traditional to modern approaches","authors":"Safoura Aghadavoud Jolfaei,&nbsp;Azadeh Mohebi","doi":"10.1007/s10462-025-11122-z","DOIUrl":"10.1007/s10462-025-11122-z","url":null,"abstract":"<div><p>Question answering systems (QAS) are designed to answer questions in natural language. The objective of these types of systems is to reduce the user’s effort to manually check the retrieved documents to find the answer to the query in natural language and to create an accurate answer to the user’s query. In recent years, with the emergence of Large Language Models (LLMs), these systems have evolved significantly across different languages. However, the development of QAS in low resource languages such as Persian, while progressing, still faces unique challenges. Development of these systems has become problematic in Persian language due to the lack of comprehensive processing tools, limited question answering datasets, and specific challenges of this language. The current study provides a brief explanation of these systems’ evolution from traditional architectures to LLM-based approaches, their classification, the challenges specific to Persian language, existing question-answering datasets and language models, and studies conducted concerning Persian QAS.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11122-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396602","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":"Scalogram based performance comparison of deep learning architectures for dysarthric speech detection","authors":"Shaik Mulla Shabber,&nbsp;E. P. Sumesh,&nbsp;Vidhya Lavanya Ramachandran","doi":"10.1007/s10462-024-11085-7","DOIUrl":"10.1007/s10462-024-11085-7","url":null,"abstract":"<div><p>Dysarthria, a speech disorder commonly associated with neurological conditions, poses challenges in early detection and accurate diagnosis. This study addresses these challenges by implementing preprocessing steps, such as noise reduction and normalization, to enhance the quality of raw speech signals and extract relevant features. Scalogram images generated through wavelet transform effectively capture the time-frequency characteristics of the speech signal, offering a visual representation of the spectral content over time and providing valuable insights into speech abnormalities related to dysarthria. Fine-tuned deep learning models, including pre-trained convolutional neural network (CNN) architectures like VGG19, DenseNet-121, Xception, and a modified InceptionV3, were optimized with specific hyperparameters using training and validation sets. Transfer learning enables these models to adapt features from general image classification tasks to classify dysarthric speech signals better. The study evaluates the models using two public datasets TORGO and UA-Speech and a third dataset collected by the authors and verified by medical practitioners. The results reveal that the CNN models achieve an accuracy (acc) range of 90% to 99%, an F1-score range of 0.95 to 0.99, and a recall range of 0.96 to 0.99, outperforming traditional methods in dysarthria detection. These findings highlight the effectiveness of the proposed approach, leveraging deep learning and scalogram images to advance early diagnosis and healthcare outcomes for individuals with dysarthria.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11085-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396601","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":"Dmixnet: a dendritic multi-layered perceptron architecture for image recognition","authors":"Weixiang Xu,&nbsp;Yaotong Song,&nbsp;Shubham Gupta,&nbsp;Dongbao Jia,&nbsp;Jun Tang,&nbsp;Zhenyu Lei,&nbsp;Shangce Gao","doi":"10.1007/s10462-025-11123-y","DOIUrl":"10.1007/s10462-025-11123-y","url":null,"abstract":"<div><p>In the field of image recognition, the all-MLP architecture (MLP-Mixer) shows superior performance. However, the current MLP-Mixer is solely based on fully connected layers. The nonlinear capability of fully connected layers is relatively weak, and their simple stacked structure has limitations under complex conditions. Therefore, inspired by the diversity of neurons in the human brain, we propose an innovative DMixNet, a dendritic multi-layered perceptron architecture. Rooted in the theory of dendritic neurons from neuroscience, we propose a dendritic neural unit (DNU) that enhances DMixNet with stronger biological interpretability and more robust nonlinear processing capabilities. The flexibility of dendritic structures allows the DNU to adjust its architecture to achieve different functionalities. Based on the DNU, we propose a novel channel fusion network <span>(text {DNU}_text {E})</span> and a dendritic classifier <span>(text {DNU}_text {C})</span>. The <span>(text {DNU}_text {E})</span> substitutes the traditional two fully connected layers as the channel mixer, constructing a dendritic mixer layer to enhance the fusion capability of channel information within the entire framework. Meanwhile, the <span>(text {DNU}_text {C})</span> replaces the traditional linear classifier, effectively improving the model’s classification performance. Experimental results demonstrate that DMixNet achieves improvements of 2.13%, 4.79%, 4.71%, 23.14% on the CIFAR-10, CIFAR-100, Tiny-ImageNet and COIL-100 benchmark image recognition datasets, respectively, as well as a 14.78% enhancement on the medical image classification dataset PathMNIST, outperforming other state-of-the-art architectures. Code is available at https://github.com/KarilynXu/DMixNet.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 5","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11123-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396603","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":"Text analytics for co-creation in public sector organizations: a literature review-based research framework","authors":"Nina Rizun,&nbsp;Aleksandra Revina,&nbsp;Noella Edelmann","doi":"10.1007/s10462-025-11112-1","DOIUrl":"10.1007/s10462-025-11112-1","url":null,"abstract":"<div><p>The public sector faces considerable challenges that stem from increasing external and internal demands, the need for diverse and complex services, and citizens’ lack of satisfaction and trust in public sector organisations (PSOs). An alternative to traditional public service delivery is the co-creation of public services. Data analytics has been fueled by the availability of immense amounts of data, including textual data, and techniques to analyze data, so it has immense potential to foster data-driven solutions for the public sector. In the paper, we systematically review the existing literature on the application of Text Analytics (TA) techniques on textual data that can support public service co-creation. In this review, we identify the TA techniques, the public services and the co-creation phase they support, as well as envisioned public values for the stakeholder groups. On the basis of the analysis, we develop a Research Framework that helps to structure the TA-enabled co-creation process in PSOs, increases awareness among public sector organizations and stakeholders on the significant potential of TA in creating value, and provides scholars with some avenues for further research.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 4","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11112-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143184714","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}