Artificial Intelligence Review最新文献

{"title":"Multi-strategy improved snow ablation optimizer: a case study of optimization of kernel extreme learning machine for flood prediction","authors":"Lele Cui,&nbsp;Gang Hu,&nbsp;Yaolin Zhu","doi":"10.1007/s10462-025-11192-z","DOIUrl":"10.1007/s10462-025-11192-z","url":null,"abstract":"<div><p>The Kernel Extreme Learning Machine (KELM) has the advantage of automatically extracting data features, learning and processing nonlinear problems from historical data, which can help achieve better prediction results for flood prediction problems with complex and sudden causes. Traditional flood disaster prediction usually only considers one influencing factor without considering the complex factors that affect flood occurrence. This article develops a new method for predicting the probability of flood occurrence based on 20 influencing factors. Firstly, in order to better utilize KELM performance, an improved snow ablation optimization algorithm (MESAO) was proposed for subsequent experiments by introducing a level based selection pressure mechanism, covariance matrix learning strategy, historical position based boundary adjustment strategy, and random centroid reverse learning strategy into snow ablation optimization (SAO). Secondly, MESAO is used to perform hyperparameter optimization on the regularization coefficient C and kernel function parameter S of the KELM model. Finally, the construction of a multi feature input–output model for the application of MESAO-KELM in flood prediction problems was completed. In terms of hyperparameter optimization, the numerical experimental results of this method were superior to the prediction results of 10 other intelligent algorithms and 5 regression prediction models. According to the evaluation index results, the best adaptability of MESAO optimized KELM and higher prediction accuracy and stability compared to other prediction models were demonstrated. This method overcomes the limitations of traditional prediction models based on a single influencing factor and can predict the probability of flood occurrence based on complex and variable factors. It can be said that MESAO-KELM has strong generalization ability. Accurate flood prediction can provide early warning and take measures in advance to protect and reduce the impact of floods on human and social development.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11192-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676420","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":"MambaYOLACT: you only look at mamba prediction head for head-neck lymph nodes","authors":"Tao Zhou,&nbsp;Wenwen Chai,&nbsp;Defang Chang,&nbsp;Kaixiong Chen,&nbsp;Zhe Zhang,&nbsp;HuiLing Lu","doi":"10.1007/s10462-025-11177-y","DOIUrl":"10.1007/s10462-025-11177-y","url":null,"abstract":"<div><p>Lymph nodes in the head-neck are often infected when malignant tumors metastasize. At present, Magnetic Resonance Imaging (MRI) is widely used in the evaluation of head-neck lymph nodes. However, there are some problems, such as different sizes, low contrast of head-neck lymph nodes. The instance segmentation accuracy of head-neck lymph nodes is decreased, which affects the patients treatment decision and the surgical effect evaluation. To solve these problems, a single stage Mamba YOLACT instance segmentation model is proposed in this paper. The main contributions are as follows: Firstly, a Cross-field and Cross-direction Feature Enhancement module (CCFE) is designed. The module through the channel grouping mechanism, effectively enhances the ability of each group of features to express different spatial semantic information, by mixing attention mechanism to improve the feature extraction ability of lesions with different dimensions. Secondly, a MambaNet-based prediction head module is designed. The module combined the State-Space Model (SSM) and self-attention mechanism to accurately capture global image dependencies, highlight the lesion area. Thirdly, A dataset of MRI images of head-neck lymph nodes is used to verify the model effectiveness. The results show that the values of APdet, APseg, ARdet, ARseg, mAPdet and mAPseg are 69.8%, 70.9%, 55.3%, 56.4%, 39.4% and 41.0%, respectively. The model can achieve accurate segmentation of the lymph nodes, which has positive significance for lymph nodes auxiliary diagnosis.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11177-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676419","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-scale graph diffusion convolutional network for multi-view learning","authors":"Shiping Wang,&nbsp;Jiacheng Li,&nbsp;Yuhong Chen,&nbsp;Zhihao Wu,&nbsp;Aiping Huang,&nbsp;Le Zhang","doi":"10.1007/s10462-025-11158-1","DOIUrl":"10.1007/s10462-025-11158-1","url":null,"abstract":"<div><p>Multi-view learning has attracted considerable attention owing to its capability to learn more comprehensive representations. Although graph convolutional networks have achieved encouraging results in multi-view research, their limitation to considering only nearest neighbors results in the decrease on the ability to obtain high-order information. Many existing methods acquire high-order correlation by stacking multiple layers onto the model, yet they could lead to the issue of over-smoothing. In this paper, we propose a framework termed multi-scale graph diffusion convolutional network, which aims to gather comprehensive higher-order information without stacking multiple convolutional layers. Specifically, in order to better expand the receptive field of the node and reduce the parameter complexity, the proposed framework utilizes a contractive mapping to transform features from multiple views on decoupled propagation rules. Our framework introduces a multi-scale graph-based diffusion mechanism to adaptively extract the abundant high-order knowledge embedded within multi-scale graphs. Experiments show that the proposed method outperforms other state-of-the-art methods in terms of multi-view semi-supervised classification.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11158-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676511","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":"Guidelines for designing visualization tools for group fairness analysis in binary classification","authors":"António Cruz,&nbsp;Teresa Salazar,&nbsp;Manuel Carvalho,&nbsp;Catarina Maçãs,&nbsp;Penousal Machado,&nbsp;Pedro Henriques Abreu","doi":"10.1007/s10462-025-11179-w","DOIUrl":"10.1007/s10462-025-11179-w","url":null,"abstract":"<div><p>The use of machine learning in decision-making has become increasingly pervasive across various fields, from healthcare to finance, enabling systems to learn from data and improve their performance over time. The transformative impact of these new technologies warrants several considerations that demand the development of modern solutions through responsible artificial intelligence—the incorporation of ethical principles into the creation and deployment of AI systems. Fairness is one such principle, ensuring that machine learning algorithms do not produce biased outcomes or discriminate against any group of the population with respect to sensitive attributes, such as race or gender. In this context, visualization techniques can help identify data imbalances and disparities in model performance across different demographic groups. However, there is a lack of guidance towards clear and effective representations that support entry-level users in fairness analysis, particularly when considering that the approaches to fairness visualization can vary significantly. In this regard, the goal of this work is to present a comprehensive analysis of current tools directed at visualizing and examining group fairness in machine learning, with a focus on both data and binary classification model outcomes. These visualization tools are reviewed and discussed, concluding with the proposition of a focused set of visualization guidelines directed towards improving the comprehensibility of fairness visualizations.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11179-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676510","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 systematic literature review on municipal solid waste management using machine learning and deep learning","authors":"Ishaan Dawar,&nbsp;Anisha Srivastava,&nbsp;Maanas Singal,&nbsp;Nirjara Dhyani,&nbsp;Suvi Rastogi","doi":"10.1007/s10462-025-11196-9","DOIUrl":"10.1007/s10462-025-11196-9","url":null,"abstract":"<div><p>Population growth and urbanization have led to a significant increase in solid waste. However, conventional methods of treating and recycling this waste have inherent problems, such as low efficiency, poor precision, high cost, and severe environmental hazards. To address these challenges, Artificial Intelligence (AI) has gained popularity in recent years as a potential solution for municipal solid-waste management (MSWM). A few applications of AI, based on Machine Learning (ML) and Deep Learning (DL) techniques, have been used for MSWM. This study reviews the current landscape in MSWM, highlighting the existing advantages and disadvantages of 69 studies published between 2018 and 2024 using the PRISMA methodology. The applications of ML and DL algorithms demonstrate their ability to enhance decision-making processes, improve resource recovery rates, and promote circular economy principles. Although these technologies offer promising solutions, challenges such as data availability, quality, and interdisciplinary collaboration hinder their effective implementation. The paper suggests future research directions focusing on developing robust datasets, fostering partnerships across sectors, and integrating advanced technologies with traditional waste management strategies. This research aligns with the United Nations’ Sustainable Development Goals (SDG), particularly Goal 11, which aims to make cities inclusive, safe, resilient, and sustainable. In the future, this research can contribute to making cities smarter, greener, and more resilient using ML and DL techniques.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11196-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143676512","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":"Emrnet: enhanced micro-expression recognition network with attention and distance correlation","authors":"Gaqiong Liu,&nbsp;Shucheng Huang,&nbsp;Gang Wang,&nbsp;Mingxing Li","doi":"10.1007/s10462-025-11159-0","DOIUrl":"10.1007/s10462-025-11159-0","url":null,"abstract":"<div><p>Micro-expression recognition (MER) is inherently challenging due to the difficulty of extracting subtle, localized changes in micro-expressions (MEs). Various optical flow-based methods have been proposed for MER, as optical flow can effectively suppress facial identity information while capturing the movement patterns of MEs. However, these methods, characterized by simple architectures, often fail to extract discriminative features, resulting in suboptimal performance. In this paper, we propose an Enhanced Micro-expression Recognition Network with attention and distance correlation (EMRNet) for MER. EMRNet consists of three key phases: First, we introduce a novel channel-wise region-aware attention mechanism within two identical Inception networks, designed to extract global and local expression features in parallel, based on the optical flow input of the same ME. Second, to enhance ME representations, we propose a regularized dilated loss function incorporating distance correlation, which improves the information entropy transferred between the two branches. Last, emotion categories are predicted by fusing the expression-dilated features in the classification branch. Extensive experiments conducted on the composite database from the MEGC 2019 challenge demonstrate the effectiveness of EMRNet under both leave-one-subject-out (LOSO) cross-validation and the composite database evaluation (CDE) protocol. The results show that our approach successfully generates discriminative features, achieving substantial performance gains. Furthermore, EMRNet outperforms existing single-stream and dual-stream models, delivering superior results in MER.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11159-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668026","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":"Bibliometric analysis of artificial intelligence cyberattack detection models","authors":"Blessing Guembe,&nbsp;Sanjay Misra,&nbsp;Ambrose Azeta,&nbsp;Ines Lopez-Baldominos","doi":"10.1007/s10462-025-11167-0","DOIUrl":"10.1007/s10462-025-11167-0","url":null,"abstract":"<div><p>Cybercriminals have increasingly adopted advanced and cutting-edge methods that expand the scale and speed of their attacks in recent years. This trend coincides with the rising demand for and scarcity of highly skilled cybersecurity specialists, making them both expensive and difficult to find. Recently, researchers have demonstrated the effectiveness of Artificial Intelligence (AI) approaches in combating sophisticated cyberattacks. However, comprehensive bibliometric data illustrating the study of AI approaches in cyberattack detection remain sparse. This study addresses this gap by investigating the current state of AI-based cyberattack detection research. The study analyzed the Scopus database using bibliometric analysis on a pool of over 2,338 articles published between 2014 and 2024, including 1217 journal articles, 828 conference papers, 121 conference reviews, 85 book chapters, 70 reviews, 5 editorials, and 2 books and short surveys. The study explores various AI-based cyberattack detection approaches globally, focusing on machine learning and deep learning algorithms. The bibliometric analysis was conducted using R, an open-source statistical tool, and Biblioshiny. The findings establish that AI, particularly machine learning and deep learning, enhances intrusion detection accuracy and is a growing research trend. Researchers have effectively employed these techniques for malware detection. The USA leads in AI cyberattack research, followed by India, China, Saudi Arabia, and Australia. Despite publishing fewer articles, Canada and Italy received significant citations. Additionally, strong research collaboration exists among the USA, China, Australia, Saudi Arabia, and India. Keyword analysis highlights AI’s effectiveness in identifying patterns and malicious behaviours, enhancing intrusion detection even in complex cyberattacks. Machine learning can detect intrusions based on anomalies caused by malicious or compromised devices, as well as unknown threats, with speed, accuracy, and a low false-positive rate.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11167-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668025","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 step gravitational search algorithm for function optimization and STTM’s synchronous feature selection-parameter optimization","authors":"Chaodong Fan,&nbsp;Laurence T. Yang,&nbsp;Leyi Xiao","doi":"10.1007/s10462-025-11193-y","DOIUrl":"10.1007/s10462-025-11193-y","url":null,"abstract":"<div><p>The support tensor train machine (STTM) can make full use of the correlation of tensor data structures, while the parameter training is inefficient and feature redundancy is large. For this, a step gravitational search algorithm (SGSA) is proposed and used for synchronous feature selection and parameter optimization of STTM in this paper. Since the single population structure of the gravitational search algorithm is difficult to balance exploration and exploitation effectively, a new dual population structure is defined by the step function. Subpopulation Pop1 focuses on exploration, and a <i>K</i>_<i>best</i><i>-Elite</i> hybrid learning strategy is designed to avoid the rapid decline of exploration ability due to the rapid reduction of the size of <i>K</i>_<i>best</i> set as well as the gravitational constant <i>G</i>. Subpopulation Pop2 focuses on exploitation, and a position update strategy that integrates Cauchy distribution and Gaussian distribution is designed to make Pop2 always have a certain exploration ability. Finally, use SGSA to solve the synchronous feature selection and parameter optimization problem of STTM (the resulting model is denoted as SGSA-STTM). The algorithm’s optimization performance test results show that SGSA can obtain relatively best results on most test functions compared with other state-of-the-art algorithms. The classification performance test on fMRI datasets shows that SGSA-STTM can remove more than 40% of redundant features on most datasets, which can effectively improve the efficiency of the algorithm, and the classification accuracy for the StarPlus fMRI dataset and the CMU Science 2008 fMRI dataset reached 60 and 70%, respectively.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11193-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667953","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":"Dna coding theory and algorithms","authors":"Jin Xu,&nbsp;Wenbin Liu,&nbsp;Kai Zhang,&nbsp;Enqiang Zhu","doi":"10.1007/s10462-025-11132-x","DOIUrl":"10.1007/s10462-025-11132-x","url":null,"abstract":"<div><p>DNA computing is an emerging computational model that has garnered significant attention due to its distinctive advantages at the molecular biological level. Since it was introduced by Adelman in 1994, this field has made remarkable progress in solving <b>NP</b>-complete problems, enhancing information security, encrypting images, controlling diseases, and advancing nanotechnology. A key challenge in DNA computing is the design of DNA coding, which aims to minimize nonspecific hybridization and enhance computational reliability. The DNA coding design is a classical combinatorial optimization problem focused on generating high-quality DNA sequences that meet specific constraints, including distance, thermodynamics, secondary structure, and sequence requirements. This paper comprehensively examines the advances in DNA coding design, highlighting mathematical models, counting theory, and commonly used DNA coding methods. These methods include the template method, multi-objective evolutionary methods, and implicit enumeration techniques.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11132-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143668024","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":"Context in object detection: a systematic literature review","authors":"Mahtab Jamali,&nbsp;Paul Davidsson,&nbsp;Reza Khoshkangini,&nbsp;Martin Georg Ljungqvist,&nbsp;Radu-Casian Mihailescu","doi":"10.1007/s10462-025-11186-x","DOIUrl":"10.1007/s10462-025-11186-x","url":null,"abstract":"<div><p>Context is an important factor in computer vision as it offers valuable information to clarify and analyze visual data. Utilizing the contextual information inherent in an image or a video can improve the precision and effectiveness of object detectors. For example, where recognizing an isolated object might be challenging, context information can improve comprehension of the scene. This study explores the impact of various context-based approaches to object detection. Initially, we investigate the role of context in object detection and survey it from several perspectives. We then review and discuss the most recent context-based object detection approaches and compare them. Finally, we conclude by addressing research questions and identifying gaps for further studies. More than 265 publications are included in this survey, covering different aspects of context in different categories of object detection, including general object detection, video object detection, small object detection, camouflaged object detection, zero-shot, one-shot, and few-shot object detection. This literature review presents a comprehensive overview of the latest advancements in context-based object detection, providing valuable contributions such as a thorough understanding of contextual information and effective methods for integrating various context types into object detection, thus benefiting researchers.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11186-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645637","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}