Artificial Intelligence Review最新文献

{"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}

{"title":"LiDAR, IMU, and camera fusion for simultaneous localization and mapping: a systematic review","authors":"Zheng Fan,&nbsp;Lele Zhang,&nbsp;Xueyi Wang,&nbsp;Yilan Shen,&nbsp;Fang Deng","doi":"10.1007/s10462-025-11187-w","DOIUrl":"10.1007/s10462-025-11187-w","url":null,"abstract":"<div><p>Simultaneous Localization and Mapping (SLAM) is a crucial technology for intelligent unnamed systems to estimate their motion and reconstruct unknown environments. However, the SLAM systems with merely one sensor have poor robustness and stability due to the defects in the sensor itself. Recent studies have demonstrated that SLAM systems with multiple sensors, mainly consisting of LiDAR, camera, and IMU, achieve better performance due to the mutual compensation of different sensors. This paper investigates recent progress on multi-sensor fusion SLAM. The review includes a systematic analysis of the advantages and disadvantages of different sensors and the imperative of multi-sensor solutions. It categorizes multi-sensor fusion SLAM systems into four main types by the fused sensors: LiDAR-IMU SLAM, Visual-IMU SLAM, LiDAR-Visual SLAM, and LiDAR-IMU-Visual SLAM, with detailed analysis and discussions of their pipelines and principles. Meanwhile, the paper surveys commonly used datasets and introduces evaluation metrics. Finally, it concludes with a summary of the existing challenges and future opportunities for multi-sensor fusion SLAM.</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/s10462-025-11187-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143645638","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 of hyperspectral image classification based on graph neural networks","authors":"Xiaofeng Zhao,&nbsp;Junyi Ma,&nbsp;Lei Wang,&nbsp;Zhili Zhang,&nbsp;Yao Ding,&nbsp;Xiongwu Xiao","doi":"10.1007/s10462-025-11169-y","DOIUrl":"10.1007/s10462-025-11169-y","url":null,"abstract":"<div><p>Hyperspectral images provide rich spectral-spatial information but pose significant classification challenges due to high dimensionality, noise, mixed pixels, and limited labeled samples. Graph Neural Networks (GNNs) have emerged as a promising solution, offering a semi-supervised framework that can capture complex spatial-spectral relationships inherent in non-Euclidean hyperspectral image data. However, existing reviews often concentrate on specific aspects, thus limiting a comprehensive understanding of GNN-based hyperspectral image classification. This review systematically outlines the fundamental concepts of hyperspectral image classification and GNNs, and summarizes leading approaches from both traditional machine learning and deep learning. Then, it categorizes GNN-based methods into four paradigms: graph recurrent neural networks, graph convolutional networks, graph autoencoders, and hybrid graph neural networks, discussing their theoretical underpinnings, architectures, and representative applications. Finally, five key directions are further highlighted: adaptive graph construction, dynamic graph processing, deeper architectures, self-supervised strategies, and robustness enhancement. These insights aim to facilitate continued innovation in GNN-based hyperspectral imaging, guiding researchers toward more efficient and accurate classification frameworks.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11169-y.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632522","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 context and sequence-based recommendation framework using GRU networks","authors":"R. V. Karthik,&nbsp;V. Pandiyaraju,&nbsp;Sannasi Ganapathy","doi":"10.1007/s10462-025-11174-1","DOIUrl":"10.1007/s10462-025-11174-1","url":null,"abstract":"<div><p>Recommendation systems play a significant contribution in e-commerce for predicting the more relevant product to the customers based on their interests. The recommendation system refers to the user-item interaction and predicts the next item by considering the similar kind of user interest or item purchased. The context-aware and sequential recommendation is built to predict the interested product based on the current context and sequential behavior pattern interactions. To fulfill the customers’ requirements, this paper proposes a new hybrid personalized recommendation system framework called Target User Context Sequential Prediction Gated Recurrent Unit (TUCSP-GRU) using deep learning methods to recommend suitable products to the users based on their interests and context. The proposed system uses the newly calculated Target User Specific Product Rating (TUS-PR) score, the proposed TUS Gated Recurrent Unit (TUS-GRU) model, and the proposed Top-N item prediction method. Here, (i) the TUS-PR score is used to improve the product rating, (ii) the new TUS-GRU model is used to find the sequence purchase behavior pattern of customers by considering their long-term and short-term interests, and (iii) the proposed Top-N item dynamic prediction method is used to adjust the next interested item list based on the response using the back propagation continuous learning method. The experiment results of the TUCSP-GRU framework show better accuracy in predicting the interested and relevant products or items when compared to existing similar recommendation systems with respect to the standard evaluation metrics.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11174-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632517","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":"Polyp segmentation in medical imaging: challenges, approaches and future directions","authors":"Abdul Qayoom,&nbsp;Juanying Xie,&nbsp;Haider Ali","doi":"10.1007/s10462-025-11173-2","DOIUrl":"10.1007/s10462-025-11173-2","url":null,"abstract":"<div><p>Colorectal cancer has been considered as the third most dangerous disease among the most common cancer types. The early diagnosis of the polyps weakens the spread of colorectal cancer and is significant for more productive treatment. The segmentation of polyps from the colonoscopy images is very critical and significant to identify colorectal cancer. In this comprehensive study, we meticulously scrutinize research papers focused on the automated segmentation of polyps in clinical settings using colonoscopy images proposed in the past five years. Our analysis delves into various dimensions, including input data (datasets and preprocessing methods), model design (encompassing CNNs, transformers, and hybrid approaches), loss functions, and evaluation metrics. By adopting a systematic perspective, we examine how different methodological choices have shaped current trends and identify critical limitations that need to be addressed. To facilitate meaningful comparisons, we provide a detailed summary table of all examined works. Moreover, we offer in-depth future recommendations for polyp segmentation based on the insights gained from this survey study. We believe that our study will serve as a great resource for future researchers in the subject of polyp segmentation offering vital support in the development of novel methodologies.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11173-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632518","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":"Machine learning operations landscape: platforms and tools","authors":"Lisana Berberi,&nbsp;Valentin Kozlov,&nbsp;Giang Nguyen,&nbsp;Judith Sáinz-Pardo Díaz,&nbsp;Amanda Calatrava,&nbsp;Germán Moltó,&nbsp;Viet Tran,&nbsp;Álvaro López García","doi":"10.1007/s10462-025-11164-3","DOIUrl":"10.1007/s10462-025-11164-3","url":null,"abstract":"<div><p>As the field of machine learning advances, managing and monitoring intelligent models in production, also known as machine learning operations (MLOps), has become essential. Organizations are increasingly adopting artificial intelligence as a strategic tool, thus increasing the need for reliable, and scalable MLOps platforms. Consequently, every aspect of the machine learning life cycle, from workflow orchestration to performance monitoring, presents both challenges and opportunities that require sophisticated, flexible, and scalable technological solutions. This research addresses this demand by providing a comprehensive assessment framework of MLOps platforms highlighting the key features necessary for a robust MLOps solution. The paper examines 16 MLOps tools widely used, which revolve around capabilities within AI infrastructure management, including but not limited to experiment tracking, model deployment, and model inference. Our three-step evaluation framework starts with a feature analysis of the MLOps platforms, then GitHub stars growth assessment for adoption and prominence, and finally, a weighted scoring method to single out the most influential platforms. From this process, we derive valuable insights into the essential components of effective MLOps systems and provide a decision-making flowchart that simplifies platform selection. This framework provides hands-on guidance for organizations looking to initiate or enhance their MLOps strategies, whether they require an end-end solutions or specialized tools.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11164-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632520","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":"Application of machine learning in early warning system of geotechnical disaster: a systematic and comprehensive review","authors":"Shan Lin,&nbsp;Zenglong Liang,&nbsp;Hongwei Guo,&nbsp;Quanke Hu,&nbsp;Xitailang Cao,&nbsp;Hong Zheng","doi":"10.1007/s10462-025-11175-0","DOIUrl":"10.1007/s10462-025-11175-0","url":null,"abstract":"<div><p>Enhancements in monitoring and computational technology have facilitated data accessibility and utilization. Machine learning, as an integral component of the realm of computational technology, is renowned for its universality and efficacy, rendering it pervasive across various domains. Geotechnical disaster early warning systems serve as a crucial safeguard for the preservation of human lives and assets. Machine learning exhibits the capacity to meet the exigencies of prompt and precise disaster prediction, prompting substantial interest in the nexus of these two domains in recent decades. This study accentuates the deployment of machine learning in addressing geotechnical engineering disaster prediction issues through an examination of four types of engineering-specialized research articles spanning the period 2009 to 2024. The study elucidates the evolution and significance of machine learning within the domain of geotechnical engineering disaster prediction, with an emphasis on data analytics and modeling. Addressing the lacunae in existing literature, a user-friendly front-end graphical interface, integrated with machine learning algorithms, is devised to better cater to the requisites of engineering professionals. Furthermore, this research delves into a critical analysis of the prevalent research limitations and puts forth prospective investigational avenues from an applied standpoint.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11175-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632519","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 learning frameworks for MRI-based diagnosis of neurological disorders: a systematic review and meta-analysis","authors":"Syed Saad Azhar Ali,&nbsp;Khuhed Memon,&nbsp;Norashikin Yahya,&nbsp;Shujaat Khan","doi":"10.1007/s10462-025-11146-5","DOIUrl":"10.1007/s10462-025-11146-5","url":null,"abstract":"<div><p>The automatic diagnosis of neurological disorders using Magnetic Resonance Imaging (MRI) is a widely researched problem. MRI is a non-invasive and highly informative imaging modality, which is one of the most widely accepted and used neuroimaging modalities for visualizing the human brain. The advent of tremendous processing capabilities, multi-modal data, and deep-learning techniques has enabled researchers to develop intelligent, sufficiently accurate classification methods. A comprehensive literature review has revealed extensive research on the automatic diagnosis of neurological disorders. However, despite numerous studies, a systematically developed framework is lacking, that relies on a sufficiently robust dataset or ensures reliable accuracy. To date, no consolidated framework has been established to classify multiple diseases and their subtypes effectively based on various types and their planes of orientation in structural and functional MR images. This systematic review provides a detailed and comprehensive analysis of research reported from 2000 to 2023. Systems developed in prior art have been categorized according to their disease diagnosis capabilities. The datasets employed and the tools developed are also summarized to assist researchers to conduct further studies in this crucial domain. The contributions of this research include facilitating the design of a unified framework for multiple neurological disease diagnoses, resulting in the development of a generic assistive tool for hospitals and neurologists to diagnose disorders precisely and swiftly thus potentially saving lives, in addition to increasing the quality of life of patients suffering from neurodegenerative disorders.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11146-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632523","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":"Classification using hyperdimensional computing: a review with comparative analysis","authors":"Pere Vergés,&nbsp;Mike Heddes,&nbsp;Igor Nunes,&nbsp;Denis Kleyko,&nbsp;Tony Givargis,&nbsp;Alexandru Nicolau","doi":"10.1007/s10462-025-11181-2","DOIUrl":"10.1007/s10462-025-11181-2","url":null,"abstract":"&lt;div&gt;&lt;p&gt;Hyperdimensional computing (HD), also known as vector symbolic architectures (VSA), is an emerging and promising paradigm for cognitive computing. At its core, HD/VSA is characterized by its distinctive approach to compositionally representing information using high-dimensional randomized vectors. The recent surge in research within this field gains momentum from its computational efficiency stemming from low-resolution representations and ability to excel in few-shot learning scenarios. Nonetheless, the current literature is missing a comprehensive comparative analysis of various methods since each of them uses a different benchmark to evaluate its performance. This gap obstructs the monitoring of the field’s state-of-the-art advancements and acts as a significant barrier to its overall progress. To address this gap, this review not only offers a conceptual overview of the latest literature but also introduces a comprehensive comparative study of HD/VSA classification methods. The exploration starts with an overview of the strategies proposed to encode information as high-dimensional vectors. These vectors serve as integral components in the construction of classification models. Furthermore, we evaluate diverse classification methods as proposed in the existing literature. This evaluation encompasses techniques such as retraining and regenerative training to augment the model’s performance. To conclude our study, we present a comprehensive empirical study. This study serves as an in-depth analysis, systematically comparing various HD/VSA classification methods using two benchmarks, the first being a set of seven popular datasets used in HD/VSA and the second consisting of 121 datasets being the subset from the UCI Machine Learning repository. To facilitate future research on classification with HD/VSA, we open-sourced the benchmarking and the implementations of the methods we review. Since the considered data are tabular, encodings based on key-value pairs emerge as optimal choices, boasting superior accuracy while maintaining high efficiency. Secondly, iterative adaptive methods demonstrate remarkable efficacy, potentially complemented by a regenerative strategy, depending on the specific problem. Furthermore, we show how HD/VSA is able to generalize while training with a limited number of training instances. Lastly, we demonstrate the robustness of HD/VSA methods by subjecting the model memory to a large number of bit-flips. The results illustrate that the model’s performance remains reasonably stable until the occurrence of 40% of bit flips, where the model’s performance is drastically degraded. Overall, this study performed a thorough performance evaluation on different methods and, on the one hand, a positive trend was observed in terms of improving classification performance but, on the other hand, these developments could often be surpassed by off-the-shelf methods. This calls for better integration with the broader machine learn","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11181-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632521","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-model integration for dynamic forecasting (MIDF): a framework for wind speed and direction prediction","authors":"Molaka Maruthi,&nbsp;Bubryur Kim,&nbsp;Song Sujeen,&nbsp;Jinwoo An,&nbsp;Zengshun Chen","doi":"10.1007/s10462-025-11140-x","DOIUrl":"10.1007/s10462-025-11140-x","url":null,"abstract":"<div><p>Accurate forecasting of wind speed and direction is critical for the efficient integration of wind power into energy systems, ensuring reliable renewable energy production and grid stability. Traditional methods often struggle with capturing nonlinear interdependencies, quantifying uncertainties, and providing reliable long-term predictions, particularly in complex atmospheric conditions. To address these challenges, this study introduces multi-model Integration for dynamic forecasting (MIDF), an ensemble machine learning framework that combines the strengths of DeepAR and temporal fusion transformer (TFT) models through a two-step meta-learning process. MIDF leverages DeepAR’s probabilistic forecasting capabilities and TFT’s attention mechanisms to enhance accuracy, robustness, and interpretability. Using a custom meteorological dataset spanning January 2010 to May 2023, the model was evaluated against standalone alternatives across multiple metrics, including MSE, RMSE, and R². MIDF achieved superior performance, with MSE, RMSE, and R² values of 0.0035, 0.01913, and 0.89 for wind speed, and 0.00052, 0.02507, and 0.86 for wind direction, significantly reducing errors compared to existing methods. These results underscore the potential of ensemble learning in advancing wind forecasting accuracy, enabling more reliable renewable energy management, operational planning, and risk mitigation in meteorological applications.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11140-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621802","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}