Artificial Intelligence Review最新文献

{"title":"Pythagorean linguistic information-based green supplier selection using quantum-based group decision-making methodology and the MULTIMOORA approach","authors":"Prasenjit Mandal,&nbsp;Leo Mrsic,&nbsp;Antonios Kalampakas,&nbsp;Tofigh Allahviranloo,&nbsp;Sovan Samanta","doi":"10.1007/s10462-025-11205-x","DOIUrl":"10.1007/s10462-025-11205-x","url":null,"abstract":"<div><p>The selection of environmentally sustainable suppliers has been a significant challenge in management decision-making (DM). Multicriteria group decision-making (MCGDM) is a ranking methodology used to select suppliers, but it is complex and influenced by the different opinions of decision-makers. Once again, extensive research on MCGDM has exposed inadequacies in the trustworthiness of experts’ judgements, which profoundly impact the ultimate ranking results. The Pythagorean linguistic number (PLN) concept has been used to address MCGDM by considering experts’ confidence levels and real-world scenarios. This study introduces an extensive technique using a quantum scenario-based Bayesian network (QSBN) and Deng entropy-based belief entropy to account for the interference of beliefs. The goal is to replicate the subjectivity of experts’ opinions during different stages of DM, including the accumulation of experts’ weights and alternative probabilities. The correlation coefficient of PLNs is introduced for determining criterion weights and employing new techniques based on entropy methods for experts’ weights. The MULTIMOORA approach consolidates the probability of alternatives in QSBN among all experts, and the interference value is computed using belief entropy, an index for quantifying the probability of uncertainty. The study provides a numerical example to illustrate the proposed methodology, specifically focusing on selecting environmentally sustainable suppliers, and demonstrates its applicability and effectiveness.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 7","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11205-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143822041","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":"Dombi weighted geometric aggregation operators on the class of trapezoidal-valued intuitionistic fuzzy numbers and their applications to multi-attribute group decision-making","authors":"Bibhuti Bhusana Meher,&nbsp;Jeevaraj S,&nbsp;Melfi Alrasheedi","doi":"10.1007/s10462-025-11200-2","DOIUrl":"10.1007/s10462-025-11200-2","url":null,"abstract":"<div><p>The trapezoidal-valued intuitionistic fuzzy numbers (TrVIFNs) are vital in dealing with real-life decision-making problems (containing uncertainty and vagueness) in engineering and management. The study of aggregation operators on the set of trapezoidal-valued intuitionistic fuzzy numbers is essential for solving decision-making problems modelled under a trapezoidal-valued intuitionistic fuzzy (TrVIF) environment. Since TrVIFNs are the generalization class of different types of intuitionistic fuzzy numbers. The main contribution of this paper is to introduce the idea of Dombi t-norm and Dombi t-conorm based aggregation operators on the class of TrVIFNs. In this paper, firstly, we develop a Trapezoidal-Valued Intuitionistic Fuzzy Dombi Weighted Geometric operator, Trapezoidal-Valued Intuitionistic Fuzzy Dombi Order Weighted Geometric operator, Trapezoidal-Valued Intuitionistic Fuzzy Dombi Hybrid Geometric operator, and we establish mathematical properties through various theorems. Secondly, we propose a multiattribute group decision-making algorithm, such as a trapezoidal-valued multiattribute group decision-making algorithm that uses the proposed aggregation operators. Thirdly, we show the applicability of the proposed decision-making method in solving a multiattribute group decision-making problem involving the photovoltaic site selection. Further, we discuss the sensitivity analysis of the proposed algorithms to demonstrate their stability and reliability. Finally, we show the efficacy of the proposed decision-making approach by comparing it with a few familiar group decision-making methods.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 7","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11200-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821960","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 comprehensive survey of loss functions and metrics in deep learning","authors":"Juan Terven,&nbsp;Diana-Margarita Cordova-Esparza,&nbsp;Julio-Alejandro Romero-González,&nbsp;Alfonso Ramírez-Pedraza,&nbsp;E. A. Chávez-Urbiola","doi":"10.1007/s10462-025-11198-7","DOIUrl":"10.1007/s10462-025-11198-7","url":null,"abstract":"<div><p>This paper presents a comprehensive review of loss functions and performance metrics in deep learning, highlighting key developments and practical insights across diverse application areas. We begin by outlining fundamental considerations in classic tasks such as regression and classification, then extend our analysis to specialized domains like computer vision and natural language processing including retrieval-augmented generation. In each setting, we systematically examine how different loss functions and evaluation metrics can be paired to address task-specific challenges such as class imbalance, outliers, and sequence-level optimization. Key contributions of this work include: (1) a unified framework for understanding how losses and metrics align with different learning objectives, (2) an in-depth discussion of multi-loss setups that balance competing goals, and (3) new insights into specialized metrics used to evaluate modern applications like retrieval-augmented generation, where faithfulness and context relevance are pivotal. Along the way, we highlight best practices for selecting or combining losses and metrics based on empirical behaviors and domain constraints. Finally, we identify open problems and promising directions, including the automation of loss-function search and the development of robust, interpretable evaluation measures for increasingly complex deep learning tasks. Our review aims to equip researchers and practitioners with clearer guidance in designing effective training pipelines and reliable model assessments for a wide spectrum of real-world applications.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 7","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11198-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143822037","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 Survey of Artificial Intelligence Enabled Channel Estimation Methods: Recent Advance, Performance, and Outlook","authors":"Binglin Li,&nbsp;Qinghe Zheng,&nbsp;Xinyu Tian,&nbsp;Mingqiang Yang,&nbsp;Guan Gui,&nbsp;Weiwei Jiang,&nbsp;Hongjiang Lei,&nbsp;Jing Jiang,&nbsp;Feng Shu,&nbsp;Abdussalam Elhanashi,&nbsp;Sergio Saponara","doi":"10.1007/s10462-025-11202-0","DOIUrl":"10.1007/s10462-025-11202-0","url":null,"abstract":"<div><p>With the continuous advancement of wireless communication and the emergence of new communication scenarios, channel estimation, as a core component of wireless system design, has become increasingly significant. This paper reviews important advancements in channel estimation within wireless communication systems, including applications in single-input single-output (SISO), multi-input multi-output (MIMO), orthogonal time frequency space (OTFS), orthogonal frequency division multiplexing (OFDM), and the latest reconfigurable intelligent surface (RIS) systems. We first revisit traditional channel estimation methods, such as least squares (LS), minimum mean square error (MMSE), and compressed sensing (CS), and detail their fundamental principles and scopes of application. Subsequently, we discuss how deep learning techniques offer new perspectives and solutions for channel estimation through models like convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), long short-term memory (LSTM), and graph neural network (GNN), particularly in terms of their potential to handle complicated and dynamic environments. Additionally, we analyze the advantages and disadvantages of these methods in emerging scenarios, including RIS-assisted communications, vehicular networks, indoor positioning, sensing mobile networks, and satellite communications. We also address current methods for evaluating channel estimation performance and highlight the importance of standardization and open data in advancing the field. Finally, we summarize potential future directions for channel estimation and consider its prospects in sixth-generation (6 G) wireless communication systems, aiming to provide a comprehensive technical reference on channel estimation and promote the design of efficient and intelligent wireless communication systems.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11202-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143818136","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 comprehensive review on financial explainable AI","authors":"Wei Jie Yeo,&nbsp;Wihan Van Der Heever,&nbsp;Rui Mao,&nbsp;Erik Cambria,&nbsp;Ranjan Satapathy,&nbsp;Gianmarco Mengaldo","doi":"10.1007/s10462-024-11077-7","DOIUrl":"10.1007/s10462-024-11077-7","url":null,"abstract":"<div><p>The success of artificial intelligence (AI), and deep learning models in particular, has led to their widespread adoption across various industries due to their ability to process huge amounts of data and learn complex patterns. However, due to their lack of explainability, there are significant concerns regarding their use in critical sectors, such as finance and healthcare, where decision-making transparency is of paramount importance. In this paper, we provide a comparative survey of methods that aim to improve the explainability of deep learning models within the context of finance. We categorize the collection of explainable AI methods according to their corresponding characteristics, and we review the concerns and challenges of adopting explainable AI methods, together with future directions we deemed appropriate and important.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-024-11077-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726712","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":"Sustainable AI-driven wind energy forecasting: advancing zero-carbon cities and environmental computation","authors":"Haytham Elmousalami,&nbsp;Aljawharah A. Alnaser,&nbsp;Felix Kin Peng Hui","doi":"10.1007/s10462-025-11191-0","DOIUrl":"10.1007/s10462-025-11191-0","url":null,"abstract":"<div><p>Accurate forecasting of wind speed and power is transforming renewable wind farm management, facilitating efficient energy supply for smart and zero-energy cities. This paper introduces a novel low-carbon Sustainable AI-Driven Wind Energy Forecasting System (SAI-WEFS) developed from a promising real-world case study in MENA region. The SAI-WEFS evaluates twelve machine learning algorithms, utilizing both single and ensemble models for forecasting wind speed (WSF) and wind power (WPF) across multiple timeframes (10 min, 30 min, 6 h, 24 h, and 36 h). The system integrates multi-time horizon predictions, where the WSF output is input for the WPF model. The environmental impact of each algorithm is assessed based on CO₂ emissions for each computational hour. Predictive accuracy is assessed using mean square error (MSE) and mean absolute percentage error (MAPE). Results indicate that ensemble algorithms consistently outperform single ML models, with tree-based models demonstrating a lower environmental impact, emitting approximately 60 g of CO₂ per computational hour compared to deep learning models, which emit up to 500 g per hour. This system enhances the Urban Energy Supply Decarbonization Framework (UESDF) by predicting the Urban Carbon Emission Index (UCEI) to illustrate the Urban Carbon Transition Curve.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11191-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726705","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":"Current and future roles of artificial intelligence in retinopathy of prematurity","authors":"Ali Jafarizadeh,&nbsp;Shadi Farabi Maleki,&nbsp;Parnia Pouya,&nbsp;Navid Sobhi,&nbsp;Mirsaeed Abdollahi,&nbsp;Siamak Pedrammehr,&nbsp;Chee Peng Lim,&nbsp;Houshyar Asadi,&nbsp;Roohallah Alizadehsani,&nbsp;Ru-San Tan,&nbsp;Sheikh Mohammed Shariful Islam,&nbsp;U. Rajendra Acharya","doi":"10.1007/s10462-025-11153-6","DOIUrl":"10.1007/s10462-025-11153-6","url":null,"abstract":"<div><p>Retinopathy of prematurity (ROP) is a severe condition affecting premature infants, leading to abnormal retinal blood vessel growth, retinal detachment, and potential blindness. While semi-automated systems have been used in the past to diagnose ROP-related plus disease by quantifying retinal vessel features, traditional machine learning (ML) models face challenges like accuracy and overfitting. Recent advancements in deep learning (DL), especially convolutional neural networks (CNNs), have significantly improved ROP detection and classification. The i-ROP deep learning (i-ROP-DL) system also shows promise in detecting plus disease, offering reliable ROP diagnosis potential. This research comprehensively examines the contemporary progress and challenges associated with using retinal imaging and artificial intelligence (AI) to detect ROP, offering valuable insights that can guide further investigation in this domain. Based on 84 original studies in this field (out of 2025 studies that were comprehensively reviewed), we concluded that traditional methods for ROP diagnosis suffer from subjectivity and manual analysis, leading to inconsistent clinical decisions. AI holds great promise for improving ROP management. This review explores AI’s potential in ROP detection, classification, diagnosis, and prognosis.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11153-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726713","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":"Self-supervised hypergraph structure learning","authors":"Mingyuan Li,&nbsp;Yanlin Yang,&nbsp;Lei Meng,&nbsp;Lu Peng,&nbsp;Haixing Zhao,&nbsp;Zhonglin Ye","doi":"10.1007/s10462-025-11199-6","DOIUrl":"10.1007/s10462-025-11199-6","url":null,"abstract":"<div><p>Traditional Hypergraph Neural Networks (HGNNs) often assume that hypergraph structures are perfectly constructed, yet real-world hypergraphs are typically corrupted by noise, missing data, or irrelevant information, limiting the effectiveness of hypergraph learning. To address this challenge, we propose SHSL, a novel Self-supervised Hypergraph Structure Learning framework that jointly explores and optimizes hypergraph structures without external labels. SHSL consists of two key components: a self-organizing initialization module that constructs latent hypergraph representations, and a differentiable optimization module that refines hypergraphs through gradient-based learning. These modules collaboratively capture high-order dependencies to enhance hypergraph representations. Furthermore, SHSL introduces a dual learning mechanism to simultaneously guide structure exploration and optimization within a unified framework. Experiments on six public datasets demonstrate that SHSL outperforms state-of-the-art baselines, achieving Accuracy improvements of 1.36%<span>(-)</span>32.37% and 2.23%<span>(-)</span>27.54% on hypergraph exploration and optimization tasks, and 1.19%<span>(-)</span>8.4% on non-hypergraph datasets. Robustness evaluations further validate SHSL’s effectiveness under noisy and incomplete scenarios, highlighting its practical applicability. The implementation of SHSL and all experimental codes are publicly available at: https://github.com/MingyuanLi88888/SHSL.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11199-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726711","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":"Pathologyvlm: a large vision-language model for pathology image understanding","authors":"Dawei Dai,&nbsp;Yuanhui Zhang,&nbsp;Qianlan Yang,&nbsp;Long Xu,&nbsp;Xiaojing Shen,&nbsp;Shuyin Xia,&nbsp;Guoyin Wang","doi":"10.1007/s10462-025-11190-1","DOIUrl":"10.1007/s10462-025-11190-1","url":null,"abstract":"<div><p>The previous advancements in pathology image understanding primarily involved developing models tailored to specific tasks. Recent studies have demonstrated that the large vision-language model can enhance the performance of various downstream tasks in medical image understanding. In this study, we developed a domain-specific large vision-language model (PathologyVLM) for pathology image understanding. Specifically, (1) we first construct a human pathology image-text dataset by cleaning the public medical image-text data for domain-specific alignment; (2) Using the proposed image-text data, we first train a pathology language-image pretraining (PLIP) model as the specialized visual encoder to extract the features of pathology image, and then we developed scale-invariant connector to avoid the information loss caused by image scaling; (3) We adopt two-stage learning to train PathologyVLM, first stage for domain alignment, and second stage for end to end visual question &amp; answering (VQA) task. In experiments, we evaluate our PathologyVLM on both supervised and zero-shot VQA datasets, our model achieved the best overall performance among multimodal models of similar scale. The ablation experiments also confirmed the effectiveness of our design. We posit that our PathologyVLM model and the datasets presented in this work can promote research in field of computational pathology. All codes are available at: https://github.com/ddw2AIGROUP2CQUPT/PA-LLaVA</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11190-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726696","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":"Computer vision based approaches for fish monitoring systems: a comprehensive study","authors":"Said Al-Abri,&nbsp;Sanaz Keshvari,&nbsp;Khalfan Al-Rashdi,&nbsp;Rami Al-Hmouz,&nbsp;Hadj Bourdoucen","doi":"10.1007/s10462-025-11180-3","DOIUrl":"10.1007/s10462-025-11180-3","url":null,"abstract":"<div><p>Fish monitoring has become increasingly popular due to its growing real-world applications and recent advancements in intelligent technologies such as AI, Computer Vision, and Robotics. The primary objective of this article is to review benchmark datasets used in fish monitoring while introducing a novel framework that categorizes fish monitoring applications into four main domains: Fish Detection and Recognition (FDR), Fish Biomass Estimation (FBE), Fish Behavior Classification (FBC), and Fish Health Analysis (FHA). Additionally, this study proposes dedicated workflows for each domain, marking the first comprehensive effort to establish such a structured approach in this field. The detection and recognition of fish involve identifying fish and fish species. Estimating fish biomass focuses on counting fish and measuring their size and weight. Fish Behavior Classification tracks and analyzes movement and extracts behavioral patterns. Finally, health analysis assesses the general health of the fish. The methodologies and techniques are analyzed separately within each domain, providing a detailed examination of their specific applications and contributions to fish monitoring. These innovations enable fish species classification, fish freshness evaluation, fish counting, and body length measurement for biomass estimation. The study concludes by reviewing the development of key datasets and techniques over time, identifying existing gaps and limitations in current frameworks, and proposing future research directions in fish monitoring applications.</p></div>","PeriodicalId":8449,"journal":{"name":"Artificial Intelligence Review","volume":"58 6","pages":""},"PeriodicalIF":10.7,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10462-025-11180-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143688428","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}