Frontiers in Artificial Intelligence最新文献_第3页

Metaverse technology tree: a holistic view. 元宇宙技术树：整体视图。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-17 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1545144

Sepehr Ghazinoory, Fatemeh Parvin, Fatemeh Saghafi, Masoud Afshari-Mofrad, Nafiseh Ghazavi, Mehdi Fatemi

{"title":"Metaverse technology tree: a holistic view.","authors":"Sepehr Ghazinoory, Fatemeh Parvin, Fatemeh Saghafi, Masoud Afshari-Mofrad, Nafiseh Ghazavi, Mehdi Fatemi","doi":"10.3389/frai.2025.1545144","DOIUrl":"https://doi.org/10.3389/frai.2025.1545144","url":null,"abstract":"Introduction: The Metaverse has emerged as a significant trend in recent years, offering solutions across diverse fields. Despite substantial investments and extensive research efforts, a comprehensive understanding of the Metaverse environment and its full potential remains elusive. This article seeks to address this gap by developing a technology tree for the Metaverse based on published standards, prior studies, and frameworks proposed by leading firms.Methods: To construct the Metaverse technology tree, a systematic literature review approach was employed. From an initial pool of 354 scientific papers, conference proceedings, book chapters, and reports, a rigorous screening process -focused on titles, abstracts, and full-texts -resulted in a selection of 81 final sources. These sources were synthesized using a meta-analysis methodology.Results: The meta-synthesis of the selected literature produced a comprehensive Metaverse technology tree encompassing seven key branches: artificial intelligence, Mirror World, extended reality, network infrastructure, lifelogging, blockchain, and the Internet of Things. Each branch represents a critical technological area necessary for the development and realization of the Metaverse.Discussion: The proposed Metaverse technology tree offers a holistic overview and roadmap of the technological domains underlying the Metaverse. By identifying these seven branches, this research provides valuable guidance for future studies and development trajectories in Metaverse technologies.","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1545144"},"PeriodicalIF":3.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12043874/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Approach for enhancing the accuracy of semantic segmentation of chest X-ray images by edge detection and deep learning integration. 基于边缘检测和深度学习的胸部x线图像语义分割精度提高方法。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-16 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1522730

Lesia Mochurad

{"title":"Approach for enhancing the accuracy of semantic segmentation of chest X-ray images by edge detection and deep learning integration.","authors":"Lesia Mochurad","doi":"10.3389/frai.2025.1522730","DOIUrl":"https://doi.org/10.3389/frai.2025.1522730","url":null,"abstract":"Introduction: Accurate segmentation of anatomical structures in chest X-ray images remains challenging, especially for regions with low contrast and overlapping structures. This limitation significantly affects the diagnosis of cardiothoracic diseases. Existing deep learning methods often struggle with preserving structural boundaries, leading to segmentation artifacts.Methods: To address these challenges, I propose a novel segmentation approach that integrates contour detection techniques with the U-net deep learning architecture. Specifically, the method employs Sobel and Scharr edge detection filters to enhance structural boundaries in chest X-ray images before segmentation. The pipeline involves pre-processing using contour detection, followed by segmentation with a U-net model trained to identify lungs, heart, and clavicles.Results: Experimental evaluation demonstrated that using edge-enhancing filters, particularly the Sobel operator, leads to a marked improvement in segmentation accuracy. For lung segmentation, the model achieved an accuracy of 99.26%, a Dice coefficient of 98.88%, and a Jaccard index of 97.54%. Heart segmentation results included 99.47% accuracy and 94.14% Jaccard index, while clavicle segmentation reached 99.79% accuracy and 89.57% Jaccard index. These results consistently outperform the baseline U-net model without edge enhancement.Discussion: The integration of contour detection methods with the U-net model significantly improves the segmentation quality of complex anatomical regions in chest X-rays. Among the tested filters, the Sobel operator proved to be the most effective in enhancing boundary information and reducing segmentation artifacts. This approach offers a promising direction for more accurate and robust computer-aided diagnosis systems in radiology.","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1522730"},"PeriodicalIF":3.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12040918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144017804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A framework for establishing shared, task-oriented understanding in hybrid open multi-agent systems. 在混合开放多智能体系统中建立共享的、面向任务的理解的框架。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-16 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1440582

Nikolaos Kondylidis, Ilaria Tiddi, Annette Ten Teije

{"title":"A framework for establishing shared, task-oriented understanding in hybrid open multi-agent systems.","authors":"Nikolaos Kondylidis, Ilaria Tiddi, Annette Ten Teije","doi":"10.3389/frai.2025.1440582","DOIUrl":"https://doi.org/10.3389/frai.2025.1440582","url":null,"abstract":"In Open Multi-Agent Systems (OMAS), the open nature of such systems precludes that all communication protocols are hardwired in advance. It is therefore essential that agents can incrementally learn to understand each other. Ideally, this is done with a minimal number of a priori assumptions, in order not to compromise the open nature of the system. This challenge becomes even harder for hybrid (human-artificial agent) populations. In such a hybrid setting, the challenge of learning to communicate is exacerbated by the requirement to do this in a minimal number of interactions with the humans involved. The difficulty arises from the conflict between making a minimal number of assumptions while also minimizing the number of interactions required. This study provides a fine-grained analysis of the process of establishing a shared task-oriented understanding for OMAS, with a particular focus on hybrid populations, i.e., containing both human and artificial agents. We present a framework that describes this process of reaching a shared task-oriented understanding. Our framework defines components that reflect decisions the agent designer needs to make, and we show how these components are affected when the agent population includes humans, i.e., when moving to a hybrid setting. The contribution of this paper is not to define yet another method for agents that learn to communicate. Instead, our goal is to provide a framework to assist researchers in designing agents that need to interact with humans in unforeseen scenarios. We validate our framework by showing that it provides a uniform way to analyze a diverse set of existing approaches from the literature for establishing shared understanding between agents. Our analysis reveals limitations of these existing approaches if they were to be applied in hybrid populations, and suggests how these can be resolved.","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1440582"},"PeriodicalIF":3.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12041212/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144040259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The imperative of diversity and equity for the adoption of responsible AI in healthcare. 在医疗保健领域采用负责任的人工智能，必须实现多样性和公平性。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-16 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1577529

Denise E Hilling, Imane Ihaddouchen, Stefan Buijsman, Reggie Townsend, Diederik Gommers, Michel E van Genderen

{"title":"The imperative of diversity and equity for the adoption of responsible AI in healthcare.","authors":"Denise E Hilling, Imane Ihaddouchen, Stefan Buijsman, Reggie Townsend, Diederik Gommers, Michel E van Genderen","doi":"10.3389/frai.2025.1577529","DOIUrl":"https://doi.org/10.3389/frai.2025.1577529","url":null,"abstract":"Artificial Intelligence (AI) in healthcare holds transformative potential but faces critical challenges in ethical accountability and systemic inequities. Biases in AI models, such as lower diagnosis rates for Black women or gender stereotyping in Large Language Models, highlight the urgent need to address historical and structural inequalities in data and development processes. Disparities in clinical trials and datasets, often skewed toward high-income, English-speaking regions, amplify these issues. Moreover, the underrepresentation of marginalized groups among AI developers and researchers exacerbates these challenges. To ensure equitable AI, diverse data collection, federated data-sharing frameworks, and bias-correction techniques are essential. Structural initiatives, such as fairness audits, transparent AI model development processes, and early registration of clinical AI models, alongside inclusive global collaborations like TRAIN-Europe and CHAI, can drive responsible AI adoption. Prioritizing diversity in datasets and among developers and researchers, as well as implementing transparent governance will foster AI systems that uphold ethical principles and deliver equitable healthcare outcomes globally.","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1577529"},"PeriodicalIF":3.0,"publicationDate":"2025-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12040885/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144064892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Editorial: Human-centered artificial intelligence in interaction processes. 社论：交互过程中以人为中心的人工智能。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-15 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1597763

Maria Chiara Caschera, Patrizia Grifoni, Francesca Cordella

引用次数: 0

Explainable machine learning to predict the cost of capital. 可解释的机器学习来预测资本成本。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-10 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1578190

Niklas Bussmann, Paolo Giudici, Alessandra Tanda, Ellen Pei-Yi Yu

引用次数: 0

AI revolution in insurance: bridging research and reality. 保险领域的人工智能革命：连接研究与现实。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-09 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1568266

Sukriti Bhattacharya, German Castignani, Leandro Masello, Barry Sheehan

{"title":"AI revolution in insurance: bridging research and reality.","authors":"Sukriti Bhattacharya, German Castignani, Leandro Masello, Barry Sheehan","doi":"10.3389/frai.2025.1568266","DOIUrl":"https://doi.org/10.3389/frai.2025.1568266","url":null,"abstract":"This paper comprehensively reviews artificial intelligence (AI) applications in the insurance industry. We focus on the automotive, health, and property insurance domains. To conduct this study, we followed the PRISMA guidelines for systematic reviews. This rigorous methodology allowed us to examine recent academic research and industry practices thoroughly. This study also identifies several key challenges that must be addressed to mitigate operational and underwriting risks, including data quality issues that could lead to biased risk assessments, regulatory compliance requirements for risk governance, ethical considerations in automated decision-making, and the need for explainable AI systems to ensure transparent risk evaluation and pricing models. This review highlights important research gaps by comparing academic studies with real-world industry implementations. It also explores emerging areas where AI can improve efficiency and drive innovation in the insurance sector. The insights gained from this work provide valuable guidance for researchers, policymakers, and insurance industry practitioners.","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1568266"},"PeriodicalIF":3.0,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12014612/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143989160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NLP-enhanced inflation measurement using BERT and web scraping. 使用BERT和网页抓取的nlp增强通货膨胀测量。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-09 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1520659

Martin Berki, Vanesa Andicsova, Milos Oravec

引用次数: 0

A short report on deep learning synergy for decentralized smart grid cybersecurity. 深度学习协同去中心化智能电网网络安全简要报告。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-09 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1557960

Saurav Verma, Ashwini Rao

引用次数: 0

The role of AI for MRI-analysis in multiple sclerosis-A brief overview. 人工智能在多发性硬化症mri分析中的作用-简要概述。

IF 3

Frontiers in Artificial Intelligence Pub Date : 2025-04-08 eCollection Date: 2025-01-01 DOI: 10.3389/frai.2025.1478068

Jean-Pierre R Falet, Steven Nobile, Aliya Szpindel, Berardino Barile, Amar Kumar, Joshua Durso-Finley, Tal Arbel, Douglas L Arnold

{"title":"The role of AI for MRI-analysis in multiple sclerosis-A brief overview.","authors":"Jean-Pierre R Falet, Steven Nobile, Aliya Szpindel, Berardino Barile, Amar Kumar, Joshua Durso-Finley, Tal Arbel, Douglas L Arnold","doi":"10.3389/frai.2025.1478068","DOIUrl":"https://doi.org/10.3389/frai.2025.1478068","url":null,"abstract":"Magnetic resonance imaging (MRI) has played a crucial role in the diagnosis, monitoring and treatment optimization of multiple sclerosis (MS). It is an essential component of current diagnostic criteria for its ability to non-invasively visualize both lesional and non-lesional pathology. Nevertheless, modern day usage of MRI in the clinic is limited by lengthy protocols, error-prone procedures for identifying disease markers (e.g., lesions), and the limited predictive value of existing imaging biomarkers for key disability outcomes. Recent advances in artificial intelligence (AI) have underscored the potential for AI to not only improve, but also transform how MRI is being used in MS. In this short review, we explore the role of AI in MS applications that span the entire life-cycle of an MRI image, from data collection, to lesion segmentation, detection, and volumetry, and finally to downstream clinical and scientific tasks. We conclude with a discussion on promising future directions.","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1478068"},"PeriodicalIF":3.0,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12011719/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144031572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0