Frontiers in Artificial Intelligence最新文献

{"title":"Examining the integration of artificial intelligence in supply chain management from Industry 4.0 to 6.0: a systematic literature review.","authors":"Alexander Samuels","doi":"10.3389/frai.2024.1477044","DOIUrl":"10.3389/frai.2024.1477044","url":null,"abstract":"<p><strong>Background: </strong>This study examines the integration of Artificial Intelligence (AI) in supply chain management (SCM) during the transition from Industry 4.0 to Industry 6.0. The focus is on improving operational efficiency, promoting human-centric collaboration, and advancing sustainability within supply chains. As industries progress, the need to incorporate AI technologies that improve decision-making and operational resilience while ensuring sustainable practices becomes increasingly critical. This systematic review aims to explore how AI is transforming SCM through these industrial transitions.</p><p><strong>Methods: </strong>Utilising the PRISMA framework, a systematic review was conducted to gather and analyse relevant literature published between 2010 and 2023. A comprehensive search of databases including Web of Science, Scopus, IEEE Xplore, Google Scholar, and ScienceDirect was performed. The review involved rigorous screening for eligibility and thematic analysis using Atlas-ti software to identify key themes and patterns related to AI integration in SCM.</p><p><strong>Results: </strong>The findings indicate that AI integration significantly improves SCM by improving demand forecasting, inventory management, and overall decision-making capabilities. Industry 5.0 focuses on human-AI collaboration, improving customisation and problem-solving. AI technologies also contribute to sustainability by optimising resource utilisation and reducing environmental impacts. However, challenges such as cybersecurity risks and workforce skill gaps need to be addressed to fully leverage AI's potential.</p><p><strong>Conclusion: </strong>Integrating AI in SCM not only improves operational efficiency and sustainability but also promotes resilience against disruptions. The insights from this review offer valuable guidance for both academics and practitioners aiming to optimise supply chain operations through AI technologies from Industry 4.0 to Industry 6.0. The study underlines the importance of a balanced approach that integrates technological developments with human-centric and sustainable practices.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1477044"},"PeriodicalIF":3.0,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11788849/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143123794","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}

{"title":"Machine learning techniques for predicting neurodevelopmental impairments in premature infants: a systematic review.","authors":"Arantxa Ortega-Leon, Daniel Urda, Ignacio J Turias, Simón P Lubián-López, Isabel Benavente-Fernández","doi":"10.3389/frai.2025.1481338","DOIUrl":"10.3389/frai.2025.1481338","url":null,"abstract":"<p><strong>Background and objective: </strong>Very preterm infants are highly susceptible to Neurodevelopmental Impairments (NDIs), including cognitive, motor, and language deficits. This paper presents a systematic review of the application of Machine Learning (ML) techniques to predict NDIs in premature infants.</p><p><strong>Methods: </strong>This review presents a comparative analysis of existing studies from January 2018 to December 2023, highlighting their strengths, limitations, and future research directions.</p><p><strong>Results: </strong>We identified 26 studies that fulfilled the inclusion criteria. In addition, we explore the potential of ML algorithms and discuss commonly used data sources, including clinical and neuroimaging data. Furthermore, the inclusion of omics data as a contemporary approach employed, in other diagnostic contexts is proposed.</p><p><strong>Conclusions: </strong>We identified limitations and emphasized the significance of employing multimodal data models and explored various alternatives to address the limitations identified in the reviewed studies. The insights derived from this review guide researchers and clinicians toward improving early identification and intervention strategies for NDIs in this vulnerable population.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1481338"},"PeriodicalIF":3.0,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11788297/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190825","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}

{"title":"The technology acceptance model and adopter type analysis in the context of artificial intelligence.","authors":"Fabio Ibrahim, Johann-Christoph Münscher, Monika Daseking, Nils-Torge Telle","doi":"10.3389/frai.2024.1496518","DOIUrl":"10.3389/frai.2024.1496518","url":null,"abstract":"<p><strong>Introduction: </strong>Artificial Intelligence (AI) is a transformative technology impacting various sectors of society and the economy. Understanding the factors influencing AI adoption is critical for both research and practice. This study focuses on two key objectives: (1) validating an extended version of the Technology Acceptance Model (TAM) in the context of AI by integrating the Big Five personality traits and AI mindset, and (2) conducting an exploratory k-prototype analysis to classify AI adopters based on demographics, AI-related attitudes, and usage patterns.</p><p><strong>Methods: </strong>A sample of <i>N</i> = 1,007 individuals individuals (60% female; <i>M</i> = 30.92; SD = 8.63 years) was collected. Psychometric data were obtained using validated scales for TAM constructs, Big Five personality traits, and AI mindset. Regression analysis was used to validate TAM, and a k-prototype clustering algorithm was applied to classify participants into adopter categories.</p><p><strong>Results: </strong>The psychometric analysis confirmed the validity of the extended TAM. Perceived usefulness was the strongest predictor of attitudes towards AI usage (<i>β</i> = 0.34, <i>p</i> < 0.001), followed by AI mindset scale growth (<i>β</i> = 0.28, <i>p</i> < 0.001). Additionally, openness was positively associated with perceived ease of use (<i>β</i> = 0.15, <i>p</i> < 0.001). The k-prototype analysis revealed four distinct adopter clusters, consistent with the diffusion of innovations model: early adopters (<i>n</i> = 218), early majority (<i>n</i> = 331), late majority (<i>n</i> = 293), and laggards (<i>n</i> = 165).</p><p><strong>Discussion: </strong>The findings highlight the importance of perceived usefulness and AI mindset in shaping attitudes toward AI adoption. The clustering results provide a nuanced understanding of AI adopter types, aligning with established innovation diffusion theories. Implications for AI deployment strategies, policy-making, and future research directions are discussed.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1496518"},"PeriodicalIF":3.0,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780378/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143068384","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}

{"title":"An analysis of artificial intelligence automation in digital music streaming platforms for improving consumer subscription responses: a review.","authors":"Nontokozo Mokoena, Ibidun Christiana Obagbuwa","doi":"10.3389/frai.2024.1515716","DOIUrl":"https://doi.org/10.3389/frai.2024.1515716","url":null,"abstract":"<p><p>The rapid adoption and evolving nature of artificial intelligence (AI) is playing a significant role in shaping the music streaming industry. AI has become a key player in transforming the digital music streaming industry, particularly in enhancing user experiences and driving subscription growth. Through AI automation, platforms personalize music recommendations, optimize subscription offerings, and improve customer support services. This article reviews the role of AI in driving consumer subscription behaviors on digital music streaming platforms (DMSP), with a focus on recommendation algorithms, dynamic pricing models, marketing automation, and the future of AI in the music industry. Potential challenges related to privacy, ethics, and algorithmic biases are also discussed, showcasing how AI is revolutionizing the music streaming industry.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1515716"},"PeriodicalIF":3.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11774895/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143068379","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}

{"title":"SineKAN: Kolmogorov-Arnold Networks using sinusoidal activation functions.","authors":"Eric Reinhardt, Dinesh Ramakrishnan, Sergei Gleyzer","doi":"10.3389/frai.2024.1462952","DOIUrl":"https://doi.org/10.3389/frai.2024.1462952","url":null,"abstract":"<p><p>Recent work has established an alternative to traditional multi-layer perceptron neural networks in the form of Kolmogorov-Arnold Networks (KAN). The general KAN framework uses learnable activation functions on the edges of the computational graph followed by summation on nodes. The learnable edge activation functions in the original implementation are basis spline functions (B-Spline). Here, we present a model in which learnable grids of B-Spline activation functions are replaced by grids of re-weighted sine functions (SineKAN). We evaluate numerical performance of our model on a benchmark vision task. We show that our model can perform better than or comparable to B-Spline KAN models and an alternative KAN implementation based on periodic cosine and sine functions representing a Fourier Series. Further, we show that SineKAN has numerical accuracy that could scale comparably to dense neural networks (DNNs). Compared to the two baseline KAN models, SineKAN achieves a substantial speed increase at all hidden layer sizes, batch sizes, and depths. Current advantage of DNNs due to hardware and software optimizations are discussed along with theoretical scaling. Additionally, properties of SineKAN compared to other KAN implementations and current limitations are also discussed.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1462952"},"PeriodicalIF":3.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11775161/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143068382","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}

{"title":"Prediction of outpatient rehabilitation patient preferences and optimization of graded diagnosis and treatment based on XGBoost machine learning algorithm.","authors":"Xuehui Fan, Ruixue Ye, Yan Gao, Kaiwen Xue, Zeyu Zhang, Jing Xu, Jingpu Zhao, Jun Feng, Yulong Wang","doi":"10.3389/frai.2024.1473837","DOIUrl":"https://doi.org/10.3389/frai.2024.1473837","url":null,"abstract":"<p><strong>Background: </strong>The Department of Rehabilitation Medicine is key to improving patients' quality of life. Driven by chronic diseases and an aging population, there is a need to enhance the efficiency and resource allocation of outpatient facilities. This study aims to analyze the treatment preferences of outpatient rehabilitation patients by using data and a grading tool to establish predictive models. The goal is to improve patient visit efficiency and optimize resource allocation through these predictive models.</p><p><strong>Methods: </strong>Data were collected from 38 Chinese institutions, including 4,244 patients visiting outpatient rehabilitation clinics. Data processing was conducted using Python software. The pandas library was used for data cleaning and preprocessing, involving 68 categorical and 12 continuous variables. The steps included handling missing values, data normalization, and encoding conversion. The data were divided into 80% training and 20% test sets using the Scikit-learn library to ensure model independence and prevent overfitting. Performance comparisons among XGBoost, random forest, and logistic regression were conducted using metrics, including accuracy and receiver operating characteristic (ROC) curves. The imbalanced learning library's SMOTE technique was used to address the sample imbalance during model training. The model was optimized using a confusion matrix and feature importance analysis, and partial dependence plots (PDP) were used to analyze the key influencing factors.</p><p><strong>Results: </strong>XGBoost achieved the highest overall accuracy of 80.21% with high precision and recall in Category 1. random forest showed a similar overall accuracy. Logistic Regression had a significantly lower accuracy, indicating difficulties with nonlinear data. The key influencing factors identified include distance to medical institutions, arrival time, length of hospital stay, and specific diseases, such as cardiovascular, pulmonary, oncological, and orthopedic conditions. The tiered diagnosis and treatment tool effectively helped doctors assess patients' conditions and recommend suitable medical institutions based on rehabilitation grading.</p><p><strong>Conclusion: </strong>This study confirmed that ensemble learning methods, particularly XGBoost, outperform single models in classification tasks involving complex datasets. Addressing class imbalance and enhancing feature engineering can further improve model performance. Understanding patient preferences and the factors influencing medical institution selection can guide healthcare policies to optimize resource allocation, improve service quality, and enhance patient satisfaction. Tiered diagnosis and treatment tools play a crucial role in helping doctors evaluate patient conditions and make informed recommendations for appropriate medical care.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1473837"},"PeriodicalIF":3.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11776094/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143068380","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}

{"title":"Clinical entity-aware domain adaptation in low resource setting for inflammatory bowel disease.","authors":"Sumam Francis, Fernando Crema Garcia, Kanimozhi Uma, Willem Mestdagh, Bart De Moor, Marie-Francine Moens","doi":"10.3389/frai.2024.1450477","DOIUrl":"10.3389/frai.2024.1450477","url":null,"abstract":"<p><p>The digitization of healthcare records has revolutionized medical research and patient care, with electronic health records (EHRs) containing a wealth of structured and unstructured data. Extracting valuable information from unstructured clinical text presents a significant challenge, necessitating automated tools for efficient data mining. Natural language processing (NLP) methods have been pivotal in this endeavor, aiming to extract crucial clinical concepts embedded within free-form text. Our research addresses the imperative for robust biomedical entity extraction, focusing specifically on inflammatory bowel disease (IBD). Leveraging novel domain-specific pre-training and entity-aware masking strategies with contrastive learning, we fine-tune and adapt a general language model to be better adapted to IBD-related information extraction scenarios. Our named entity recognition (NER) tool streamlines the retrieval process, supporting annotation, correction, and visualization functionalities. In summary, we developed a comprehensive pipeline for clinical Dutch NER encompassing an efficient domain adaptation strategy with domain-aware masking and model fine-tuning enhancements, and an end-to-end entity extraction tool, significantly advancing medical record curation and clinical workflows.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1450477"},"PeriodicalIF":3.0,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11772291/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143060693","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}

{"title":"Fine-tuning a local LLaMA-3 large language model for automated privacy-preserving physician letter generation in radiation oncology.","authors":"Yihao Hou, Christoph Bert, Ahmed Gomaa, Godehard Lahmer, Daniel Höfler, Thomas Weissmann, Raphaela Voigt, Philipp Schubert, Charlotte Schmitter, Alina Depardon, Sabine Semrau, Andreas Maier, Rainer Fietkau, Yixing Huang, Florian Putz","doi":"10.3389/frai.2024.1493716","DOIUrl":"10.3389/frai.2024.1493716","url":null,"abstract":"<p><strong>Introduction: </strong>Generating physician letters is a time-consuming task in daily clinical practice.</p><p><strong>Methods: </strong>This study investigates local fine-tuning of large language models (LLMs), specifically LLaMA models, for physician letter generation in a privacy-preserving manner within the field of radiation oncology.</p><p><strong>Results: </strong>Our findings demonstrate that base LLaMA models, without fine-tuning, are inadequate for effectively generating physician letters. The QLoRA algorithm provides an efficient method for local intra-institutional fine-tuning of LLMs with limited computational resources (i.e., a single 48 GB GPU workstation within the hospital). The fine-tuned LLM successfully learns radiation oncology-specific information and generates physician letters in an institution-specific style. ROUGE scores of the generated summary reports highlight the superiority of the 8B LLaMA-3 model over the 13B LLaMA-2 model. Further multidimensional physician evaluations of 10 cases reveal that, although the fine-tuned LLaMA-3 model has limited capacity to generate content beyond the provided input data, it successfully generates salutations, diagnoses and treatment histories, recommendations for further treatment, and planned schedules. Overall, clinical benefit was rated highly by the clinical experts (average score of 3.4 on a 4-point scale).</p><p><strong>Discussion: </strong>With careful physician review and correction, automated LLM-based physician letter generation has significant practical value.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1493716"},"PeriodicalIF":3.0,"publicationDate":"2025-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11772293/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143060738","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}

{"title":"Evaluating the effectiveness of prompt engineering for knowledge graph question answering.","authors":"Catherine Kosten, Farhad Nooralahzadeh, Kurt Stockinger","doi":"10.3389/frai.2024.1454258","DOIUrl":"10.3389/frai.2024.1454258","url":null,"abstract":"<p><p>Many different methods for prompting large language models have been developed since the emergence of OpenAI's ChatGPT in November 2022. In this work, we evaluate six different few-shot prompting methods. The first set of experiments evaluates three frameworks that focus on the quantity or type of shots in a prompt: a baseline method with a simple prompt and a small number of shots, random few-shot prompting with 10, 20, and 30 shots, and similarity-based few-shot prompting. The second set of experiments target optimizing the prompt or enhancing shots through Large Language Model (LLM)-generated explanations, using three prompting frameworks: Explain then Translate, Question Decomposition Meaning Representation, and Optimization by Prompting. We evaluate these six prompting methods on the newly created Spider4SPARQL benchmark, as it is the most complex SPARQL-based Knowledge Graph Question Answering (KGQA) benchmark to date. Across the various prompting frameworks used, the commercial model is unable to achieve a score over 51%, indicating that KGQA, especially for complex queries, with multiple hops, set operations and filters remains a challenging task for LLMs. Our experiments find that the most successful prompting framework for KGQA is a simple prompt combined with an ontology and five random shots.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1454258"},"PeriodicalIF":3.0,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11770024/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052586","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}

{"title":"The sociolinguistic foundations of language modeling.","authors":"Jack Grieve, Sara Bartl, Matteo Fuoli, Jason Grafmiller, Weihang Huang, Alejandro Jawerbaum, Akira Murakami, Marcus Perlman, Dana Roemling, Bodo Winter","doi":"10.3389/frai.2024.1472411","DOIUrl":"10.3389/frai.2024.1472411","url":null,"abstract":"<p><p>In this article, we introduce a sociolinguistic perspective on language modeling. We claim that language models in general are inherently modeling <i>varieties of language</i>, and we consider how this insight can inform the development and deployment of language models. We begin by presenting a technical definition of the concept of a variety of language as developed in sociolinguistics. We then discuss how this perspective could help us better understand five basic challenges in language modeling: <i>social bias, domain adaptation, alignment, language change</i>, and <i>scale</i>. We argue that to maximize the performance and societal value of language models it is important to carefully compile training corpora that accurately represent the specific varieties of language being modeled, drawing on theories, methods, and descriptions from the field of sociolinguistics.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1472411"},"PeriodicalIF":3.0,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11770026/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143052629","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}