Frontiers in Artificial Intelligence最新文献

{"title":"Enhanced vehicle routing for medical waste management via hybrid deep reinforcement learning and optimization algorithms.","authors":"Norhan Khallaf, Osama Abd-El Rouf, Abeer D Algarni, Mohy Hadhoud, Ahmed Kafafy","doi":"10.3389/frai.2025.1496653","DOIUrl":"10.3389/frai.2025.1496653","url":null,"abstract":"<p><p>Modern technologies, particularly artificial intelligence, play a crucial role in improving medical waste management by developing intelligent systems that optimize the shortest routes for waste transport, from its generation to final disposal. Algorithms such as Q-learning and Deep Q Network enhance the efficiency of transport and disposal while reducing environmental pollution risks. In this study, artificial intelligence algorithms were trained using Homogeneous agent systems with a capacity of 3 tons to optimize routes between hospitals within the Closed Capacitated Vehicle Routing Problem framework. Integrating AI with pathfinding techniques, especially the hybrid A*-Deep Q Network approach, led to advanced results despite initial challenges. K-means clustering was used to divide hospitals into zones, allowing agents to navigate the shortest paths using the Deep Q Network. Analysis revealed that the agents' capacity was not fully utilized. This led to the application of Fractional Knapsack dynamic programming with Deep Q Network to maximize capacity utilization while achieving optimal routes. Since the criteria used to compare the algorithms' effectiveness are the number of vehicles and the utilization of the total vehicle capacity, it was found that the Fractional Knapsack with DQN stands out by requiring the fewest number of vehicles (4), achieving 0% loss in this metric as it matches the optimal value. Compared to other algorithms that require 5 or 7 vehicles, it reduces the fleet size by 20 and 42.86%, respectively. Additionally, it maximizes vehicle capacity utilization at 100%, unlike other methods, which utilize only 33 to 66% of vehicle capacity. However, this improvement comes at the cost of a 9% increase in distance, reflecting the longer routes needed to serve more hospitals per trip. Despite this trade-off, the algorithm's ability to minimize fleet size while fully utilizing vehicle capacity makes it the optimal choice in scenarios where these factors are critical. This approach not only improved performance but also enhanced environmental sustainability, making it the most effective and challenging solution among all the algorithms used in the study.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1496653"},"PeriodicalIF":3.0,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11861366/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143516806","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":"Language writ large: LLMs, ChatGPT, meaning, and understanding.","authors":"Stevan Harnad","doi":"10.3389/frai.2024.1490698","DOIUrl":"10.3389/frai.2024.1490698","url":null,"abstract":"<p><p>Apart from what (little) OpenAI may be concealing from us, we all know (roughly) how Large Language Models (LLMs) such as ChatGPT work (their vast text databases, statistics, vector representations, and huge number of parameters, next-word training, etc.). However, none of us can say (hand on heart) that we are <i>not</i> surprised by what ChatGPT has proved to be able to do with these resources. This has even driven some of us to conclude that ChatGPT actually understands. It is not true that it understands. But it is also not true that we understand how it can do what it can do. I will suggest some hunches about benign \"biases\"-convergent constraints that emerge at the LLM scale that may be helping ChatGPT do so much better than we would have expected. These biases are inherent in the nature of language itself, at the LLM scale, and they are closely linked to what it is that ChatGPT <i>lacks</i>, which is <i>direct sensorimotor grounding</i> to connect its words to their referents and its propositions to their meanings. These convergent biases are related to (1) the parasitism of indirect verbal grounding on direct sensorimotor grounding, (2) the circularity of verbal definition, (3) the \"mirroring\" of language production and comprehension, (4) iconicity in propositions at LLM scale, (5) computational counterparts of human \"categorical perception\" in category learning by neural nets, and perhaps also (6) a conjecture by Chomsky about the laws of thought. The exposition will be in the form of a dialogue with ChatGPT-4.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1490698"},"PeriodicalIF":3.0,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11861094/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143516877","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":"Ontology-based prompt tuning for news article summarization.","authors":"A R S Silva, Y H P P Priyadarshana","doi":"10.3389/frai.2025.1520144","DOIUrl":"10.3389/frai.2025.1520144","url":null,"abstract":"<p><p>Ontology-based prompt tuning and abstractive text summarization techniques represent an advanced approach to enhancing the quality and contextual relevance of news article summaries. Despite the progress in natural language processing (NLP) and machine learning, existing methods often rely on extractive summarization, which lacks the ability to generate coherent and contextually rich summaries. Moreover, these approaches rarely integrate domain-specific knowledge, resulting in generic and sometimes inaccurate summaries. In this study, we propose a novel framework, which combines ontology-based prompt tuning with abstractive text summarization to address these limitations. By leveraging ontological knowledge, our model fine-tunes the summarization process, ensuring that the generated summaries are not only accurate but also contextually relevant to the domain. This integration allows for a more nuanced understanding of the text, enabling the generation of summaries that better capture the essence of the news articles. Our evaluation results demonstrate significant improvements over state-of-the-art methods such as BART, BERT, and GPT-3.5. The results show that the proposed architecture achieved a 5.1% higher ROUGE-1 score and a 9.8% improvement in ROUGE-L compared to baseline models. Additionally, our model showed significance in F1, precision, and recall metrics, with major improvements of 6.7, 3.9, and 4.8%, respectively. These results underscore the effectiveness of integrating ontological insights into the prompt tuning process, offering a robust solution for generating high-quality, domain-specific news summaries.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1520144"},"PeriodicalIF":3.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11850540/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143504709","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":"One size fits all: Enhanced zero-shot text classification for patient listening on social media.","authors":"Veton Matoshi, Maria Carmela De Vuono, Roberto Gaspari, Mark Kröll, Michael Jantscher, Sara Lucia Nicolardi, Giuseppe Mazzola, Manuela Rauch, Vedran Sabol, Eileen Salhofer, Riccardo Mariani","doi":"10.3389/frai.2024.1397470","DOIUrl":"10.3389/frai.2024.1397470","url":null,"abstract":"<p><p>Patient-focused drug development (PFDD) represents a transformative approach that is reshaping the pharmaceutical landscape by centering on patients throughout the drug development process. Recent advancements in Artificial Intelligence (AI), especially in Natural Language Processing (NLP), have enabled the analysis of vast social media datasets, also called Social Media Listening (SML), providing insights not only into patient perspectives but also into those of other interest groups such as caregivers. In this method study, we propose an NLP framework that-given a particular disease-is designed to extract pertinent information related to three primary research topics: identification of interest groups, understanding of challenges, and assessing treatments and support systems. Leveraging external resources like ontologies and employing various NLP techniques, particularly zero-shot text classification, the presented framework yields initial meaningful insights into these research topics with minimal annotation effort.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1397470"},"PeriodicalIF":3.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11850375/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143504706","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":"Dual feature-based and example-based explanation methods.","authors":"Andrei Konstantinov, Boris Kozlov, Stanislav Kirpichenko, Lev Utkin, Vladimir Muliukha","doi":"10.3389/frai.2025.1506074","DOIUrl":"10.3389/frai.2025.1506074","url":null,"abstract":"<p><p>A new approach to the local and global explanation based on selecting a convex hull constructed for the finite number of points around an explained instance is proposed. The convex hull allows us to consider a dual representation of instances in the form of convex combinations of extreme points of a produced polytope. Instead of perturbing new instances in the Euclidean feature space, vectors of convex combination coefficients are uniformly generated from the unit simplex, and they form a new dual dataset. A dual linear surrogate model is trained on the dual dataset. The explanation feature importance values are computed by means of simple matrix calculations. The approach can be regarded as a modification of the well-known model LIME. The dual representation inherently allows us to get the example-based explanation. The neural additive model is also considered as a tool for implementing the example-based explanation approach. Many numerical experiments with real datasets are performed for studying the approach. A code of proposed algorithms is available. The proposed results are fundamental and can be used in various application areas. They do not involve specific human subjects and human data.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1506074"},"PeriodicalIF":3.0,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847891/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143493956","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":"Construction of a prediction and visualization system for cognitive impairment in elderly COPD patients based on self-assigning feature weights and residual evolution model.","authors":"Wenwen Cheng, Chen Yu, Xiaohui Liu","doi":"10.3389/frai.2025.1473223","DOIUrl":"10.3389/frai.2025.1473223","url":null,"abstract":"<p><strong>Background: </strong>Assessing cognitive function in patients with chronic obstructive pulmonary disease (COPD) is crucial for ensuring treatment efficacy and avoiding moderate cognitive impairment (MCI) or dementia. We aimed to build better machine learning models and provide useful tools to provide better guidance and assistance for COPD patients' treatment and care.</p><p><strong>Methods: </strong>A total of 863 COPD patients from a local general hospital were collected and screened, and they were separated into two groups: cognitive impairment (356 patients) and cognitively normal (507 patients). The Montreal Cognitive Assessment (MoCA) was used to test cognitive function. The swarm intelligence optimization algorithm (SIOA) was used to direct feature weighting and hyperparameter optimization, which were considered simultaneous activities. A self-assigning feature weights and residual evolution (SAFWRE) algorithm was built on the concept of linear and nonlinear information fusion.</p><p><strong>Results: </strong>The best method in SIOA was the circle search algorithm. On the training set, SAFWRE's ROC-AUC was 0.9727, and its PR-AUC was 0.9663; on the test set, SAFWRE's receiver operating characteristic-area under curve (ROC-AUC) was 0.9243, and its precision recall-area under curve (PR-AUC) was 0.9059, and its performance was much superior than that of the control technique. In terms of external data, the classification and prediction performance of various models are comprehensively evaluated. SAFWRE has the most excellent classification performance, with ROC-AUC of 0.8865 and pr-auc of 0.8299.</p><p><strong>Conclusion: </strong>This work develops a practical visualization system based on these weight attributes which has strong application importance and promotion value.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1473223"},"PeriodicalIF":3.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11842389/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143484158","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":"MPAR-RCNN: a multi-task network for multiple person detection with attribute recognition.","authors":"S Raghavendra, S K Abhilash, Venu Madhav Nookala, Jayashree Shetty, Praveen Gurunath Bharathi","doi":"10.3389/frai.2025.1454488","DOIUrl":"10.3389/frai.2025.1454488","url":null,"abstract":"<p><p>Multi-label attribute recognition is a critical task in computer vision, with applications ranging across diverse fields. This problem often involves detecting objects with multiple attributes, necessitating sophisticated models capable of both high-level differentiation and fine-grained feature extraction. The integration of object detection and attribute recognition typically relies on approaches such as dual-stage networks, where accurate predictions depend on advanced feature extraction techniques, such as Region of Interest (RoI) pooling. To meet these demands, an efficient method that achieves both reliable detection and attribute classification in a unified framework is essential. This study introduces an innovative MTL framework designed to incorporate Multi-Person Attribute Recognition (MPAR) within a single-model architecture. Named MPAR-RCNN, this framework unifies object detection and attribute recognition tasks through a spatially aware, shared backbone, facilitating efficient and accurate multi-label prediction. Unlike the traditional Fast Region-based Convolutional Neural Network (R-CNN), which separately manages person detection and attribute classification with a dual-stage network, the MPAR-RCNN architecture optimizes both tasks within a single structure. Validated on the WIDER (Web Image Dataset for Event Recognition) dataset, the proposed model demonstrates an improvement over current state-of-the-art (SOTA) architectures, showcasing its potential in advancing multi-label attribute recognition.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1454488"},"PeriodicalIF":3.0,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11842310/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143484199","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":"Targeted generative data augmentation for automatic metastases detection from free-text radiology reports.","authors":"Maede Ashofteh Barabadi, Xiaodan Zhu, Wai Yip Chan, Amber L Simpson, Richard K G Do","doi":"10.3389/frai.2025.1513674","DOIUrl":"10.3389/frai.2025.1513674","url":null,"abstract":"<p><p>Automatic identification of metastatic sites in cancer patients from electronic health records is a challenging yet crucial task with significant implications for diagnosis and treatment. In this study, we demonstrate how advancements in natural language processing, namely the instruction-following capability of recent large language models and extensive model pretraining, made it possible to automate metastases detection from radiology reports texts with a limited amount of gold-labeled data. Specifically, we prompt Llama3, an open-source instruction-tuned large language model, to generate synthetic training data to expand our limited labeled data and adapt BERT, a small pretrained language model, to the task. We further investigate three targeted data augmentation techniques which selectively expand the original training samples, leading to comparable or superior performance compared to vanilla data augmentation, in most cases, while being substantially more computationally efficient. In our experiments, data augmentation improved the average F1-score by 2.3, 3.5, and 3.9 points for lung, liver, and adrenal glands, the organs for which we had access to expert-annotated data. This observation suggests that Llama3, which has not been specifically tailored to this task or clinical data in general, can generate high-quality synthetic data through paraphrasing in the clinical context. We also compare metastasis identification accuracy between models utilizing institutionally standardized reports vs. non-structured reports, which complicate the extraction of relevant information, and show how including patient history with a customized model architecture narrows the gap between those two setups from 7.3 to 4.5 points on F1-score under LoRA tuning. Our work delivers a broadly applicable solution with remarkable performance that does not require model customization for each institution, making large-scale, low-cost spatio-temporal cancer progression pattern extraction possible.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1513674"},"PeriodicalIF":3.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11839598/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143469436","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":"Edge computing for detection of ship and ship port from remote sensing images using YOLO.","authors":"Vasavi Sanikommu, Sai Pravallika Marripudi, Harini Reddy Yekkanti, Revanth Divi, R Chandrakanth, P Mahindra","doi":"10.3389/frai.2025.1508664","DOIUrl":"10.3389/frai.2025.1508664","url":null,"abstract":"<p><p>In marine security and surveillance, accurately identifying ships and ship ports from satellite imagery remains a critical challenge due to the inefficiencies and inaccuracies of conventional approaches. The proposed method uses an enhanced YOLO (You Only Look Once) model, a robust real-time object detection method. The method involves training the YOLO model on an extensive collection of annotated satellite images to detect ships and ship ports accurately. The proposed system delivers a precision of 86% compared to existing methods; this approach is designed to allow for real-time deployment in the context of resource-constrained environments, especially with a Jetson Nano edge device. This deployment will ensure scalability, efficient processing, and reduced reliance on central computing resources, making it especially suitable for maritime settings in which real-time monitoring is vital. The findings of this study, therefore, point out the practical implications of this improved YOLO model for maritime surveillance: offering a scalable and efficient solution to strengthen maritime security.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1508664"},"PeriodicalIF":3.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11839658/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143469429","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":"From Llama to language: prompt-engineering allows general-purpose artificial intelligence to rate narratives like expert psychologists.","authors":"Barry Dauphin, Caleb Siefert","doi":"10.3389/frai.2025.1398885","DOIUrl":"10.3389/frai.2025.1398885","url":null,"abstract":"<p><strong>Introduction: </strong>Artificial intelligence (AI) has tremendous potential for use in psychology. Among the many applications that may benefit from development of AI applications is narrative-personality assessment. Use of these tools and research methods is notably time-consuming and resource intensive. AI has potential to address these issues in ways that would greatly reduce clinician and researcher burden. Nonetheless, it is unclear if current AI models are sufficiently sophisticated to perform the complex downstream tasks, such as narrative assessment.</p><p><strong>Methodology: </strong>The purpose of this study is to explore if an expert-refined prompt generation process can enable AI-empowered chatbots to reliably and accurately rate narratives using the Social Cognition and Object Relations scales - Global Rating Method (SCORS-G). Experts generated prompt inputs by engaging in a detailed review of SCORS-G training materials. Prompts were then improved using an systematic process in which experts worked with <i>Llama-2-70b</i> to refine prompts. The utility of the prompts was then tested on two AI-empowered chatbots, <i>ChatGPT-4</i> (OpenAI, 2023) and <i>CLAUDE-2-100k</i>, that were not used in the prompt refinement process.</p><p><strong>Results: </strong>Results showed that the refined prompts allowed chatbots to reliably rate narratives at the global level, though accuracy varied across subscales. Averaging ratings from two chatbots notably improved reliability for the global score and all subscale scores. Experimentation indicated that expert-refined prompts outperformed basic prompts regarding interrater reliability and absolute agreement with gold standard ratings. Only the expert-refined prompts were able to generate acceptable single-rater interrater reliability estimates.</p><p><strong>Discussion: </strong>Findings suggest that AI could significantly reduce the time and resource burdens on clinicians and researchers using narrative rating systems like the SCORS-G. Limitations and implications for future research are discussed.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1398885"},"PeriodicalIF":3.0,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11839667/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143469430","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}