Frontiers in Artificial Intelligence最新文献

{"title":"Exploring the potential of AI-driven food waste management strategies used in the hospitality industry for application in household settings.","authors":"Quintana M Clark, Disha Basavaraja Kanavikar, Jason Clark, Patrick J Donnelly","doi":"10.3389/frai.2024.1429477","DOIUrl":"10.3389/frai.2024.1429477","url":null,"abstract":"<p><p>This study explores the potential for adapting AI-driven food waste management strategies from the hospitality industry for application in household settings. The hospitality industry, particularly hotels and restaurants, has implemented AI technologies through companies like Leanpath, Winnow, and Kitro, which use real-time data and predictive analytics to monitor, categorize, and reduce food waste. These AI-driven systems have demonstrated significant reductions in food waste, offering economic savings and environmental benefits. This study employs an instrumental case study approach, utilizing semi-structured interviews with representatives from these companies to gain insights into the technologies and strategies that have proven effective in hospitality. The findings suggest that with modifications for scale, cost, and user engagement, AI-driven solutions could enhance household food management by providing insights into consumption patterns, offering expiration reminders, and supporting sustainable practices. Highlighted are key considerations for household adaptation, including policy support, educational strategies, economic incentives, and integration with smart home systems. Ultimately, this study identifies a promising avenue for reducing household food waste through AI, underscoring the need for continued research and policy initiatives to facilitate the transition of these technologies from commercial kitchens to everyday homes.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1429477"},"PeriodicalIF":3.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11799730/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143365794","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":"Phenology analysis for trait prediction using UAVs in a MAGIC rice population with different transplanting protocols.","authors":"Shoji Taniguchi, Toshihiro Sakamoto, Haruki Nakamura, Yasunori Nonoue, Di Guan, Akari Fukuda, Hirofumi Fukuda, Kaede C Wada, Takuro Ishii, Jun-Ichi Yonemaru, Daisuke Ogawa","doi":"10.3389/frai.2024.1477637","DOIUrl":"10.3389/frai.2024.1477637","url":null,"abstract":"<p><p>Unmanned aerial vehicles (UAVs) are one of the most effective tools for crop monitoring in the field. Time-series RGB and multispectral data obtained with UAVs can be used for revealing changes of three-dimensional growth. We previously showed using a rice population with our regular cultivation protocol that canopy height (CH) parameters extracted from time-series RGB data are useful for predicting manually measured traits such as days to heading (DTH), culm length (CL), and aboveground dried weight (ADW). However, whether CH parameters are applicable to other rice populations and to different cultivation methods, and whether vegetation indices such as the chlorophyll index green (CIg) can function for phenotype prediction remain to be elucidated. Here we show that CH and CIg exhibit different patterns with different cultivation protocols, and each has its own character for the prediction of rice phenotypes. We analyzed CH and CIg time-series data with a modified logistic model and a double logistic model, respectively, to extract individual parameters for each. The CH parameters were useful for predicting DTH, CL, ADW and stem and leaf weight (SLW) in a newly developed rice population under both regular and delayed cultivation protocols. The CIg parameters were also effective for predicting DTH and SLW, and could also be used to predict panicle weight (PW). The predictive ability worsened when different cultivation protocols were used, but this deterioration was mitigated by a calibration procedure using data from parental cultivars. These results indicate that the prediction of DTH, CL, ADW and SLW by CH parameters is robust to differences in rice populations and cultivation protocols, and that CIg parameters are an indispensable complement to the CH parameters for the predicting PW.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1477637"},"PeriodicalIF":3.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11799559/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143365795","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":"Cyberinfrastructure for machine learning applications in agriculture: experiences, analysis, and vision.","authors":"Lucas Waltz, Sushma Katari, Chaeun Hong, Adit Anup, Julian Colbert, Anirudh Potlapally, Taylor Dill, Canaan Porter, John Engle, Christopher Stewart, Hari Subramoni, Scott Shearer, Raghu Machiraju, Osler Ortez, Laura Lindsey, Arnab Nandi, Sami Khanal","doi":"10.3389/frai.2024.1496066","DOIUrl":"10.3389/frai.2024.1496066","url":null,"abstract":"<p><strong>Introduction: </strong>Advancements in machine learning (ML) algorithms that make predictions from data without being explicitly programmed and the increased computational speeds of graphics processing units (GPUs) over the last decade have led to remarkable progress in the capabilities of ML. In many fields, including agriculture, this progress has outpaced the availability of sufficiently diverse and high-quality datasets, which now serve as a limiting factor. While many agricultural use cases appear feasible with current compute resources and ML algorithms, the lack of reusable hardware and software components, referred to as cyberinfrastructure (CI), for collecting, transmitting, cleaning, labeling, and training datasets is a major hindrance toward developing solutions to address agricultural use cases. This study focuses on addressing these challenges by exploring the collection, processing, and training of ML models using a multimodal dataset and providing a vision for agriculture-focused CI to accelerate innovation in the field.</p><p><strong>Methods: </strong>Data were collected during the 2023 growing season from three agricultural research locations across Ohio. The dataset includes 1 terabyte (TB) of multimodal data, comprising Unmanned Aerial System (UAS) imagery (RGB and multispectral), as well as soil and weather sensor data. The two primary crops studied were corn and soybean, which are the state's most widely cultivated crops. The data collected and processed from this study were used to train ML models to make predictions of crop growth stage, soil moisture, and final yield.</p><p><strong>Results: </strong>The exercise of processing this dataset resulted in four CI components that can be used to provide higher accuracy predictions in the agricultural domain. These components included (1) a UAS imagery pipeline that reduced processing time and improved image quality over standard methods, (2) a tabular data pipeline that aggregated data from multiple sources and temporal resolutions and aligned it with a common temporal resolution, (3) an approach to adapting the model architecture for a vision transformer (ViT) that incorporates agricultural domain expertise, and (4) a data visualization prototype that was used to identify outliers and improve trust in the data.</p><p><strong>Discussion: </strong>Further work will be aimed at maturing the CI components and implementing them on high performance computing (HPC). There are open questions as to how CI components like these can best be leveraged to serve the needs of the agricultural community to accelerate the development of ML applications in agriculture.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1496066"},"PeriodicalIF":3.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11798914/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143365783","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":"Enhancing Africa's agriculture and food systems through responsible and gender inclusive AI innovation: insights from AI4AFS network.","authors":"Nicholas Ozor, Joel Nwakaire, Alfred Nyambane, Wentland Muhatiah, Cynthia Nwobodo","doi":"10.3389/frai.2024.1472236","DOIUrl":"10.3389/frai.2024.1472236","url":null,"abstract":"<p><p>The integration of artificial intelligence (AI) technologies into agriculture holds urgent and transformative potential for enhancing food security across Sub-Saharan Africa (SSA), a region acutely impacted by climate change and resource constraints. This paper examines experiences from the Artificial Intelligence for Agriculture and Food Systems (AI4AFS) Innovation Research Network, which provided funding to innovative projects in eight SSA countries. Through a set of case studies, we explore AI-driven solutions for pest and disease detection across crops such as cashew, maize, tomato, and cassava, including a real-time health monitoring tool for Nsukka Yellow pepper. Using participatory design, and key informant interview, robust monitoring and evaluation, and incorporating ethical frameworks, the research prioritizes gender equality, social inclusion, and environmental sustainability in AI development and deployment. Our results demonstrate that responsible AI practices can significantly enhance agricultural productivity while maintaining low carbon footprints. This research offers a unique, localized perspective on AI's role in addressing SSA's agricultural challenges, with implications for global food security as demand rises and environmental resources shrink. Key recommendations include establishing robust policy frameworks, strengthening capacity-building efforts, and securing sustainable funding mechanisms to support long-term AI adoption. This work provides the global community, policymakers, and stakeholders with critical insights on establishing ethical, responsible, and inclusive AI practices that can be adapted to similar agricultural contexts worldwide, contributing to sustainable food systems on an international scale.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1472236"},"PeriodicalIF":3.0,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11798938/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143365793","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":"Commentary: Implications of causality in artificial intelligence.","authors":"Jean-Christophe Bélisle-Pipon","doi":"10.3389/frai.2024.1488359","DOIUrl":"10.3389/frai.2024.1488359","url":null,"abstract":"","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1488359"},"PeriodicalIF":3.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794494/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143256955","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":"Self-trainable and adaptive sensor intelligence for selective data generation.","authors":"Arghavan Rezvani, Wenjun Huang, Hanning Chen, Yang Ni, Mohsen Imani","doi":"10.3389/frai.2024.1403187","DOIUrl":"10.3389/frai.2024.1403187","url":null,"abstract":"<p><p>With the increasing integration of machine learning into IoT devices, managing energy consumption and data transmission has become a critical challenge. Many IoT applications depend on complex computations performed on server-side infrastructure, necessitating efficient methods to reduce unnecessary data transmission. One promising solution involves deploying compact machine learning models near sensors, enabling intelligent identification and transmission of only relevant data frames. However, existing near-sensor models lack adaptability, as they require extensive pre-training and are often rigidly configured prior to deployment. This paper proposes a novel framework that fuses online learning, active learning, and knowledge distillation to enable adaptive, resource-efficient near-sensor intelligence. Our approach allows near-sensor models to dynamically fine-tune their parameters post-deployment using online learning, eliminating the need for extensive pre-labeling and training. Through a sequential training and execution process, the framework achieves continuous adaptability without prior knowledge of the deployment environment. To enhance performance while preserving model efficiency, we integrate knowledge distillation, enabling the transfer of critical insights from a larger teacher model to a compact student model. Additionally, active learning reduces the required training data while maintaining competitive performance. We validated our framework on both benchmark data from the MS COCO dataset and in a simulated IoT environment. The results demonstrate significant improvements in energy efficiency and data transmission optimization, highlighting the practical applicability of our method in real-world IoT scenarios.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1403187"},"PeriodicalIF":3.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794785/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255960","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":"Application of human-in-the-loop hybrid augmented intelligence approach in security inspection system.","authors":"Ying Huang, XiaoKan Wang, Yong Zhang, Li Chen, HongJi Zhang","doi":"10.3389/frai.2025.1518850","DOIUrl":"10.3389/frai.2025.1518850","url":null,"abstract":"<p><p>A security inspection system exemplifies human-machine collaboration, and enhancing its safety and reliability through advanced technology remains a key research priority. While deep learning has incrementally improved the autonomous capabilities of security inspection equipment for automatic contraband detection, a gap persists between current technological capabilities and practical implementation. Recognizing that humans excel at learning, reasoning, and collaborating, while artificial intelligence offers normative, repeatable, and logical processing, we propose a human-in-the-loop hybrid augmented intelligence approach. This approach addresses the practical needs of security inspection systems by introducing a hybrid decision-making method that leverages two distinct strategies: \"Reject-priority\" and \"Clear-priority.\" These strategies play complementary roles in bolstering the decision-making process's overall performance. Comparative experiments on a dataset from a specific security inspection site confirmed the hybrid method's effectiveness, drawing several conclusions. This \"Hybrid decision-making\" method not only enhances risk perception, thereby widening the safety margin of the security inspection system, but also reduces the need for human labor, leading to increased efficiency and reduced labor costs. Additionally, it is less time-consuming, further improving the system's overall efficiency. By integrating human and machine intelligence, this method significantly boosts decision-making effectiveness. Tailored to their unique characteristics, the method based on \"Reject-priority\" strategy is particularly well-suited for security inspection scenarios that demand stringent safety protocols, while the \"Clear-priority\" method is ideal for scenarios with high-volume traffic flow, where efficiency is paramount. As the volume of collected data grows, this approach will enable seamless adaptation of the method to evolving application needs.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1518850"},"PeriodicalIF":3.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794215/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143256030","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":"Gaussian process latent variable models-ANN based method for automatic features selection and dimensionality reduction for control of EMG-driven systems.","authors":"Maham Nayab, Asim Waris, Muhammad Jawad Khan, Dokhyl AlQahtani, Ahmed Imran, Syed Omer Gilani, Umer Hameed Shah","doi":"10.3389/frai.2025.1506042","DOIUrl":"10.3389/frai.2025.1506042","url":null,"abstract":"<p><p>Electromyography (EMG) signals have gained significant attention due to their potential applications in prosthetics, rehabilitation, and human-computer interfaces. However, the dimensionality of EMG signal features poses challenges in achieving accurate classification and reducing computational complexity. To overcome such issues, this paper proposes a novel approach that integrates feature reduction techniques with an artificial neural network (ANN) classifier to enhance the accuracy of high-dimensional EMG classification. This approach aims to improve the classification accuracy of EMG signals while substantially reducing computational costs, offering valuable implications for all EMG-related processes on such data. The proposed methodology involves extracting time and frequency domain features from twelve channels of EMG signals, followed by dimensionality reduction using techniques such as PCA, LDA, PPCA, Lasso and GPLVM, and classification using an ANN. Our investigation revealed that LDA is not appropriate for this dataset. The dimensionality reduction models did not have any significant effect on the accuracy, but the computational cost decreased significantly. In individual comparisons, GPLVM had the shortest computational time (29 s), which was significantly less than that of all the other models (<i>p</i> < 0.05), with PCA following at approximately 35 s and Relief at approximately 57 s, while PPCA took approximately 69 s, and Lasso exhibited higher computational costs than all the models but lower computational costs than did the original set. Using the best-performing features, all possible sets of 2, 3, 4 and 5 features were tested, and the 5-feature set exhibited the best performance. This research demonstrates the effectiveness of dimensionality reduction and feature selection in improving the accuracy of movement recognition in myoelectric control.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"8 ","pages":"1506042"},"PeriodicalIF":3.0,"publicationDate":"2025-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11794267/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143256042","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 overview of pink eye infection to evaluate its medications: group decision-making approach with 2-tuple linguistic <i>T</i>-spherical fuzzy WASPAS method.","authors":"M Waheed Rasheed, Hind Y Saleh, Areen A Salih, Jahangeer Karamat, Muhammad Bilal","doi":"10.3389/frai.2024.1496689","DOIUrl":"10.3389/frai.2024.1496689","url":null,"abstract":"<p><p>An infectious eye illness known as pink eye results in ocular redness, irritation, and mucus. Schools are an especially vulnerable region for dissemination because they can propagate that contagious disease quickly via direct or indirect interactions. Choosing the right medication to treat pink eye infection is typically thought of as an intricate multi-attribute group decision-making concern. The goal of this research is to construct a multi-attribute group decision-making framework that assesses six pink eye treatment medications, including Bleph-10, Moxeza, Zymar, Romycin, Polytrim, and Bacticin. The constructed multi-attribute group decision-making framework includes the following scenario: (1) In contrast to other types of fuzzy sets, the 2-tuple linguistic <i>T</i>-spherical fuzzy set (2TL<i>T</i>-SFS) looks to be a potent tool for dealing with informational inconsistencies in decision-making scenarios; (2) in order to render the 2TL<i>T</i>-SF accumulation details processing more flexible, the addition, multiplication, scalar multiplication, and exponential laws that are predicated on the Schweizer-Sklar collection of <i>t</i>-conorms and <i>t</i>-norms are described; (3) the Schweizer-Sklar weighted average and Schweizer-Sklar weighted geometric operators are then put forward employing the aforementioned operations to combine the data; (4) subsequently, using newly developed operators (referred to as 2TL<i>T</i>-SF Schweizer-Sklar weighted average and 2TL<i>T</i>-SF Schweizer-Sklar weighted geometric), this work enhances the conventional weighted aggregated sum product assessment (WASPAS) approach. The computation procedure for this methodology is thoroughly given to rank the alternatives; (5) to confirm the viability of the suggested approach, thorough computational and simulation assessments are conducted. An examination of the developed and existing research is compared to demonstrate the benefits of the suggested analysis.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1496689"},"PeriodicalIF":3.0,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11792285/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190823","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":"A conceptual ethical framework to preserve natural human presence in the use of AI systems in education.","authors":"Werner Alexander Isop","doi":"10.3389/frai.2024.1377938","DOIUrl":"10.3389/frai.2024.1377938","url":null,"abstract":"<p><p>In recent years, there has been a remarkable increase of interest in the ethical use of AI systems in education. On one hand, the potential for such systems is undeniable. Used responsibly, they can meaningfully support and enhance the interactive process of teaching and learning. On the other hand, there is a risk that natural human presence may be gradually replaced by arbitrarily created AI systems, particularly due to their rapidly increasing yet partially unguided capabilities. State-of-the-art ethical frameworks suggest high-level principles, requirements, and guidelines, but lack detailed low-level models of concrete processes and according properties of the involved actors in education. In response, this article introduces a detailed Unified Modeling Language (UML)-based ancillary framework that includes a novel set of low-level properties. Whilst not incorporated in related work, particularly the ethical behavior and visual representation of the actors are intended to improve transparency and reduce the potential for misinterpretation and misuse of AIS. The framework primarily focuses on school education, resulting in a more restrictive model, however, reflects on potentials and challenges in terms of improving flexibility toward different educational levels. The article concludes with a discussion of key findings and implications of the presented framework, its limitations, and potential future research directions to sustainably preserve natural human presence in the use of AI systems in education.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1377938"},"PeriodicalIF":3.0,"publicationDate":"2025-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11790613/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143190819","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}