Pub Date : 2024-11-05eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1392611
Seyed-Ali Sadegh-Zadeh, Sanaz Khanjani, Shima Javanmardi, Bita Bayat, Zahra Naderi, Amir M Hajiyavand
This study addresses the research problem of enhancing In-Vitro Fertilization (IVF) success rate prediction by integrating advanced machine learning paradigms with gynecological expertise. The methodology involves the analysis of comprehensive datasets from 2017 to 2018 and 2010-2016. Machine learning models, including Logistic Regression, Gaussian NB, SVM, MLP, KNN, and ensemble models like Random Forest, AdaBoost, Logit Boost, RUS Boost, and RSM, were employed. Key findings reveal the significance of patient demographics, infertility factors, and treatment protocols in IVF success prediction. Notably, ensemble learning methods demonstrated high accuracy, with Logit Boost achieving an accuracy of 96.35%. The implications of this research span clinical decision support, patient counseling, and data preprocessing techniques, highlighting the potential for personalized IVF treatments and continuous monitoring. The study underscores the importance of collaboration between gynecologists and data scientists to optimize IVF outcomes. Prospective studies and external validation are suggested as future directions, promising to further revolutionize fertility treatments and offer hope to couples facing infertility challenges.
{"title":"Catalyzing IVF outcome prediction: exploring advanced machine learning paradigms for enhanced success rate prognostication.","authors":"Seyed-Ali Sadegh-Zadeh, Sanaz Khanjani, Shima Javanmardi, Bita Bayat, Zahra Naderi, Amir M Hajiyavand","doi":"10.3389/frai.2024.1392611","DOIUrl":"https://doi.org/10.3389/frai.2024.1392611","url":null,"abstract":"<p><p>This study addresses the research problem of enhancing <i>In-Vitro</i> Fertilization (IVF) success rate prediction by integrating advanced machine learning paradigms with gynecological expertise. The methodology involves the analysis of comprehensive datasets from 2017 to 2018 and 2010-2016. Machine learning models, including Logistic Regression, Gaussian NB, SVM, MLP, KNN, and ensemble models like Random Forest, AdaBoost, Logit Boost, RUS Boost, and RSM, were employed. Key findings reveal the significance of patient demographics, infertility factors, and treatment protocols in IVF success prediction. Notably, ensemble learning methods demonstrated high accuracy, with Logit Boost achieving an accuracy of 96.35%. The implications of this research span clinical decision support, patient counseling, and data preprocessing techniques, highlighting the potential for personalized IVF treatments and continuous monitoring. The study underscores the importance of collaboration between gynecologists and data scientists to optimize IVF outcomes. Prospective studies and external validation are suggested as future directions, promising to further revolutionize fertility treatments and offer hope to couples facing infertility challenges.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1392611"},"PeriodicalIF":3.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11573753/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142677232","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}
Pub Date : 2024-11-05eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1477447
Jeremy A Balch, A Hayes Chatham, Philip K W Hong, Lauren Manganiello, Naveen Baskaran, Azra Bihorac, Benjamin Shickel, Ray E Moseley, Tyler J Loftus
Background: The algorithmic patient preference predictor (PPP) has been proposed to aid in decision making for incapacitated patients in the absence of advanced directives. Ethical and legal challenges aside, multiple practical barriers exist for building a personalized PPP. Here, we examine previous work using machine learning to predict patient reported outcome measures (PROMs) for capacitated patients undergoing diverse procedures, therapies, and life events. Demonstrating robust performance in predicting PROMs for capacitated patients could suggest opportunities for developing a model tailored to incapacitated ones.
Methods: We performed a scoping review of PubMed, Embase, and Scopus using the PRISMA-ScR guidelines to capture studies using machine learning to predict PROMs following a medical event alongside qualitative studies exploring a theoretical PPP.
Results: Sixty-eight studies used machine learning to evaluate PROMs; an additional 20 studies focused on a theoretical PPP. For PROMs, orthopedic surgeries (n = 33) and spinal surgeries (n = 12) were the most common medical event. Studies used demographic (n = 30), pre-event PROMs (n = 52), comorbidities (n = 29), social determinants of health (n = 30), and intraoperative variables (n = 124) as predictors. Thirty-four different PROMs were used as the target outcome. Evaluation metrics varied by task, but performance was overall poor to moderate for the best reported scores. In models that used feature importance, pre-event PROMs were the most predictive of post-event PROMs. Fairness assessments were rare (n = 6). These findings reinforce the necessity of the integrating patient values and preferences, beyond demographic factors, to improve the development of personalized PPP models for incapacitated patients.
Conclusion: The primary objective of a PPP is to estimate patient-reported quality of life following an intervention. Use of machine learning to predict PROMs for capacitated patients introduces challenges and opportunities for building a personalized PPP for incapacitated patients without advanced directives.
{"title":"Predicting patient reported outcome measures: a scoping review for the artificial intelligence-guided patient preference predictor.","authors":"Jeremy A Balch, A Hayes Chatham, Philip K W Hong, Lauren Manganiello, Naveen Baskaran, Azra Bihorac, Benjamin Shickel, Ray E Moseley, Tyler J Loftus","doi":"10.3389/frai.2024.1477447","DOIUrl":"https://doi.org/10.3389/frai.2024.1477447","url":null,"abstract":"<p><strong>Background: </strong>The algorithmic patient preference predictor (PPP) has been proposed to aid in decision making for incapacitated patients in the absence of advanced directives. Ethical and legal challenges aside, multiple practical barriers exist for building a personalized PPP. Here, we examine previous work using machine learning to predict patient reported outcome measures (PROMs) for capacitated patients undergoing diverse procedures, therapies, and life events. Demonstrating robust performance in predicting PROMs for capacitated patients could suggest opportunities for developing a model tailored to incapacitated ones.</p><p><strong>Methods: </strong>We performed a scoping review of PubMed, Embase, and Scopus using the PRISMA-ScR guidelines to capture studies using machine learning to predict PROMs following a medical event alongside qualitative studies exploring a theoretical PPP.</p><p><strong>Results: </strong>Sixty-eight studies used machine learning to evaluate PROMs; an additional 20 studies focused on a theoretical PPP. For PROMs, orthopedic surgeries (<i>n</i> = 33) and spinal surgeries (<i>n</i> = 12) were the most common medical event. Studies used demographic (<i>n</i> = 30), pre-event PROMs (<i>n</i> = 52), comorbidities (<i>n</i> = 29), social determinants of health (<i>n</i> = 30), and intraoperative variables (<i>n</i> = 124) as predictors. Thirty-four different PROMs were used as the target outcome. Evaluation metrics varied by task, but performance was overall poor to moderate for the best reported scores. In models that used feature importance, pre-event PROMs were the most predictive of post-event PROMs. Fairness assessments were rare (<i>n</i> = 6). These findings reinforce the necessity of the integrating patient values and preferences, beyond demographic factors, to improve the development of personalized PPP models for incapacitated patients.</p><p><strong>Conclusion: </strong>The primary objective of a PPP is to estimate patient-reported quality of life following an intervention. Use of machine learning to predict PROMs for <i>capacitated</i> patients introduces challenges and opportunities for building a personalized PPP for <i>incapacitated</i> patients without advanced directives.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1477447"},"PeriodicalIF":3.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11573790/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142677233","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}
Pub Date : 2024-11-04eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1474019
Andrew Runge, Yigal Attali, Geoffrey T LaFlair, Yena Park, Jacqueline Church
Introduction: Assessments of interactional competence have traditionally been limited in large-scale language assessments. The listening portion suffers from construct underrepresentation, whereas the speaking portion suffers from limited task formats such as in-person interviews or role plays. Human-delivered tasks are challenging to administer at large scales, while automated assessments are typically very narrow in their assessment of the construct because they have carried over the limitations of traditional paper-based tasks to digital formats. However, computer-based assessments do allow for more interactive, automatically administered tasks, but come with increased complexity in task creation. Large language models present new opportunities for enhanced automated item generation (AIG) processes that can create complex content types and tasks at scale that support richer assessments.
Methods: This paper describes the use of such methods to generate content at scale for an interactive listening measure of interactional competence for the Duolingo English Test (DET), a large-scale, high-stakes test of English proficiency. The Interactive Listening task assesses test takers' ability to participate in a full conversation, resulting in a more authentic assessment of interactive listening ability than prior automated assessments by positing comprehension and interaction as purposes of listening.
Results and discussion: The results of a pilot of 713 tasks with hundreds of responses per task, along with the results of human review, demonstrate the feasibility of a human-in-the-loop, generative AI-driven approach for automatic creation of complex educational assessments at scale.
简介在大规模语言评估中,对互动能力的评估历来受到限制。听力部分存在语篇代表性不足的问题,而口语部分则存在任务形式有限的问题,如面谈或角色扮演。大规模的人工任务具有挑战性,而自动评估由于将传统纸质任务的局限性转化为数字格式,因此对语构的评估通常非常狭窄。不过,基于计算机的评估的确可以实现互动性更强的自动管理任务,但同时也增加了任务创建的复杂性。大型语言模型为增强自动项目生成(AIG)流程提供了新的机遇,该流程可以大规模创建复杂的内容类型和任务,从而支持更丰富的评估:本文介绍了如何利用这些方法为杜林格英语测试(Duolingo English Test,DET)(一项大规模、高风险的英语水平测试)的互动听力能力测量大规模生成内容。互动听力任务评估的是应试者参与完整对话的能力,通过将理解和互动作为听力的目的,对互动听力能力的评估比以前的自动评估更加真实:713 项任务的试验结果(每项任务有数百个回答)以及人工审核的结果,证明了以人工智能为驱动的 "人在回路中 "生成方法在大规模自动创建复杂教育评估方面的可行性。
{"title":"A generative AI-driven interactive listening assessment task.","authors":"Andrew Runge, Yigal Attali, Geoffrey T LaFlair, Yena Park, Jacqueline Church","doi":"10.3389/frai.2024.1474019","DOIUrl":"10.3389/frai.2024.1474019","url":null,"abstract":"<p><strong>Introduction: </strong>Assessments of interactional competence have traditionally been limited in large-scale language assessments. The listening portion suffers from construct underrepresentation, whereas the speaking portion suffers from limited task formats such as in-person interviews or role plays. Human-delivered tasks are challenging to administer at large scales, while automated assessments are typically very narrow in their assessment of the construct because they have carried over the limitations of traditional paper-based tasks to digital formats. However, computer-based assessments do allow for more interactive, automatically administered tasks, but come with increased complexity in task creation. Large language models present new opportunities for enhanced automated item generation (AIG) processes that can create complex content types and tasks at scale that support richer assessments.</p><p><strong>Methods: </strong>This paper describes the use of such methods to generate content at scale for an interactive listening measure of interactional competence for the Duolingo English Test (DET), a large-scale, high-stakes test of English proficiency. The Interactive Listening task assesses test takers' ability to participate in a full conversation, resulting in a more authentic assessment of interactive listening ability than prior automated assessments by positing comprehension and interaction as purposes of listening.</p><p><strong>Results and discussion: </strong>The results of a pilot of 713 tasks with hundreds of responses per task, along with the results of human review, demonstrate the feasibility of a human-in-the-loop, generative AI-driven approach for automatic creation of complex educational assessments at scale.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1474019"},"PeriodicalIF":3.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571064/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142669235","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}
Pub Date : 2024-11-01eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1455331
Geofrey Kapalaga, Florence N Kivunike, Susan Kerfua, Daudi Jjingo, Savino Biryomumaisho, Justus Rutaisire, Paul Ssajjakambwe, Swidiq Mugerwa, Seguya Abbey, Mulindwa H Aaron, Yusuf Kiwala
Foot-and-mouth disease poses a significant threat to both domestic and wild cloven-hoofed animals, leading to severe economic losses and jeopardizing food security. While machine learning models have become essential for predicting foot-and-mouth disease outbreaks, their effectiveness is often compromised by distribution shifts between training and target datasets, especially in non-stationary environments. Despite the critical impact of these shifts, their implications in foot-and-mouth disease outbreak prediction have been largely overlooked. This study introduces the Calibrated Uncertainty Prediction approach, designed to enhance the performance of Random Forest models in predicting foot-and-mouth disease outbreaks across varying distributions. The Calibrated Uncertainty Prediction approach effectively addresses distribution shifts by calibrating uncertain instances for pseudo-label annotation, allowing the active learner to generalize more effectively to the target domain. By utilizing a probabilistic calibration model, Calibrated Uncertainty Prediction pseudo-annotates the most informative instances, refining the active learner iteratively and minimizing the need for human annotation and outperforming existing methods known to mitigate distribution shifts. This reduces costs, saves time, and lessens the dependence on domain experts while achieving outstanding predictive performance. The results demonstrate that Calibrated Uncertainty Prediction significantly enhances predictive performance in non-stationary environments, achieving an accuracy of 98.5%, Area Under the Curve of 0.842, recall of 0.743, precision of 0.855, and an F1 score of 0.791. These findings underscore Calibrated Uncertainty Prediction's ability to overcome the vulnerabilities of existing ML models, offering a robust solution for foot-and-mouth disease outbreak prediction and contributing to the broader field of predictive modeling in infectious disease management.
口蹄疫对家养和野生蹄类动物都构成了重大威胁,导致严重的经济损失并危及粮食安全。虽然机器学习模型已成为预测口蹄疫爆发的关键,但其有效性往往会因训练数据集和目标数据集之间的分布变化而受到影响,尤其是在非稳态环境中。尽管这些变化具有重要影响,但它们在口蹄疫疫情预测中的意义却在很大程度上被忽视了。本研究介绍了校准不确定性预测方法,旨在提高随机森林模型在不同分布情况下预测口蹄疫爆发的性能。校准不确定性预测方法通过校准伪标签注释的不确定实例来有效解决分布偏移问题,从而使主动学习器更有效地泛化到目标领域。通过利用概率校准模型,"校准不确定性预测 "会对信息量最大的实例进行伪标注,从而迭代改进主动学习器,最大限度地减少对人工标注的需求,并超越已知可减轻分布偏移的现有方法。这降低了成本,节省了时间,减少了对领域专家的依赖,同时实现了出色的预测性能。结果表明,校准不确定性预测显著提高了非稳态环境下的预测性能,准确率达到 98.5%,曲线下面积为 0.842,召回率为 0.743,精确度为 0.855,F1 分数为 0.791。这些发现强调了校准不确定性预测克服现有 ML 模型弱点的能力,为口蹄疫疫情预测提供了强大的解决方案,并为更广泛的传染病管理预测建模领域做出了贡献。
{"title":"Enhancing random forest predictive performance for foot and mouth disease outbreaks in Uganda: a calibrated uncertainty prediction approach for varying distributions.","authors":"Geofrey Kapalaga, Florence N Kivunike, Susan Kerfua, Daudi Jjingo, Savino Biryomumaisho, Justus Rutaisire, Paul Ssajjakambwe, Swidiq Mugerwa, Seguya Abbey, Mulindwa H Aaron, Yusuf Kiwala","doi":"10.3389/frai.2024.1455331","DOIUrl":"10.3389/frai.2024.1455331","url":null,"abstract":"<p><p>Foot-and-mouth disease poses a significant threat to both domestic and wild cloven-hoofed animals, leading to severe economic losses and jeopardizing food security. While machine learning models have become essential for predicting foot-and-mouth disease outbreaks, their effectiveness is often compromised by distribution shifts between training and target datasets, especially in non-stationary environments. Despite the critical impact of these shifts, their implications in foot-and-mouth disease outbreak prediction have been largely overlooked. This study introduces the Calibrated Uncertainty Prediction approach, designed to enhance the performance of Random Forest models in predicting foot-and-mouth disease outbreaks across varying distributions. The Calibrated Uncertainty Prediction approach effectively addresses distribution shifts by calibrating uncertain instances for pseudo-label annotation, allowing the active learner to generalize more effectively to the target domain. By utilizing a probabilistic calibration model, Calibrated Uncertainty Prediction pseudo-annotates the most informative instances, refining the active learner iteratively and minimizing the need for human annotation and outperforming existing methods known to mitigate distribution shifts. This reduces costs, saves time, and lessens the dependence on domain experts while achieving outstanding predictive performance. The results demonstrate that Calibrated Uncertainty Prediction significantly enhances predictive performance in non-stationary environments, achieving an accuracy of 98.5%, Area Under the Curve of 0.842, recall of 0.743, precision of 0.855, and an F1 score of 0.791. These findings underscore Calibrated Uncertainty Prediction's ability to overcome the vulnerabilities of existing ML models, offering a robust solution for foot-and-mouth disease outbreak prediction and contributing to the broader field of predictive modeling in infectious disease management.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1455331"},"PeriodicalIF":3.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11564173/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142649200","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}
Pub Date : 2024-11-01eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1452131
Chien Ching Lee, Malcolm Yoke Hean Low
{"title":"Using genAI in education: the case for critical thinking.","authors":"Chien Ching Lee, Malcolm Yoke Hean Low","doi":"10.3389/frai.2024.1452131","DOIUrl":"https://doi.org/10.3389/frai.2024.1452131","url":null,"abstract":"","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1452131"},"PeriodicalIF":3.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11564148/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142649201","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}
Pub Date : 2024-10-30eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1447171
Tamar Gur, Boaz Hameiri, Yossi Maaravi
In a world grappling with technological advancements, the concept of Artificial Intelligence (AI) in governance is becoming increasingly realistic. While some may find this possibility incredibly alluring, others may see it as dystopian. Society must account for these varied opinions when implementing new technologies or regulating and limiting them. This study (N = 703) explored Leftists' (liberals) and Rightists' (conservatives) support for using AI in governance decision-making amidst an unprecedented political crisis that washed through Israel shortly after the proclamation of the government's intentions to initiate reform. Results indicate that Leftists are more favorable toward AI in governance. While legitimacy is tied to support for using AI in governance among both, Rightists' acceptance is also tied to perceived norms, whereas Leftists' approval is linked to perceived utility, political efficacy, and warmth. Understanding these ideological differences is crucial, both theoretically and for practical policy formulation regarding AI's integration into governance.
{"title":"Political ideology shapes support for the use of AI in policy-making.","authors":"Tamar Gur, Boaz Hameiri, Yossi Maaravi","doi":"10.3389/frai.2024.1447171","DOIUrl":"10.3389/frai.2024.1447171","url":null,"abstract":"<p><p>In a world grappling with technological advancements, the concept of Artificial Intelligence (AI) in governance is becoming increasingly realistic. While some may find this possibility incredibly alluring, others may see it as dystopian. Society must account for these varied opinions when implementing new technologies or regulating and limiting them. This study (<i>N</i> = 703) explored Leftists' (liberals) and Rightists' (conservatives) support for using AI in governance decision-making amidst an unprecedented political crisis that washed through Israel shortly after the proclamation of the government's intentions to initiate reform. Results indicate that Leftists are more favorable toward AI in governance. While legitimacy is tied to support for using AI in governance among both, Rightists' acceptance is also tied to perceived norms, whereas Leftists' approval is linked to perceived utility, political efficacy, and warmth. Understanding these ideological differences is crucial, both theoretically and for practical policy formulation regarding AI's integration into governance.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1447171"},"PeriodicalIF":3.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11557559/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142629583","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}
Pub Date : 2024-10-30eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1435686
Md Nazmuzzaman Khan, Adibuzzaman Rahi, Veera P Rajendran, Mohammad Al Hasan, Sohel Anwar
The goal of achieving autonomous navigation for agricultural robots poses significant challenges, mostly arising from the substantial natural variations in crop row images as a result of weather conditions and the growth stages of crops. The processing of the detection algorithm also must be significantly low for real-time applications. In order to address the aforementioned requirements, we propose a crop row detection algorithm that has the following features: Firstly, a projective transformation is applied to transform the camera view and a color-based segmentation is employed to distinguish crop and weed from the background. Secondly, a clustering algorithm is used to differentiate between the crop and weed pixels. Lastly, a robust line-fitting approach is implemented to detect crop rows. The proposed algorithm is evaluated throughout a diverse range of scenarios, and its efficacy is assessed in comparison to four distinct existing solutions. The algorithm achieves an overall intersection over union (IOU) of 0.73 and exhibits robustness in challenging scenarios with high weed growth. The experiments conducted on real-time video featuring challenging scenarios show that our proposed algorithm exhibits a detection accuracy of over 90% and is a viable option for real-time implementation. With the high accuracy and low inference time, the proposed methodology offers a viable solution for autonomous navigation of agricultural robots in a crop field without damaging the crop and thus can serve as a foundation for future research.
{"title":"Real-time crop row detection using computer vision- application in agricultural robots.","authors":"Md Nazmuzzaman Khan, Adibuzzaman Rahi, Veera P Rajendran, Mohammad Al Hasan, Sohel Anwar","doi":"10.3389/frai.2024.1435686","DOIUrl":"10.3389/frai.2024.1435686","url":null,"abstract":"<p><p>The goal of achieving autonomous navigation for agricultural robots poses significant challenges, mostly arising from the substantial natural variations in crop row images as a result of weather conditions and the growth stages of crops. The processing of the detection algorithm also must be significantly low for real-time applications. In order to address the aforementioned requirements, we propose a crop row detection algorithm that has the following features: Firstly, a projective transformation is applied to transform the camera view and a color-based segmentation is employed to distinguish crop and weed from the background. Secondly, a clustering algorithm is used to differentiate between the crop and weed pixels. Lastly, a robust line-fitting approach is implemented to detect crop rows. The proposed algorithm is evaluated throughout a diverse range of scenarios, and its efficacy is assessed in comparison to four distinct existing solutions. The algorithm achieves an overall intersection over union (IOU) of 0.73 and exhibits robustness in challenging scenarios with high weed growth. The experiments conducted on real-time video featuring challenging scenarios show that our proposed algorithm exhibits a detection accuracy of over 90% and is a viable option for real-time implementation. With the high accuracy and low inference time, the proposed methodology offers a viable solution for autonomous navigation of agricultural robots in a crop field without damaging the crop and thus can serve as a foundation for future research.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1435686"},"PeriodicalIF":3.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11558879/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142629588","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}
Pub Date : 2024-10-25eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1424371
Ömer Ates, Garima Pandey, Athanasios Gousiopoulos, Theodoros G Soldatos
Recent developments on artificial intelligence (AI) and machine learning (ML) techniques are expected to have significant impact on public health in several ways. Indeed, modern AI/ML methods have been applied on multiple occasions on topics ranging from drug discovery and disease diagnostics to personalized medicine, medical imaging, and healthcare operations. While such developments may improve several quality-of-life aspects (such as access to health services and education), it is important considering that some individuals may face more challenges, particularly in extreme or emergency situations. In this work, we focus on utilizing AI/ML components to support scenarios when visual impairment or other limitations hinder the ability to interpret the world in this way. Specifically, we discuss the potential and the feasibility of automatically transferring key visual information into audio communication, in different languages and in real-time-a setting which we name 'audible reality' (AuRa). We provide a short guide to practical options currently available for implementing similar solutions and summarize key aspects for evaluating their scope. Finally, we discuss diverse settings and functionalities that AuRA applications could have in terms of broader impact, from a social and public health context, and invite the community to further such digital solutions and perspectives soon.
{"title":"A brief reference to AI-driven audible reality (AuRa) in open world: potential, applications, and evaluation.","authors":"Ömer Ates, Garima Pandey, Athanasios Gousiopoulos, Theodoros G Soldatos","doi":"10.3389/frai.2024.1424371","DOIUrl":"https://doi.org/10.3389/frai.2024.1424371","url":null,"abstract":"<p><p>Recent developments on artificial intelligence (AI) and machine learning (ML) techniques are expected to have significant impact on public health in several ways. Indeed, modern AI/ML methods have been applied on multiple occasions on topics ranging from drug discovery and disease diagnostics to personalized medicine, medical imaging, and healthcare operations. While such developments may improve several quality-of-life aspects (such as access to health services and education), it is important considering that some individuals may face more challenges, particularly in extreme or emergency situations. In this work, we focus on utilizing AI/ML components to support scenarios when visual impairment or other limitations hinder the ability to interpret the world in this way. Specifically, we discuss the potential and the feasibility of automatically transferring key visual information into audio communication, in different languages and in real-time-a setting which we name '<i>au</i>dible <i>r</i>e<i>a</i>lity' (AuRa). We provide a short guide to practical options currently available for implementing similar solutions and summarize key aspects for evaluating their scope. Finally, we discuss diverse settings and functionalities that AuRA applications could have in terms of broader impact, from a social and public health context, and invite the community to further such digital solutions and perspectives soon.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1424371"},"PeriodicalIF":3.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11543578/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142629550","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}
Pub Date : 2024-10-25eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1326153
Djavan De Clercq, Elias Nehring, Harry Mayne, Adam Mahdi
Coverage of ChatGPT-style large language models (LLMs) in the media has focused on their eye-catching achievements, including solving advanced mathematical problems and reaching expert proficiency in medical examinations. But the gradual adoption of LLMs in agriculture, an industry which touches every human life, has received much less public scrutiny. In this short perspective, we examine risks and opportunities related to more widespread adoption of language models in food production systems. While LLMs can potentially enhance agricultural efficiency, drive innovation, and inform better policies, challenges like agricultural misinformation, collection of vast amounts of farmer data, and threats to agricultural jobs are important concerns. The rapid evolution of the LLM landscape underscores the need for agricultural policymakers to think carefully about frameworks and guidelines that ensure the responsible use of LLMs in food production before these technologies become so ingrained that policy intervention becomes challenging.
{"title":"Large language models can help boost food production, but be mindful of their risks.","authors":"Djavan De Clercq, Elias Nehring, Harry Mayne, Adam Mahdi","doi":"10.3389/frai.2024.1326153","DOIUrl":"https://doi.org/10.3389/frai.2024.1326153","url":null,"abstract":"<p><p>Coverage of ChatGPT-style large language models (LLMs) in the media has focused on their eye-catching achievements, including solving advanced mathematical problems and reaching expert proficiency in medical examinations. But the gradual adoption of LLMs in agriculture, an industry which touches every human life, has received much less public scrutiny. In this short perspective, we examine risks and opportunities related to more widespread adoption of language models in food production systems. While LLMs can potentially enhance agricultural efficiency, drive innovation, and inform better policies, challenges like agricultural misinformation, collection of vast amounts of farmer data, and threats to agricultural jobs are important concerns. The rapid evolution of the LLM landscape underscores the need for agricultural policymakers to think carefully about frameworks and guidelines that ensure the responsible use of LLMs in food production before these technologies become so ingrained that policy intervention becomes challenging.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1326153"},"PeriodicalIF":3.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11543567/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142629563","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}
Pub Date : 2024-10-24eCollection Date: 2024-01-01DOI: 10.3389/frai.2024.1471208
Stefan Haas, Konstantin Hegestweiler, Michael Rapp, Maximilian Muschalik, Eyke Hüllermeier
Machine learning has made tremendous progress in predictive performance in recent years. Despite these advances, employing machine learning models in high-stake domains remains challenging due to the opaqueness of many high-performance models. If their behavior cannot be analyzed, this likely decreases the trust in such models and hinders the acceptance of human decision-makers. Motivated by these challenges, we propose a process model for developing and evaluating explainable decision support systems that are tailored to the needs of different stakeholders. To demonstrate its usefulness, we apply the process model to a real-world application in an enterprise context. The goal is to increase the acceptance of an existing black-box model developed at a car manufacturer for supporting manual goodwill assessments. Following the proposed process, we conduct two quantitative surveys targeted at the application's stakeholders. Our study reveals that textual explanations based on local feature importance best fit the needs of the stakeholders in the considered use case. Specifically, our results show that all stakeholders, including business specialists, goodwill assessors, and technical IT experts, agree that such explanations significantly increase their trust in the decision support system. Furthermore, our technical evaluation confirms the faithfulness and stability of the selected explanation method. These practical findings demonstrate the potential of our process model to facilitate the successful deployment of machine learning models in enterprise settings. The results emphasize the importance of developing explanations that are tailored to the specific needs and expectations of diverse stakeholders.
近年来,机器学习在预测性能方面取得了巨大进步。尽管取得了这些进步,但由于许多高性能模型的不透明性,在高风险领域使用机器学习模型仍具有挑战性。如果无法对其行为进行分析,很可能会降低对此类模型的信任度,并阻碍人类决策者对其的接受。在这些挑战的激励下,我们提出了一个流程模型,用于开发和评估可解释的决策支持系统,以满足不同利益相关者的需求。为了证明其实用性,我们将该流程模型应用于企业环境中的实际应用。我们的目标是提高一家汽车制造商为支持人工商誉评估而开发的现有黑盒模型的接受度。按照建议的流程,我们针对应用程序的利益相关者进行了两次定量调查。我们的研究表明,在所考虑的用例中,基于局部特征重要性的文字说明最符合利益相关者的需求。具体来说,我们的研究结果表明,所有利益相关者,包括业务专家、商誉评估员和 IT 技术专家,都认为这种解释能显著提高他们对决策支持系统的信任度。此外,我们的技术评估证实了所选解释方法的忠实性和稳定性。这些实际研究结果表明,我们的流程模型具有促进机器学习模型在企业环境中成功部署的潜力。结果强调了根据不同利益相关者的具体需求和期望制定解释的重要性。
{"title":"Stakeholder-centric explanations for black-box decisions: an XAI process model and its application to automotive goodwill assessments.","authors":"Stefan Haas, Konstantin Hegestweiler, Michael Rapp, Maximilian Muschalik, Eyke Hüllermeier","doi":"10.3389/frai.2024.1471208","DOIUrl":"https://doi.org/10.3389/frai.2024.1471208","url":null,"abstract":"<p><p>Machine learning has made tremendous progress in predictive performance in recent years. Despite these advances, employing machine learning models in high-stake domains remains challenging due to the opaqueness of many high-performance models. If their behavior cannot be analyzed, this likely decreases the trust in such models and hinders the acceptance of human decision-makers. Motivated by these challenges, we propose a process model for developing and evaluating explainable decision support systems that are tailored to the needs of different stakeholders. To demonstrate its usefulness, we apply the process model to a real-world application in an enterprise context. The goal is to increase the acceptance of an existing black-box model developed at a car manufacturer for supporting manual goodwill assessments. Following the proposed process, we conduct two quantitative surveys targeted at the application's stakeholders. Our study reveals that textual explanations based on local feature importance best fit the needs of the stakeholders in the considered use case. Specifically, our results show that all stakeholders, including business specialists, goodwill assessors, and technical IT experts, agree that such explanations significantly increase their trust in the decision support system. Furthermore, our technical evaluation confirms the faithfulness and stability of the selected explanation method. These practical findings demonstrate the potential of our process model to facilitate the successful deployment of machine learning models in enterprise settings. The results emphasize the importance of developing explanations that are tailored to the specific needs and expectations of diverse stakeholders.</p>","PeriodicalId":33315,"journal":{"name":"Frontiers in Artificial Intelligence","volume":"7 ","pages":"1471208"},"PeriodicalIF":3.0,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11540772/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142606638","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}