Pub Date : 2024-07-26DOI: 10.3390/informatics11030054
Moonkyoung Jang
With the increasing use of large-scale language model-based AI tools in modern learning environments, it is important to understand students’ motivations, experiences, and contextual influences. These tools offer new support dimensions for learners, enhancing academic achievement and providing valuable resources, but their use also raises ethical and social issues. In this context, this study aims to systematically identify factors influencing the usage intentions of text-based GenAI tools among undergraduates. By modifying the core variables of the Unified Theory of Acceptance and Use of Technology (UTAUT) with AI literacy, a survey was designed to measure GenAI users’ intentions to collect participants’ opinions. The survey, conducted among business students at a university in South Korea, gathered 239 responses during March and April 2024. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS software (Ver. 4.0.9.6). The findings reveal that performance expectancy significantly affects the intention to use GenAI, while effort expectancy does not. In addition, AI literacy and social influence significantly influence performance, effort expectancy, and the intention to use GenAI. This study provides insights into determinants affecting GenAI usage intentions, aiding the development of effective educational strategies and policies to support ethical and beneficial AI use in academic settings.
{"title":"AI Literacy and Intention to Use Text-Based GenAI for Learning: The Case of Business Students in Korea","authors":"Moonkyoung Jang","doi":"10.3390/informatics11030054","DOIUrl":"https://doi.org/10.3390/informatics11030054","url":null,"abstract":"With the increasing use of large-scale language model-based AI tools in modern learning environments, it is important to understand students’ motivations, experiences, and contextual influences. These tools offer new support dimensions for learners, enhancing academic achievement and providing valuable resources, but their use also raises ethical and social issues. In this context, this study aims to systematically identify factors influencing the usage intentions of text-based GenAI tools among undergraduates. By modifying the core variables of the Unified Theory of Acceptance and Use of Technology (UTAUT) with AI literacy, a survey was designed to measure GenAI users’ intentions to collect participants’ opinions. The survey, conducted among business students at a university in South Korea, gathered 239 responses during March and April 2024. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS software (Ver. 4.0.9.6). The findings reveal that performance expectancy significantly affects the intention to use GenAI, while effort expectancy does not. In addition, AI literacy and social influence significantly influence performance, effort expectancy, and the intention to use GenAI. This study provides insights into determinants affecting GenAI usage intentions, aiding the development of effective educational strategies and policies to support ethical and beneficial AI use in academic settings.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"53 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141798692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-22DOI: 10.3390/informatics11030052
Parya Fathi, Mita Bhattacharya, Sankar Bhattacharya, Nemai Karmakar
Effective monitoring of perishable food products has become increasingly important for ensuring quality, enabling smart packaging to be a key consideration for food companies. Among the promising technologies available for transforming packaging into intelligent packaging, chipless radio frequency identification (RFID) sensors stand out. Despite the high initial implementation costs associated with chipless RFID technology, the potential benefits could outweigh the costs if electrical challenges can be overcome. We examine various economic methods to analyze the economic benefits of chipless RFID technology, evaluating the benefits of using this technology for the quality monitoring of seafood products of an Australian seafood producer, Tassal. The analysis considers three primary business drivers, viz. quality monitoring, operational efficiency, and tracking and tracing, using net present value and return on investment as the key indicators to assess the feasibility of implementing the technology. Based on sensitivity analysis, we suggest chipless RFID technology is currently best suited for large firms facing significant quality monitoring and operational efficiency challenges. However, as the cost of chipless RFID sensors decreases with further development, this technology may become a more viable option for small businesses in the future.
有效监控易腐食品对确保质量越来越重要，这使得智能包装成为食品公司的一个重要考虑因素。在将包装转变为智能包装的众多前景看好的技术中，无芯片射频识别（RFID）传感器脱颖而出。尽管无芯片 RFID 技术的初期实施成本较高，但如果能克服电气方面的挑战，其潜在效益可能会超过成本。我们研究了各种经济方法来分析无芯片 RFID 技术的经济效益，评估了澳大利亚海产品生产商 Tassal 使用该技术监控海产品质量的效益。分析考虑了三个主要业务驱动因素，即质量监控、运营效率以及跟踪和追溯，并将净现值和投资回报率作为评估实施该技术可行性的关键指标。根据敏感性分析，我们认为无芯片 RFID 技术目前最适合面临重大质量监控和运营效率挑战的大型企业。不过，随着无芯片 RFID 传感器成本的进一步降低，这项技术未来可能会成为小型企业更可行的选择。
{"title":"Use of Chipless Radio Frequency Identification Technology for Smart Food Packaging: An Economic Analysis for an Australian Seafood Industry","authors":"Parya Fathi, Mita Bhattacharya, Sankar Bhattacharya, Nemai Karmakar","doi":"10.3390/informatics11030052","DOIUrl":"https://doi.org/10.3390/informatics11030052","url":null,"abstract":"Effective monitoring of perishable food products has become increasingly important for ensuring quality, enabling smart packaging to be a key consideration for food companies. Among the promising technologies available for transforming packaging into intelligent packaging, chipless radio frequency identification (RFID) sensors stand out. Despite the high initial implementation costs associated with chipless RFID technology, the potential benefits could outweigh the costs if electrical challenges can be overcome. We examine various economic methods to analyze the economic benefits of chipless RFID technology, evaluating the benefits of using this technology for the quality monitoring of seafood products of an Australian seafood producer, Tassal. The analysis considers three primary business drivers, viz. quality monitoring, operational efficiency, and tracking and tracing, using net present value and return on investment as the key indicators to assess the feasibility of implementing the technology. Based on sensitivity analysis, we suggest chipless RFID technology is currently best suited for large firms facing significant quality monitoring and operational efficiency challenges. However, as the cost of chipless RFID sensors decreases with further development, this technology may become a more viable option for small businesses in the future.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"70 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141817594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The surging prevalence of diabetes globally necessitates advancements in non-invasive diagnostics, particularly for the early detection of cardiovascular anomalies associated with the condition. This study explores the efficacy of Pulse Wave Analysis (PWA) for distinguishing diabetic from non-diabetic individuals through morphological examination of pressure pulse waveforms. The research unfolds in four phases: data accrual, preprocessing, Convolutional Neural Network (CNN) model construction, and performance evaluation. Data were procured using a multipara patient monitor, resulting in 2000 pulse waves equally divided between healthy individuals and those with diabetes. These were used to train, validate, and test three distinct CNN architectures: the conventional CNN, Visual Geometry Group (VGG16), and Residual Networks (ResNet18). The accuracy, precision, recall, and F1 score gauged each model’s proficiency. The CNN demonstrated a training accuracy of 82.09% and a testing accuracy of 80.6%. The VGG16, with its deeper structure, surpassed the baseline with training and testing accuracies of 90.2% and 86.57%, respectively. ResNet18 excelled, achieving a training accuracy of 92.50% and a testing accuracy of 92.00%, indicating its robustness in pattern recognition within pulse wave data. Deploying deep learning for diabetes screening marks progress, suggesting clinical use and future studies on bigger datasets for refinement.
{"title":"Non-Invasive Diagnostic Approach for Diabetes Using Pulse Wave Analysis and Deep Learning","authors":"Hiruni Gunathilaka, Rumesh Rajapaksha, Thosini Kumarika, Dinusha Perera, Uditha Herath, Charith Jayathilaka, Janitha Liyanage, Sudath Kalingamudali","doi":"10.3390/informatics11030051","DOIUrl":"https://doi.org/10.3390/informatics11030051","url":null,"abstract":"The surging prevalence of diabetes globally necessitates advancements in non-invasive diagnostics, particularly for the early detection of cardiovascular anomalies associated with the condition. This study explores the efficacy of Pulse Wave Analysis (PWA) for distinguishing diabetic from non-diabetic individuals through morphological examination of pressure pulse waveforms. The research unfolds in four phases: data accrual, preprocessing, Convolutional Neural Network (CNN) model construction, and performance evaluation. Data were procured using a multipara patient monitor, resulting in 2000 pulse waves equally divided between healthy individuals and those with diabetes. These were used to train, validate, and test three distinct CNN architectures: the conventional CNN, Visual Geometry Group (VGG16), and Residual Networks (ResNet18). The accuracy, precision, recall, and F1 score gauged each model’s proficiency. The CNN demonstrated a training accuracy of 82.09% and a testing accuracy of 80.6%. The VGG16, with its deeper structure, surpassed the baseline with training and testing accuracies of 90.2% and 86.57%, respectively. ResNet18 excelled, achieving a training accuracy of 92.50% and a testing accuracy of 92.00%, indicating its robustness in pattern recognition within pulse wave data. Deploying deep learning for diabetes screening marks progress, suggesting clinical use and future studies on bigger datasets for refinement.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":" 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141823008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Currently, utilizing virtualization technology in data centers often imposes an increasing burden on the host machine (HM), leading to a decline in VM performance. To address this issue, live virtual migration (LVM) is employed to alleviate the load on the VM. This study introduces a hybrid machine learning model designed to estimate the direct migration of pre-copied migration virtual machines within the data center. The proposed model integrates Markov Decision Process (MDP), genetic algorithm (GA), and random forest (RF) algorithms to forecast the prioritized movement of virtual machines and identify the optimal host machine target. The hybrid models achieve a 99% accuracy rate with quicker training times compared to the previous studies that utilized K-nearest neighbor, decision tree classification, support vector machines, logistic regression, and neural networks. The authors recommend further exploration of a deep learning approach (DL) to address other data center performance issues. This paper outlines promising strategies for enhancing virtual machine migration in data centers. The hybrid models demonstrate high accuracy and faster training times than previous research, indicating the potential for optimizing virtual machine placement and minimizing downtime. The authors emphasize the significance of considering data center performance and propose further investigation. Moreover, it would be beneficial to delve into the practical implementation and dissemination of the proposed model in real-world data centers.
目前，在数据中心使用虚拟化技术往往会给主机（HM）带来越来越大的负担，导致虚拟机性能下降。为解决这一问题，采用了实时虚拟迁移（LVM）来减轻虚拟机的负担。本研究介绍了一种混合机器学习模型，旨在估算数据中心内预复制迁移虚拟机的直接迁移。提出的模型集成了马尔可夫决策过程（MDP）、遗传算法（GA）和随机森林（RF）算法，用于预测虚拟机的优先移动并确定最佳主机目标。与之前利用 K 近邻、决策树分类、支持向量机、逻辑回归和神经网络的研究相比，混合模型的准确率达到了 99%，而且训练时间更短。作者建议进一步探索深度学习方法（DL），以解决其他数据中心性能问题。本文概述了增强数据中心虚拟机迁移的可行策略。与之前的研究相比，混合模型表现出更高的准确性和更快的训练时间，这表明了优化虚拟机放置和最大限度减少停机时间的潜力。作者强调了考虑数据中心性能的重要性，并提出了进一步研究的建议。此外，深入研究拟议模型在现实世界数据中心的实际应用和推广也将大有裨益。
{"title":"Machine Learning to Estimate Workload and Balance Resources with Live Migration and VM Placement","authors":"Taufik Hidayat, K. Ramli, Nadia Thereza, Amarudin Daulay, Rushendra Rushendra, Rahutomo Mahardiko","doi":"10.3390/informatics11030050","DOIUrl":"https://doi.org/10.3390/informatics11030050","url":null,"abstract":"Currently, utilizing virtualization technology in data centers often imposes an increasing burden on the host machine (HM), leading to a decline in VM performance. To address this issue, live virtual migration (LVM) is employed to alleviate the load on the VM. This study introduces a hybrid machine learning model designed to estimate the direct migration of pre-copied migration virtual machines within the data center. The proposed model integrates Markov Decision Process (MDP), genetic algorithm (GA), and random forest (RF) algorithms to forecast the prioritized movement of virtual machines and identify the optimal host machine target. The hybrid models achieve a 99% accuracy rate with quicker training times compared to the previous studies that utilized K-nearest neighbor, decision tree classification, support vector machines, logistic regression, and neural networks. The authors recommend further exploration of a deep learning approach (DL) to address other data center performance issues. This paper outlines promising strategies for enhancing virtual machine migration in data centers. The hybrid models demonstrate high accuracy and faster training times than previous research, indicating the potential for optimizing virtual machine placement and minimizing downtime. The authors emphasize the significance of considering data center performance and propose further investigation. Moreover, it would be beneficial to delve into the practical implementation and dissemination of the proposed model in real-world data centers.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"104 23","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141821890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-19DOI: 10.3390/informatics11030049
Yan Cong
AI language models are increasingly transforming language research in various ways. How can language educators and researchers respond to the challenge posed by these AI models? Specifically, how can we embrace this technology to inform and enhance second language learning and teaching? In order to quantitatively characterize and index second language writing, the current work proposes the use of similarities derived from contextualized meaning representations in AI language models. The computational analysis in this work is hypothesis-driven. The current work predicts how similarities should be distributed in a second language learning setting. The results suggest that similarity metrics are informative of writing proficiency assessment and interlanguage development. Statistically significant effects were found across multiple AI models. Most of the metrics could distinguish language learners’ proficiency levels. Significant correlations were also found between similarity metrics and learners’ writing test scores provided by human experts in the domain. However, not all such effects were strong or interpretable. Several results could not be consistently explained under the proposed second language learning hypotheses. Overall, the current investigation indicates that with careful configuration and systematic metrics design, AI language models can be promising tools in advancing language education.
{"title":"AI Language Models: An Opportunity to Enhance Language Learning","authors":"Yan Cong","doi":"10.3390/informatics11030049","DOIUrl":"https://doi.org/10.3390/informatics11030049","url":null,"abstract":"AI language models are increasingly transforming language research in various ways. How can language educators and researchers respond to the challenge posed by these AI models? Specifically, how can we embrace this technology to inform and enhance second language learning and teaching? In order to quantitatively characterize and index second language writing, the current work proposes the use of similarities derived from contextualized meaning representations in AI language models. The computational analysis in this work is hypothesis-driven. The current work predicts how similarities should be distributed in a second language learning setting. The results suggest that similarity metrics are informative of writing proficiency assessment and interlanguage development. Statistically significant effects were found across multiple AI models. Most of the metrics could distinguish language learners’ proficiency levels. Significant correlations were also found between similarity metrics and learners’ writing test scores provided by human experts in the domain. However, not all such effects were strong or interpretable. Several results could not be consistently explained under the proposed second language learning hypotheses. Overall, the current investigation indicates that with careful configuration and systematic metrics design, AI language models can be promising tools in advancing language education.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"101 51","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141821807","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-16DOI: 10.3390/informatics11030047
Inas Al Khatib, A. Shamayleh, Malick Ndiaye
In recent years, the Internet of medical things (IoMT) has become a significant technological advancement in the healthcare sector. This systematic review aims to identify and summarize the various applications, key challenges, and proposed technical solutions within this domain, based on a comprehensive analysis of the existing literature. This review highlights diverse applications of the IoMT, including mobile health (mHealth) applications, remote biomarker detection, hybrid RFID-IoT solutions for scrub distribution in operating rooms, IoT-based disease prediction using machine learning, and the efficient sharing of personal health records through searchable symmetric encryption, blockchain, and IPFS. Other notable applications include remote healthcare management systems, non-invasive real-time blood glucose measurement devices, distributed ledger technology (DLT) platforms, ultra-wideband (UWB) radar systems, IoT-based pulse oximeters, accident and emergency informatics (A&EI), and integrated wearable smart patches. The key challenges identified include privacy protection, sustainable power sources, sensor intelligence, human adaptation to sensors, data speed, device reliability, and storage efficiency. The proposed mitigations encompass network control, cryptography, edge-fog computing, and blockchain, alongside rigorous risk planning. The review also identifies trends and advancements in the IoMT architecture, remote monitoring innovations, the integration of machine learning and AI, and enhanced security measures. This review makes several novel contributions compared to the existing literature, including (1) a comprehensive categorization of IoMT applications, extending beyond the traditional use cases to include emerging technologies such as UWB radar systems and DLT platforms; (2) an in-depth analysis of the integration of machine learning and AI in IoMT, highlighting innovative approaches in disease prediction and remote monitoring; (3) a detailed examination of privacy and security measures, proposing advanced cryptographic solutions and blockchain implementations to enhance data protection; and (4) the identification of future research directions, providing a roadmap for addressing current limitations and advancing the scientific understanding of IoMT in healthcare. By addressing current limitations and suggesting future research directions, this work aims to advance scientific understanding of the IoMT in healthcare.
{"title":"Healthcare and the Internet of Medical Things: Applications, Trends, Key Challenges, and Proposed Resolutions","authors":"Inas Al Khatib, A. Shamayleh, Malick Ndiaye","doi":"10.3390/informatics11030047","DOIUrl":"https://doi.org/10.3390/informatics11030047","url":null,"abstract":"In recent years, the Internet of medical things (IoMT) has become a significant technological advancement in the healthcare sector. This systematic review aims to identify and summarize the various applications, key challenges, and proposed technical solutions within this domain, based on a comprehensive analysis of the existing literature. This review highlights diverse applications of the IoMT, including mobile health (mHealth) applications, remote biomarker detection, hybrid RFID-IoT solutions for scrub distribution in operating rooms, IoT-based disease prediction using machine learning, and the efficient sharing of personal health records through searchable symmetric encryption, blockchain, and IPFS. Other notable applications include remote healthcare management systems, non-invasive real-time blood glucose measurement devices, distributed ledger technology (DLT) platforms, ultra-wideband (UWB) radar systems, IoT-based pulse oximeters, accident and emergency informatics (A&EI), and integrated wearable smart patches. The key challenges identified include privacy protection, sustainable power sources, sensor intelligence, human adaptation to sensors, data speed, device reliability, and storage efficiency. The proposed mitigations encompass network control, cryptography, edge-fog computing, and blockchain, alongside rigorous risk planning. The review also identifies trends and advancements in the IoMT architecture, remote monitoring innovations, the integration of machine learning and AI, and enhanced security measures. This review makes several novel contributions compared to the existing literature, including (1) a comprehensive categorization of IoMT applications, extending beyond the traditional use cases to include emerging technologies such as UWB radar systems and DLT platforms; (2) an in-depth analysis of the integration of machine learning and AI in IoMT, highlighting innovative approaches in disease prediction and remote monitoring; (3) a detailed examination of privacy and security measures, proposing advanced cryptographic solutions and blockchain implementations to enhance data protection; and (4) the identification of future research directions, providing a roadmap for addressing current limitations and advancing the scientific understanding of IoMT in healthcare. By addressing current limitations and suggesting future research directions, this work aims to advance scientific understanding of the IoMT in healthcare.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"6 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141642169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-15DOI: 10.3390/informatics11030046
Helia Farhood, I. Joudah, Amin Beheshti, Samuel Muller
Predicting student outcomes is an essential task and a central challenge among artificial intelligence-based personalised learning applications. Despite several studies exploring student performance prediction, there is a notable lack of comprehensive and comparative research that methodically evaluates and compares multiple machine learning models alongside deep learning architectures. In response, our research provides a comprehensive comparison to evaluate and improve ten different machine learning and deep learning models, either well-established or cutting-edge techniques, namely, random forest, decision tree, support vector machine, K-nearest neighbours classifier, logistic regression, linear regression, and state-of-the-art extreme gradient boosting (XGBoost), as well as a fully connected feed-forward neural network, a convolutional neural network, and a gradient-boosted neural network. We implemented and fine-tuned these models using Python 3.9.5. With a keen emphasis on prediction accuracy and model performance optimisation, we evaluate these methodologies across two benchmark public student datasets. We employ a dual evaluation approach, utilising both k-fold cross-validation and holdout methods, to comprehensively assess the models’ performance. Our research focuses primarily on predicting student outcomes in final examinations by determining their success or failure. Moreover, we explore the importance of feature selection using the ubiquitous Lasso for dimensionality reduction to improve model efficiency, prevent overfitting, and examine its impact on prediction accuracy for each model, both with and without Lasso. This study provides valuable guidance for selecting and deploying predictive models for tabular data classification like student outcome prediction, which seeks to utilise data-driven insights for personalised education.
预测学生成绩是一项重要任务，也是基于人工智能的个性化学习应用所面临的核心挑战。尽管有多项研究对学生成绩预测进行了探索，但对多种机器学习模型和深度学习架构进行有条不紊的评估和比较的综合比较研究却明显缺乏。为此，我们的研究提供了一个全面的比较，以评估和改进十种不同的机器学习和深度学习模型，这些模型有的是成熟技术，有的是前沿技术，即随机森林、决策树、支持向量机、K-近邻分类器、逻辑回归、线性回归、最先进的极端梯度提升（XGBoost），以及全连接前馈神经网络、卷积神经网络和梯度提升神经网络。我们使用 Python 3.9.5 实现并微调了这些模型。我们以预测准确性和模型性能优化为重点，在两个基准公共学生数据集上对这些方法进行了评估。我们采用了双重评估方法，利用 k 倍交叉验证和保持方法来全面评估模型的性能。我们的研究主要侧重于通过确定学生的成败来预测学生在期末考试中的成绩。此外，我们还探讨了使用无处不在的 Lasso 进行特征选择以提高模型效率、防止过拟合的重要性，并考察了其对使用和不使用 Lasso 的每个模型的预测准确性的影响。这项研究为选择和部署预测模型提供了有价值的指导，这些模型适用于学生成绩预测等表格数据分类，旨在利用数据驱动的洞察力实现个性化教育。
{"title":"Evaluating and Enhancing Artificial Intelligence Models for Predicting Student Learning Outcomes","authors":"Helia Farhood, I. Joudah, Amin Beheshti, Samuel Muller","doi":"10.3390/informatics11030046","DOIUrl":"https://doi.org/10.3390/informatics11030046","url":null,"abstract":"Predicting student outcomes is an essential task and a central challenge among artificial intelligence-based personalised learning applications. Despite several studies exploring student performance prediction, there is a notable lack of comprehensive and comparative research that methodically evaluates and compares multiple machine learning models alongside deep learning architectures. In response, our research provides a comprehensive comparison to evaluate and improve ten different machine learning and deep learning models, either well-established or cutting-edge techniques, namely, random forest, decision tree, support vector machine, K-nearest neighbours classifier, logistic regression, linear regression, and state-of-the-art extreme gradient boosting (XGBoost), as well as a fully connected feed-forward neural network, a convolutional neural network, and a gradient-boosted neural network. We implemented and fine-tuned these models using Python 3.9.5. With a keen emphasis on prediction accuracy and model performance optimisation, we evaluate these methodologies across two benchmark public student datasets. We employ a dual evaluation approach, utilising both k-fold cross-validation and holdout methods, to comprehensively assess the models’ performance. Our research focuses primarily on predicting student outcomes in final examinations by determining their success or failure. Moreover, we explore the importance of feature selection using the ubiquitous Lasso for dimensionality reduction to improve model efficiency, prevent overfitting, and examine its impact on prediction accuracy for each model, both with and without Lasso. This study provides valuable guidance for selecting and deploying predictive models for tabular data classification like student outcome prediction, which seeks to utilise data-driven insights for personalised education.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"27 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141646475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-11DOI: 10.3390/informatics11030045
Raza Nowrozy
ChatGPT, a Large Language Model (LLM) utilizing Natural Language Processing (NLP), has caused concerns about its impact on job sectors, including cybersecurity. This study assesses ChatGPT’s impacts in non-managerial cybersecurity roles using the NICE Framework and Technological Displacement theory. It also explores its potential to pass top cybersecurity certification exams. Findings reveal ChatGPT’s promise to streamline some jobs, especially those requiring memorization. Moreover, this paper highlights ChatGPT’s challenges and limitations, such as ethical implications, LLM limitations, and Artificial Intelligence (AI) security. The study suggests that LLMs like ChatGPT could transform the cybersecurity landscape, causing job losses, skill obsolescence, labor market shifts, and mixed socioeconomic impacts. A shift in focus from memorization to critical thinking, and collaboration between LLM developers and cybersecurity professionals, is recommended.
{"title":"GPTs or Grim Position Threats? The Potential Impacts of Large Language Models on Non-Managerial Jobs and Certifications in Cybersecurity","authors":"Raza Nowrozy","doi":"10.3390/informatics11030045","DOIUrl":"https://doi.org/10.3390/informatics11030045","url":null,"abstract":"ChatGPT, a Large Language Model (LLM) utilizing Natural Language Processing (NLP), has caused concerns about its impact on job sectors, including cybersecurity. This study assesses ChatGPT’s impacts in non-managerial cybersecurity roles using the NICE Framework and Technological Displacement theory. It also explores its potential to pass top cybersecurity certification exams. Findings reveal ChatGPT’s promise to streamline some jobs, especially those requiring memorization. Moreover, this paper highlights ChatGPT’s challenges and limitations, such as ethical implications, LLM limitations, and Artificial Intelligence (AI) security. The study suggests that LLMs like ChatGPT could transform the cybersecurity landscape, causing job losses, skill obsolescence, labor market shifts, and mixed socioeconomic impacts. A shift in focus from memorization to critical thinking, and collaboration between LLM developers and cybersecurity professionals, is recommended.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"32 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141658675","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-09DOI: 10.3390/informatics11030044
Reza Torkman, A. Ghapanchi, Reza Ghanbarzadeh
Health information systems (HISs) are essential information systems used by organisations and individuals for various purposes. Past research has studied different types of HIS, such as rostering systems, Electronic Medical Records (EMRs), and Personal Health Records (PHRs). Although several past confirmatory studies have quantitatively examined EMR uptake by health professionals, there is a lack of exploratory and qualitative studies that uncover various drivers of healthcare professionals’ uptake of EMRs. Applying an exploratory and qualitative approach, this study introduces various antecedents of healthcare professionals’ uptake of EMRs. This study conducted 78 semi-structured, open-ended interviews with 15 groups of healthcare professional users of EMRs in two large Australian hospitals. Data analysis of qualitative data resulted in proposing a framework comprising 23 factors impacting healthcare professionals’ uptake of EMRs, which are categorised into ten main categories: perceived benefits of EMR, perceived difficulties, hardware/software compatibility, job performance uncertainty, ease of operation, perceived risk, assistance society, user confidence, organisational support, and technological support. Our findings have important implications for various practitioner groups, such as healthcare policymakers, hospital executives, hospital middle and line managers, hospitals’ IT departments, and healthcare professionals using EMRs. Implications of the findings for researchers and practitioners are provided herein in detail.
{"title":"A Framework for Antecedents to Health Information Systems Uptake by Healthcare Professionals: An Exploratory Study of Electronic Medical Records","authors":"Reza Torkman, A. Ghapanchi, Reza Ghanbarzadeh","doi":"10.3390/informatics11030044","DOIUrl":"https://doi.org/10.3390/informatics11030044","url":null,"abstract":"Health information systems (HISs) are essential information systems used by organisations and individuals for various purposes. Past research has studied different types of HIS, such as rostering systems, Electronic Medical Records (EMRs), and Personal Health Records (PHRs). Although several past confirmatory studies have quantitatively examined EMR uptake by health professionals, there is a lack of exploratory and qualitative studies that uncover various drivers of healthcare professionals’ uptake of EMRs. Applying an exploratory and qualitative approach, this study introduces various antecedents of healthcare professionals’ uptake of EMRs. This study conducted 78 semi-structured, open-ended interviews with 15 groups of healthcare professional users of EMRs in two large Australian hospitals. Data analysis of qualitative data resulted in proposing a framework comprising 23 factors impacting healthcare professionals’ uptake of EMRs, which are categorised into ten main categories: perceived benefits of EMR, perceived difficulties, hardware/software compatibility, job performance uncertainty, ease of operation, perceived risk, assistance society, user confidence, organisational support, and technological support. Our findings have important implications for various practitioner groups, such as healthcare policymakers, hospital executives, hospital middle and line managers, hospitals’ IT departments, and healthcare professionals using EMRs. Implications of the findings for researchers and practitioners are provided herein in detail.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"58 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141664789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-07-03DOI: 10.3390/informatics11030043
Choyeal Park, Jikyeong Park
This study examined the awareness of the EMR certification system among employees of public and private hospitals that have obtained EMR certification. It also assessed how this awareness impacted the evaluation of EMR interoperability. The objective of this study is to contribute to the stable adoption and further development of EMR system certification in Korea. Data were collected through 3600 questionnaires distributed over three years from 2021 to 2023. After excluding 24 questionnaires owing to missing values or insincere responses, 3576 responses were analyzed. The analysis involved descriptive statistics, cross-tabulation, t-tests, ANOVA, and multiple regression using SPSS 26.0. The significance level (α) for statistical tests was set at 0.05. This study revealed differences in awareness of EMR system certification and interoperability among hospital employees. In both public and private hospitals, awareness of the EMR system certification positively influences the evaluation of interoperability.
{"title":"Impact of Hospital Employees’ Awareness of the EMR System Certification on Interoperability Evaluation: Comparison of Public and Private Hospitals","authors":"Choyeal Park, Jikyeong Park","doi":"10.3390/informatics11030043","DOIUrl":"https://doi.org/10.3390/informatics11030043","url":null,"abstract":"This study examined the awareness of the EMR certification system among employees of public and private hospitals that have obtained EMR certification. It also assessed how this awareness impacted the evaluation of EMR interoperability. The objective of this study is to contribute to the stable adoption and further development of EMR system certification in Korea. Data were collected through 3600 questionnaires distributed over three years from 2021 to 2023. After excluding 24 questionnaires owing to missing values or insincere responses, 3576 responses were analyzed. The analysis involved descriptive statistics, cross-tabulation, t-tests, ANOVA, and multiple regression using SPSS 26.0. The significance level (α) for statistical tests was set at 0.05. This study revealed differences in awareness of EMR system certification and interoperability among hospital employees. In both public and private hospitals, awareness of the EMR system certification positively influences the evaluation of interoperability.","PeriodicalId":507941,"journal":{"name":"Informatics","volume":"89 s377","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141682646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：