检索结果-内蒙古大学图书馆

2nd International Conference on Machine learning and Autonomous Systems, ICMLAS 2025

作者： Pisal, Tejas Hajare, Rasika Verma, Prateek Gote, Pradnyawant M. Jiet, Mosses Chaudhri, Shiv Nath Faculty of Engineering and Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

This paper presents an advanced system that integrates Google's Speech Recognition API with the Gemini-l.5-flash model to improve audio processing and response generation, particularly in the context of healthcare communication. The system is designed to transcribe audio files of doctor-patient conversations accurately and generate contextually relevant responses using AI. A user-friendly interface, developed with Tkinter, allows seamless uploading and processing of these audio files. The integration of these technologies aims to enhance the efficiency and effectiveness of automated response systems, thereby improving patient-provider communication. The system's capabilities were evaluated using real-world healthcare datasets, demonstrating its potential to streamline the workflow from audio input to meaningful textual output. This work not only showcases the practical application of AI in healthcare but also lays the groundwork for future innovations in automated medical communication systems. © 2025 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Assessment of Machine learning Models for Predicting Glucose Intolerance Risk

引用

SN Computer Science 2024年第7期5卷 894页

作者： Kumar, B. P. Pradeep Manoj, H.M. Department of Computer Science and Design Atria Institute of Technology Affiliated to VTU Karnataka Bangalore India Department of Artificial Intelligence and Machine Learning BMS Institute of Technology and Management Affiliated to VTU Karnataka Bangalore India

This study focuses on predictive analytics and healthcare, specifically the prediction of Glucose Intolerance, a chronic metabolic disease with significant global health implications. The research aims to develop efficient tools for risk assessment and early identification, offering medical practitioners reliable instruments for identifying high-risk patients and implementing preventive measures in a timely manner. A significant challenge in managing Glucose Intolerance is the absence of effective and precise prediction models. Traditional risk assessment techniques often fail to capture the multifaceted nature of Glucose Intolerance development, leading to delayed treatments and suboptimal patient outcomes. To address this issue, we conducted a comprehensive study utilizing various machine learning algorithms, including Decision Trees, Random Forest, Gradient Boosting, CatBoost, K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Logistic Regression, and a Voting Classifier, to predict Glucose Intolerance. The primary objective was to identify the most effective combination of features and models for accurate predictions. Key factors considered included patient demographics, lifestyle characteristics, medical history, and genetic susceptibility, which were used to build robust and personalized prediction models. We conducted a comparative analysis of the machine learning models' performance based on cross-validated accuracy with test-train splits and folds: 0.2, 6;0.05, 4;0.1, 2;0.2, 6;and 0.05, 2. The results showed that Random Forest achieved test accuracies of 74%, 76%, 82%, 75%, and 79%;KNN achieved 70%, 72%, 74%, 75%, and 72%;SVC achieved 74%, 72%, 77%, 77%, and 72%;Logistic Regression achieved 73%, 76%, 79%, 73%, and 76%;Gradient Boosting achieved 72%, 79%, 75%, 73%, and 79%;XGBoost achieved 72%, 79%, 77%, 74%, and 79%;CatBoost achieved 74%, 76%, 79%, 75%, and 76%;Decision Tree achieved 60%, 83%, 74%, 70%, and 79%;and Voting Classifier achieved 74%, 7

关键词： Algorithmic approaches Chronic disease Data-driven healthcare Early detection Glucose Intolerance Healthcare analytics Machine learning Personalized medicine Prediction Predictive modelling Risk stratification

来源：评论

学校读者我要写书评

暂无评论

An investigation of personalized entertaining three-tier tests: a prior knowledge perspective

引用

Interactive learning Environments 2023年第10期31卷 6260-6278页

作者： Chen, Sherry Y. Tseng, Chia-Yi Cheng, Chao-Yang Graduate Institute of Network Learning Technology National Central University Zhongli District Taiwan Department of E-learning Design and Management National Chiayi University Chiayi City Taiwan

This study proposed a three-tier test to help students learn English grammar. To reduce students' anxiety, game-based learning was incorporated into the three-tier test, where personalization was also implemented to accommodate students' different needs. More specifically, we developed a Personalized Entertaining Three-Tier Test (PET3), which consisted of the three-tier test, game-based learning and personalization. On the other hand, diversities exist among learners, especially prior knowledge. To this end, this study aimed to provide the complete understandings of the effects of prior knowledge in the PET3 context, in terms of test performance, task performance, learning behavior and gaming behavior. Regarding test performance, high prior knowledge learners (HPK) performed better than low prior knowledge learners (LPK). Regarding task performance, HPK was superior to LPK in two aspects, i.e., the reasons of the main questions and advanced questions, while LPK performed better than HPK in the aspect of the review questions. Regarding learning behavior, HPK and LPK favored to use different hints. Regarding gaming behavior, HPK tended to be a winner while LPK had a tendency to be looser. Based on these findings, we developed a framework, which could help designers and instructors to know the preferences of diverse learners. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

关键词： digital games prior knowledge Three-tier tests

来源：评论

学校读者我要写书评

暂无评论

The influences of academic emotion and prior knowledge in the context of online tests

引用

Interactive learning Environments 2023年第5期31卷 3257-3272页

作者： Cheng, Chao-Yang Chen, Jim-Ming Chen, Sherry Y. Department of E-learning Design and Management National Chiayi University Chiayi City Taiwan Graduate Institute of Network Learning Technology National Central University Jhongli City Taiwan

Online tests offer many advantages but they still belong to assessment, which may make learners have anxiety. Thus, students may experience certain emotion. Academic emotion is a branch of emotion and has great effects on student learning. Such effects can be associated with individual differences, especially prior knowledge. To this end, this study examined the influences of academic emotion and prior knowledge in the context of an online test. The results indicated that the positive academic emotion of high prior knowledge learners (HPKs) and low prior knowledge learners (LPKs) was connected with their pre-test scores while no connection was found for their post-test scores. Additionally, HPKs had higher positive academic emotion and lower negative academic emotion than LPKs. On the other hand, HPKs got better pre-and post-test scores than LPKs whereas LPKs had higher gain scores. Furthermore, HPKs and LPKs exhibited different behavior sequences. More specifically, LPKs tended to acquire small-scaled information from the Chinese hint only while HPKs preferred to obtain both small-scaled information and large-scaled information from the Chinese hint and sentence hint, respectively. According to the findings of this study, we develop a framework, which can be applied to help understand the needs of HPKs and LPKs. © 2021 Informa UK Limited, trading as Taylor & Francis Group.

关键词： academic emotion individual differences online assessment Online tests prior knowledge

来源：评论

学校读者我要写书评

暂无评论

Engaging Environmental learning: A Tangible Approach for Conveying Environmental Data in Education Using Weight 24

Engaging Environmental Learning: A Tangible Approach for Con...

引用

18th International Conference on Tangible, Embedded, and Embodied Interaction, TEI 2024

作者： Hedin, Bjorn Blomqvist, Anders G. Menon, Arjun Rajendran Kth Royal Institute of Technology Department of Learning in Engineering Science Sweden Kth Royal Institute of Technology Vetenskapens Hus Sweden Kth Royal Institute of Technology Division of Media Technology and Interaction Design Sweden

ISBN: (纸本)9798400704024

This paper presents a novel method for communicating environmental information in an engaging and memorable manner. Instead of traditional visual or written communication, our approach involves physical representation of data, using weight as the key element. Using food as a case study, we demonstrate the carbon footprint of food items through life-sized models that accurately reflect their actual weight. In an educational setting, students collectively discuss and estimate emissions for sample foods, followed by hands-on interaction. Each model's weight mirrors its carbon footprint, from 50 grams for half a kilo of potatoes to 13 kilograms for half a kilo of beef. Early tests show a significant "Wow!"factor, particularly for high-emission foods. This tangible experience leaves a lasting impression, potentially influencing future choices. Our approach can extend to other areas like energy. The paper concludes with design recommendations for future work. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Natural Language Processing in Healthcare 4

A Review on the Applications of Natural Language Processing ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Warbhe, Mohan K. Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Design Sawangi Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331529635

In healthcare, Natural Language Processing (NLP) is a technique to improve clinical decision support, patient care, and medical research. By automating clinical recording, NLP enhances the calibre of medical records and professional communication. It makes Electronic Health Records (EHRs) easier to use by facilitating quick and easy data entry, retrieval, and access to vital patient data that helps with precise diagnosis and efficient treatment planning. Through the analysis of patient-specific data, NLP supports clinical decision support by delivering prompt recommendations. Chatbots and virtual assistants managing repetitive duties like booking appointments also improve patient connection. NLP makes it easier to analyse vast amounts of literature for medical research, facilitating the extraction and summary of important discoveries. Healthcare data processing requires text preparation, sentiment analysis, Named Entity Recognition (NER), semantic parsing, and Natural Language Generation (NLG). However, there are obstacles to overcome, like bias, ethical concerns, system integration, privacy, and data quality. The healthcare industry can use NLP to enhance patient outcomes, promote personalized medication, and streamline healthcare delivery by guaranteeing interoperability and setting standards. © 2024 IEEE.

关键词： Challenges of NLP in Healthcare Future treads of NLP for healthcare Healthcare NLP

来源：评论

学校读者我要写书评

暂无评论

A Type-1 Fuzzy Logic Framework for Early Risk Assessment of Gestational Diabetes Mellitus Using Clinical Risk Factors 2

A Type-1 Fuzzy Logic Framework for Early Risk Assessment of ...

引用

2nd International Conference on Machine learning and Autonomous Systems, ICMLAS 2025

作者： Suman, Saurabh Pacharaney, Utkarsha Gote, Pradnyawant M. Faculty of Engineering and - Technology Department of Computer Science & Design Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence & Machine Learning Maharashtra Wardha442001 India

ISBN: (纸本)9798331505745

Gestational Diabetes Mellitus (GDM) is a condition that can put at risk both mother and fetus but early and proper risk assessment need to be carried out for effective management. This paper discloses a Mamdani-kind Fuzzy Inference System to evaluate GDM risk dependent on clinical parameters like age, parity, glucose levels, body mass index (BMI), and insulin levels. The system can simulate all the numerous risk factors in a more gentle way by the utilization of the triangular membership function that converts accurate clinical data into a fuzzy format. A clear rule base, got from the knowledge maps in the clinical field, is put together from the input data to determining the GDM risk levels. This is neither then defuzzied via the centroid method to generate a determinable score. Results show that this system can be used along with the experts, thus yielding the same results as them, meanwhile, it is capable of providing an intelligible output. It lends further credence to the role of fuzzy logic in uncertainties in medical data and their potential by decision support systems in clinical context. While reasonably beneficial results from the system are reported, the static nature of the membership functions implies, for the future, adaptability in methodologies for relative accuracy. This study still emphasizes that fuzzy logic finds application in settings of clinical delineation, which are distinctly more complex for their intended usefulness for conditions such as GDM here. © 2025 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

A Review on Implementation of Wearable Devices in Healthcare 7

A Review on Implementation of Wearable Devices in Healthcare

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Suman, Saurabh Choudhary, Vishal Kumar Pacharaney, Utkarsha Kumar, Abhishek Kumar, Dhiraj Raushan, Rahul Faculty of Engineering And Technology Department of Computer Science And Design Maharashtra Wardha India Faculty of Engineering And Technology Department of Computer Science And Medical Engineering Maharashtra Wardha India Faculty of Engineering And Technology Department of Artificial Intelligence And Machine Learning Maharashtra Wardha India

ISBN: (纸本)9798350359299

The capacity to get additional patient data, including clinical, behavioral, and self-monitored data, has enhanced by the expanding usage of wearable technology. Large volumes of previously unobtainable data are now available, providing a chance to create new instruments with sophisticated analysis and decision support systems for application in clinical settings. Additionally, it gives patients additional options by arming them with personalized decision-support resources and information, enabling them to take charge of their own health care while maintaining their sense of autonomy. Especially well-suited for miniaturization and integration into microfluidic devices are biosensors with electrochemical sensors. Applications cover activities in the domains of diagnostics, food and environmental control, and the identification of complete cells, the parts of cells, proteins, and tiny compounds. Microfluidic technologies can be as basic as sample transport tubes or as sophisticated as platforms with extra components for sample preparation and sensing electrode integration. The kind of detection, application, and sample material all influence the microfluidics design. The next issue for the healthcare industry will be how to use newly acquired information in a way that benefits patients, healthcare organizations, and professionals all while reducing costs and workloads. Given the current limitations, the challenge for wearable technology designers is to provide solutions that healthcare practitioners can readily integrate and use. © 2024 IEEE.

关键词： Biosensors

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov Arnold Network for Hyperspectral Image Classification: A Detailed Explanation 2

Kolmogorov Arnold Network for Hyperspectral Image Classifica...

引用

2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry, IDICAIEI 2024

作者： Suman, Saurabh Pacharaney, Utkarsha Choudhary, Vishal Kumar Raushan, Rahul Kumar, Abhishek Kumar, Gulshan Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Maharashtra Wardha India Faculty of Engineering and Technology Department of Computer Science and Medical Engineering Maharashtra Wardha India

ISBN: (纸本)9798331528713

Hyperspectral imaging (HSI) has been proved to be useful in numerous fields because of its ability to acquire the spectral information across the hundreds of contiguous bands. Nevertheless, the vast dimensionality of the hyperspectral data presents a great problem especially during data processing as well as during classification. Recently, one of the techniques that have attracted most interest for the classification of hyperspectral images is Kolmogorov Arnold Network (KAN), which is efficient with regard to those high-dimensional non- linear data sets found in hyperspectral imagery. This study focuses on how KAN can be utilized for classifying hyperspectral images, how B-spline curves can be used for augmenting the performance of the model, and what experimentation was done with the state-of-the-art hyperspectral data set. From these results, it was established that KAN plus B-spline curves was a good strategy for hyperspectral images classification compared to existing systems in both accuracy and speed. © 2024 IEEE.

关键词： Splines

来源：评论

学校读者我要写书评

暂无评论

Introducing Children to Computational Thinking Concepts Through A Tabletop Board Game: An Exploratory Study

引用

Journal of Formative design in learning 2025年 1-15页

作者： Yang, Dayae Kopcha, Theodore J. Learning Design and Technology Department of Workforce Education and Instructional Technology Mary Frances Early College of Education University of Georgia Athens USA

Computer programming is recognized as a crucial component of K-12 education for fostering students’ computational thinking skills. Unplugged methods, such as board games, have proven effective in introducing programming concepts to children in an accessible and engaging manner. This exploratory pilot study takes a qualitative approach to investigate the potential of the coding board game Lucky Codes to support elementary students’ engagement with foundational programming concepts through unplugged methods. Video recordings and multimodal transcriptions of gameplay sessions with four students were analyzed to examine their interactions and strategies across two rounds of gameplay. The findings reveal that Lucky Codes facilitated meaningful engagement with programming concepts such as sequencing, decomposition, and conditionals. Participants demonstrated progress in applying these concepts between rounds, reflecting their growing ability to use these ideas strategically to achieve gameplay objectives. The study highlights the potential of intentionally designed board games as accessible and engaging tools for introducing programming concepts to young learners.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：