检索结果-内蒙古大学图书馆

2024 7th International Conference on Healthcare Service Management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ATP_mCNN: Predicting ATP binding sites through pretrained language models and multi-window neural networks

引用

computers in Biology and Medicine 2025年 185卷 109541-109541页

作者： Le, Van-The Malik, Muhammad-Shahid Lin, Yi-Jing Liu, Yu-Chen Chang, Yan-Yun Ou, Yu-Yen Department of Computer Science and Engineering Yuan Ze University Chung-Li32003 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Chung-Li32003 Taiwan Department of Computer Sciences Karakoram International University Gilgit-Baltistan 15100 Pakistan

Adenosine triphosphate plays a vital role in providing energy and enabling key cellular processes through interactions with binding proteins. The increasing amount of protein sequence data necessitates computational methods for identifying binding sites. However, experimental identification of adenosine triphosphate-binding residues remains challenging. To address the challenge, we developed a multi-window convolutional neural network architecture taking pre-trained protein language model embeddings as input features. In particular, multiple parallel convolutional layers scan for motifs localized to different window sizes. Max pooling extracts salient features concatenated across windows into a final multi-scale representation for residue-level classification. On benchmark datasets, our model achieves an area under the ROC curve of 0.95, significantly improving on prior sequence-based models and outperforming convolutional neural network baselines. This demonstrates the utility of pre-trained language models and multi-window convolutional neural networks for advanced sequence-based prediction of adenosine triphosphate-binding residues. Our approach provides a promising new direction for elucidating binding mechanisms and interactions from primary structure. © 2024 Elsevier Ltd

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Damage-Free Neutral Beam Etching for Gate Recess in E-Mode AlGaN/GaN HEMTs

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2025年第5期46卷 705-708页

作者： Chen, Yi-Ho Chu, Fu-Chuan Aslam, Muhammad Lee, Yao-Jen Li, Yiming Samukawa, Seiji National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Graduate Degree Program of College of Electrical and Computer Engineering Hsinchu300093 Taiwan National Chung-Shan Institute of Science and Technology Solid State Devices Section Electronic System Research Division Taoyuan325 Taiwan National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Electrical Engineering and Computer Science International Graduate Program Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation National Yang Ming Chiao Tung University Hsinchu300093 Taiwan Institute of Pioneer Semiconductor Innovation Institute of Artificial Intelligence Innovation National Yang Ming Chiao Tung University Parallel and Scientific Computing Laboratory Institute of Biomedical Engineering Department of Electronics and Electrical Engineering Institute of Communications Engineering Hsinchu300093 Taiwan National Yang Ming Chiao Tung University Institute of Communications Engineering Department of Electronics and Electrical Engineering Hsinchu300093 Taiwan

Recess gate etching is a critical technique for achieving enhancement-mode (E-mode) AlGaN/GaN high-electron mobility transistors (HEMTs) because the interface is susceptible to the etching damage. This study fabricates recess gates using the neutral beam etching (NBE) technique. By adjusting the aperture thickness in the NBE apparatus, we simulate both NB-mode and plasma-mode etching. The electrical characteristics of E-mode HEMTs fabricated using these two modes are analyzed and compared through DC, noise, and pulsed IV measurements. The results demonstrate that NB-recessed HEMTs exhibit superior performance. © 1980-2012 IEEE.

关键词： Aluminum gallium nitride

来源：评论

学校读者我要写书评

暂无评论

Joint Source Decomposition of Concurrent EEG-FMRI Data in Epilepsy and Control Groups

Joint Source Decomposition of Concurrent EEG-FMRI Data in Ep...

引用

IEEE International Symposium on biomedical Imaging

作者： J. Mason Harding Haatef Pourmotabbed Yamin Li Kimberly Rogge-Obando Kate Wang Sarah E. Goodale Shiyu Wang Camden Bibro Bergen Allee Caroline Martin Victoria L. Morgan Dario J. Englot Catie Chang Department of Electrical and Computer Engineering Vanderbilt University Department of Biomedical Engineering Vanderbilt University Department of Computer Science Vanderbilt University Neuroscience Graduate Program Vanderbilt University Vanderbilt Memory and Alzheimer's Center Vanderbilt University Medical Center Department of Neurological Surgery Vanderbilt University Medical Center Department of Radiology Vanderbilt University Medical Center

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

EEG and fMRI are complementary, noninvasive technologies for investigating human brain function. These modalities have been used to uncover large-scale functional networks and their disruptions in clinical populations. Given the high temporal resolution of EEG and high spatial resolution of fMRI, integrating these modalities can provide a more holistic understanding of brain activity. This work explores a multimodal source decomposition technique for extracting shared modes of temporal variation between fMRI BOLD signals and EEG spectral power fluctuations in the resting state. The resulting components are then compared between patients with focal epilepsy and controls, revealing multimodal network differences between groups.

关键词： Neuroimaging Brain Fluctuations Epilepsy Functional magnetic resonance imaging Electroencephalography Pattern recognition Hemodynamics Spatial resolution Signal resolution

来源：评论

学校读者我要写书评

暂无评论

Predicting the physiological effects of multiple drugs using electronic health record

引用

computers in Biology and Medicine 2025年 184卷 109485-109485页

作者： Jeon, Junhyeok Hong, Eujin Kim, Jong-Yeup Lee, Suehyun Kim, Hyun Uk Daejeon34141 Korea Republic of Department of Biomedical Informatics College of Medicine Konyang University Daejeon35365 Korea Republic of Healthcare Data Science Center Konyang University Hospital Daejeon35365 Korea Republic of Department of Computer Engineering Gachon University Seongnam13120 Korea Republic of Graduate School of Engineering Biology KAIST Daejeon34141 Korea Republic of BioProcess Engineering Research Center and BioInformatics Research Center KAIST Daejeon34141 Korea Republic of

Various computational models have been developed to understand the physiological effects of drug-drug interactions, which can contribute to more effective drug treatments. However, they mostly focus on interactions of only two drugs, and do not consider the patient information. To address this challenge, we use publicly available electronic health record (EHR), MIMIC-IV, to develop machine learning models that predict the physiological effects of two or more drugs. This study involves extensive preprocessing of laboratory measurement data, prescription data and patient data. The resulting machine learning models predict potential abnormalities across 20 selected measurement items (e.g., concentrations of metabolites and blood cells) in the form of a sentence. Analysis of the model predictions showed that age, specific active pharmaceutical ingredients, and male/female appeared to be the most influential features. The model development process showcased in this study can be extended to other measurement items for a target EHR. © 2024 Elsevier Ltd

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Keypoint Detection in Low-Resolution Thermal TUG Test Images

arXiv

引用

arXiv 2025年

作者： Chen, Wei-Lun Hsieh, Chia-Yeh Kao, Yu-Hsiang Liu, Kai-Chun Peng, Sheng-Yu Tsao, Yu Research Center for Information Technology Innovation Academic Sinica Taiwan Graduate Institute of Electrical Engineering National Taiwan University Taiwan Bachelor’s Program in Medical Informatics and Innovative Applications Fu Jen Catholic University Taiwan Department of Electrical Engineering National Taiwan University Taiwan College of Information and Computer Sciences University of Massachusetts AmherstMA01003 United States Department of Electrical Engineering National Taiwan University of Science of Technology Taiwan

This study presents a novel approach to human keypoint detection in low-resolution thermal images using transfer learning techniques. We introduce the first application of the Timed Up and Go (TUG) test in thermal image computer vision, establishing a new paradigm for mobility assessment. Our method leverages a MobileNetV3-Small encoder and a ViTPose decoder, trained using a composite loss function that balances latent representation alignment and heatmap accuracy. The model was evaluated using the Object Keypoint Similarity (OKS) metric from the COCO Keypoint Detection Challenge. The proposed model achieves better performance with AP, AP50, and AP75 scores of 0.861, 0.942, and 0.887 respectively, outperforming traditional supervised learning approaches like Mask R-CNN and ViTPose-Base. Moreover, our model demonstrates superior computational efficiency in terms of parameter count and FLOPS. This research lays a solid foundation for future clinical applications of thermal imaging in mobility assessment and rehabilitation monitoring. Copyright © 2025, The Authors. All rights reserved.

关键词： Thermography (imaging)

来源：评论

学校读者我要写书评

暂无评论

Bayesian curriculum generation in sparse reward reinforcement learning environments

引用

engineering science and Technology, an International Journal 2025年 66卷

作者： Akgün, Onur Üre, N. Kemal Istanbul Technical University Graduate School Mechatronics Engineering Program Maslak Istanbul 34469 Turkey Turkish-German University Faculty of Engineering Mechatronics Engineering Department Beykoz Istanbul 34820 Turkey Istanbul Technical University Faculty of Computer and Informatics Engineering Artificial Intelligence and Data Engineering Department Maslak Istanbul 34469 Turkey Istanbul Technical University Artificial Intelligence and Data Science Research Center Maslak Istanbul 34469 Turkey

This paper introduces the Bayesian Curriculum Generation Algorithm, a sophisticated approach for curriculum learning in sparse reward reinforcement learning contexts. Diverging from traditional methodologies, this algorithm utilizes Bayesian networks to dynamically create tasks by altering problem parameters, thereby impacting task difficulty. It operates independently from the core reinforcement learning algorithm, enabling compatibility with a variety of RL techniques. A notable feature of our algorithm is its capability for unsupervised task classification, utilizing a clustering process applicable to both image outputs and scalar values. This method efficiently categorizes tasks based on difficulty, circumventing the need for exhaustive training for each task. However, the effectiveness of this approach is contingent upon the presence of definable parameters within the environment and necessitates domain expertise to determine the appropriate tool, be it image output or scalar parameter analysis. The algorithm selects tasks from a curated pool corresponding to specific difficulty levels and adapts according to the agent's performance. Successful task completion triggers the generation of more complex tasks, whereas encountering challenges results in the maintenance or minor adjustment of task complexity. This adaptive feature significantly enhances the efficiency of the learning process. Empirical evaluations conducted in various environments, characterized by maze-like structures, discrete or continuous settings, and the presence of adversarial entities hindering the agent's mission, demonstrate the algorithm's efficacy and its superiority over conventional methods. The Bayesian Curriculum Generation Algorithm represents a significant advancement in reinforcement learning, providing a dynamic and adaptable solution for complex learning challenges. © 2025 The Authors

关键词： Bayesian networks Curriculum learning Reinforcement learning Unsupervised clustering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

引用

International Symposium on Applied science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Applying an Agile science Roadmap to Integrate and Evaluate Ethical Frameworks Throughout the Lifecycle and Use of Artificial Intelligence Tools in the Intensive Care Unit

引用

Critical Care Nursing Clinics of North America 2025年第2期37卷 347-363页

作者： Lindroth, Heidi Sahajwani, Juhi Hudson, Mark Heier, Laura Gonzalez, Andrew A. Bhattacharyya, Anirban Zheng, Zhi Boustani, Malaz Herasevich, Vitaly McGowan, Michelle Barry, Barbara Division of Nursing Research Department of Nursing Mayo Clinic Rochester MN United States Center for Aging Research Regenstrief Institute School of Medicine Indiana University Indianapolis IN United States Center for Health Innovation and Implementation Science School of Medicine Indiana University Indianapolis IN United States Department of Critical Care Medicine Mayo Clinic Jacksonville FL United States School of Psychology and Counselling The Open University Milton Keynes United Kingdom Department of Graduate Nursing Viterbo University La Crosse WI United States Department of Neurosurgery Mayo Clinic Rochester MN United States Center for Health Services Research Regenstrief Institute School of Medicine Indiana University Indianapolis IN United States Surgical Outcomes and Quality Improvement Center Department of Surgery School of Medicine Indiana University Indianapolis IN United States Department of Electrical Engineering University of Notre Dame Notre Dame IN United States Department of Anesthesiology and Perioperative Medicine Mayo Clinic Rochester MN United States Biomedical Ethics Departments of Quantitative Health Sciences and Artificial Intelligence and Informatics Biomedical Ethics Research Program Mayo Clinic Rochester MN United States Kern Center Mayo Clinic Rochester MN United States

This article summarizes existing ethical frameworks for healthcare artificial intelligence (AI) and ambient sensing technology, such as computer vision, and examines their application to improve patient outcomes in the intensive care unit (ICU). Integrating ethical considerations such as privacy, fairness, and autonomy into the lifecycle of an AI tool is necessary to fully harvest AI's potential to deliver safe, high-quality, personalized, and low-cost healthcare services that provide positive experiences for patients, families, and clinicians while improving health outcomes. Drawing from agile science, the article proposes a practical roadmap for clinician and researcher use to identify, integrate, and monitor ethical considerations throughout the lifecycle of an AI tool with the intention to improve patient care. A use case illustrates the application of the agile science-informed roadmap that details the development of a passive digital marker for delirium severity.

关键词： Agile science AI tools Artificial intelligence computer vision Delirium severity Ethical frameworks for health care AI ICU Passive digital marker

来源：评论

学校读者我要写书评

暂无评论

Advantages of two quantum programming platforms in quantum computing and quantum chemistry

引用

Journal of cheminformatics 2025年第1期17卷 77页

作者： Pei-Hua Wang Wei-Yeh Wu Che-Yu Lee Jia-Cheng Hong Yufeng Jane Tseng Undergraduate Program in Intelligent Computing and Big Data Chung Yuan Christian University No. 200 Zhongbei Road Taoyuan 320314 Taiwan. Quantum Information Center Chung Yuan Christian University No. 200 Zhongbei Road Taoyuan 320314 Taiwan. Department of Computer Science and Information Engineering National Taiwan University No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan. Graduate Institute of Biomedical Electronics and Bioinformatics College of Electrical Engineering and Computer Science National Taiwan University No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan. Department of Computer Science and Information Engineering National Taiwan University No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan. yjtseng@csie.ntu.edu.tw. Graduate Institute of Biomedical Electronics and Bioinformatics College of Electrical Engineering and Computer Science National Taiwan University No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan. yjtseng@csie.ntu.edu.tw. Physics Division National Center for Theoretical Sciences No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan. yjtseng@csie.ntu.edu.tw. Center for Quantum Science and Engineering National Taiwan University No. 1 Sec. 4 Roosevelt Road Taipei 10617 Taiwan. yjtseng@csie.ntu.edu.tw.

Quantum computing is at the forefront of technological advancement and has the potential to revolutionize various fields, including quantum chemistry. Choosing an appropriate quantum programming language becomes critical as quantum education and research increase. In this paper, we comprehensively compare two leading quantum programming languages, Qiskit and PennyLane, focusing on their suitability for teaching and research. We delve into their basic and advanced usage, examine their learning curves, and evaluate their capabilities in quantum computing experiments. We also demonstrate using a quantum programming language to build a half adder and a machine learning model. Our study reveals that each language has distinct advantages. While PennyLane excels in research applications due to its flexibility to adjust parameters in detail and access multiple sources of real quantum devices, Qiskit stands out in education because of its web-based graphical user interface and smaller code size. The codes and the dataset used in the studies are available at https://***/wangpeihua1231/quantum-programming-platform .

关键词： PennyLane Qiskit Quantum chemistry Quantum computing Quantum programming language

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：