检索结果-内蒙古大学图书馆

IS and T International Symposium on Electronic Imaging: High Performance Computing for Imaging, HPCI 2023

作者： Wang, Zekun Wang, Pengwei Louis, Peter C. Wheless, Lee E. Huo, Yuankai Data Science Institute Vanderbilt University NashvilleTN United States Department of Information Science and Engineering Shandong University Qingdao China Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States

The COVID-19 epidemic has been a significant healthcare challenge across the world. COVID-19 is transmitted predominately by respiratory droplets generated when people breathe, talk, cough, or sneeze. Wearing a mask is the primary, effective, and convenient method of blocking 80% of respiratory infections. Therefore, many face mask detection systems have been developed to supervise hospitals, airports, publication transportation, sports venues, and retail locations. However, the current commercial solutions are typically bundled with software or hardware, impeding public accessibility. In this paper, we propose an in-browser serverless edge-computing-based face mask detection solution, called Web-based efficient AI recognition of masks (WearMask), which can be deployed on common devices (e.g., cell phones, tablets, computers) with internet connections using web browsers. The serverless edge-computing design minimizes hardware costs (e.g., specific devices or cloud computing servers). It provides a holistic edge-computing framework for integrating (1) deep learning models (YOLO), (2) high-performance neural network inference computing framework (NCNN), and (3) a stack-based virtual machine (WebAssembly). For end-users, our solution has the advantages of (1) serverless edge-computing design with minimal device limitation and privacy risk, (2) installation-free deployment, (3) low computing requirements, and (4) high detection speed. Our application has been launched with public access at ***. © 2023, Society for Imaging science and Technology.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Modeling Emotion Analysis of Indonesian Tweets

Modeling Emotion Analysis of Indonesian Tweets

引用

Information Technology and Digital Applications (ICITDA), IEEE International Conference on

作者： Annisa Zahra Dhomas Hatta Fudholi Department of Informatics Center of Data Science Universitas Islam Indonesia Yogyakarta Indonesia Department of Informatics Universitas Islam Indonesia Yogyakarta Indonesia

Emotion analysis in social media plays a pivotal role in deciphering the underlying feelings and attitudes of users towards topics, brands, or events. It helps businesses and researchers to understand public opinion, predict trends, and inform decision making. In this study, we are conducting an emotion analysis task by using 6 different types of deep learning model architecture to see which model produced the best result for a relatively low resource data (less than 7000 data) with imbalance class. In our experiment, we use the context of the homecoming ban during COVID-19 pandemic in Indonesia. The dataset is taken during Eid al-Fitr holiday in 2021. The dataset shows the diversity in emotion shown in Twitter. Hence, we use the dataset and the emotions that arise from opinions circulating on Twitter. We used 6,990 manually labelled data from Twitter that has different forms of emotions, such as tender, scared, angry, excited, sad, happy, and wonder. From our experiments, it turns out that Bidirectional Long Short-Term Memory with Attention layer got the best accuracy of 91.40%. It is also proven that the addition of an attention layer to the model architecture can increase the accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guest editorial preface information and communication technology

Informatica (Slovenia)

引用

Informatica (Slovenia) 2023年第3期47卷 301-302页

作者： Binh, Huynh Thi Thanh Ide, Ichiro School of Information and Communication Technology Hanoi University of Science and Technology Viet Nam Nagoya University School of Informatics Mathematical and Data Science Center Japan

来源：评论

学校读者我要写书评

暂无评论

Mapping Study Variables to Common data Elements Using GPT for Sheets: Towards Standardized data Collection and Sharing

Mapping Study Variables to Common Data Elements Using GPT fo...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Pritham Ram Na Hong Hua Xu Xiaoqian Jiang Section of Biomedical Informatics and Data Science School of Medicine Yale University New Haven CT USA McWilliams School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston TX USA

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

Secondary use or reuse of biomedical research data has drawn significant attention and is of growing importance. Non-standardized representation and wide variability of clinical and observational data of biomedical research pose a major challenge to data collection, integration, analysis, and sharing. To address this requirement, we present experiences of using GPT for Sheets as a tool to map study-level biomedical research variables or data elements to Common data Elements (CDEs). In this study, the trial variables were extracted from the data dictionaries in the RADx-rad program, and the NIH Pediatric COVID-19 Working Group recommended CDEs that include children (0 – 21 years) were used as the reference CDEs. Mapping experimental variables (vague data elements) to CDEs resulted in an Fl-score of 0.82 when considering only the first recommendation and 0.85 when considering either the first or second recommendation. Our results indicate that GPT language models can differentiate freely defined study variables and map them to standard CDEs. This, in turn, potentially further enhances interoperability with a wider range of biomedical studies.

关键词： Pediatrics Dictionaries Biological system modeling Medical services data collection data models informatics

来源：评论

学校读者我要写书评

暂无评论

GPU-accelerated PostgreSQL for Scalable Management and Processing of Irregular Time-Series data using SPI

GPU-accelerated PostgreSQL for Scalable Management and Proce...

引用

2023 IEEE International Conference on Big data, Bigdata 2023

作者： Saied-Walker, Jamal Gupta, Pallavi Yi, Ruhan Marchal, Noah Skubic, Marjorie Scott, Grant J. University of Missouri Dept. of Ee & Computer Science ColumbiaMO65211 United States University of Missouri Institute for Data Science & Informatics ColumbiaMO65211 United States University of Missouri Center to Stream Healthcare in Place ColumbiaMO65211 United States

ISBN: (纸本)9798350324457

As the demand for real-time signal processing increases in various fields, such as healthcare, artificial intelligence, machine learning, and scientific research, there is a need for more efficient methods to analyze large amounts of data. To address this challenge and explore the opportunities to accelerate different signal processing algorithms, this paper proposes the integration of graphics processing units (GPUs) with database management systems (DBMS) using the PostgreSQL server programming interface (SPI). The performance of the proposed method is evaluated by comparing central processing unit (CPU) and GPU approaches for feature extraction using a data processing pipeline for heart rate estimation from hydraulic bed sensor data. Furthermore, the paper analyzes timing metrics, usability, adaptability, and discusses precision differences between CPU and GPU code by performing different thread and block configurations. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PARAMETER-EFFICIENT TRANSFER LEARNING FOR MUSIC FOUNDATION MODELS

arXiv

引用

arXiv 2024年

作者： Ding, Yiwei Lerch, Alexander Center for Artificial Intelligence and Data Science University of Würzburg Germany Music Informatics Group Georgia Institute of Technology United States

More music foundation models are recently being released, promising a general, mostly task independent encoding of musical information. Common ways of adapting music foundation models to downstream tasks are probing and fine-tuning. These common transfer learning approaches, however, face challenges. Probing might lead to suboptimal performance because the pre-trained weights are frozen, while fine-tuning is computationally expensive and is prone to overfitting. Our work investigates the use of parameter-efficient transfer learning (PETL) for music foundation models which integrates the advantage of probing and fine-tuning. We introduce three types of PETL methods: adapter-based methods, prompt-based methods, and reparameterization-based methods. These methods train only a small number of parameters, and therefore do not require significant computational resources. Results show that PETL methods outperform both probing and fine-tuning on music auto-tagging. On key detection and tempo estimation, they achieve similar results as fine-tuning with significantly less training cost. However, the usefulness of the current generation of foundation model on key and tempo tasks is questioned by the similar results achieved by training a small model from scratch. Code available at https://***/suncerock/peft-music/. © 2024, CC BY.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of Activity Logs of GakuNin LMS in the Use of the Information Security Course at Gunma University 27

Analysis of Activity Logs of GakuNin LMS in the Use of the I...

引用

27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Hamamoto, Nobukuni Ogawa, Koichi Ueda, Hiroshi Furukawa, Masako Nakamura, Motonori Yamaji, Kazutsuna Library and IT center Gunma University 4-2 Aramaki-machi Gunma Maebashi371-8510 Japan Research Center for Computing and Multimedia Studies Hosei University Japan Research Center for Open Science and Data Platform National Institute of Informatics Japan Institute for Information Management and Communication Kyoto University Japan

The GakuNin LMS operated by the National Institute of informatics (NII) provides an information security teaching course called "Princess Rin-Rin's security column". Gunma University extensively encourages students, faculty members, and staff to take this course. In this paper, we have classified the participants who took this course at Gunma University in the first semester of 2022 according to their course status and the results of the final test. Hierarchical clustering and K-means clustering, which are unsupervised learning methods, were used for the classification. The course status was classified into eight clusters, and the result of the final test was into four clusters. We have identified the most excellent cluster of the final test by investigating the clusters where the participants complete the final test with fewer attempts and in a shorter period of time. Furthermore, we have identified clusters of course status that include relatively good participants compared to the overall average using the relation between the clusters of course status and the clusters of final tests. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Clustering Infomation Security e-learing Learing Analytics Moodle

来源：评论

学校读者我要写书评

暂无评论

Optimized Artificial Neural Network-Based Control Strategy for Boost Converters

Optimized Artificial Neural Network-Based Control Strategy f...

引用

2022 International Conference on Electrical, Computer, Communications and Mechatronics Engineering, ICECCME 2022

作者： Panahidoost, Reza Mirshekali, Hamid Dashti, Rahman Samsami, Reza Rezaei, Mohammad Hossein Shaker, Hamid Reza Clinical Laboratory Center of Power Systems & Protection Faculty of Intelligent Systems Engineering & Data Science Persian Gulf University Bushehr*** Iran Center of Energy Informatics University of Southern Demark Odense Denmark

ISBN: (数字)9781665470957

ISBN: (纸本)9781665470957

Due to the rapid development of adaptive control and industrial automation science, the necessity of the boost converters is perceiving more and more, accordingly, designing a controller for these components which is dynamically characterized could be advantageous both theoretically and practically. Consequently, A machine learning-based controller using an artificial neural network (ANN) is designed, which is able to regulate the voltage of DC-DC Boost converters. In this paper, the primary controller is a linear quadratic regulator (LQR) based controller which is replaced by an ANN controller after generating training and testing data. After training the neural network, the Genetic Algorithm (GA) and an integral control action are used to minimize the system's overshoot and steady-state error, respectively. All in all, for the performance validation and making comparison accurately, the output voltage of a boost converter controlled by the optimized ANN model is simulated in the MATLAB/Simulink, which is conclusive that the new ANN controller can track the reference voltage properly. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

CFGNet: Coarse-to-Fine Grained Network for Image Classification of Confusing Fly Species 7

CFGNet: Coarse-to-Fine Grained Network for Image Classificat...

引用

7th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2024

作者： Niu, Lin Wang, Bo Niu, Baomin Zhang, Jin Liang, Danning Wu, Jingpeng Zhou, Rong Deng, Jianqiang School of Biomedical Informatics and Engineering Hainan Medical University Haikou China Hainan Vocational College of Political Science and Law Hainan Gongping Forensic Center Haikou China School of Big Data and Artificial Intelligence Zhengzhou University of Science and Technology Zhengzhou China Center for Educational Technology Hainan Medical University Haikou China Medicine of Hainan Medical University Department of Forensic Haikou China

ISBN: (纸本)9798350350890

In the realm of fine-grained image classification (FGIC), despite substantial technological advancements, models frequently misclassify certain fly species with exceedingly high inter-class similarity, thereby impacting overall classification accuracy. To address this challenge, we propose an innovative Coarse-to-Fine Grained Network Framework (CFGNet). This architecture tackles the issue through two stages: Initially, to alleviate classification complexity, closely related and easily confused categories are amalgamated. Subsequently, a lightweight coarse-grained information extraction network (CM) is introduced to enhance the classification accuracy of samples with relatively larger class differences. In the second stage, for precise identification of challenging samples, a fine-grained feature extraction network (FM) is proposed exclusively for difficult-to-distinguish images. Additionally, we introduce a novel feature reuse method to deeply mine and repurpose coarse-grained features from the previous stage to guide fine-grained classification and improve performance in this stage. To validate our approach, we curated a dataset based on merged confusion classes annotation (Flies-MCC). Experimental results demonstrate that our proposed network architecture achieves significant advancements in fine-grained fly classification and offers a pioneering solution for precise fly identification. © 2024 IEEE.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

IRnet: Immunotherapy response prediction using pathway knowledge-informed graph neural network

引用

Journal of Advanced Research 2024年 72卷 319-331页

作者： Jiang, Yuexu Immadi, Manish Sridhar Wang, Duolin Zeng, Shuai On Chan, Yen Zhou, Jing Xu, Dong Joshi, Trupti Department of Electrical Engineering and Computer Science University of Missouri-Columbia Columbia MO United States Christopher S. Bond Life Sciences Center University of Missouri-Columbia Columbia MO United States MU Institute for Data Science and Informatics University of Missouri-Columbia Columbia MO United States Department of Surgery University of Missouri-Columbia Columbia MO United States Department of Biomedical Informatics Biostatistics and Medical Epidemiology University of Missouri-Columbia Columbia MO United States

Introduction: Immune checkpoint inhibitors (ICIs) are potent and precise therapies for various cancer types, significantly improving survival rates in patients who respond positively to them. However, only a minority of patients benefit from ICI treatments. Objectives: Identifying ICI responders before treatment could greatly conserve medical resources, minimize potential drug side effects, and expedite the search for alternative therapies. Our goal is to introduce a novel deep-learning method to predict ICI treatment responses in cancer patients. Methods: The proposed deep-learning framework leverages graph neural network and biological pathway knowledge. We trained and tested our method using ICI-treated patients’ data from several clinical trials covering melanoma, gastric cancer, and bladder cancer. Results: Our results demonstrate that this predictive model outperforms current state-of-the-art methods and tumor microenvironment-based predictors. Additionally, the model quantifies the importance of pathways, pathway interactions, and genes in its predictions. A web server for IRnet has been developed and deployed, providing broad accessibility to users at https://***. Conclusion: IRnet is a competitive tool for predicting patient responses to immunotherapy, specifically ICIs. Its interpretability also offers valuable insights into the mechanisms underlying ICI treatments. © 2024

关键词： Biological pathway Checkpoint inhibitors Graph neural network Immunotherapy response Machine learning Model interpretability

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：