检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Hang Lou, Qian Wang, Yanshan Intelligent Systems Program School of Computing and Information University of Pittsburgh PA United States Department of Computer Science University of Central Florida OrlandoFL United States Department of Health Information Management University of Pittsburgh PA United States Department of Biomedical Informatics University of Pittsburgh PA United States Clinical and Translational Science Institute University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center PittsburghPA United States

Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study systematically assesses the vulnerabilities of seven LLMs to three advanced black-box jailbreaking techniques within medical contexts. To quantify the effectiveness of these techniques, we propose an automated and domain-adapted agentic evaluation pipeline. Experiment results indicate that leading commercial and open-source LLMs are highly vulnerable to medical jailbreaking attacks. To bolster model safety and reliability, we further investigate the effectiveness of Continual Fine-Tuning (CFT) in defending against medical adversarial attacks. Our findings underscore the necessity for evolving attack methods evaluation, domain-specific safety alignment, and LLM safety-utility balancing. This research offers actionable insights for advancing the safety and reliability of AI clinicians, contributing to ethical and effective AI deployment in healthcare. © 2025, CC BY-NC-SA.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

A Review of Implementation and Obstacles in Predictive Machine Learning Model at Educational Institutions 2

A Review of Implementation and Obstacles in Predictive Machi...

引用

2nd International Conference on computer, science, Engineering, and Technology, ICComSET 2019

作者： Ranggadara, Indra Sari, Yunita Sartika Dwiasnati, Saruni Prihandi, Ifan Sfenrianto Computer Science Department Mercu Buana University Indonesia Information Systems Management Department BINUS Graduate Program - Master of Information Systems Management Bina Nusantara University Jakarta11480 Indonesia

Machine learning is a system that can learn by itself by using training data and testing data testing. In a variety of machine learning research has various obstacles in implementation especially in education institution, in its application, many things need to considered for more information to enrich research in the area of machine learning by way of comparing various obstacles in implementation in similar research. So that in this study is to find similarities and anticipations made in the initial stages of pre-processing to visualisation, as well as the contribution that can give in this study explains the best alternative for researching following the experience of several researchers in conducting machine learning research. © 2020 IOP Publishing Ltd. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Smart Agricultural Greenhouses for Earthworm Farming

Smart Agricultural Greenhouses for Earthworm Farming

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Worawut Yimyam Mahasak Ketcham Thittaporn Ganokratanaa Patiyuth Pramkeaw Narumol Chumuang Department. of Business Information Management Phetchaburi Rajabhat University Phetchaburi Thailand Department of Information Technology Management King Mongkut's University of Technology North Bangkok Bangkok Thailand Applied Computer Science Program King Mongkut's University of Technology Thonburi Bangkok Thailand Media Technology Program King Mongkut's University of Technology Thonburi Bangkok Thailand Department of Digital Media Technology Muban Chombueng Rajabhat University Ratchaburi Thailand

In this research, the design of the earthworm rearing house was presented. Internet of Things, in which the research has designed houses and various equipment to be designed. The results showed that the traditional way of raising earthworms by walking to check the humidity in the cultured basin by touching and regularly watering compared to using the IOT system to measure the moisture. And there is a notification when the humidity drops below or above the specified threshold. and has an automatic watering system when the humidity is below a specified threshold It was found that the IOT-based method was more productive than the traditional method.

关键词： Legged locomotion Technological innovation Insects Humidity measurement Moisture Humidity Soil

来源：评论

学校读者我要写书评

暂无评论

Pillow for Detecting Snoring with Embedded Techniques for Elderly People with Snoring Problems

Pillow for Detecting Snoring with Embedded Techniques for El...

引用

Cybernetics and Innovations (ICCI), International Conference on

This research aimed to design, produce, and assess a snoring detection neck pillow for elderly individuals with snoring symptoms. The research process began with finding information on snoring. The data obtained were used to design a snore detection neck pillow in the form of a U-shaped neck pillow. The functional principle was that when the microphone module detects the snoring sound, it activates a vibrating motor to alert the snorer to awake or change sleeping positions and stop snoring. There was a program to control the operation. The results of the snoring detection neck pillow test with a sample size of 20 people showed an average efficiency of 80%.

关键词： Performance evaluation Technological innovation Sleep apnea Neck Delays Older adults Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Globally Harmonized System Label detection using Color Segmentation

Globally Harmonized System Label detection using Color Segme...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Thidarat Pinthong Mahasak Ketcham Thittaporn Ganokratanaa Patiyuth Pramkeaw Narumol Chumuang Department. of Business Information Management Phetchaburi Rajabhat University Phetchaburi Thailand Department of Information Technology Management King Mongkut's University of Technology North Bangkok Bangkok Thailand Applied Computer Science Program King Mongkut's University of Technology Thonburi Bangkok Thailand Media Technology Program King Mongkut's University of Technology Thonburi Bangkok Thailand Department of Digital Media Technology Muban Chombueng Rajabhat University Ratchaburi Thailand

This paper presents an approach for color detection and segmentation based on Image Processing Process to retrieve candidate regions of GHS Sign. For color classification, where the dimension of each vector can be extended by a group of neighboring pixels. The experimental results are highly accurate and robust for our testing database, where samples are recorded on various states of environment. But in the meantime, it was found that the error processing. It is an image that looks asymmetrical image. It is impossible to detect the symbol GHS.

关键词： Image segmentation Technological innovation Image resolution Image color analysis Shape Symbols Transportation

来源：评论

学校读者我要写书评

暂无评论

Automatic computer Shutdown with Image Processing via Webcam to Save Energy

Automatic Computer Shutdown with Image Processing via Webcam...

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Narumol Chumuang Mahasak Ketcham Thittaporn Ganokratanaa Patiyuth Pramkeaw Worawut Yimyam Chuamoo Dep. of Digital Media Technology Muban Chombueng Rajabhat University (MCRU) Thailand Dep. of Information Technology Management King Mongkut's University of Technology North Bangkok Thailand Applied Computer Science Program King Mongkut's University of Technology Thonburi Bangkok Thailand Media Technology Program King Mongkut's University of Technology Thonburi Bangkok Thailand Dep. of Business Information Management Phetchaburi Rajabhat University Thailand

The purpose of this research is to help save electricity within organizations and workplaces that use computers. Due to the behavior of general users today, they do not give importance to saving electricity. The researcher has developed an automatic computer shutdown system. with image processing via a webcam By using image processing techniques (Image Processing) applied to a webcam. By using a webcam to capture the user on the computer screen. Then the images are analyzed and examined with the principles of image processing with the Face Detection technique using the algorithm of Haar-like Features to detect human faces and ROI. Define a specific area of interest The system will then check the amount of inactivity on the screen. or does not show the face image within 10 minutes, the system will automatically turn off the computer. with image processing This research can make it easier to turn off computers when not in use. and helps to save electricity for the organization or agencies as well.

关键词： computers Performance evaluation Technological innovation Webcams Organizations Inspection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Sorting Red and Green Chilies by Digital Image Processing

Sorting Red and Green Chilies by Digital Image Processing

引用

Cybernetics and Innovations (ICCI), International Conference on

作者： Narumol Chumuang Mahasak Ketcham Thittaporn Ganokratanaa Patiyuth Pramkeaw Jiratha Chongsri Worawut Yimyam Dep. of Digital Media Technology Muban Chombueng Rajabhat University (MCRU) Thailand Dep. of Information Technology Management King Mongkut's University of Technology North Bangkok Thailand Applied Computer Science Program King Mongkut's University of Technology Thonburi Bangkok Thailand Media Technology Program King Mongkut's University of Technology Thonburi Bangkok Thailand Dep. of Business Information Management Phetchaburi Rajabhat University Thailand

The purpose of this research is to help save electricity within organizations and workplaces that use computers. Due to the behavior of general users today, they do not give importance to saving electricity. This work has developed an automatic computer shutdown system. with image processing via a webcam by using image processing techniques (image processing) applied to a webcam by using a webcam to capture the user on the computer screen. Then the images are analyzed and examined with the principles of image processing with the face detection technique using the algorithm of Haar -like features to detect human faces and ROI. define a specific area of interest. The system will then check the amount of inactivity on the screen. or does not show the face image within 10 minutes, the system will automatically turn off the computer. with image processing. This work can make it easier to turn off computers when not in use. and helps to save electricity for the organization or agencies as well.

关键词： computers Technological innovation Webcams Digital images Employment Organizations Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Development and Validation of Customer Intention Factors for Live-Stream Shopping

Development and Validation of Customer Intention Factors for...

引用

Conference on New Media Studies (CoNMedia)

作者： Erick Fernando Desman Hidayat Christian Haposan Pengaribuan Yulius Denny Prabowo Department of Information System Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Management Department BINUS Entrepreneurship Center Bina Nusantara University Jakarta Indonesia Management Study Program Faculty of Business Sampoerna University Jakarta Indonesia Computer Science Department Binus Online Learning Bina Nusantara University Jakarta Indonesia

Along with technological improvements, online shopping is currently developing quickly. Online shops started by selling electronics, clothing, food, and home appliances and continue to evolve, selling various things. Currently, digital marketing has a novel technique, namely live shopping, where sellers can present, promote and offer their products directly through live streaming on social media and e-commerce platforms. This research will focus on gaining insight into the factors influencing customers to watch and purchase through live streaming. This research is an early-stage study of exploring and searching for research models. The study used a literature review approach by reviewing similar previous research articles. Several variable components were used in this study. The findings of the factors include visibility capacity, meta-vocation capacity, purchase orientation capacity, social presence, price, perceived product quality, perceived enjoyment, purchase orientation, perceived usefulness, and intention to buy. These factors were tested and proved to be valid with Cronbach's Alpha value being more than 0.5 and reliable with the value of the loading factor a greater than 0.6. Criteria The factors of the findings for further analysis of the relationship between factors and other variables.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and Data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

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

Research on Data Security and Privacy of Smart Grids

引用

International Journal of Network Security 2024年第5期26卷 901-910页

作者： Hwang, Min-Shiang Chang, Yung-Ling Lin, Ko-Yu Lin, Iuon-Chang Yang, Cheng-Ying Department of Computer Science & Information Engineering Asia University 500 Lioufeng Rd. Wufeng Taichung Taichung41354 Taiwan Fintech and Blockchain Research Center Asia University 500 Lioufeng Rd. Wufeng Taichung Taichung41354 Taiwan The Ph.D. Program in Artificial Intelligence Asia University Taiwan Department of Management Information Systems National Chung Hsing University 500 Lioufeng Rd. Wufeng Taichung Taichung41354 Taiwan Department of Computer Science University of Taipei Taipei Taiwan

Developing a smart grid is a trend nowadays and an indispensable basic necessity of life. In recent years, the electricity demand has risen rapidly due to economic development and quality of life improvement. The power grid in significant cities is unstable due to old equipment, and power outages occur frequently. The smart grid can adjust the grid’s distribution strategy through the consumer’s real-time electricity demand so that the consumer’s electricity consumption data is always transmitted to the grid. Failure to protect the privacy and security of such information will expose consumers’ habits and even make the grid unnecessarily wasteful. The smart grid’s abnormality detection efficiency determines the overall grid’s stability. Failure to detect anomalies or power theft in the grid promptly will not only lead to the selection of the wrong distribution strategy for the smart grid but also reduce the transmission efficiency of the grid. This research ensures the privacy and security of transmitted data to enhance the efficiency of abnormality detection in the smart grid. The research issues are divided into privacy of transmitted data, data security authentication, and anomaly detection efficiency. © (2024), (International Journal of Network Security). All rights reserved.

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：