检索结果-内蒙古大学图书馆

Magnetic Conference - Short Papers (INTERMAG Short Papers), IEEE International

作者： Masaaki Takezawa Tomoya Nagaki Satoshi Motozuka Iwao Sasaki Yoshito Ando Hiroyuki Narahara Naoki Mori Toru Shikayama Shinichiro Mukai Shuhei Maeda Shuhei Sakima Takaaki Ishii Faculty of Engineering Kyushu Institute of Technology Kitakyushu Japan Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology Kitakyushu Japan Yaskawa Electric Corporation Kitakyushu Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan

Fe-based nanocrystalline alloys have high magnetic flux density and low loss. So, in this study, the magnetic domain structure of ball-milled magnetic powders of these nanocrystalline alloys was observed using a Kerr effect microscope. The effect of strain removal heat treatment on the magnetic properties of the powder was also investigated by observing and comparing the magnetic domain structure of the milled powder before and after heat treatment during the preparation process of the nanocrystalline milled powder. Our findings showed that the strain removal heat treatment changed the size and shape of the magnetic domains to a simple structure. In addition, the magnetic wall motion was found to occur quickly, resulting in soft magnetic properties.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue Detection

Revolutionizing Road Safety: YOLOv8-Powered Driver Fatigue D...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Xie, Shuaiyue Chuah, Joong Huang Chai, Grace Mei Ting Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom University of Malaya Faculty of Engineering Department of Electrical Engineering Kuala Lumpur50603 Malaysia Smart Manufacturing Systems Research Group University of Southampton Malaysia Johor Iskandar Puteri79100 Malaysia

ISBN: (纸本)9798350341072

Driver fatigue is a significant cause of road accidents. Effective real-time fatigue detection systems are necessary to improve road safety. Utilizing a lightweight and fast model and creating an effective fatigue judgment rule is important in detecting fatigue in real-time. In this research, we propose a fatigue detection model based on You Look Only Once version 8 (YOLOv8) model to detect driver's facial features and use percentage of eyelid closure over the pupil over time (PERCLOS) and Percentage of Open Mouth (POM) indicators to identify fatigue. This research is divided into two parts. The first part involves creating, labeling, and preprocessing the dataset. We use the YawDD dataset as the original dataset and manually label a new dataset using the Roboflow platform. We then preprocessed the new dataset to train the YOLOv8 model for face features detection. In the second part, we established a multi-indicator fatigue determination rule that uses PERCLOS and POM indicators and set a threshold to determine whether the driver is fatigue. By combining the YOLOv8 model with the fatigue determination rules based on PERCLOS and POM, we successfully built a model to identify a driver's fatigue. Finally, the fatigue detection model based on YOLOv8 achieves a high accuracy rate of 96.9% and a high speed of 11.4 ms/frame in face features detection, surpassing other traditional models and previous generations of YOLO models. This model can effectively detect fatigue in both driver-driving pictures and videos. © 2023 IEEE.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuned Deep Learning Enabled Cyberbullying Classification in Social Media

引用

computers, Materials & Continua 2022年第12期73卷 5011-5024页

作者： Mesfer Al Duhayyim Heba G.Mohamed Saud S.Alotaibi Hany Mahgoub Abdullah Mohamed Abdelwahed Motwakel Abu Sarwar Zamani Mohamed I.Eldesouki Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversityMuhayel AseerSaudi Arabia Faculty of Computers and Information Computer Science DepartmentMenoufia UniversityEgypt Research Centre Future University in EgyptNew Cairo11845Egypt Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl KharjSaudi Arabia

Cyberbullying(CB)is a challenging issue in social media and it becomes important to effectively identify the occurrence of *** recently developed deep learning(DL)models pave the way to design CB classifier models with maximum *** the same time,optimal hyperparameter tuning process plays a vital role to enhance overall *** study introduces a Teacher Learning Genetic Optimization with Deep Learning Enabled Cyberbullying Classification(TLGODL-CBC)model in Social *** proposed TLGODL-CBC model intends to identify the existence and non-existence of CB in social media ***,the input data is cleaned and pre-processed to make it compatible for further *** by,independent recurrent autoencoder(IRAE)model is utilized for the recognition and classification of ***,the TLGO algorithm is used to optimally adjust the parameters related to the IRAE model and shows the novelty of the *** assuring the improved outcomes of the TLGODLCBC approach,a wide range of simulations are executed and the outcomes are investigated under several *** simulation outcomes make sure the improvements of the TLGODL-CBC model over recent approaches.

关键词： Social media deep learning cyberbullying cybersecurity hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Generalization Performance of Drowsiness Estimation AI in Drivers Using Time-Series Data from FAUs with Limited Datasets

Enhancing the Generalization Performance of Drowsiness Estim...

引用

Advanced Applied Informatics Winter (IIAI-AAI-Winter), International Congress on

作者： Tomoya Kubo Tomoyuki Yokogawa Kazutami Arimoto Masaki Hokari Isao Kayano Faculty of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Health Science and Technology Kawasaki University of Medical Welfare Kurashiki Okayama Japan

We developed an AI for Facial Expression Estimation to predict driver drowsiness levels, mimicking human evaluation. Traditional Image-based AIs struggle with limited data generalization in drowsiness prediction. Our proposed AI framework overcomes this by extracting Facial Action Units (FAU) from facial images, using these dynamic expression elements as primary features, making evaluation more humanlike. In our study involving 19 participants, we validated the generalization performance using a Gated Recurrent Unit (GRU) with FAU values and compared it with a Convolutional Neural Network (CNN) model based on VGGFACE (ResNet50). The proposed method demonstrated enhanced performance, showcasing potential improvements in drowsiness estimation with limited data, expecting to significantly reduce the data required for accurate drowsiness level estimation. Furthermore, the results obtained through the process of improving generalization performance imply that there exists a trade-off relationship between performance specialized to specific individuals and generalized performance in learning models utilizing features such as FAUs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Watermarking and Encryption for Electronic Medical Records (EMR) Security Based on mCloud 2

Watermarking and Encryption for Electronic Medical Records (...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Abdulshaheed, Haider Rasheed Abbas, Yaseen Saadi Tawfeq, Jamal F. Ateeq, Karamath Alnawayseh, Saif. E. A. Ghazal, Taher M. Baghdad College Of Economic Sciences University Computer Engineering Techniques Department Baghdad Iraq College Of Engineering Al-Nahrain University Electronic And Communications Engineering Department Baghdad Iraq Medical Technical College Al-Farahidi University Department Of Medical Instrumentation Technical Engineering Baghdad10070 Iraq School Of Computing Skyline University College University City Sharjah Sharjah United Arab Emirates College Of Engineering Mutah University Department Of Electrical Engineering Al-Karak Jordan Khalifa University Centre For Cyber Physical Systems Computer Science Department United Arab Emirates Center For Cyber Security Faculty Of Information Science And Technology Selangor Bangi43600 Malaysia

ISBN: (纸本)9798350394962

Providing quality healthcare services and promoting collaborative clinical research are easier and more efficient with electronic medical record (EMR) systems. All aspects of care are included in electronic health records. Data characterized by volume, variety, and velocity is what IBM defines as big data. Therefore, we evidently have a significant problem managing 'big EMR data' from a volume, accuracy, and velocity perspective. Data misuse and patient safety are significant risks associated with poorly implemented EMR-based systems. Storage, access, and retrieval of big data are all aspects of security to consider. Location is another important aspect of secure data use, in addition to strong access control mechanisms. Researchers are investigating secure mobile data usage based on location after recent reports of illegal trade and theft of patient data over mobile devices. To improve work flow dynamics and efficiency, healthcare facilities are increasingly using mobile devices. In spite of this, mobile devices are becoming more and more common. A new technique for preventing EMR infiltration and manipulation by hackers using the cloud is presented in this article. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Precision Health: Maximizing Well-being with IAHN Integration

Precision Health: Maximizing Well-being with IAHN Integratio...

引用

Automation, Computing and Renewable systems (ICACRS), International Conference on

作者： Shaik Jumlesha S. Hrushikesava Raju S. Adinarayna U.Sesadri Nabanita Choudhury Vijaya Chandra Jadala Department of CSE Annamacharya Institute of Technology and Science Tirupati AP Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Department of Computer Science and Systems Engineering College of Engineering Andhra University Visakhapatnam Department of CSE Vardhaman College of Engineering Hyderabad Telangana Faculty of Computer Technology Assam Down Town University Guwahati Assam School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798331532420

ISBN: (纸本)9798331532437

Precision health is emerging as a significant trend in healthcare, emphasizing the customization of medical care and interventions to align with the unique characteristics of each patient, ultimately maximizing health outcomes and well-being. Traditional approaches to personalized care are often time-consuming and lack the necessary focus on individual patient needs, leading to inadequate monitoring of disease progression and insufficient patient engagement. To address these challenges, the proposed approach employs an Improved Adaptive Health Navigator (IAHN) that continuously monitors each patient and formulates eco-friendly medications tailored to their specific symptoms. This innovative process incorporates various factors such as lifestyle choices, genomic data, family history, and other relevant parameters to inform precision medicine recommendations. The resulting precision medicine approach is designed to enhance recovery speed and improve patient outcomes. By adopting a proactive strategy, this model facilitates early detection of health issues, reduces the incidence of illnesses, enhances quality of life, and optimizes resource allocation. The IAHN plays a crucial role in the ongoing development of personalized medicine by ensuring continuous health monitoring, empowering healthcare providers, and enabling diagnostic tools to make informed decisions for disease prevention.

关键词： Renewable energy sources Adaptive systems Navigation Reviews Precision medicine Medical services Resource management Medical diagnostic imaging Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Montenegrin Academic Digital Innovation Hub 27

Evaluation of the Montenegrin Academic Digital Innovation Hu...

引用

27th International Conference on Information Technology, IT 2023

作者： Lakovic, Luka Kara, Peter A. Ognjanovic, Ivana Bokor, Laszlo Sendelj, Ramo Reich, Christoph Roganovic, Milovan Zoulias, Emmanouil Erakovic, Jevto Radusinovic, Tanja Rakocevic, Nada Simon, Aniko University of Donja Gorica Faculty for Information Systems and Technologies Podgorica81000 Montenegro Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services Budapest1111 Hungary Faculty of Science Engineering and Computing Kingston University Wireless Multimedia and Networking Research Group Department of Computer Science School of Computer Science and Mathematics LondonKT1 2EE United Kingdom University of Donja Gorica Humanistic Studies Podgorica81000 Montenegro Furtwangen University Institute of Data Science Cloud Computing and It Security Furtwangen78120 Germany Clinical Centre of Montenegro Clinic for Neurology Podgorica81000 Montenegro National and Kapodistrian University of Athens Faculty of Nursing School of Health Sciences Goudi 11527 Greece Chamber of Economy of Montenegro Podgorica81000 Montenegro Sigma Technology Budapest1093 Hungary

ISBN: (纸本)9798350397512

In the era of global digitalization, digital innovation hubs have become essential, as they function as transforming forces. In this paper, we provide an analysis of the Montenegrin Academic Digital Innovation Hub by applying multi-criteria qualitative evaluation over several criteria: process flow of fully digitized operations of the Hub (with aspects of the innovation life-cycle, ethics, and security), resource management, strategic goals, and feasibility. The paper also proposes a model of comprehensive resource management via the perspective of smart specialization priorities of Montenegro. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Nonequilibrium phase transitions of a nematic liquid crystal under ac field-driven electroconvection

引用

Physical Review E 2022年第1期106卷 014702-014702页

作者： Jong-Hoon Huh Department of Physics and Information Technology Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka 820-8502 Japan

We report on phase transitions between isotropic and nematic liquid crystal phases in nonequilibrium systems (NESs). ac field-driven electroconvection (EC) provides an NES, which can be well controlled by the voltage V and frequency f; it arises electrohydrodynamically at a threshold voltage Vc. In continuous cooling and heating processes with various rates R, the critical temperature Tc was determined at a critical time tc for phase transitions. Moreover, the morphological and dynamical features in the phase transitions were examined using an electro-optical image processing method. In comparison with an equilibrium system (V=0), two typical turbulent ECs (i.e., NESs), which are called dynamic scattering mode 1 (DSM1 for V>Vc) and DSM2 (for V≫Vc), were examined to understand the nonequilibrium phase transitions. In particular, our results show that in high voltage-induced turbulence (i.e., DSM2), Tc can be determined effectively without considering R; this provides a possibility for a material technology application in nonequilibrium-based circumstances.

关键词： Dissipative dynamics Patterns in complex systems Phase transitions by order Transition temperature Liquid crystals

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for Cardiovascular Disease Risk Evaluation

A Hybrid Approach for Cardiovascular Disease Risk Evaluation

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： U. Sesadri Shaik Jumlesha S.Hrushikesava Raju S. Adinarayna Nabanita Choudhury Vijaya Chandra Jadala Department of CSE Vardhaman College of Engineering Hyderabad Telangana Department of CSE Annamacharya Institute of Technology and Science Tirupati Chittoor(dt) AP Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Department of Computer Science and Systems Engineering College of Engineering Andhra University Visakhapatnam Faculty of Computer Technology Assam down town University Guwahati Assam School of Computer Science and Artificial Intelligence SR University Hanumakonda Warangal Telangana India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Nowadays, the risk estimators are to be applied based on the population characteristics of their country, which is termed as race attribute. There were specific tools to determine the risk of cardiovascular disease. Among many diseases, the mortality rate of the people is increasing due to a lack of quality lifestyle. In order to provide a guide to the individual based on their specific characteristics and lifestyle, would classify the risk into specific categories like severe (High), Moderate, and normal(Low) with pre-defined threshold constraints. The risk assessment estimators alert the individual to control certain modifiable attributes irrespective of their non-modifiable elements. The integration of random forests and intelligent rule mining would generate the CVD risk prediction. Efficiency as well as interpretability are important in this competitive hybrid model. The ultimate benefits assured are extending the lives of the patients by knowing the importance of daily work, habits, and their control food, presenting a powerful opportunity by practicing better personalization monitoring and improved patient care, and improved informed decisions for immediate action. The early prevention initiation by identifying the risk severity optimizes follow-up of better practices and treatment styles, resulting in improved decision making for better health care of the individual.

关键词： Measurement Calculators Prevention and mitigation Mortality Medical services Cardiovascular diseases Informatics Random forests Monitoring Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Explaining Learned Reward Functions with Counterfactual Trajectories

arXiv

引用

arXiv 2024年

作者： Wehner, Jan Oliehoek, Frans Siebert, Luciano Cavalcante CISPA Helmholtz Center for Information Security Germany Department of Intelligent Systems Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

Learning rewards from human behavior or feedback is a promising approach to aligning AI systems with human values but fails to consistently extract correct reward functions. Interpretability tools could enable users to understand and evaluate possible flaws in learned reward functions. We propose Counterfactual Trajectory Explanations (CTEs) to interpret reward functions in Reinforcement Learning by contrasting an original and a counterfactual trajectory and the rewards they each receive. We derive six quality criteria for CTEs and propose a novel Monte-Carlo-based algorithm for generating CTEs that optimizes these quality criteria. To evaluate how informative the generated explanations are to a proxy-human model, we train it to predict rewards from CTEs. CTEs are demonstrably informative for the proxy-human model, increasing the similarity between its predictions and the reward function on unseen trajectories. Further, it learns to accurately judge differences in rewards between trajectories and generalizes to out-of-distribution examples. Although CTEs do not lead to a perfect prediction of the reward, our method, and more generally the adaptation of XAI methods, are presented as a fruitful approach for interpreting learned reward functions and thus enabling users to evaluate them. © 2024, CC BY.

关键词： Contrastive Learning

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：