检索结果-内蒙古大学图书馆

19th IEEE International Multi-Conference on systems, Signals and Devices, SSD 2022

作者： Lachekhab, Fadhila Zamoum, Razika Boushaki Bougheloum, Dhya Eddine Benyahia, Sofiane Acheli, Dalila Kouzou, Abdellah University of Mhamed Bougara Systems and Telecommunications Engineering Laboratory Faculty of Hydocarbons and Chemistry Boumerdes Algeria Iinstitute of Electrical and Electronic Engeneering University of Boumerdes Systems and Telecommunications Engineering Laboratory Boumerdes Algeria Institute of Electrical and Electronic Engeneering University of Boumerdes Boumerdes Algeria University of Mhamed Bougara Systems and Telecommunications Engineering Laboratory Faculty of Technology Boumerdes Algeria University of Djelfa Applied Automation and Industrial Diagnostics Laboratory Laadi Faculty of Science and Technology Djelfa Algeria

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

The major goal of this work is to develop a control mechanism for the squirrel cage induction motor that will deliver the best dynamic response. This will be accomplished through the use of vector control techniques and the integration of fuzzy logic with traditional controllers. MATLAB/SIMULINK was used to compare controllers (PID, Fuzzy, and Fuzzy -PID) to the standard PI controller at various load situations, analyzing performance such as rising time (tr), overshoot (Mp), settling time (ts), and steady state error. © 2022 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

IoT Enabled Driver Compatible Cost-Effective System for Drowsiness Detection with Optimized Response Time 3rd

IoT Enabled Driver Compatible Cost-Effective System for Drow...

引用

3rd EAI International Conference on Cognitive Computing and Cyber Physical systems, IC4S 2022

作者： Sarkar, Argha Kundu, Mayuri Pareek, Prakash Gupta, Nishu Reis, Manuel J. Cabral S. School of Computer Science and Engineering REVA University Karnataka Bangalore560064 India Department of Electronics and Communication Engineering Vishnu Institute of Technology Andhra Pradesh Bhimavaram534202 India Department of Electronic Systems Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Gjøvik2815 Norway Engineering Department UTAD/IEETA Vila Real5001-801 Portugal

ISBN: (纸本)9783031289743

The present work researches driver drowsiness, which constitutes a huge problem, and can turn into fatal incidents potentially involving the losing of lives, being it while driving in a highway (car, bus, truck, etc.), in the railway, or any other transportation mean (ship, airplane, etc.). Recent technology has been involved in the study of the fatigue behaviour. The purpose of this work is to identify the in-driver’s drowsiness, contributing to get rid of the accidents, mainly during the night, and to ensure better safety in train and on the highways. A camera is used to capture images from the driver, and face detection is executed in real-time to find out the exact position of driver’s face. Here, the blinking of the driver’s eye is under consideration. The fundamental concept lies in the closing of the driver’s eye for a specific duration of time. If the closing time exceeds that certain duration, drowsiness is detected and an alarm is sounded for awareness. Python and OpenCV (using Haarcascade library) are the fundamental programming platforms for sensing the facial attributes. In this work, a cost-effective system for the driver’s drowsiness detection is aimed. Further, the result also indicates the reduction of response and processing time, which is ideal for real time detection. © 2023, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Performance of NPG in Countable State-Space Average-Cost RL

arXiv

引用

arXiv 2024年

作者： Murthy, Yashaswini Grosof, Isaac Maguluri, Siva Theja Srikant, R. Electrical and Computer Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA30332 United States

We consider policy optimization methods in reinforcement learning settings where the state space is arbitrarily large, or even countably infinite. The motivation arises from control problems in communication networks, matching markets, and other queueing systems. Specifically, we consider the popular Natural Policy Gradient (NPG) algorithm, which has been studied in the past only under the assumption that the cost is bounded and the state space is finite, neither of which holds for the aforementioned control problems. Assuming a Lyapunov drift condition, which is naturally satisfied in some cases and can be satisfied in other cases at a small cost in performance, we design a state-dependent step-size rule which dramatically improves the performance of NPG for our intended applications. In addition to experimentally verifying the performance improvement, we also theoretically show that the iteration complexity of NPG can be made independent of the size of the state space. The key analytical tool we use is the connection between NPG stepsizes and the solution to Poisson’s equation. In particular, we provide policy-independent bounds on the solution to Poisson’s equation, which are then used to guide the choice of NPG stepsizes. © 2024, CC BY.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Deep nonparametric estimation of operators between infinite dimensional spaces

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 1239-1305页

作者： Hao Liu Haizhao Yang Minshuo Chen Tuo Zhao Wenjing Liao Department of Mathematics Hong Kong Baptist University Hong Kong Department of Mathematics and Department of Computer Science University of Maryland College Park Department of Electrical and Computer Engineering Princeton University School of Industrial and Systems Engineering Georgia Institute of Technology School of Mathematics Georgia Institute of Technology

Learning operators between infinitely dimensional spaces is an important learning task arising in machine learning, imaging science, mathematical modeling and simulations, etc. This paper studies the nonparametric estimation of Lipschitz operators using deep neural networks. Non-asymptotic upper bounds are derived for the generalization error of the empirical risk minimizer over a properly chosen network class. Under the assumption that the target operator exhibits a low dimensional structure, our error bounds decay as the training sample size increases, with an attractive fast rate depending on the intrinsic dimension in our estimation. Our assumptions cover most scenarios in real applications and our results give rise to fast rates by exploiting low dimensional structures of data in operator estimation. We also investigate the influence of network structures (e.g., network width, depth, and sparsity) on the generalization error of the neural network estimator and propose a general suggestion on the choice of network structures to maximize the learning efficiency quantitatively.

关键词： deep neural networks nonparametric estimation operator learning generalization error analysis

来源：评论

学校读者我要写书评

暂无评论

An Optimized Design of Antenna Arrays for the Smart Antenna systems

引用

computers, Materials & Continua 2021年第11期69卷 1979-1994页

作者： Fahd N.Al-Wesabi Murad A.A.Almekhlafi Huda G.Iskandar Adnan Zain Saleh Alzahrani Mohammed Alamgeer Nadhem Nemri Sami Dhabi Mohammad Medani Ali.M.Al-Sharafi Department of Computer Science King Khalid UniversityMuhayel AseerKingdom of Saudi Arabia Faculty of Computer and IT Sana’a UniversitySana’aYemen Department of Electrical Engineering–Communication Engineering Sana’a UniversityYemen School of Computing Faculty of EngineeringUniversiti Teknologi MalaysiaMalaysia Department of Electronics and Communication Engineering Faculty of EngineeringUniversity of AdenYemen Department of Information Systems King Khalid UniversityMuhayel AseerKingdom of Saudi Arabia Department of Computer Science College of Computers and Information TechnologyUniversity of BishaKSA

In recent years,there has been an increasing demand to improve cellular communication services in several *** aspect that received the most attention is improving the quality of coverage through using smart antennas which consist of array *** paper investigates the main characteristics and design of the three types of array antennas of the base station for better coverage through simulation(MATLAB)which provides field and strength patterns measured in polar and rectangular coordinates for a variety of conditions including broadsides,ordinary End-fire,and increasing directivity End-fire which is typically used in smart *** method of analysis was applied to twenty experiments of process design to each antenna type separately,so sixty results were obtained from the radiation pattern indicating the parameters for each radiation ***,nineteen design experiments were described in this *** is hoped that the results obtained from this study will help engineers solve coverage problems as well as improve the quality of cellular communication networks.

关键词： Smart antenna antenna arrays patterns construction coverage

来源：评论

学校读者我要写书评

暂无评论

Mathematical modeling and dragonfly algorithm for optimizing sustainable agritourism supply chains

Journal of Engineering Research

引用

Journal of engineering Research 2025年第2期13卷 751-762页

作者： Gongwang Zhang Chun-Nan Chen Mohammad Shokouhifar Alireza Goli Hangzhou Administrative College Hangzhou 310024 Zhejiang China College of Management Chang Jung Christian University Tainan 711301 Taiwan China Department of Electrical and Computer Engineering Shahid Beheshti University Tehran *** Iran Department of Industrial Engineering and Future Studies Faculty of Engineering University of Isfahan Iran

The management of agritourism supply chains plays a pivotal role in promoting sustainable rural development and cultivating economic growth within agricultural communities. The study devises a comprehensive methodology aimed at designing and optimizing agritourism supply chain networks. To achieve this purpose, a two-objective mixed-integer linear programming mathematical model is introduced, tailored to accommodate diverse water consumption priorities across different gardens within the chain. Recognizing the NP-hardness of this intricate problem, a metaheuristic-driven solution approach based on MIN-MAX goal programming and dragonfly algorithm is presented to solve the designed model, aiming to simultaneously maximize the total profit and minimize overall water consumption within the supply chain. To assess the effectiveness of the proposed methodology, we adopted a real-world case study of an agritourism supply chain in China. The obtained results indicate the adoption of the proposed method can efficiently lead to the development and mechanization of agriculture in villages. The numerical analysis highlights that recruitment and production costs significantly influence the total profit of the agritourism supply chain. Additionally, the research underscores the pivotal role of sustainable rural development in creating job opportunities within the agritourism supply chain, thereby stimulating economic growth and fostering more profitable enterprises.

关键词： Supply chain network design Mathematical modeling Optimization Dragonfly algorithm Sustainability Water consumption

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Learning Performance in First-Year University Programming Course 10

Predictive Analytics for Learning Performance in First-Year ...

引用

10th IEEE International Conference on Smart Instrumentation, Measurement and Applications, ICSIMA 2024

作者： Kartiwi, Mira Gunawan, Teddy Surya Yusoff, Nelidya Md International Islamic University Malaysia Department of Information Systems Kuala Lumpur53100 Malaysia International Islamic University Malaysia Electrical and Computer Engineering Dept. Kuala Lumpur53100 Malaysia Universiti Teknologi Malaysia Faculty of Artificial Intelligence Kuala Lumpur51400 Malaysia

ISBN: (纸本)9798350365283

The increasing demand for programming skills has highlighted the need for effective teaching strategies to support student success in programming courses. Despite significant advancements in learning analytics, predictive models explicitly tailored to programming courses remain underexplored. This research aims to develop a machine learning model to predict student performance in programming courses offered within IT programs by analyzing gender, type of activity (readings, coding exercises, assignments), and frequency of access to different activities. Our study utilizes log data of the asynchronous learning activities in the learning management systems of the students enrolled in programming courses. We employ machine learning techniques, decision trees, gradient boosting machines (GBM), and logistic regression to build robust predictive models. In this study, the decision tree model outperformed logistic regression (77.77%) and gradient boosting machine (GBM) (86.57%) by achieving the highest accuracy of 89.09% and excelling in predicting 'Poor' student performance with a recall of 90.67%, establishing it as the most effective model for this predictive analysis. The findings from this research offer actionable insights for educators, enabling early intervention for at-risk students and developing tailored teaching strategies to enhance student performance through strategically provisioning the learning materials in programming courses. This study contributes to the growing knowledge of learning analytics and provides a foundation for future research in predictive modeling for diverse educational contexts. © 2024 IEEE.

关键词： Predictive analytics

来源：评论

学校读者我要写书评

暂无评论

An observer comparison study to evaluate a machine learning model to quantify the infected pneumonia on lung CT images

An observer comparison study to evaluate a machine learning ...

引用

Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment

作者： Abdihamzehkolaei, Alireza Mirniaharikandehei, Seyedehnafiseh Choquehuanca, Angel Aedo, Marco Pacheco, Wilmer Estacio, Laura Cahui, Victor Huallpa, Luis Quiñonez, Kevin Calderón, Valeria Gutierrez, Ana Maria Vargas, Ana Gamero, Dery Castro-Gutierrez, Eveling Qiu, Yuchen Zheng, Bin Jo, Javier A. School of Electrical and Computer Engineering University of Oklahoma NormanOK United States School of Systems Engineering and Informatics Universidad Nacional de San Agustín de Arequipa Arequipa Peru Medicine Faculty Universidad Nacional de San Agustín de Arequipa Arequipa Peru

ISBN: (数字)9781510660403

ISBN: (纸本)9781510660397

Quantification of infected lung volume using computed tomography (CT) images can play a critical role in predicting the severity of pulmonary infectious disease. Manual segmentation of infected areas from several CT image slices, however, is not efficient and viable in clinical practice. To assist clinicians in overcoming this challenge, we developed a new method to automatically segment and quantify the percentage of the infected lung volume. First, we used a public dataset of 20 COVID-19 patients, which consists of manually annotated lung and infection masks, to train a new joint deep learning (DL) model for lung and infection segmentation. As for lung segmentation, a Mask-RCNN model was applied to the lung volume with a novel postprocessing technique. Following that, an ensemble model with a customized residual attention UNet model and feature pyramid network (FPN) models was employed for infection segmentation. Next, we assembled another set of 80 CT scans of Covid-19 patients. Two chest radiologists manually evaluated each CT scan and reported the infected lung volume percentage using a customized graphical user interface (GUI). The developed DL-model was also employed to process these CT images. Then, we compared the agreement between the radiologist (manual) and model-based (automated) percentages of diseased regions. Additionally, the GUI was used to let radiologists rate acceptance of the DL-model generated segmentation results. Analyzing the results demonstrate that the agreement between manual and automated segmentation is >95% in 28 testing cases. Furthermore, >53% of testing cases received the top assessment rating scores from two radiologists (between four-five- score). Thus, this study illustrates the feasibility of developing a DL-model based automated tool to effectively provide quantitative evaluation of infected lung regions to assist in improving the efficiency of radiologists in infection diagnosis. © COPYRIGHT SPIE. Downloading of the abstract

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

5G Use Cases in Metaverse Using Open Source Software

5G Use Cases in Metaverse Using Open Source Software

引用

International Technical Conference o Circuits/systems, computers and Communications (ITC-CSCC)

作者： Pisit Vanichchanunt Sirapop Saengthongkam Natthapong Waichampa Navy Wuttiananchai Pruk Sasithong Vitawat Sittakul Lunchakorn Wuttisittikulkij Sukritta Paripurana Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut's University of Technology North Bangkok Bangkok Thailand Department of Electrical Engineering Faculty of Engineering Chulalongkorn University Bangkok Thailand Department of Electronic Engineering Technology College of Industrial Technology King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350379051

ISBN: (纸本)9798350379068

Designing, implementing, and testing a practical 5G use case usually consumes large amount of time, budget, and effort. To alleviate unexpected problems and also ensure the functionalities of a 5G project, this paper proposes the integration of 5G system and a virtual use case in metaverse for designing and pretesting by using open source software. This software-based approach in metaverse not only enhances the perspectives on the consideration for designing and testing but also escalates the project ready for 5G digital twin. A virtual smart warehouse is selected to demonstrate 5G use cases since it employs smart components/machines, such as Automated Guided Vehicles (AGVs) and autonomous forklifts, as well as uses various types of IoT devices including temperature sensors, humidity sensors, CCTV cameras, light detectors, and RFID cards. To enable such smart components and devices to function in metaverse, the 5G network slices are designed to support three types of IoT services including Broadband IoT, Critical IoT, and Massive IoT which require high data rate, low-latency, and massive connectivity respectively.

关键词： Temperature sensors 5G mobile communication Metaverse Robot vision systems Cameras Digital twins Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Solutions for Digital Interaction of a Resilient Energy Community in a Service-oriented Framework 12

Solutions for Digital Interaction of a Resilient Energy Comm...

引用

12th International Conference and Exposition on electrical and Power engineering, EPE 2022

作者： Sanduleac, Mihai Ionescu, Constantin Mandis, Alexandru Gropa, Victor Efremov, Cristina Sanduleac, Vlad Department of Power Systems Faculty of Energy Engineering University Politehnica of Bucharest Bucharest Romania Dep. of Energy Generation and Use Faculty of Energy Engineering University Politehnica of Bucharest Bucharest Romania Faculty of Energetics and Electrical Engineering Technical University of Moldova Chisinau Moldova Department of Computer Science and Engineering Faculty of Automatic Control and Computers University Politehnica of Bucharest Romania

ISBN: (数字)9781665489942

ISBN: (纸本)9781665489942

Energy communities are emerging entities which need their own Information and Communication System. Resilience is a key metric of such communities, and it has to be implemented for both energy supply versus public network outages and for its information system versus cyber-attacks, acting as cyber-citadels which have to resist external malicious attacks while having also digital interactions with external entities. The paper presents solutions for a resilient energy community with appropriate implementations of digital interaction for data exchange, in order to acquire external energy service for specialized companies and to deliver also information and communication-related services for external users. Principles of a Contractual Data Protection Regulation are presented, as an adaptation of data protection tailored for automated energy services and based on secure data exchange. The principles are verified in a demonstration project which has also external entities with digital interaction. © 20XX IEEE.

关键词： Cybersecurity

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：