检索结果-内蒙古大学图书馆

16th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2024

作者： Bai, Yidong Sugawara, Toshiharu Waseda University Dept. of Computer Science and Communications Eng. Tokyo169-8555 Japan

ISBN: (纸本)9798350377903

In multi-agent reinforcement learning, decentralized execution is a common approach, yet it suffers from the re-dundant computation problem. This occurs when multiple agents redundantly perform the same or similar computation due to overlapping observations. To address this issue, this study introduces a novel method referred to as locally centralized team transformer (LCTT). LCTT establishes a locally centralized execution framework where selected agents serve as leaders, issuing instructions, while the rest agents, designated as workers, act as these instructions without activating their policy networks. For LCTT, we proposed the team-transformer (T-Trans) archi-tecture that allows leaders to provide specific instructions to each worker, and the leadership shift mechanism that allows agents autonomously decide their roles as leaders or workers. Our experimental results demonstrate that the proposed method effectively reduces redundant computation, does not decrease reward levels, and leads to faster learning convergence. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Doppler Radar Assessment of Environmental Noise Effect on Cardiovascular and Respiratory Activity 11

Doppler Radar Assessment of Environmental Noise Effect on Ca...

引用

11th International Conference on electrical, Electronic and Computing eng.neering, IcETRAN 2024

作者： Sameera, Jannatun Noor Sherstyuk, Ksenia Ishrak, Mohammad Shadman Lubecke, Victor M. Boric-Lubecke, Olga University of Hawaii at Manoa Dept. of Electrical and Computer Eng. HonoluluHI United States Boston University Dept. of Mechanical Eng. BostonMA United States

ISBN: (纸本)9798350386998

The significant impact of environmental noise on cardiovascular health is becoming more widely recognized. However, detailed studies related to environmental noise and human physiology are very limited. This study provides a detailed evaluation of heart rate and respiratory responses to different noise levels in a controlled experimental environment using Doppler radar. The findings indicate that while respiratory rates show notable variations, heart rates remain largely unchanged with alterations in noise levels. This non-invasive approach to assessing the effects of environmental noise using Doppler radar could help improve indoor environmental quality by adapting conditions to enhance acoustic comfort and reduce stress for occupants. © 2024 IEEE.

关键词： Background noise

来源：评论

学校读者我要写书评

暂无评论

Robust decentralized plug and play voltage tracker of islanded microgrids under loads and lines uncertainties by the invariant ellipsoids

引用

Journal of King Saud University - eng.neering sciences 2024年第6期36卷 409-419页

作者： Bayoumi, Ehab H.E. Soliman, Hisham M. El-Sheikhi, Farag Ali Shafiq, M. Awad, Hilmy Energy and Renewable Energy Department Egyptian Chinese University Cairo Egypt Dept. of Electrical Power Eng. Faculty of Eng Cairo University Cairo Egypt Dept. of Electrical and Electronics Engineering Istanbul Esenyurt University Istanbul Turkey Dept. of Electrical and Computer Engineering Sultan Qaboos University Muscat Oman Dept. of Electrical Technology Faculty of Technology and Education Helwan University Egypt

Microgrids (MGs) comprising of distributed generation units (DGs) are subjected to plug-and-play operation (PnP), lines (connecting the DGs) parameters uncertainty, and load changes. Robust stability and an authentic operation for islanded microgrids can be guaranteed through a robust decentralized voltage tracker developed in this paper. The proposed controller design has the following merits: 1) fully decentralized, 2) scalable, and 3) maintains robust stability against PnP of DGs, load changes, and lines parameters’ uncertainties. A sufficient condition is developed by linear matrix inequality convex optimization is exploited to solve the problem. The MGs’ changes in load and the line's parameters are modelled as norm-bounded uncertainties. The suggested controller uses local measurements from DGs, i.e., decentralized by the decomposition of the global system into subsystems. For each subsystem, the rest of the system's impact is considered disturbances, whose influence must be minimized. The proposed disturbance rejection control algorithm is based on the method of invariant-ellipsoids. Several time-domain scenarios such as connecting and disconnecting a number of DGs, local load changes, and variation of transmission line parameters are executed to assess the suggested controller's effectiveness, using MATLAB /Sim PowerSystems Toolbox. © 2021 The Authors

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Estimation of Multi-Attribute Differential Graphs with Non-Convex Penalties

Estimation of Multi-Attribute Differential Graphs with Non-C...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Tugnait, Jitendra K. Dept. of Electrical & Computer Eng. Auburn University AuburnAL36849 United States

ISBN: (纸本)9798350368741

We consider the problem of estimating differences in two multi-attribute Gaussian graphical models (GGMs) which are known to have similar structure, using a penalized D-trace loss function with nonconvex penalties. The GGM structure is encoded in its precision (inverse covariance) matrix. Existing methods for multi-attribute differential graph estimation are based on a group lasso penalized loss function. In this paper, we consider a penalized D-trace loss function with nonconvex (log-sum and smoothly clipped absolute deviation (SCAD)) penalties. Two proximal gradient descent methods are presented to optimize the objective function. Theoretical analysis establishing local consistency in support recovery, local convexity and estimation in high-dimensional settings is provided. We illustrate our approach with a numerical example. © 2025 IEEE.

关键词： ifferential graph learning log-sum multiattribute graphs SCAD penalties undirected graph

来源：评论

学校读者我要写书评

暂无评论

Coronary Heart Disease Prediction on Small Datasets: A Comparative Analysis 26

Coronary Heart Disease Prediction on Small Datasets: A Compa...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Rashid, Rahela Atia Binte Salam, Nazia Raisa, Samiha Noor, Asmita Choudhury, Najeefa Nikhat BRAC University Dept. of Computer Science & Eng. Dhaka Bangladesh

ISBN: (纸本)9798350359015

Coronary Heart Disease (CHD) is one of the major causes of death worldwide. Bangladesh and other developing nations face similar challeng.s. Most people wait until it is too late to recognise that their cardiac problems are getting worse. For this reason, early detection is essential to reduce the death toll or major health effects from CHD. This paper's main goal is to use supervised machine learning (ML) techniques to improve the accuracy of CHD prediction for a Bangladeshi population. ML methods including KNN, Random Forest, Decision Tree, Naive Bayes, and Binary Logistic Regression Model are used in our research methodology to predict CHD on two distinct datasets: one from Bangladesh and the other from Canada. Synthetic data for Bangladeshi dataset were generated by using ADASYN which produces accuracy of 88.12%. On the other hand, using SMOTE, the obtained accuracy was around 93.79%. Both accuracies were achieved by applying Random Forest Algorithm. Binary Logistic Regression obtained highest accuracy for the Canadian dataset which is 72.33%. © 2023 IEEE.

关键词： ADASYN Binary logistic Regression Coronary Heart Disease Decision Tree K-Nearest Neighbor Naive bayes Random Forest SMOTE Supervised Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Automated segmentation and classification of the atherosclerotic carotid plaque in ultrasound videos 24

Automated segmentation and classification of the atheroscler...

引用

24th International Conference on Digital Signal Processing, DSP 2023

作者： Liapi, Georgia D. Gemenaris, Michalis Loizou, Christos P. Kyriacou, Efthyvoulos Constatninou, Kyriacos P. Nicolaides, Andrew Dept. of Electrical Eng. Computer Eng. and Informatics Cyprus University of Technology Limassol Cyprus Dept. of Computer Science University of Cyprus Nicosia Cyprus Vascular Screening and Diagnostic Centre Nicosia Cyprus

ISBN: (纸本)9798350339598

The automated and reliable delineation of atherosclerotic carotid plaques in ultrasound (CUS) videos is of significant clinical relevance for management of the disease and the prediction of future stroke events. To facilitate stroke risk assessment, in this study, we propose an integrated software system for the automated segmentation and classification of atherosclerotic carotid plaques in longitudinal CUS videos, which was evaluated using 10 CUS videos, from 10 patients (5 Asymptomatic, AS, and 5 Symptomatic, SY). The proposed methodology involves the following steps: a) CUS video frame (VF) resolution and intensity normalization, b) speckle reduction filtering, c) Motion-mode state-based cardiac cycle (CC) identification, d) deep learning (DL)-based plaque segmentation, e) extraction and selection of plaque region of interest (ROI)-specific textural features, and f) machine learning (ML)-based plaque classification. Initially, one CC (cardiac diastole-systole-diastole) was selected per CUS video, and the CC's consecutive VFs were identified and reduced in number to exclude redundant VFs. All standardized VFs per patient were extracted, cropped and resized to mainly accommodate the ROI and were fed into a priorly trained and evaluated 2-dimensional DL plaque segmentation model. For each VF, the DL-based segmented plaque ROI was projected onto its primary resolution-normalized VF counterpart, from which textural and amplitude modulation-frequency modulation (AM-FM) plaque ROI features were extracted. Statistical analysis on the total AS and SY VFs was used for feature selection. We identified 2 plaque-originating AM-FM features, which exhibited statistically significant differences between the AS and SY standardized VFs (p © 2023 IEEE.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

A Study of Digital Games as a Method of Reducing Stress for Students in the Modern World : Study took place at Indian Institute of Information Technology Dharwad (IIIT Dharwad) 19

A Study of Digital Games as a Method of Reducing Stress for ...

引用

19th IEEE International Conference on e-Business eng.neering, ICEBE 2023

作者： Singh, Digant Kothari, Devwardhan Saha, Lupam K Iiit Dharwad Dept. of Computer Science and Eng. Dharwad India

ISBN: (纸本)9798350325553

Objective: This research explores the link between playing digital games and stress reduction among students across diverse educational levels. The study investigates optimal gaming duration for stress reduction. Method: The study employs two approaches: a broad survey capturing student opinions and a focused method involving 14 volunteers playing games while monitoring stress levels using a questionnaire pre-gaming and post-gaming, over a 21-day span. Key Results: The general survey indicates that over 80% of students find digital games helpful in stress reduction. However, an in-dept. analysis reveals around 55% to 60% experience actual relaxation post-gaming, typically lasting less than 2 hours. Few exhibit consistent long-term stress reduction. The focus group shows daily stress reduction for some, with occasional spikes attributed to academic stress. Conclusion: Digital games have a positive impact on student stress levels, providing effective daily stress reduction in short gaming sessions of 15 to 30 minutes. The impact of longer gaming duration remains beyond this study's scope. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Hybrid Reinforcement Learning for Data Stream Freshness in Autonomous Vehicle Networks

Hybrid Reinforcement Learning for Data Stream Freshness in A...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Ebrahimi, Dariush Ghosh, Pronab Alzhouri, Fadi De Oliveira, Thiago E. Alves Wilfrid Laurier University Dept. of Computer Science WaterlooON Canada Lakehead University Dept. of Computer Science Thunder BayON Canada Concordia University Dept. of Elec. & Computer Eng. MontrealQC Canada

ISBN: (纸本)9798350351255

Autonomous vehicles (AVs) are poised to become integral components of intelligent transportation systems, particularly within the framework of future smart cities. Traditional performance metrics such as throughput and latency fall short in adequately addressing the temporal relevance and freshness of data in critical applications such as autonomous driving and accident prevention. Consequently, this paper delves into the challeng. of reducing the Age of Information (AoI) for disseminating data streams within AV-assisted vehicular networks. Given the dynamic nature of the environment, the problem is formulated as a Markov decision process and tackled using Q-learning and DDQN, both prominent reinforcement learning (RL) algorithms. Additionally, a heuristic approach is introduced to augment the performance of the RL algorithms, expediting environmental learning convergence. The numerical findings underscore the effectiveness of the proposed methodologies in minimizing the aggregate AoI across all data streams. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Smart Network Intrusion Detection System for Cyber Security of Industrial IoT 3

A Smart Network Intrusion Detection System for Cyber Securit...

引用

3rd International Conference on Intelligent Data science Technologies and Applications, IDSTA 2023

作者： Alzhouri, Fadi Gunjal, Hardik Patel, Preetkumar Hammad, Ahmad Ebrahimi, Dariush Concordia University Dept. of Elect. & Computer Eng. Montreal Canada Lakehead University Dept. of Computer Science Thunder Bay Canada Kuwait University Dept. of Computer Eng. Kuwait Kuwait

ISBN: (纸本)9798350339253

In the industrial sectors, machines and sensors communicate with each other and with the control or central units through the Internet;this forms a network of Industrial devices called the Industrial Internet of Things (IIoT). IIoT is an emerging trend that generates big data which could be vulnerable to cyber-attacks. In the IIoT network, data and control instructions are usually flown through a Supervisory Control and Data Acquisition (SCADA) system. We propose to install a Network Intrusion Detection System (NIDS) between SCADA and IIoT devices to monitor real-time network traffic and detect cyber-attacks. Several deep learning algorithms can be used on a large dataset for intrusion detection. In this paper, we implement and compare three deep learning algorithms, namely, MultiLayer Perceptron (MLP), Fully Connected Deep Neural Network (FCNN), and Convolutional Neural Network (CNN), on two different datasets by varying the number of selected features for classifications using the XGBoost algorithm. The study shows that CNN with XGBoost is superior in its performance over other methods applied to NIDS. Our proposed methodology has proven to be effective regardless of the highly unbalanced dataset. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Availability Model of a 5G-MEC System 32

Availability Model of a 5G-MEC System

引用

32nd International Conference on computer Communications and Networks, ICCCN 2023

作者： Pathirana, Thilina Nencioni, Gianfranco University of Stavanger Dept of Electrical Eng. and Computer Science Stavanger Norway

ISBN: (纸本)9798350336184

Multi-access Edge Computing (MEC) is one of the enabling technologies of the fifth generation (5G) of mobile networks. MEC enables services with strict latency requirements by bringing computing capabilities close to the users. As with any new technology, the dependability of MEC is one of the aspects that need to be carefully studied. In this paper, we propose a twolevel model to compute the availability of a 5G-MEC system. We then use the model to evaluate the availability of a 5G-MEC system under various configurations. The results show that having a single redundancy of the 5G-MEC elements leads to an acceptable availability. To reach a high availability, the software failure intensity of the management elements of 5G and MEC should be reduced. © 2023 IEEE.

关键词： 5G mobile communication systems

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：