检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Smart Technologies for Power, Energy and Control, STPEC 2023

作者： Kumar, Avneet Reza, Motiur Singh, Aakash Singh, Santosh K Behera, Ranjan Kumar Indian Institute of Technology Department of Electrical Engineering Patna India Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Varanasi India

ISBN: (纸本)9798350304732

Severa1 applications such as Fuel Cell vehicle, HVDC system, aero-space industry require dc-dc converters having higher voltage gain. To provide optimum solution, a novel non-isolated, non-coupled inductor type dc-dc converters is proposed. The proposed dc-dc converter evolved by integrating active switched network and multiple switched capacitor network. Through this design, following features are achieved: high voltage gain, lower current stress on active switches, lower inductor current, lower voltage stress across devices and lower voltage stress across capacitors. The developed converter exhibits higher voltage gain along with lower voltage stress contrasted with other active switched inductor topologies. The operational and design analysis of the proposed converter is discussed and comparative analysis with the existing topologies are presented. A prototype of 200 W is developed in laboratory for boosting 20 V to 200 V and experimentation is carried out to verify the design. Additionally, the proposed converter is also tested under dynamic condition which illustrates the robustness of the converter with parameter variation. The reported maximum efficiency of the converter is found equal to 92.45%. © 2023 IEEE.

关键词： Switched Inductor Voltage Gain Voltage Stress

来源：评论

学校读者我要写书评

暂无评论

Physical-Design Aware Scan Cell Reordering for Low Power Testing

Physical-Design Aware Scan Cell Reordering for Low Power Tes...

引用

2024 IEEE East-West Design and Test Symposium, EWDTS 2024

作者： Badjatya, Rohit Vinay Kumar, Rahul Tudu, Jaynarayan T Fujita, Masahiro Singh, Virendra Indian Institute of Technology Bombay Dept. of Electrical Engineering Mumbai India Indian Institute of Technology Tirupati India Dept. of Computer Science Engineering Tirupati India University of Tokyo Dept. of Electrical Engineering Tokyo Japan

ISBN: (纸本)9798331515768

Scan chain architecture is widely employed in modern VLSI design for test applications. However, it often leads to high power consumption during testing. The architecture experiences elevated simultaneous switching activity due to non-functional input patterns applied during test time, resulting in significant peak power in the circuits. This increased power consumption can cause IR drop issues, negatively impacting the chip's yield. This paper proposes an innovative approach to reduce both peak power and routing length by effectively reordering the scan chains. Experimental results show that the proposed approach is effective for the ISCAS'89 and ITC'99 benchmark circuits and this method achieves lower peak power and routing length compared to the state of the art. © 2024 IEEE.

关键词： low power testing peak power routing constraint scan chain reordering voltage drop

来源：评论

学校读者我要写书评

暂无评论

Globally Stable Neural Imitation Policies

arXiv

引用

arXiv 2024年

作者： Abyaneh, Amin Guzmán, Mariana Sosa Lin, Hsiu-Chin The Department of Electrical and Computer Engineering McGill University Montreal Canada The Department of Electrical and Computer Engineering Universidad Veracruzana Veracruz Mexico The School of Computer Science The Department of Electrical and Computer Engineering McGill University Montreal Canada

Imitation learning mitigates the resource-intensive nature of learning policies from scratch by mimicking expert behavior. While existing methods can accurately replicate expert demonstrations, they often exhibit unpredictability in unexplored regions of the state space, thereby raising major safety concerns when facing perturbations. We propose SNDS, an imitation learning approach aimed at efficient training of scalable neural policies while formally ensuring global stability. SNDS leverages a neural architecture that enables the joint training of the policy and its associated Lyapunov candidate to ensure global stability throughout the learning process. We validate our approach through extensive simulations and deploy the trained policies on a real-world manipulator arm. The results confirm SNDS's ability to address instability, accuracy, and computational intensity challenges highlighted in the literature, positioning it as a promising solution for scalable and stable policy learning in complex environments. © 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

Network Intrusion Detection Using K-Nearest Neighbors (KNN) and Recurrent Neural Networks (RNN)

Network Intrusion Detection Using K-Nearest Neighbors (KNN) ...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adebiyi, Marion O. Atanda, Oladayo G. Okeke, Chidinma Adebiyi, Ayodele A. Adebiyi, Abayomi A. Landmark University SDG 3: Good Health and Well-Being Department of Computer Science Omu-Aran Nigeria Landmark University SDG 11: Sustainable Cities and Community Department of Computer Science Omu-Aran Nigeria Landmark University Department of Computer Science Omu-Aran Nigeria Durban University of Technology Department of Electrical Power Engineering South Africa

ISBN: (纸本)9798350358155

In today's interconnected world, the security of computer networks is of utmost importance due to the prevalence of cyber threats. To tackle this challenge, a machine learning-based methodology for detecting network intrusions was adopted. The approach leverages two powerful algorithms: K-Nearest Neighbors (KNN) and Recurrent Neural Network (RNN). The proposed methodology involves several steps: data collection, preprocessing, feature extraction, training KNN and RNN models concurrently to capture temporal dependencies, merging model outputs to enhance accuracy, and testing the integrated model on various data types to reduce false alarms. For evaluation, a dataset simulating intrusions in a military network environment was employed. The dataset includes normal and attack instances, and preprocessing techniques were applied to prepare the data for model training. KNN's architecture involves identifying K nearest neighbors based on distance measures, while RNN captures temporal dependencies in sequential data. Confusion metrics, including true positives, true negatives, false positives, and false negatives, along with performance metrics such as accuracy, precision, sensitivity, and F1 score, were utilized to assess model performance. In conclusion, the adopted methodology utilizing KNN and RNN demonstrates strong performance in network intrusion detection. Both algorithms exhibit high accuracy, precision, and sensitivity, making them effective tools for combating cyber threats in real-world network environments. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Position: A Roadmap to Pluralistic Alignment 41

Position: A Roadmap to Pluralistic Alignment

引用

41st International Conference on Machine Learning, ICML 2024

作者： Sorensen, Taylor Moore, Jared Fisher, Jillian Gordon, Mitchell Mireshghallah, Niloofar Rytting, Christopher Michael Ye, Andre Jiang, Liwei Lu, Ximing Dziri, Nouha Althoff, Tim Choi, Yejin Department of Computer Science University of Washington SeattleWA United States Department of Computer Science Stanford University StanfordCA United States Department of Statistics University of Washington SeattleWA United States Department of Electrical Engineering and Computer Science MIT CambridgeMA United States Allen Institute for Artificial Intelligence SeattleWA United States

With increased power and prevalence of AI systems, it is ever more critical that AI systems are designed to serve all, i.e., people with diverse values and perspectives. However, aligning models to serve pluralistic human values remains an open research question. In this piece, we propose a roadmap to pluralistic alignment, specifically using large language models as a test bed. We identify and formalize three possible ways to define and operationalize pluralism in AI systems: 1) Overton pluralistic models that present a spectrum of reasonable responses;2) Steerably pluralistic models that can steer to reflect certain perspectives;and 3) Distributionally pluralistic models that are well-calibrated to a given population in distribution. We also formalize and discuss three possible classes of pluralistic benchmarks: 1) Multi-objective benchmarks, 2) Tradeoff steerable benchmarks that incentivize models to steer to arbitrary trade-offs, and 3) Jury-pluralistic benchmarks that explicitly model diverse human ratings. We use this framework to argue that current alignment techniques may be fundamentally limited for pluralistic AI;indeed, we highlight empirical evidence, both from our own experiments and from other work, that standard alignment procedures might reduce distributional pluralism in models, motivating the need for further research on pluralistic alignment. Copyright 2024 by the author(s)

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Koopman-Based Reinforcement Learning for LQ Control Gains Estimation of Quadrotors

Koopman-Based Reinforcement Learning for LQ Control Gains Es...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Simone Martini Serhat Sünmez Margareta Stefanovic Matthew J. Rutherford Kimon P. Valavanis Department of Electrical and Computer Engineering Ritchie School of Engineering and Computer Science University of Denver USA Department of Aviation Electrical & Electronics Istanbul Medeniyet University Istanbul Turkiye Department of Computer Science Ritchie School of Engineering and Computer Science University of Denver Denver USA

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

In this research, Koopman operator theory is employed to achieve faster training time and improved performance of a reinforcement learning (RL) based linear quadratic controller (LQ). The proposed methodology, called K-RLLQ, is implemented for the trajectory tracking problem of a quadrotor UAV. Using the evolution of analytically derived Koopman generalized eigenfunctions allows for the embedding of quadrotor nonlinear dynamics into a quasi-linear model. Specifically, the resulting Koopman based quadrotor dynamics has linear state matrix and state dependent control matrix. Additionally, the obtained formulation is fully actuated, hence, compared to traditional model based hierarchical control the advantages are twofold: i) the controller can be formulated using linear control strategies in Koopman formulation which will result in a nonlinear control law in the original state space; ii) the trajectory tracking task can be achieved through a single control loop. Using this formulation, an RL agent is trained to estimate the controller parameters of a linear quadratic control law. Notably, it is shown that, using a reward function and observation space based on Koopman generalized eigenfunctions over the state space, leads to a considerably faster training time and improved overall performances.

关键词： Training Trajectory tracking Dynamics Reinforcement learning Transforms Aerospace electronics Eigenvalues and eigenfunctions Mathematical models Nonlinear dynamical systems Quadrotors

来源：评论

学校读者我要写书评

暂无评论

Predictive Storage Management for Cloud-Based Video Streaming Using ML ARIMA Model 66

Predictive Storage Management for Cloud-Based Video Streamin...

引用

2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023

作者： Darwich, Mahmoud Khalil, Kasem Ismail, Yasser Bayoumi, Magdy University of Mount Union Department of Mathematics and Computer Science AllianceOH44601 United States University of Mississippi Department of Electrical and Computer Engineering MS38677 United States Southern University A&m College Electrical Engineering Department Baton RougeLA70807 United States University of Louisiana at Lafayette Department of Electrical and Computer Engineering LA70504 United States

ISBN: (纸本)9798350302103

The exponential increase in video streaming has overburdened data centers, making efficient video streaming in the cloud essential. One potential solution is the tradeoff between transcoding and storing a video stream, as storing operations are cheaper than transcoding. This research explores the use of machine learning ARIMA algorithms to predict the number of views for each video in the repository for the next period of time. This enables informed decisions about which videos to keep or delete from the cloud, ultimately reducing cloud service costs. The study evaluates the accuracy of the ARIMA model in predicting future views for three datasets of varying sizes and levels of variability. Our results show 82% of predicting accurate views, indicating that the ARIMA model can effectively capture the overall trend of video views, providing valuable insights for service providers looking to optimize their storage management practices and reduce costs. This research contributes to the development of more cost-efficient video streaming in the cloud, which is essential for meeting the increasing volume of video stream traffic. By leveraging the ARIMA model, cloud-based platforms can make informed decisions on storage management, enhancing their overall service quality and user experience. © 2023 IEEE.

关键词： ARIMA cloud machine learning video streaming

来源：评论

学校读者我要写书评

暂无评论

Graph-based deep learning models in the prediction of early-stage Alzheimers 46

Graph-based deep learning models in the prediction of early-...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Thapaliya, Bishal Wu, Zundong Sapkota, Ram Ray, Bhaskar Suresh, Pranav Ghimire, Santosh Calhoun, Vince Liu, Jingyu Georgia State University Department of Computer Science Atlanta United States Tri-Institutional Center for Translational Research in Neuroimaging and Data Science United States Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta United States Tribhuvan University Department of Applied Sciences and Chemical Engineering Nepal

ISBN: (纸本)9798350371499

Alzheimer's disease is the most common age-related problem and progresses in different stages, from cognitively normal to early mild cognitive impairment, and severe dementia. This study investigates the predictive potential of resting-state functional magnetic resonance imaging (rs-fMRI) and its derived functional connectivity (FC) in understanding Alzheimer's progression. Leveraging deep learning and graph-based models, we introduce two key contributions: 1) a comparative analysis of rs-fMRI time points and FC for Alzheimer's prediction. 2) an innovative graph transformer variant incorporating self-clustering for enhanced prediction accuracy. Experiments on the Alzheimer's Disease Neuroimaging Initiative dataset with 830 subjects reveal two notable conclusions. Firstly, rs-fMRI time points offer limited utility compared to functional network connectivity for transformer-based models, even when considering temporal information. Secondly, a clustering-based attention module proves effective for classifying brain networks in predicting Alzheimer's disease progression, providing valuable insights for future research and clinical applications. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Low-Latency and Energy-Efficient Task Scheduling for End-Edge-Cloud Collaborative Computing

Low-Latency and Energy-Efficient Task Scheduling for End-Edg...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Li, Jingyao Yuan, Haitao Ma, Yaofei Bi, Jing Yang, Jinhong Zhang, Jia School of Automation Science and Electrical Engineering Beihang University Beijing100191 China College of Computer Beijing University of Technology Beijing100124 China Cssc Systems Engineering Research Institute Beijing China Southern Methodist University Dept. of Computer Science DallasTX75275 United States

ISBN: (纸本)9781665410205

Mobile edge computing (MEC) is a new paradigm that improves the quality of service compared with traditional cloud computing. In MEC, computational tasks are submitted by numerous end users and are partially offloaded to edge servers or a central cloud. However, the characteristics of tasks are different from each other, and the limited resources of computational nodes are also heterogeneous, which brings great challenges to computation offloading and resource allocation for MEC. This work establishes an end-edge-cloud collaborative computing network, which consists of end devices, edge servers, and a central cloud. Task execution location and CPU running frequency determine the execution time and energy consumption to finish the tasks. Considering the aforementioned factors, a multi-objective constrained optimization problem is formulated. To solve the problem, an improved Non-dominated Sorting Genetic Algorithm II (NSGA-II) with self-adaptive crossover and mutation rates is proposed, which is called Improved NSGA-II with _Self-adaptive Crossover and Mutation (INSCM). The total execution time and energy consumption can be jointly minimized with our proposed INSCM. Numerous experiments are carried out to test the performance of INSCM. Simulation results show that INSCM effectively improves the performance of NSGA-II and surpasses random offloading and NSGA-III, which shows practical use in real-life scenarios. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A machine learning-guided design and manufacturing of wearable nanofibrous acoustic energy harvesters

引用

Nano Research 2024年第10期17卷 9181-9192页

作者： Negar Hosseinzadeh Kouchehbaghi Maryam Yousefzadeh Aliakbar Gharehaghaji Safoora Khosravi Danial Khorsandi Reihaneh Haghniaz Ke Cao Mehmet R.Dokmeci Mohammad Rostami Ali Khademhosseini Yangzhi Zhu Terasaki Institute for Biomedical Innovation Los AngelesCA 91367USA Department of Textile Engineering Amirkabir University of Technology(Tehran Polytechnic)Hafez Avenue*** TehranIran Department of Electrical and Computer Engineering University of British ColumbiaVancouverBC V6T1Z4Canada Chemical Sciences Division Oak Ridge National LaboratoryOak RidgeTN 37831USA Department of Computer Science University of Southern CaliforniaLos AngelesCA 90007USA

Nanofibrous acoustic energy harvesters(NAEHs)have emerged as promising wearable platforms for efficient noise-to-electricity conversion in distributed power energy systems and wearable sound amplifiers for assistive listening ***,their reallife efficacy is hampered by low power output,particularly in the low-frequency range(<1 kHz).This study introduces a novel approach to enhance the performance of NAEHs by applying machine learning(ML)techniques to guide the synthesis of electrospun polyvinylidene fluoride(PVDF)/polyurethane(PU)nanofibers,optimizing their application in wearable *** use a feed-forward neural network along with solving an optimization problem to find the optimal input values of the electrospinning(applied voltage,nozzle-collector distance,electrospinning time,and drum rotation speed)to generate maximum output performance(acoustic-to-electricity conversion efficiency).We first prepared a dataset to train the network to predict the output power given the input variables with high *** introducing the neural network,we fix the network and then solve an optimization problem using a genetic algorithm to search for the input values that lead to the maximum energy harvesting *** ML-guided wearable PVDF/PU NAEH platform can deliver a maximal acoustoelectric power density output of 829μW/cm^(3) within the surrounding noise *** addition,our system can function stably in a broad frequency(0.1-2 kHz)with a high energy conversion efficiency of 66%.Sound recognition analysis reveals a robust correlation exceeding 0.85 among lexically akin terms with varying sound intensities,contrasting with a diminished correlation below 0.27 for words with disparate semantic ***,this work provides a previously unexplored route to utilize ML in advancing wearable NAEHs with excellent practicability.

关键词： wearable electronics acoustic energy harvester machine learning piezoelectric nanogenerator electrospun nanofiber

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：