检索结果-内蒙古大学图书馆

The State of Lithium-Ion Battery Health Prognostics in the CPS Era

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shinde, Gaurav Mohapatra, Rohan Krishan, Pooja Garg, Harish Prabhu, Srikanth Das, Sanchari Masum, Mohammad Sengupta, Saptarshi Department of Engineering San Jose State University San JoseCA United States Department of Computer Science San Jose State University San JoseCA United States School of Mathematics Thapar Institute of Engineering & Technology Punjab Patiala147004 India Department of Computer Science and Engineering Manipal Institute of Technology KA Manipal India Department of Computer Science University of Denver DenverCO United States Department of Applied Data Science San Jose State University San JoseCA United States

Lithium-ion batteries (Li-ion) have revolutionized energy storage technology, becoming integral to our daily lives by powering a diverse range of devices and *** high energy density, fast power response, recyclability, and mobility advantages have made them the preferred choice for numerous sectors. This paper explores the seamless integration of Prognostics and Health Management within batteries, presenting a multidisciplinary approach that enhances the reliability, safety, and performance of these powerhouses. Remaining useful life (RUL), a critical concept in prognostics, is examined in depth, emphasizing its role in predicting component failure before it occurs. The paper reviews various RUL prediction methods, from traditional models to cutting-edge data-driven techniques. Furthermore, it highlights the paradigm shift toward deep learning architectures within the field of Li-ion battery health prognostics, elucidating the pivotal role of deep learning in addressing battery system *** applications of PHM across industries are also explored, offering readers insights into real-world *** paper serves as a comprehensive guide, catering to both researchers and practitioners in the field of Li-ion battery *** Codes 68 Copyright © 2024, The Authors. All rights reserved.

关键词： Lithium-ion batteries

Neural Network Interpretability: Methods for Understanding and Visualizing Deep Learning Models

学校读者我要写书评

暂无评论

Neural Network Interpretability: Methods for Understanding a...

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Angatha Veera Venkata Sudhakar M. K. Sharma Chinnem Rama Mohan Er. Suraj Singh Kuldeep Chouhan B. T. Geetha Department of EEE School of Engineering SR University Warangal Telangana India Mathematics Chaudhary Charan Singh University Meerut Uttar Pradesh India Department of Computer Science and Engineering Narayana Engineering College Nellore Andhra Pradesh India Electrical Engineering Department M. M. Engineering College Maharishi Markandeshwar (Deemed to be University) Mullana-Ambala Haryana India Department of Computer Science and Applications Sharda School of Engineering and Technology Sharda University Greater Noida India Department of ECE Saveetha School of Engineering (SIMATS) Saveetha University Tamil Nadu India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

Neural networks, which are a type of deep learning model, are massively criticized due to their ‘black box’ approach, which does not allow interpreting their decisions. In this research, several post-hoc interpretability techniques, which seek to explain the behavior of such models, are discussed. Specifically, this paper aims to evaluate the application of activation maps, feature importance, and attention mechanisms for explaining CNN and LSTM architectures within two distinct datasets namely Fashion MNIST and IMDB. Thus, the work has a focus on showing that these interpretability methods are not only useful for understanding deep learning models, as well as for reducing bias, fairness, and trust in AI systems. It emphasizes that the complexity and interpretability of models used in socially important tasks should be more thoroughly researched in order to develop effective means of improving artificial intelligence systems while maintaining explanatory power and non-discriminatory approach.

关键词： Deep learning Training Ethics Visualization Sentiment analysis Attention mechanisms Recurrent neural networks Predictive models Convolutional neural networks Long short term memory

Turning Around and Around: Motion Planning through Thick and Thin Turnstiles 33

学校读者我要写书评

暂无评论

Turning Around and Around: Motion Planning through Thick and...

33rd Canadian Conference on Computational Geometry, CCCG 2021

作者： Greenblatt, Aster Hernandez, Oscar Hearn, Robert A. Hou, Yichao Ito, Hiro Kang, Minwoo Williams, Aaron Winslow, Andrew Division of Science Mathematics and Computing Bard College at Simon’s Rock United States Department of Mathematics & Statistics University of Alaska Fairbanks United States School of Informatics and Engineering University of Electro-Communications Japan Electrical Engineering and Computer Science University of California Berkeley United States Department of Computer Science Williams College United States

We examine the computational complexity of turnstile puzzles, which are grid-based tour puzzles with walls and turnstiles. A turnstile is a wall that can be rotated in 90° increments, either clockwise or counter-clockwise, around a central pivot when pushed by the player’s token. In a ‘thick’ turnstile, the pivot and arms occupy cells of the grid, whereas in a’thin’ turnstile the pivot and arms occupy grid points and lines, respectively. We prove that reaching an exit is PSPACE-hard, even when restricted to just one of the following turnstiles types:,,,,, or . This establishes PSPACE-hardness for a dozen video games spanning several decades, including Kwirk (1989), Pokemon Ruby (2002), and Super Mario Odyssey (2017). Our hardness results are obtained by applying the motion planning framework in Jayson Lynch’s PhD thesis A framework for proving the computational intractability of motion planning problems [MIT, 2020]. We also show that the decision problem can be solved in polynomial-time when restricted to or . We also formulate new open problems, and provide a survey of puzzles and games using turnstiles, which have also been called rotating doors, revolving gates, and spinning blocks. © 2021 Meng He and Don Sheehy.

关键词： Motion planning

Efficient Pooling Designs and Screening Performance in Group Testing for Two Types of Defectives

学校读者我要写书评

暂无评论

Efficient Pooling Designs and Screening Performance in Group...

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Hiroyasu Matsushima Yusuke Tajima Xiao-Nan Lu Masakazu Jimbo Data Science and AI Innovation Reseach Promotion Center Shiga University Hikone Japan Department of Electrical Electronic and Computer Engineering Gifu University Gifu Japan Center for Training Professors in Statistics The Institute of Statistical Mathematics Tokyo Japan

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

Group testing is utilized in the case when we want to find a few defectives among a large amount of items. Testing $n$ items one by one requires $n$ tests, but if the ratio of defectives is small, group testing is an efficient way to reduce the number of tests. Many researches have been developed for group testing for a single type of defectives. In this paper, we consider the case where two types of defective A and B exist. For two types of defectives, we develop a belief propagation algorithm to compute the marginal posterior probability of defectives. Furthermore, we construct several kinds of collections of pools in order to test for A and B. And, by utilizing our belief propagation algorithm, we evaluate the performance of group testing by conducting simulations.

关键词： Geometry Computational modeling Posterior probability Software algorithms Software Testing Belief propagation

Comparative Analysis of AES, RC and Twofish Algorithms for Data Encryption and Decryption

学校读者我要写书评

暂无评论

Comparative Analysis of AES, RC and Twofish Algorithms for D...

Computing and Information Technology (ICCIT-1441), 2020 International Conference on

作者： Ahmad Faizal Bin Tajuddin Mohammad Hafiz Mohd Yusof Mohammed Balfaqih Akram A. Almohammedi Sam Darshi Nadhem Qaid College of Computing Informatics and Mathematics Universiti Teknologi MARA UiTM Tapah Malaysia College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia Electrical and Electronic Engineering Department Karabük University Karabük Turkey Department of Electrical Engineering Indian Institute of Tehcnology Ropar Punjab India R&D Engineer Lead Marine Powertrain Controls & Electronics Caterpillar Inc Houstan Texas USA

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

This paper presents a comparative analysis of three widely used encryption algorithms, namely AES (Advanced Encryption Standard), RC (Rivest Cipher), and Twofish, with a focus on their performance in data encryption and decryption. The study aims to evaluate the strengths and weaknesses of these algorithms in terms of security, speed, and efficiency. The analysis involves benchmarking the algorithms against various performance metrics, including encryption time, decryption time, key size, and resistance against cryptanalysis attacks. Additionally, the research explores the impact of different data sizes and configurations on the performance of each algorithm. The findings of this study will provide valuable insights for decision-makers and practitioners in selecting the most suitable encryption algorithm for their specific needs, considering the tradeoffs between security and performance.

关键词： Resistance Ciphers Three-dimensional displays Data security Benchmark testing Encryption Timing Information technology Standards

Adaptive Differentially Quantized Subspace Perturbation (ADQSP): A Unified Framework for Privacy-Preserving Distributed Average Consensus

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Qiongxiu Gundersen, Jaron Skovsted Lopuhaä-Zwakenberg, Milan Heusdens, Richard Tsinghua University China The Department of Electronic Systems Aalborg University Denmark University of Twente Netherlands Netherlands The Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands

Privacy-preserving distributed average consensus has received significant attention recently due to its wide applicability. Based on the achieved performances, existing approaches can be broadly classified into perfect accuracy-prioritized approaches such as secure multiparty computation (SMPC), and worst-case privacy-prioritized approaches such as differential privacy (DP). Methods of the first class achieve perfect output accuracy but reveal some private information, while methods from the second class provide privacy against the strongest adversary at the cost of a loss of accuracy. In this paper, we propose a general approach named adaptive differentially quantized subspace perturbation (ADQSP) which combines quantization schemes with so-called subspace perturbation. Although not relying on cryptographic primitives, the proposed approach enjoys the benefits of both accuracy-prioritized and privacy-prioritized methods and is able to unify them. More specifically, we show that by varying a single quantization parameter the proposed method can vary between SMPC-type performances and DP-type performances. Our results show the potential of exploiting traditional distributed signal processing tools for providing cryptographic guarantees. In addition to a comprehensive theoretical analysis, numerical validations are conducted to substantiate our results. © 2023, CC BY.

关键词： Differential privacy

MOMENTUM DIMINISHES THE EFFECT OF SPECTRAL BIAS IN PHYSICS-INFORMED NEURAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Farhani, Ghazal Kazachek, Alexander Wang, Boyu Department of Electrical and Computer Engineering The University of Western Ontario LondonON Canada Department of Mathematics The University of Western Ontario LondonON Canada Department of Computer Science The University of Western Ontario LondonON Canada

Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs). However, they often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under stochastic gradient descent with momentum (SGDM). This demonstrates SGDM significantly reduces the effect of spectral bias. We have also examined why training a model via the Adam optimizer can accelerate the convergence while reducing the spectral bias. Moreover, our numerical experiments have confirmed that wide-enough networks using SGDM still converge to desirable solutions, even in the presence of high-frequency features. In fact, we show that the width of a network plays a critical role in convergence. © 2022, CC0.

关键词： Momentum

Resource allocation for vehicle platooning in 5G NR-V2X via deep reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Liu Yin, Hao Department of Electrical and Computer Engineering University of Washington Seattle United States Department of Applied Mathematics University of Washington Seattle United States

Vehicle platooning, one of the advanced services supported by 5G New Radio V2X (NR-V2X), improves traffic efficiency in the connected intelligent transportation systems (C-ITSs). However, the packet collision probability of platoon communication, especially in the out-of-coverage area, is significantly impacted by the random selection algorithm employed in the current resource allocation scheme. In this paper, we first analyze the collision probability via the random selection algorithm based on the current standard. Subsequently, we investigate the deep reinforcement learning (DRL) algorithm that decreases the collision probability by letting the agent (platoon leader) learn from the communication environment. Monte Carlo simulation is utilized to verify the results obtained in the analytical model and to compare the results between the two discussed algorithms. Numerical results show that the proposed DRL algorithm outperforms the random selection algorithm in terms of different vehicle density, which at least lowering the collision probability by 73% and 45% in low and high vehicle density respectively. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Vector tomography for reconstructing electric fields with non-zero divergence in bounded domains

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Koulouri, Alexandra Brookes, Mike Rimpiläinen, Ville Institute for Computational and Applied Mathematics University of Münster Einsteinstrasse 62 Münster48149 Germany Department of Electrical and Electronic Engineering Imperial College London Exhibition Road LondonSW7 2BT United Kingdom Department of Mathematics University of Auckland Private Bag 92019 Auckland1142 New Zealand

In vector tomography (VT), the aim is to reconstruct an unknown multi-dimensional vector field using line integral data. In the case of a 2-dimensional VT, two types of line integral data are usually required. These data correspond to integration of the parallel and perpendicular projection of the vector field along integration lines. VT methods are non-invasive, non-intrusive and offer more information on the field than classical point measurements;they are typically used to reconstruct divergence-free (or source-free) velocity and flow fields. In this paper, we show that VT can also be used for the reconstruction of fields with non-zero divergence. In particular, we study electric fields generated by dipole sources in bounded domains which arise, for example, in electroencephalography (EEG) source imaging. To the best of our knowledge, VT has not previously been used to reconstruct such fields. We explain in detail the theoretical background, the derivation of the electric field inverse problem and the numerical approximation of the line integrals. We show that fields with non-zero divergence can be reconstructed from the longitudinal measurements with the help of two sparsity constraints that are constructed from the transverse measurements and the vector Laplace operator. As a comparison to EEG source imaging, we note that VT does not require mathematical modelling of the sources. By numerical simulations, we show that the pattern of the electric field can be correctly estimated using VT and the location of the source activity can be determined accurately from the reconstructed magnitudes of the field. © 2024, CC BY.

关键词： Electric fields