检索结果-内蒙古大学图书馆

Semi-supervised estimation of capacity degradation for lithium ion batteries with electrochemical impedance spectroscopy

引用

Journal of Energy Chemistry 2023年第1期76卷 404-413,I0010页

作者： Rui Xiong Jinpeng Tian Weixiang Shen Jiahuan Lu Fengchun Sun Department of Vehicle Engineering School of Mechanical EngineeringBeijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyHawthornVictoria 3122Australia

Machine learning-based methods have emerged as a promising solution to accurate battery capacity estimation for battery management ***,they are generally developed in a supervised manner which requires a considerable number of input features and corresponding capacities,leading to prohibitive costs and efforts for data *** response to this issue,this study proposes a convolutional neural network(CNN)based method to perform end-to-end capacity estimation by taking only raw impedance spectra as *** importantly,an input reconstruction module is devised to effectively exploit impedance spectra without corresponding capacities in the training process,thereby significantly alleviating the cost of collecting training *** large battery degradation datasets encompassing over 4700 impedance spectra are developed to validate the proposed *** results show that accurate capacity estimation can be achieved when substantial training samples with measured capacities are ***,the estimation performance of supervised machine learning algorithms sharply deteriorates when fewer samples with measured capacities are *** this case,the proposed method outperforms supervised benchmarks and can reduce the root mean square error by up to 50.66%.A further validation under different current rates and states of charge confirms the effectiveness of the proposed *** method provides a flexible approach to take advantage of unlabelled samples for developing data-driven models and is promising to be generalised to other battery management tasks.

关键词： Lithium-ion battery Capacity degradation Electrochemical impedance spectroscopy Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fibrillar adhesives with unprecedented adhesion strength,switchability and scalability

引用

National Science Review 2024年第10期11卷 20-33页

作者： Changhong Linghu Yangchengyi Liu Xudong Yang Dong Li Yee Yuan Tan Mohamed Haziq Bin Mohamed Hafiz Mohammad Fadhli Bin Rohani Zihao Du Jiangtao Su Yan Li Yucheng Huo Hanyan Xu Xiufeng Wang Yifan Wang Jing Yu Huajian Gao K.Jimmy Hsia School of Mechanical and Aerospace Engineering Nanyang Technological University School of Materials Science and Engineering Xiangtan University Department of Engineering Mechanics Zhejiang University School of Materials Science and Engineering Nanyang Technological University Institute of High-Performance Computing A*STAR Mechano-X Institute Applied Mechanics Laboratory Department of Engineering Mechanics Tsinghua University School of Chemistry Chemical Engineering and BiotechnologyNanyang Technological University

Bio-inspired fibrillar adhesives have received worldwide attention but their potentials have been limited by a trade-off between adhesion strength and adhesion switchability, and a size scale effect that restricts the fibrils to micro/nanoscales. Here, we report a class of adhesive fibrils that achieve unprecedented adhesion strength（～2 MPa）, switchability（～2000）, and scalability（up to millimeter-scale at the single fibril level）,by leveraging the rubber-to-glass（R2G） transition in shape memory polymers（SMPs）. Moreover, R2G SMP fibrillar adhesive arrays exhibit a switchability of >1000（with the aid of controlled buckling） and an adhesion efficiency of 57.8%, with apparent contact area scalable to 1000 mm2, outperforming existing fibrillar adhesives. We further demonstrate that the SMP fibrillar adhesives can be used as soft grippers and reusable superglue devices that are capable of holding and releasing heavy objects >2000 times of their own weight. These findings represent significant advances in smart fibrillar adhesives for numerous applications,especially those involving high-payload scenarios.

关键词： JKR-DMT transition rubber-to-glass (R2G) transition R2G fibrillar adhesives shape memory polymers adhesion switchability and scalability

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching with Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2516-2533页

作者： Maale, Gerald Tietaa Kuadey, Noble Arden Elorm Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong School of Computer Science and Engineering Chengdu611731 China National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Research Institute of Intelligent Computing Chengdu611731 China School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to unmanned aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Myocardial Infarction Detection Using Hybrid Deep Learning on Phonocardiogram Data 7

Myocardial Infarction Detection Using Hybrid Deep Learning o...

引用

7th International Conference on Data Science and Its Applications, ICoDSA 2024

作者： Axel Ariapaskha, Mohammad Mandala, Satria School of Computing Telkom University Bandung Indonesia Engineering School of Computing Telkom University Bandung Indonesia

ISBN: (纸本)9798350365351

Cardiovascular diseases are the primary cause of mortality globally, with Myocardial Infarction (MI) being a significant factor. Timely and precise detection is vital for effective treatment and management. This study investigates the effectiveness of a hybrid deep learning approach using Phono-cardiogram (PCG) data to detect MI. We propose a hybrid model combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, designed to capture both the spatial and temporal features of cardiac sound signals. The model was trained and tested on data from Hasan Sadikin Hospital, Bandung, including both normal and MI heart sounds. The performance of the CNN-LSTM model was assessed using metrics such as accuracy, precision, sensitivity, and F1 score. In the non tuned model, the highest accuracy achieved across five iterations was 86.9%, with a precision of 91.01%, sensitivity of 85.26%, and an F1-Score of 88.04%. Iteration 3 marked the best performance for this configuration. After tuning, the model showed significant improvement, with iteration 3 achieving an accuracy of 92.86%, precision of 94.38%, sensitivity of 92.31%, and an F1-Score of 93.33%. These results demonstrate the model's competitive accuracy, highlighting its potential as a non-invasive, cost-effective tool for MI detection. This research advances cardiac healthcare technology, potentially aiding the development of real-time, accurate diagnostic systems. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hybrid Seagull and Whale Optimization Algorithm-Based Dynamic Clustering Protocol for Improving Network Longevity in Wireless Sensor Networks

引用

China Communications 2024年第10期21卷 113-131页

作者： P.Vinoth Kumar K.Venkatesh Department of Networking and Communications School of ComputingCollege of Engineering and TechnologySRM Institute of Science and TechnologyKattankulathur 603203India

Energy efficiency is the prime concern in Wireless Sensor Networks(WSNs) as maximized energy consumption without essentially limits the energy stability and network lifetime. Clustering is the significant approach essential for minimizing unnecessary transmission energy consumption with sustained network lifetime. This clustering process is identified as the Non-deterministic Polynomial(NP)-hard optimization problems which has the maximized probability of being solved through metaheuristic *** adoption of hybrid metaheuristic algorithm concentrates on the identification of the optimal or nearoptimal solutions which aids in better energy stability during Cluster Head(CH) selection. In this paper,Hybrid Seagull and Whale Optimization Algorithmbased Dynamic Clustering Protocol(HSWOA-DCP)is proposed with the exploitation benefits of WOA and exploration merits of SEOA to optimal CH selection for maintaining energy stability with prolonged network lifetime. This HSWOA-DCP adopted the modified version of SEagull Optimization Algorithm(SEOA) to handle the problem of premature convergence and computational accuracy which is maximally possible during CH selection. The inclusion of SEOA into WOA improved the global searching capability during the selection of CH and prevents worst fitness nodes from being selected as CH, since the spiral attacking behavior of SEOA is similar to the bubble-net characteristics of WOA. This CH selection integrates the spiral attacking principles of SEOA and contraction surrounding mechanism of WOA for improving computation accuracy to prevent frequent election process. It also included the strategy of levy flight strategy into SEOA for potentially avoiding premature convergence to attain better trade-off between the rate of exploration and exploitation in a more effective manner. The simulation results of the proposed HSWOADCP confirmed better network survivability rate, network residual energy and network overall throughput on par wi

关键词： clustering energy stability network lifetime seagull optimization algorithm(SEOA) whale optimization algorithm(WOA) wireless sensor networks(WSNs)

来源：评论

学校读者我要写书评

暂无评论

Modified Black Widow Optimization-Based Enhanced Threshold Energy Detection Technique for Spectrum Sensing in Cognitive Radio Networks

引用

Computer Modeling in engineering & Sciences 2024年第3期138卷 2339-2356页

作者： R.Saravanan R.Muthaiah A.Rajesh School of Computing SASTRA Deemed UniversityThanjavur613401India School of Electrical&Electronics Engineering SASTRA Deemed UniversityThanjavur613401India

This study develops an Enhanced Threshold Based Energy Detection approach(ETBED)for spectrum sensing in a cognitive radio *** threshold identification method is implemented in the received signal at the secondary user based on the square *** proposed method is implemented with the signal transmission of multiple outputs-orthogonal frequency division ***,the proposed method is considered the dynamic detection threshold adjustments and energy identification spectrum sensing technique in cognitive radio *** the dynamic threshold,the signal ratio-based threshold is *** threshold is computed by considering the Modified Black Widow Optimization Algorithm(MBWO).So,the proposed methodology is a combination of dynamic threshold detection and *** general threshold-based detection technique has different limitations such as the inability optimal signal threshold for determining the presence of the primary user *** limitations undermine the sensing accuracy of the energy identification ***,the ETBED technique is developed to enhance the energy efficiency of cognitive radio *** projected approach is executed and analyzed with performance and comparison *** proposed method is contrasted with the conventional techniques of theWhale Optimization Algorithm(WOA)and GreyWolf Optimization(GWO).It indicated superior results,achieving a high average throughput of 2.2 Mbps and an energy efficiency of 3.8,outperforming conventional techniques.

关键词： Cognitive radio network spectrum sensing noise uncertainty modified black widow optimization algorithm energy detection technique

来源：评论

学校读者我要写书评

暂无评论

Deep Mining of Wearable Spatial Variability for Efficient Edge computing

Deep Mining of Wearable Spatial Variability for Efficient Ed...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Gangadharan, Kiirthanaa Zhang, Qingxue Purdue University School of Engineering and Technology Electrical and Computing Engineering IN United States Purdue University School of Engineering and Technology Electrical and Computing Engineering Biomedical Engineering IN United States

ISBN: (纸本)9798350324136

Wearable biomechanical sensors can be placed on different body locations and each sensor may have multiple channels. Deep mining of the spatial variability in these sensor locations and channels, is essential for not only optimal system configuration towards energy efficient edge computing, but also comprehensive musculoskeletal dynamics understanding. Targeting these needs, we propose to leverage deep learning to investigate seven body locations and six channels for each location, thereby demonstrating the spatial variability among 42 combinations. The research findings indicate that the thigh location and the accelerometer axis-Y is the best configuration. Further, experimental results also indicate the diverse spatial variability among different sensor locations and sensor channels, which provide interesting and rich information about the biomechanical dynamics. This study will thus greatly advance our understanding of the spatial variability in wearable biomechanical sensors and channels, thereby minimizing the data analytics load and facilitating energy efficient edge computing for big biomechanical data mining. © 2024 IEEE.

关键词： Big Data Deep Learning Edge computing Spatial Variability Wearable Computer

来源：评论

学校读者我要写书评

暂无评论

Smart Compiler Assistant: An AST based Python Code Analysis 15

Smart Compiler Assistant: An AST based Python Code Analysis

引用

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Aneesh, C.H. Saumik, Gembali Varun, K.V.V. Belwal, Meena Amrita School of Computing Artificial Inteligence Engineering Bengaluru India Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350370249

There are many challenges when it comes to compiling huge lines of code or codes with huge time complexity. Also, if there is an error in the last line of the code, for example, a simple syntax error or a syntactic error, all the time for compiling the code is wasted. To reduce the time and to compile an error-free code, The novel 'Smart Compiler Assistant', a tool is designed to revolutionize the coding experience for developers by learning the words and structure of code. The 'smart compile assistant' offers guidance in the optimization, completion, and correction of code, that in turn, improves productivity and the quality of the code. Equipped with smooth interoperability into commonly used development tools, 'Smart Compiler Assistant', lets developers produce cleaner, more efficient codes with greater accuracy and less hassle, boosting the overall efficiency of the software development cycle. © 2024 IEEE.

关键词： Coding errors

来源：评论

学校读者我要写书评

暂无评论

Resilient and Safe Platooning Control of Connected Automated Vehicles Against Intermittent Denial-of-Service Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1234-1251页

作者： Xiaohua Ge Qing-Long Han Qing Wu Xian-Ming Zhang the School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourne VIC 3122Australia the School of Engineering and Technology Central Queensland UniversityRockhampton QLD 4701Australia

Connected automated vehicles(CAVs)serve as a promising enabler for future intelligent transportation systems because of their capabilities in improving traffic efficiency and driving safety,and reducing fuel consumption and vehicle emissions.A fundamental issue in CAVs is platooning control that empowers a convoy of CAVs to be cooperatively maneuvered with desired longitudinal spacings and identical velocities on *** paper addresses the issue of resilient and safe platooning control of CAVs subject to intermittent denial-of-service(DoS)attacks that disrupt vehicle-to-vehicle ***,a heterogeneous and uncertain vehicle longitudinal dynamic model is presented to accommodate a variety of uncertainties,including diverse vehicle masses and engine inertial delays,unknown and nonlinear resistance forces,and a dynamic platoon ***,a resilient and safe distributed longitudinal platooning control law is constructed with an aim to preserve simultaneous individual vehicle stability,attack resilience,platoon safety and ***,a numerically efficient offline design algorithm for determining the desired platoon control law is developed,under which the platoon resilience against DoS attacks can be maximized but the anticipated stability,safety and scalability requirements remain ***,extensive numerical experiments are provided to substantiate the efficacy of the proposed platooning method.

关键词： Connected automated vehicles(CAVs) cooperative adaptive cruise control denial-of-service(DoS)attacks resilient control vehicle platooning vehicle-to-vehicle communication

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Defected Ground Structure Fractal Antenna based on Osgood Curve for C-band Modern Wireless Communications

Advanced Electromagnetics

引用

Advanced Electromagnetics 2025年第1期14卷 23-29页

作者： Singh, Gurmeet Kumar, Ashish School of Computing Science and Engineering Galgotias University Greater Noida India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

Multifunctional behavioral antennas are one of the significant features of the modern wireless communication systems. This is due to the fact that the miniaturized sizes of the devices demand compact and low-profile antennas that cover limited space and provide multi-frequency functionalities over a wide range of the spectrum. In view of these prerequisites, this paper presents the two design approaches utilizing Osgood Curve Fractal structure as the antenna element with different feeding techniques. The proposed antennas resonate at multiple frequencies covering S-and C-band with excellent impedance matching. The designs have been optimized in terms of scaling factor and position of microstrip feed line with peak gain of 4.5 dBi. Design 1 has significant bandwidth for required applications;however, design 2 possesses low bandwidth with small frequency ratio. Both the proposed designs are fabricated, and results are quite promising. The proposed designs can be utilized for various sub-6 GHz 5G automotive applications as it can easily integrated in the various parts of the modern passenger car. © 2025, Advanced Electromagnetics. All rights reserved.

关键词： Bandwidth

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：