检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Li, Haochen Zhang, Rui Yao, Hantao Zhang, Xin Hao, Yifan Song, Xinkai Li, Xiaqing Zhao, Yongwei Li, Ling Chen, Yunji Intelligent Software Research Center Institute of Software CAS Beijing China State Key Lab of Processors Institute of Computing Technology CAS Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation CAS Beijing China University of Chinese Academy of Sciences Beijing China

Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain. As the visual-language models (VLMs) can provide essential general knowledge on unseen images, freezing the visual encoder and inserting a domain-agnostic adapter can learn domain-invariant knowledge for DAOD. However, the domain-agnostic adapter is inevitably biased to the source domain. It discards some beneficial knowledge discriminative on the unlabelled domain, ***-specific knowledge of the target domain. To solve the issue, we propose a novel Domain-Aware Adapter (DA-Ada) tailored for the DAOD task. The key point is exploiting domain-specific knowledge between the essential general knowledge and domain-invariant knowledge. DA-Ada consists of the Domain-Invariant Adapter (DIA) for learning domain-invariant knowledge and the Domain-Specific Adapter (DSA) for injecting the domain-specific knowledge from the information discarded by the visual encoder. Comprehensive experiments over multiple DAOD tasks show that DA-Ada can efficiently infer a domain-aware visual encoder for boosting domain adaptive object detection. Our code is available at https://***/Therock90421/DA-Ada. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Temporal Sensitivity Analysis of Internal Temperature Informed Charging Algorithms and Rapid Thermal Management System for E-mobility

Temporal Sensitivity Analysis of Internal Temperature Inform...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Akash Samanta Chandan Chetri Dominic Karnehm Antje Neve Sheldon Williamson Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada Institute of Intelligent Distributed Systems Bundeswehr University Munich Germany

ISBN: (数字)9798350376067

ISBN: (纸本)9798350376074

The experimental studies presented in this paper reveal that existing thermal management systems (TMS) and temperature-informed charging algorithms exhibit a response time lag of at least 5.3 minutes due to their reliance on surface temperature measurements. The results indicate that changes in the internal thermal state of lithium-ion batteries (LIBs), induced by variations in charging currents, take an average of 2 minutes to manifest on the battery surface, particularly evident in cylindrical cells. Current thermal management systems for automotive battery packs solely rely on surface temperature measurements, neglecting the approximately 5.8°C temperature difference between the core and surface in TMS control. Consequently, changes in the battery's thermal state due to internal heat losses are not promptly detected by surface-mounted temperature sensors. This delayed response time accelerates battery degradation and increases the risk of thermal runaway events. In this study, temperature-informed fast charging algorithms, tested under various ambient conditions for LIBs, along with a comparative analysis, demonstrate that response time can be reduced by at least 2 minutes by considering internal temperature rather than relying solely on surface temperature measurements. Moreover, accounting for the temperature difference between the core and surface facilitates rapid TMS control and health-conscious fast charging, thereby mitigating the risk of thermal runaway events.

关键词： Temperature measurement Temperature sensors Heating systems Sensitivity analysis Surface charging Thermal management Time measurement Fast charging Time factors Thermal degradation

来源：评论

学校读者我要写书评

暂无评论

HGCUDF: Hierarchical Grid Clustering using Data Field

引用

Chinese Journal of Electronics 2025年第1期23卷 37-42页

作者： Shuliang Wang Jinghua Fan Meng Fang Hanning Yuan School of Software Beijing Institute of Technology Beijing China International School of Software Wuhan University Wuhan China Centre for Quantum Computation and Intelligent Systems University of Technology Sydney Broadway NSW Australia

A new clustering algorithm of Hierarchical grid clustering using data field (HGCUDF) is proposed. Under the distributed characteristics of data points on objects, the hierarchical grids divide and conquer the large datasets in their hierarchical subsets, which reduces the scope in search of the clustering centers, and minifies the area of data space for generating data field. The compared experiments show that HGCUDF computes the grids rather than retrieves all data from database, for improving the efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Voltage Relaxation Pattern Recognition for Efficient Sorting of Healthy Cells for Second-Life Applications of Retired Electric Vehicle Batteries

Voltage Relaxation Pattern Recognition for Efficient Sorting...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Akash Samanta Dominic Karnehm Antje Neve Sheldon Williamson Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada Institute of Intelligent Distributed Systems University of the Bundeswehr Munich Neubiberg Germany

ISBN: (数字)9798350340266

ISBN: (纸本)9798350340273

First-generation electric vehicle (EV) batteries are now retiring from their first life with 70–80%of their initial capacity and are becoming available in the market. To harness the remaining capacity of retired batteries before they reach the end of their life, researchers have proposed various methods, including backup and emergency power supplies for homes, grid-tied stationary energy storage, and storage for renewable energy applications. These applications are collectively termed second-life applications. The first step in utilizing these retired batteries is the selection of healthy cells, as cells in an EV battery pack do not degrade evenly. State-of-the-art cell selection and sorting techniques are either ineffective for industrial-grade applications or highly time-consuming processes. Therefore, this paper proposes a charging voltage relaxation pattern recognition method to efficiently sort healthy cells, powered by data-driven machine learning algorithms. A wide range of battery cycling data collected under different ambient and charging conditions is used for training, testing, and validating the proposed sorting strategy. Furthermore, a comparative analysis is conducted to demonstrate the effectiveness of the proposed strategy compared to state-of-the-art methods.

关键词： Training Renewable energy sources Machine learning algorithms Clustering algorithms Voltage Electric vehicles Batteries

来源：评论

学校读者我要写书评

暂无评论

Five-layer IoT and Fog Computing Framework Towards Digital Twinning of Battery Management systems for e-Transportation

Five-layer IoT and Fog Computing Framework Towards Digital T...

引用

Workshop on Smart Grid and Renewable Energy (SGRE)

作者： Dominic Karnehm Akash Samanta Antje Neve Sheldon Williamson Institute of Intelligent Distributed Systems University of the Bundeswehr Munich Neubiberg Germany Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada

It is needless to mention that the proven capability of cloud computing and digital twin-based monitoring and control systems will play a major role in the implementation of digital twin-based lithium-ion battery management systems (BMS) for e-transportation. In this context, the combination of the Internet of Things (IoT) and fog computing emerges as an enabling technology that facilitates bidirectional data communication and processing. This paper proposes a five-layer IoT framework for the implementation of cloud-based battery monitoring and BMS. Additionally, it critically analyzes the existing IoT frameworks applied to BMS and justifies the suitability of the five-layer architecture. Furthermore, the advantages of fog computing, such as low latency, fault tolerance, limitless systems, multiple applications, and shared responsibility, are discussed. The paper also explores four previously proposed computing-enabled architectures: centralized, hybrid, distributed, and hybrid-distributed computing. Moreover, the potential of utilizing hybrid computing architectures, incorporating fog computing as a supplement to cloud computing, is highlighted to address fault, privacy, or latency issues in cloud-based BMS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data-informed Healthy Cell Clustering Technique for Second-life Applications of Retired Electric Vehicle Batteries

Data-informed Healthy Cell Clustering Technique for Second-l...

引用

IEEE Transportation Electrification Conference and Expo (ITEC)

作者： Akash Samanta Dominic Karnehm Antje Neve Sheldon Williamson Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa Canada Institute of Intelligent Distributed Systems University of the Bundeswehr Munich Neubiberg Germany

ISBN: (数字)9798350317664

ISBN: (纸本)9798350317671

The electric vehicles (EVs) adoption rate has been significant in the last decade and keeps on increasing. Recently, the retired EV battery packs which no longer provide satisfactory performance to power an EV started appearing in the market. Typically, EV batteries are declared unfit for EV applications when the battery capacity is reduced to 70-80% of its nominal capacity. Various end-of-life (EOL) options are proposed by researchers before sending the retired batteries to recycle such as low-demanding e-mobility, grid-tired energy storage systems, storage of renewable energy, and home emergency power supplies. It is predicted that this may create new value pools in the energy and transportation sectors shortly. It is noticed in lithium-ion battery packs that all cells do not age similarly, thus clustering of healthy cells among the retired batteries is very crucial for safe and reliable operation in second-life applications. Thus, an efficient cell clustering method utilizing voltage relaxation curves powered by a data-driven BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies) algorithm is proposed in this paper. The efficiency and efficacy of the proposed algorithm compared to the state-of-the-art cell sorting technique are also demonstrated in the paper.

关键词： Renewable energy sources Accuracy Clustering methods Clustering algorithms Transportation Voltage Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Towards Digital Twining of Lithium-ion Battery Management systems: An Extended Kalman Filter for State-of-Charge Estimation in Cloud-platform

Towards Digital Twining of Lithium-ion Battery Management Sy...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Dominic Karnehm Latha Anekal Akash Samanta Antje Neve Sheldon Williamson Institute of Intelligent Distributed Systems Bundeswehr University Munich Neubiberg Germany Electrical Computer and Software Engineering Ontario Tech University ON Canada

In practice, extended Kalman filter (EKF) is one of the most popular lithium-ion battery (LIB) state of charge (SOC) estimation algorithms in electric vehicles onboard battery management system (BMS). With the increasing necessity of off-loading the computational burden and data storage capacity of onboard BMS, the application of battery digital twin and cloud-BMS are getting popularity. Therefore, to assess the performance of EKF in terms of accuracy, the computational time, and overall request and execution time, an EKF-based SOC estimation method is developed in the cloud platform of Amazon Web Services (AWS). For a specific battery test data set, the cloud-based EKF demonstrated a mean absolute error of 0.00226 and a request time of 0.028s that are highly satisfactory towards developing a digital twin enabled cloud-based BMS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sea Level Anomalies Prediction Via Two-Stage Spatiotemporal Transformer 21

Sea Level Anomalies Prediction Via Two-Stage Spatiotemporal ...

引用

21st International Conference on Networking, Sensing and Control, ICNSC 2024

作者： Fang, Shaoteng Zhao, Yuehao Wang, Kefan Tian, Chenyu Kang, Qi Tongji University Department of Control Science and Engineering Shanghai China The School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney Sydney Australia Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China School of Software Technology Dalian University of Technology Dalian China

ISBN: (纸本)9798350365221

This study successfully applies the spatiotemporal transformer-based model to sea surface height anomaly prediction task. An improved ResNet autoencoder, named SW-GD Autoencoder, is proposed based on Sliced-Wasserstein distance and Gradient Difference loss functions to extract spatial feature information. This autoencoder demonstrates a reduced complexity and training difficulty compared to GAN-based architectures while maintaining high data generation quality. Additionally, the VidHRFormer model is employed for inference, introducing a large receptive field spatial feed-forward network module that enhances information transmission between adjacent patches in the feature map, thereby improving the observability of prediction results. To simplify training, we used a two-stage approach: first training the autoencoder separately, then combining it with VidHRFormer for final training. Compared to state-of-the-art ConvLSTM models, our method yields superior results. © 2024 IEEE.

关键词： Sea level

来源：评论

学校读者我要写书评

暂无评论

A survey for light field super-resolution

引用

High-Confidence Computing 2024年第1期4卷 118-129页

作者： Mingyuan Zhao Hao Sheng Da Yang Sizhe Wang Ruixuan Cong Zhenglong Cui Rongshan Chen Tun Wang Shuai Wang Yang Huang Jiahao Shen State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Key Laboratory of Data Science and Intelligent Computing International Innovation InstituteBeihang UniversityHangzhou 311115China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

Compared to 2D imaging data,the 4D light field(LF)data retains richer scene’s structure information,which can significantly improve the computer’s perception capability,including depth estimation,semantic segmentation,and LF ***,there is a contradiction between spatial and angular resolution during the LF image acquisition *** overcome the above problem,researchers have gradually focused on the light field super-resolution(LFSR).In the traditional solutions,researchers achieved the LFSR based on various optimization frameworks,such as Bayesian and Gaussian *** learning-based methods are more popular than conventional methods because they have better performance and more robust generalization *** this paper,the present approach can mainly divided into conventional methods and deep learning-based *** discuss these two branches in light field spatial super-resolution(LFSSR),light field angular super-resolution(LFASR),and light field spatial and angular super-resolution(LFSASR),***,this paper also introduces the primary public datasets and analyzes the performance of the prevalent approaches on these ***,we discuss the potential innovations of the LFSR to propose the progress of our research field.

关键词： Light field super-resolution Convolutional neural network Transformer Sub-aperture image Epipolar-plane image

来源：评论

学校读者我要写书评

暂无评论

Multiscale Bilateral Attention Fusion Network for Pansharpening

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5828-5843页

作者： Guo, Zhongyuan Li, Jiawei Lei, Jia Liu, Jinyuan Zhou, Shihua Wang, Bin Kasabov, Nikola K. Dalian University Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education School of Software Engineering Dalian116622 China University of the Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Dalian University of Technology School of Mechanical Engineering Dalian116024 China Auckland University of Technology Knowledge Engineering and Discovery Research Institute Auckland1061 New Zealand University of Ulster Intelligent Systems Research Center LondonderryBT48 7JL United Kingdom Bulgarian Academy of Sciences IICT Sofia1000 Bulgaria

High-resolution multispectral (HRMS) images combine spatial and spectral information originating from panchromatic (PAN) and reduced-resolution multispectral (LRMS) images. Pansharpening performs well and is widely used to obtain HRMS images. However, most pansharpening approaches determine the ratio of PAN and LRMS images through direct interpolation, which may introduce artifacts and distort the color of the fused results. To address this issue, an unsupervised progressive pansharpening framework, MSBANet, is proposed, which adopts a multistage fusion strategy. Each stage contains an attention interactive extraction module (AIEM) and a multiscale bilateral fusion module (MBFM). The AIEM extracts spatial and spectral features from input images and captures the correlations between features. The MBFM can efficiently integrate information from the AIEM and improve MSBANet context awareness. We design a hybrid loss function that enhances the ability of the fusion network to store spectral and texture details. In qualitative and quantitative experimental studies on four datasets, MSBANet outperformed state-of-the-art pansharpening techniques. The code will be released. © 2024 IEEE.

关键词： Data mining

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：