检索结果-内蒙古大学图书馆

A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries

Frontiers of Computer science 2024年第5期18卷 1-10页

作者： Lingling ZHAO Shitao SONG Pengyan WANG Chunyu WANG Junjie WANG Maozu GUO Faculty of Computing Harbin Institute of TechnologyHarbin 150001China School of Electrical Engineering Liaoning University of TechnologyJinzhou 121004China School of Computer Science Northeast Electric Power UniversityJilin 132000China Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing 211166China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer and Mixture of Expert(MMMe)model,for RUL *** MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable RUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.

关键词： lithium-ion battery remaining useful life deep learning MLP-Mixer mixture-of-experts

来源：评论

学校读者我要写书评

暂无评论

Evaluating Human Experiences of Touching Virtual Reality: A State of The Art Review 3

Evaluating Human Experiences of Touching Virtual Reality: A ...

引用

3rd IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2024

作者： Aldhous, Joanna Sobolewska, Emilia Webster, Gemma School of Computing Engineering & the Built Environment Edinburgh Napier University United Kingdom School of Science and Engineering University of Dundee United Kingdom

ISBN: (纸本)9798350378009

Technological advances offer the potential for compelling multisensory experiences where users can touch virtuality and interact with one another. However, designing a good user experience (UX) is challenging due to the interdisciplinary and subjective nature of the problem. Technological advances alone are unable to account for human factors or ensure a good experience, making UX evaluation crucial for technology adoption. A state-of-the-art review explores the UX evaluation in practice for virtual experiences using wearable and handheld haptic (touch) devices since the launch of the Oculus in 2018. This review provides insight into the challenges related to user experience evaluations, an extensive overview of the approaches utilized, the dimensions and qualities under examination, and a taxonomy of methods of value to those interested in evaluating user experience for touch in virtual reality. Findings indicate that evaluation methods designed to assess haptic experiences in virtual environments are needed, and qualitative approaches designed to gather direct feedback can inform and improve the development of high-quality experiences. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

S-MGHSTN: Towards An Effective Streaming Traffic Accident Risk Prediction Framework

引用

IEEE Transactions on Knowledge and Data engineering 2025年第7期37卷 4285-4298页

作者： Chen, Minxiao Yuan, Haitao Jiang, Nan Zheng, Zhihan Bao, Zhifeng Zhou, Ao Jiang, Jiaxin Wang, Shangguang Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore RMIT University School of Computing Technologies MelbourneVIC3000 Australia National University of Singapore School of Computing 117417 Singapore

Traffic accidents pose a significant risk to human health and property safety. To address this issue, predicting their risks has garnered growing interest. We argue that a desired prediction solution should demonstrate resilience to the complexity of traffic accidents. In particular, it should adequately consider the streaming nature of data and key related aspects, such as regional background, accurately capture both proximity and similarity while bridging the disparities, and effectively address the sparsity. However, these factors are often overlooked or difficult to incorporate. In this paper, we propose a novel streaming multi-granularity hierarchical spatio-temporal network. Initially, we innovate by incorporating remote sensing data, facilitating the creation of hierarchical multi-granularity structure and the comprehension of regional background. We construct multiple high-level risk prediction tasks to enhance model's ability to cope with sparsity. Subsequently, to capture and bridge spatial proximity and semantic similarity, region features and multi-view graph undergo encoding processes to distill effective representations, followed by a graph-enhanced representation alignment module that reconciles their disparities. At last, an alternating experience replay with a dual-memory buffer is employed to accommodate streaming data scenarios. Extensive experiments on two real datasets verify the superiority of our model against the state-of-the-art methods. © 1989-2012 IEEE.

关键词： Accidents Semantics Remote Sensing Correlation Urban Areas Streaming Media Roads Predictive Models Encoding Data Models Traffic Accident Risk Prediction Streaming Data Spatio Temporal Data Remote Sensing Car Accident Risk Of Traffic Accidents Hierarchical Structure Sparsity Regional Characteristics Remote Sensing Data Streams Semantic Similarity Spatial Proximity Background Regions Similarity Graph Experience Replay Short Term Memory Point Of Interest Semantic Features Incremental Learning Spatiotemporal Characteristics Weight Training Node Features Self Supervised Learning Traffic Risk Traffic Prediction Remote Sensing Images Point Of Interest Data Semantic Graph Feature Encoder Geographical Correlation Graph Features Temporal Modulation Concept Drift

来源：评论

学校读者我要写书评

暂无评论

Real-Time Traffic Prediction And Optimization using Machine Learning 3

Real-Time Traffic Prediction And Optimization using Machine ...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Vineetha, Kundrapu Tharun Reddy, M. Jaffer Ali, Md. Prathima, Narisetty Rajagopal, Shinu M. Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

The Real-Time Traffic Prediction and Optimization System may be described as enriched, spacious, algorithm-oriented, and designed to help contribute to the anti-symptomatic deprievement of increasingly congested urban traffic streams. The system with the help of integrating real time data of numerous sources like GPS tracker, traffic sensor as well as weather API, the system using advanced machine learning algorithm in order to predict traffic accurately and optimize routes based on it. This predictive capability then greatly improves the flow of vehicles, the time taken, and the occurrence of choke points. The structure of the system is fully based in the cloud, which makes it easy to scale and very compatible with other systems to amalgamate a vast array of data inputs with high dependability. Fully customizable and intuitive control panel gives live view of traffic, offers actionable stats, and instant control mechanisms to traffic operators to make correct decisions quickly. Congestion in urban areas has an influence on time taken to cover a certain distance, fuel consumption and emission to the atmosphere. On the basis of the above analysis, this work extends a Real-Time Traffic Prediction and Optimization System (RTPOPS) using machine learning approach to predict the traffic density and to further optimize traffic signals and routes. The used system demonstrated successful management and reduction of vehicle density by 30%, and increasing speed limits by 18% and proved that Intelligent Urban Mobility has the potential to be achieved. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Short Circuit Fault Diagnosis for a Parallel Lithium-Ion Battery Pack in Electric Vehicles 3rd

Short Circuit Fault Diagnosis for a Parallel Lithium-Ion Bat...

引用

3rd International Joint Conference on Energy, Electrical and Power engineering, CoEEPE 2023

作者： Xu, Yiming Ge, Xiaohua Guo, Ruohan Hu, Cungang Shen, Weixiang School of Science Computing and Engineering Swinburne University of Technology Melbourne Australia School of Electrical Engineering and Automation Anhui University Hefei China

ISBN: (纸本)9789819739394

Lithium-ion battery packs are widely deployed as power sources in transportation electrification solutions. To ensure safe and reliable operation of battery packs, it is of critical importance to monitor battery operation status and diagnose battery faults early. This paper proposes a soft short circuit (SC) fault detection method for a parallel battery pack. Since it is impractical to equip current sensors for all the cells in a parallel pack, a reconstructed state-space equation combining the electrical dynamic of a battery cell and the electrical characteristics of a parallel battery pack is designed for the cell current estimation. Then, the occurrence of an SC fault can be timely detected based on the difference between the measured and estimated branch current flowing through the first interconnected resistance. Simulations on a parallel-connected battery pack under a 10 Ω SC resistance are conducted to verify the effectiveness of the proposed method. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Healthcare AI Sensitivity through Affective computing: Analyzing Human Emotions 1

Enhancing Healthcare AI Sensitivity through Affective Comput...

引用

1st IEEE International Conference on Advances in computing, Communication and Networking, ICAC2N 2024

作者： Singh, Rahul Kumar, Avadhesh Sagar, Shraddha Sharma, Vishnu Galgotias University School of Computing Science and Engineering Greater Noida India ITS Engineering College Department of Computer Science Engineering Greater Noida India

ISBN: (纸本)9798350356816

Affective computing (AC), also known as emotion AI, is a concept that applies modern technology to help systems to recognize and process human emotions and their feelings. Several uses of affective computing have been demonstrated, including marketing, healthcare, driving assistance, and education. Linear Support vector machines (SVM), k-nearest neighbor (k-NN), Hidden Markov models (HMMs), Gaussian mixture models (GMM), discriminate classifiers (LDC), decision tree algorithms and artificial neural networks (ANN), are the classifiers that are most frequently used in research on identifying and categorizing human emotions. Selecting the right classifier can significantly increase the system's overall efficiency, as numerous studies have conclusively demonstrated. Through use of cameras, microphones, skin sensors, or other devices, affective computing gathers signals from human users, gathering data on their facial expressions, voice tones, gestures, and other characteristics that can hint at their emotional states. The system deduces the user's emotional state from those data points. This study emphasizes on the fundamentals of computing emotions. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

On Neutrosophy logic for Multiple Correlation Analysis in Fuzzy Uncertain Database

引用

Neutrosophic Sets and Systems 2025年 76卷 1-17页

作者： Wazir, Samar Beg, M.M. Sufyan Ahmad, Tanvir Sohail, Shahab Saquib Department of Computer Engineering Jamia Millia Islamia New Delhi India Department of Computer Engineering Aligarh Muslim University Aligarh India School of Computing Science and Engineering VIT Bhopal University MP Sehore466114 India

The primary goal of this paper is to introduce a novel method for mining frequent and interesting items by incorporating correlation analysis between two items in an uncertain transactional database using the OWA operator. The work is further expanded by proposing two additional methods for mining frequent and interesting items, utilizing fuzzy means and the OWA operator along with multiple correlation analysis for more than two items in uncertain transactional databases. The effectiveness of the proposed methods is evaluated by running the algorithms on both standard and example datasets, with results compared to the traditional probabilistic approach for identifying frequent and interesting items through multiple correlation. While multiple correlation analysis highlights the relationships of interestingness and uninterestingness between items, the OWA operator enhances the results when combined with fuzzy means and probabilistic methods. Additionally, the paper suggests a future research direction using Neutrosophy logic, which is anticipated to open new avenues for further exploration in this field. © 2025, University of New Mexico. All rights reserved.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Cooperative Target Tracking Control of Unmanned Surface Vehicles Under Data Falsification Attacks

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-11页

作者： Liu, Zhao-Qing Ge, Xiaohua Han, Qing-Long Wang, Yu-Long Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne VIC Australia School of Mechatronic Engineering and Automation Shanghai University Shanghai China

This paper deals with the problem of cooperative target tracking control for multiple networked unmanned surface vehicles under data falsification attacks. First, a data falsification attack model is constructed to account for unknown falsified control commands. Next, a networked cooperative target tracking model is developed by integrating the concurrent impacts of data falsification attacks and network-induced delays. Then, a reinforcement learning-based compensation mechanism, consisting of an actor neural network and an adaptive critic function, is developed to offset the adverse effects caused by the unknown dynamics and external disturbances. Meanwhile, to cope with data falsification attacks and reduce the neural network approximation errors, a secure control input is subtly developed. Based on the developed compensation mechanism and secure control input, a dynamic control law is constructed to regulate the action of involved unmanned surface vehicles. Furthermore, a resilient cooperative target tracking control scheme is proposed to achieve the expected cooperative target tracking control objectives. At last, two case studies are provided to validate the efficacy of the designed resilient cooperative target tracking control scheme. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Electricity Cost Minimization for Multi-Workflow Allocation in Geo-Distributed Data Centers

引用

IEEE Transactions on Services computing 2025年第03期18卷 1397-1411页

作者： Wang, Shuang Zhang, He Wu, Tianxing Zhang, Yueyou Zhang, Wei Emma Sheng, Quan Z. Southeast University School of Computer Science and Engineering Nanjing211189 China The University of Adelaide School of Computer and Mathematical Sciences Australian Institute for Machine Learning Australia Macquarie University School of Computing SydneyNSW2109 Australia

Worldwide, Geo-distributed Data Centers (GDCs) provide computing and storage services for massive workflow applications, resulting in high electricity costs that vary depending on geographical locations and time. How to reduce electricity costs while satisfying the deadline constraints of workflow applications is important in GDCs, which is determined by the execution time of servers, power, and electricity price. Determining the completion time of workflows with different server frequencies can be challenging, especially in scenarios with heterogeneous computing resources in GDCs. Moreover, the electricity price is also different in geographical locations and may change dynamically. To address these challenges, we develop a geo-distributed system architecture and propose an Electricity Cost aware Multiple Workflows Scheduling algorithm (ECMWS) for servers of GDCs with fixed frequency and power. ECMWS comprises four stages, namely workflow sequencing, deadline partitioning, task sequencing, and resource allocation where two graph embedding models and a policy network are constructed to solve the Markov Decision Process (MDP). After statistically calibrating parameters and algorithm components over a comprehensive set of workflow instances, the proposed algorithms are compared with the state-of-the-art methods over two types of workflow instances. The experimental results demonstrate that our proposed algorithm significantly outperforms other algorithms, achieving an improvement of over 15% while maintaining an acceptable computational time. The source codes are available at https://***/public-artifacts/ecmws-experiments. © 2025 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

SHARP POINTWISE-IN-TIME ERROR ESTIMATE OF L1 SCHEME FOR NONLINEAR SUBDIFFUSION EQUATIONS

引用

Journal of Computational Mathematics 2024年第3期42卷 662-678页

作者： Dongfang Li Hongyu Qin Jiwei Zhang School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China School of Mathematics and Statistics Wuhan UniversityWuhan 430072China

An essential feature of the subdiffusion equations with theα-order time fractional derivative is the weak singularity at the initial *** weak regularity of the solution is usually characterized by a regularity parameterσ∈(0,1)∪(1,2).Under this general regularity assumption,we present a rigorous analysis for the truncation errors and develop a new tool to obtain the stability results,i.e.,a refined discrete fractional-type Grönwall inequality(DFGI).After that,we obtain the pointwise-in-time error estimate of the widely used L1 scheme for nonlinear subdiffusion *** present results fill the gap on some interesting convergence results of L1 scheme onσ∈(0,α)∪(α,1)∪(1,2].Numerical experiments are provided to demonstrate the effectiveness of our theoretical analysis.

关键词： Sharp pointwise-in-time error estimate Ll scheme Nonlinear subdiffusion equations Non-smooth solutions

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：