检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ye, Guangzai Feng, Li Guo, Jianlan Chen, Yuqiang School of Computer Science and Engineering Macau University of Science and Technology China Dongguan Polytechnic Dongguan China

Accurately estimating the Remaining Useful Life (RUL) of lithium-ion batteries is crucial for maintaining the safe and stable operation of rechargeable battery management systems. However, this task is often challenging due to the complex temporal dynamics. Recently, attention-based networks, such as Transformers and Informer, have been the popular architecture in time series forecasting. Despite their effectiveness, these models with abundant parameters necessitate substantial training time to unravel temporal patterns. To tackle these challenges, we propose a simple MLP-Mixer-based architecture named "Intra-Inter Patch Mixer" (IIP-Mixer), which is an architecture based exclusively on multi-layer perceptrons (MLPs), extracting information by mixing operations along both intra-patch and inter-patch dimensions for battery RUL prediction. The proposed IIP-Mixer comprises parallel dual-head mixer layers: the intra-patch mixing MLP, capturing local temporal patterns in the short-term period, and the inter-patch mixing MLP, capturing global temporal patterns in the long-term period. Notably, to address the varying importance of features in RUL prediction, we introduce a weighted loss function in the MLP-Mixer-based architecture, marking the first time such an approach has been employed. Our experiments demonstrate that IIP-Mixer achieves competitive performance in battery RUL prediction, outperforming other popular time-series frameworks. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Robust Trajectory Azimuth Control Strategy for Mitigating Weight-on-bit Uncertainty

A Robust Trajectory Azimuth Control Strategy for Mitigating ...

引用

第43届中国控制会议

作者： She Wang Jing Xiao Zhen Cai Hai Huang School of Computer and Information Engineering Wuhan City Polytechnic University School of Information Science and Engineering Wuhan University of Science and Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

This study concentrates on trajectory azimuth control amidst the uncertainty of weight-on-bit in the directional drilling *** trajectory azimuth model intricately considers the variable weight-on-bit and integrates the uncertainty factor within its framework. A sophisticated two-layer observer-based control scheme has been crafted to address the challenges posed by the lack of direct azimuth measurement, the weight-on-bit uncertainty, and external interferences. The stability of the system is meticulously appraised using the Lyapunov function, which is subsequently transformed into linear matrix inequality(LMI) to derive the control parameter gains efficiently. Ultimately, simulations demonstrate that our control system adeptly negates the impact of weight-on-bit uncertainty and extrinsic disruptions, showcasing its effectiveness.

关键词： Trajectory Azimuth Attitude Control Weight-on-bit Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection Authentication Protocol for Consumer Internet of Things in Horizontal Federated Learning Environment

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Sun, Zhanfang Xu, Jingxiu Li, Jing Zhang, Tingliang School of Electronic Information Engineering Henan Institute of Technology Henan Xinxiang453000 China College of Computer Science and Technology Huanggang Normal University Huanggang438000 China School of Electronic Information and Electrical Engineering Anyang Institute of Technology Henan Anyang455000 China

—With the widespread application of Consumer Internet of Things (CIoT) devices, especially in the fields of smart wearable and health devices, the generation and transmission for a large amount of personal health data has raised concerns about user privacy and data security. In this context, federated learning technology provides a new approach to privacy protection by enabling model training without directly accessing raw data. However, the semi-honest CIoT devices participating in federated learning may lead to the risk of indirect privacy leakage. Therefore, this paper proposes a privacy protection authentication protocol for CIoT in horizontal federated learning environments. This protocol adopts elliptic curve cryptosystem to implement mutual authentication and data transmission between a set of CIoT devices and server, avoiding signaling overload. Then AVISPA and informal security analysis prove that the protocol is secure and can resist known attacks. The experimental results show that the protocol has increased signal overhead and computational overhead by at least 33% and 50%. And the protocol exhibits a variety of security attributes and achieves a balance of security and overhead in performance, which is suitable for horizontal federated learning training environment. © 2025 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Neural Networks for Environmental Monitoring: A Web Application for Image Recognition 7

Neural Networks for Environmental Monitoring: A Web Applicat...

引用

7th International Conference of Artificial Intelligence, Medical Engineering, Education, AIMEE 2023

作者： Bernatska, Nataliya Dzhumelia, Elvira Typilo, Iryna Kochan, Orest Salamon, Ivan Department of Physical Analytical and General Chemistry Institute of Chemistry and Chemical Technologies Lviv Polytechnic National University Lviv79000 Ukraine Software Department Institute of Computer Science and Information Technologies Lviv Polytechnic National University Lviv79000 Ukraine Department of Information-Measuring Technologies Institute of Computer Technologies Automation and Metrology Lviv Polytechnic National University Lviv79000 Ukraine School of Computer Science Hubei University of Technology Wuhan430068 China Department of Ecology Faculty of Humanities and Natural Sciences University of Presov Presov080 01 Slovakia

ISBN: (纸本)9781643684901

Environmental monitoring is increasingly reliant on image recognition through neural networks, automating the identification and classification of environmental threats. This automation optimizes resource allocation, enhances monitoring accuracy, and empowers researchers to address climate-related challenges. In response to this, we present a web application built using *** and ***, which enables real-time image recognition. This application facilitates tasks ranging from climate analysis to disaster response and wildlife conservation, offering valuable insights into environmental trends. Moreover, it engages the public, promotes awareness, and contributes to conservation efforts, making it a versatile and cost-effective tool for environmental monitoring. The application leverages advancements in image recognition technology, availability of datasets, open-source frameworks, and cloud computing infrastructure. It supports a wide range of applications, promotes global collaboration, and ensures data security. While challenges exist, the potential of neural networks in environmental monitoring is promising. The web application combines the power of *** and artificial neural networks, enhancing environmental monitoring efficacy and fostering sustainable practices on a global scale. Ongoing research and standardization efforts are essential for refining and expanding this approach. © 2024 The Authors.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-domain NER with Generated Task-Oriented Knowledge: An Empirical Study from Information Density Perspective

Cross-domain NER with Generated Task-Oriented Knowledge: An ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zhang, Zhihao Lee, Sophia Yat Mei Wu, Junshuang Zhang, Dong Li, Shoushan Cambria, Erik Zhou, Guodong School of Computer Science & Technology NLP Lab Soochow University China Department of Chinese and Bilingual Studies The Hong Kong Polytechnic University Hong Kong Beijing Jinghang Research Institute of Computing and Communication China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761643

Cross-domain Named Entity Recognition (CDNER) is crucial for Knowledge Graph (KG) construction and natural language processing (NLP), enabling learning from source to target domains with limited data. Previous studies often rely on manually collected entity-relevant sentences from the web or attempt to bridge the gap between tokens and entity labels across domains. These approaches are time-consuming and inefficient, as these data are often weakly correlated with the target task and require extensive pre-training. To address these issues, we propose automatically generating task-oriented knowledge (GTOK) using large language models (LLMs), focusing on the reasoning process of entity extraction. Then, we employ task-oriented pre-training (TOPT) to facilitate domain adaptation. Additionally, current cross-domain NER methods often lack explicit explanations for their effectiveness. Therefore, we introduce the concept of information density to better evaluate the model's effectiveness before performing entity recognition. We conduct systematic experiments and analyses to demonstrate the effectiveness of our proposed approach and the validity of using information density for model evaluation. © 2024 Association for Computational Linguistics.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Hunger games search optimization with deep learning model for sustainable supply chain management

引用

Discover Internet of Things 2023年第1期3卷 10页

作者： Xu, Zheng Jain, Deepak Kumar Neelakandan, S. Abawajy, Jemal School of Computer and Information Engineering Institute for Artificial Intelligence Shanghai Polytechnic University Shanghai201209 China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China School of Artificial Intelligence Dalian China Symbiosis Institute of Technology Symbiosis International University Pune India Department of Computer Science and Engineering R.M.K Engineering College Taluk India Deakin University Geelong Australia

The supply chain network is one of the most important areas of focus in the majority of business circumstances. Blockchain technology is a feasible choice for secure information sharing in a supply chain network. Despite the fact that maintaining security at all levels of the blockchain is difficult, cryptographic methods are commonly used in existing works. Effective supply chain management (SCM) offers various benefits to organizations, such as enhanced customer satisfaction, increased operational efficiency, competitive advantage, and cost reduction. Potential SCM for agricultural and food supply chains needs distributors, coordination and collaboration among farmers, retailers, and stakeholders. The use of technology like Block Chain (BC), sensors, and data analytics, can boost traceability and visibility, decrease waste, and ensure safety and quality throughout the supply chain. Therefore, this study develops a Hunger Games Search Optimization with Deep Learning Model for Sustainable agricultural and food Supply Chain Management (HGSODL-ASCM) technique. The fundamental goal of the HGSODL-ASCM technique is to improve decision-making processes for agricultural and food commodity production and storage in order to optimise revenue. In the provided HGSODL-ASCM technique, a bidirectional long short-term memory (Bi-LSTM) model is built to determine the amount of productivity and storage required to maximise profit. In order to boost the performance of the Bi-LSTM classification process, the HGSO algorithm has been utilized in this work. The presented HGSODL-ASCM technique can independently achieve the SCM policies via interaction with complicated and adaptive environments. A brief set of simulations were performed to ensure the improved performance of the HGSODL-ASCM technique. The simulation results demonstrated how superior the HGSODL-ASCM method is to other methods already in use. © The Author(s) 2023.

关键词： Food supply

来源：评论

学校读者我要写书评

暂无评论

Rethinking Cancer Gene Identification Through Graph Anomaly Analysis 39

Rethinking Cancer Gene Identification Through Graph Anomaly ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zang, Yilong Ren, Lingfei Li, Yue Wang, Zhikang Selby, David Antony Wang, Zheng Vollmer, Sebastian Josef Yin, Hongzhi Song, Jiangning Wu, Junhang School of Hotel and Tourism Management The Hong Kong Polytechnic University Hong Kong School of Computing and Artificial Intelligence Southwest University of Finance and Economics China School of Computer Science Wuhan University China Biomedicine Discovery Institute Department of Biochemistry and Molecular Biology Monash University Australia RPTU Kaiserslautern Germany The University of Queensland Australia College of Information Science and Technology Shihezi University China

ISBN: (纸本)157735897X

Graph neural networks (GNNs) have shown promise in integrating protein-protein interaction (PPI) networks for identifying cancer genes in recent studies. However, due to the insufficient modeling of the biological information in PPI networks, more faithfully depiction of complex protein interaction patterns for cancer genes within the graph structure remains largely unexplored. This study takes a pioneering step toward bridging biological anomalies in protein interactions caused by cancer genes to statistical graph anomaly. We find a unique graph anomaly exhibited by cancer genes, namely weight heterogeneity, which manifests as significantly higher variance in edge weights of cancer gene nodes within the graph. Additionally, from the spectral perspective, we demonstrate that the weight heterogeneity could lead to the "flattening out" of spectral energy, with a concentration towards the extremes of the spectrum. Building on these insights, we propose the HIerarchical-Perspective Graph Neural Network (HIPGNN) that not only determines spectral energy distribution variations on the spectral perspective, but also perceives detailed protein interaction context on the spatial perspective. Extensive experiments are conducted on two reprocessed datasets STRINGdb and CPDB, and the experimental results demonstrate the superiority of HIPGNN. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

MSPGait: A Mask Slice Pyramid Spatiotemporal Feature Fusion Method for Gait Recognition 25

MSPGait: A Mask Slice Pyramid Spatiotemporal Feature Fusion ...

引用

Proceedings of the 4th International Conference on computer, Artificial Intelligence and Control Engineering

作者： Shaomin Lai Huimin Zhao Jian Zhong Huakang Li Kaihan Lin Huanyu Wang Wenzhe Wang School of Computer Science Guangdong Polytechnic Normal University Guangzhou Guangdong China School of Computer Science and Engineering Guangzhou Institute of Science and Technology Guangzhou Guangdong China School of Computer Science and Engineering South China University of Technology Guangzhou Guangdong China

ISBN: (纸本)9798400712647

In current gait recognition methods, researchers typically extract local features by partitioning the human body into fixed regions. However, under complex conditions, these methods lack flexibility. Additionally, traditional temporal feature extraction methods often do not fully capture the temporal information in gait data. To address these issues, we propose a mask slice pyramid spatiotemporal feature fusion gait recognition method, named MSPGait. This approach introduces three key modules: the dynamic mask slice feature module (DMSFM), the multi-scale temporal attention module (MTAM), and the pyramid adaptive feature fusion module (PAFF), which significantly enhance the model's flexibility in complex environments and its ability to model temporal features. Specifically, DMSFM improves gait feature representation and environmental adaptability by dynamically generating masks and performing slicing operations. MTAM aggregates multiscale temporal features to integrate global temporal features of body parts with short time sequence features. PAFF, on the other hand, enhances recognition accuracy and robustness by fusing spatial and temporal features at multiple levels. Comprehensive evaluations on the CASIA-B dataset validate the effectiveness and superiority of the proposed method. On the publicly available CASIA-B gait recognition dataset, our approach attains recognition accuracy rates of 98.12% for normal walking (NM), 95.82% for backpack walking (BG), and 89.59% for coat-wearing walking (CL), respectively, with an overall average recognition rate of 94.51%.

关键词： attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Effects of strain rates on dynamic deformation behavior of Cu-20Ag alloy

引用

Journal of Materials science & technology 2021年第20期79卷 75-87页

作者： Kexing Song Yongfeng Geng Yijie Ban Yi Zhang Zhou Li Xujun Mi Jun Cao Yanjun Zhou Xuebin Zhang School of Materials Science and Engineering Henan University of Science and TechnologyLuoyang471023China Provincial and Ministerial Co-Construction of Collaborative Innovation Center for Non-Ferrous Metal New Materials and Advanced Processing Technology Henan ProvinceLuoyang471023China Henan Province Key Laboratory of Nonferrous Materials Science and Processing Technology Luoyang471023China School of Materials Science and Engineering Central South UniversityChangsha410083China General Research Institute for Nonferrous Metals Beijing100088China Henan Polytechnic University Henan ProvinceJiaozuo454010China

Copper alloy is widely used in high-speed railway,aerospace and other fields due to its excellent electrical conductivity and mechanical *** speed deformation and dynamic loading under impact load is a complex service condition,which widely exists in the field of national defense,military and industrial ***,the dynamic deformation behavior of the Cu-20Ag alloy was investigated by Split Hopkinson Pressure Bar(SHPB)with the strain rates of 1000-25000 s^(-1),high-speed hydraulic servo material testing machine with the strain rates of 1-500 s^(-1).The effect of strain rate on flow stress and adiabatic shear sensitivity was *** results show that the increase of strain rate will increase the flow stress and critical strain,that is to say,the increase of strain rate will reduce the adiabatic shear sensitivity of the Cu-20Ag *** Cu-Ag interface has obvious orientation relationship with;(111)_(Cu)//(111)_(Ag):(^(-)111)_(Cu)//(^(-)111)_(Ag):(^(-)200)_(Cu)//(^(-)200)_(Ag) and [0^(-)11]_(Cu)//[0^(-)11]_(Ag) with the increase of strain *** increase of strain rate promotes the precipitation of Ag and increases the number of interfaces in the microstructure,which hinders the movement of dislocations and improves the stress and yield strength of the Cu-20Ag *** concentration and distribution density of dislocations and the precipitation of Ag were the main reasons improve the flow stress and yield strength of the Cu-20Ag alloy.

关键词： Cu-20Ag alloy Dynamic deformation Split Hopkinson Pressure Bar Adiabatic shear sensitivity

来源：评论

学校读者我要写书评

暂无评论

Multi-level Teaching Text Classification based on the Fusion of Deep Learning Models 23

Multi-level Teaching Text Classification based on the Fusion...

引用

Proceedings of the 2023 International Conference on Information Education and Artificial Intelligence

作者： Guanghao Jin Junhua Zhao Yuqing Wang Jieying Wang Hui Du Qingzeng Song School of Artificial Intelligence Beijing Polytechnic China School of Computer Science and Technology Tiangong University China

ISBN: (纸本)9798400716157

Deep learning is widely used in text classification, which can be help the collection of teaching text samples from multiple datasets. On the other side, the variety of texts causes the difficulty of the classification. To solve this problem, we design a multi-level text classification system that fuses multiple models to increase the accuracy of the classification. In more details, we train the deep learning models on some public datasets. Then, we organize these to construct multi-level sets of models. On a text sample, we firstly detect if the dataset classification is needed. Then, we send this sample to the proper level of model set. Finally, we continuously optimize the system based on the collected samples. As the experimental results show, our method can achieve higher accuracy than the existing ones.

关键词：

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：