检索结果-内蒙古大学图书馆

Fault Detection of Automotive Engine System Based on Canonical Variate Analysis Combined With Bhattacharyya Distance

引用

Journal of Dynamic Systems, Measurement and Control 2025年第4期147卷 041004页

作者： Cheng, Zhang Yun-Fei, Wang Yu-Yu, Lao Yuan, Li College of Science Shenyang University of Chemical Technology Liaoning Shenyang110142 China College of Computer Science and Technology Shenyang University of Chemical Technology Liaoning Shenyang110142 China College of Information Engineering Shenyang University of Chemical Technology Liaoning Shenyang110142 China

Aiming at the nonlinear and dynamic characteristics of data in automotive engine systems, a fault detection method based on canonical variate analysis combined with Bhattacharyya distance (CVA-BD) is proposed in this paper. First, CVA is utilized to calculate the state space of the system data. Second, a sliding window is introduced in the state space to quantify the difference in data distribution within the window using Bhattacharyya distance, thereby constructing a novel statistical indicator. Finally, the control limit for statistical indicator is determined to achieve process monitoring of automotive engine systems. CVA-BD effectively enhances the performance of process monitoring by capturing the sequential correlation of data through CVA and eliminating the nonlinear impact between samples using similarity measurement metrics. Simulation experiments are conducted using a numerical case and experimental data from turbocharged spark ignition (TCSI) engines. The simulation results further confirm that, compared with principal component analysis (PCA), dynamic principal component analysis (DPCA), canonical variable analysis (CVA), dissimilar canonical variable analysis (CVDA), auto-encoder (AE), and stacked auto-encoder (SAE) CVA-BD has demonstrated an improvement of at least 41%. Copyright © 2025 by ASME.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Harnessing Trend Theory to Enhance Distributed Proximal Point Algorithm Approaches for Multi-Area Economic Dispatch Optimization

引用

computers, Materials & Continua 2025年第3期82卷 4503-4533页

作者： Yaming Ren Xing Deng College of Mechanical and Control Engineering Guilin University of TechnologyGuilin541006China School of Computer Jiangsu University of Science and TechnologyZhenjiang212003China

The exponential growth in the scale of power systems has led to a significant increase in the complexity of dispatch problem resolution,particularly within multi-area interconnected power *** complexity necessitates the employment of distributed solution methodologies,which are not only essential but also highly *** the realm of computational modelling,the multi-area economic dispatch problem(MAED)can be formulated as a linearly constrained separable convex optimization *** proximal point algorithm(PPA)is particularly adept at addressing such mathematical constructs *** study introduces parallel(PPPA)and serial(SPPA)variants of the PPA as distributed algorithms,specifically designed for the computational modelling of the *** PPA introduces a quadratic term into the objective function,which,while potentially complicating the iterative updates of the algorithm,serves to dampen oscillations near the optimal solution,thereby enhancing the convergence ***,the convergence efficiency of the PPA is significantly influenced by the parameter *** address this parameter sensitivity,this research draws on trend theory from stock market analysis to propose trend theory-driven distributed PPPA and SPPA,thereby enhancing the robustness of the computational *** computational models proposed in this study are anticipated to exhibit superior performance in terms of convergence behaviour,stability,and robustness with respect to parameter selection,potentially outperforming existing methods such as the alternating direction method of multipliers(ADMM)and Auxiliary Problem Principle(APP)in the computational simulation of power system dispatch *** simulation results demonstrate that the trend theory-based PPPA,SPPA,ADMM and APP exhibit significant robustness to the initial value of parameter c,and show superior convergence characteristics compared to the residual balancing ADMM.

关键词： Multi-area economic dispatch problem proximal point algorithm trend theory

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Aware Multimodal Explainable Fake News Detection 5

Knowledge-Aware Multimodal Explainable Fake News Detection

引用

5th International Conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2024

作者： Liu, Xin Dai, Lican Cao, Kaichen Song, Dan Lu, Liangyu Wang, Shengze Liu, Haibo The Southwest Institute of Electronic Technology Chengdu China Harbin Engineering University College of Computer Science and Technology Harbin China

ISBN: (纸本)9798331533991

This paper addresses the limited interpretability of current deep learning-based fake news identification methods, which often fail to incorporate background knowledge embedded in the news. It leverages commonsense knowledge extracted from the Baidu Baike commonsense knowledge graph as evidence to clarify the detection process. To effectively utilize the external knowledge implicit in the news, relevant commonsense is extracted from the ConceptNet knowledge graph, providing essential background knowledge for detection. We introduce the Commonsense-based Multimodal Fake News Detection Network (CMFNDN), designed to integrate evidence, commonsense, text, and image information for effective fake news detection. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Healthcare Privacy-Preserving Federated Transfer Learning using CKKS-Based Homomorphic Encryption and PYHFEL Tool

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2024年第3期5卷 473-488页

作者： Al-Janabi, Anmar A. Al-Janabi, Sufyan Al-Khateeb, Belal Computer Science Department University of Technology – Iraq Baghdad10066 Iraq University of Anbar Ramadi Iraq College of Computer Science & Information Technology Anbar Ramadi31001 Iraq

Digitization of healthcare data has shown an urgent necessity to deal with privacy concerns within the field of deep learning for healthcare organizations. A promising approach is federated transfer learning, enabling medical institutions to train deep learning models collaboratively through sharing model parameters rather than raw data. The objective of this research is to improve the current privacy-preserving federated transfer learning systems that use medical data by implementing homomorphic encryption utilizing PYthon for Homomorphic Encryption Libraries (PYFHEL). The study leverages a federated transfer learning model to classify cardiac arrhythmia. The procedure begins by converting raw Electrocardiogram (ECG) scans into 2-D ECG images. Then, these images are split and fed into the local models for extracting features and complex patterns through a finetuned ResNet50V2 pre-trained model. Optimization techniques, including real-time augmentation and balancing, are also applied to maximize model performance. Deep learning models can be vulnerable to privacy attacks that aim to access sensitive data. By encrypting only model parameters, the Cheon-Kim-Kim-Song (CKKS) homomorphic scheme protects deep learning models from adversary attacks and prevents sensitive raw data sharing. The aggregator uses a secure federated averaging method that averages encrypted parameters to provide a global model protecting users’ privacy. The system achieved an accuracy rate of 84.49% when evaluated using the MIT-BIH arrhythmia dataset. Furthermore, other comprehensive performance metrics were computed to gain deeper insights, including a precision of 72.84%, recall of 51.88%, and an F1-score of 55.13%, reflecting a better understanding of the adopted framework. Our findings indicate that employing the CKKS encryption scheme in a federated environment with transfer cutting-edge technology achieves relatively high accuracy but at the cost of other performance metrics, which is lower

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-radio fast routing recovery protocol based on spectrum situation awareness

引用

Chinese Journal of Aeronautics 2025年第3期38卷 435-446页

作者： Chuanxin ZHOU Chao DONG Xiaojun ZHU Fuhui ZHOU Qihui WU Zhengrui QIN Ministry of Industry and Information Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China School of Computer Science and Information Systems Northwest Missouri State UniversityMaryville 64468USA

UAV networks often encounter jamming attacks, under which multi-radio protocols have to switch radios to accelerate communication recovery. However, the existing protocols rely on exchange of hello messages to detect jamming, leading to long sensing time and thus slow routing recovery. To address the issues raised by jamming attacks, we propose a new routing protocol, Electromagnetic Spectrum situation awareness Optimized Link State Routing (ESOLSR) protocol, to improve the existing OLSRv2 protocol. ESOLSR utilizes the spectrum situation awareness capability from the physical layer, and adopts joint-updating of link status, updating of interface functions, and adaptive adjustment of parameters. Our simulation results show that the improved protocol, ESOLSR, can recover routing and resume normal communication 26.6% faster compared to the existing protocols.

关键词： UAV ad hoc network OLSR protocol Routing recovery Electromagnetic spectrum situation awareness Multi-radio

来源：评论

学校读者我要写书评

暂无评论

Defect Detection of Aluminum Wine Bottle Cap Based on Improved YOLOv4

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第4期8卷 1373-1387页

作者： Han, Jin Li, Yujie Wu, Wenhao College of Computer Science and Technology Shandong University of science and technology Shandong Province Qingdao266590 China

The defect detection of wine bottle cap is an important part of industrial quality inspection in distillery. High detection accuracy, low missed detection rate and fast detection speed are important reference performance of wine bottle cap defect detection. At present, wine bottle cap detection based on deep learning hasn’t been extensively used. Therefore, this paper introduces an improved YOLOv4 model, which aims to improve the detection accuracy and reduce the missed detection rate of the model without sacrificing the detection speed. Firstly, the Loss Function of YOLOv4 model is improved to accelerate its convergence speed;Secondly, BAM is drew into the backbone to enhance its capacity of extracting useful information and reduce the computational complexity of the model;In addition, the residual feature augmentation module is improved and introduced into the feature extraction layer to reduce the loss of feature information caused by convolution operation;Finally, the original image data of wine bottle cap defects comes from Alibaba Cloud Tianchi competition platform. The dataset is expanded through operations such as data flipping. The results of this experiment show that the improved YOLOv4 is superior than the original model, and the mAP reaches 94.17%, which can meet the requirements of industrial quality inspection. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Distilleries

来源：评论

学校读者我要写书评

暂无评论

User selection based on user-union and relative entropy in mobile crowdsensing

引用

The Journal of China Universities of Posts and Telecommunications 2022年第3期29卷 34-42页

作者： Shao Zihao Qu Tianguang Wang Huiqiang Zou Yifan Lü Hongwu College of Computer Science and Technology Harbin Engineering UniversityHarbin 150001China National Secrecy Science and Technology Evaluation Center Beijing 100044China

A critical issue in mobile crowdsensing(MCS) involves selecting appropriate users from a number of participants to guarantee the completion of a sensing task. Users may upload unnecessary data to the sensing platform, leading to redundancy and low user selection efficiency. Furthermore, using exact values to evaluate the quality of the user-union will further reduce selection accuracy when users form a union. This paper proposes a user selection method based on user-union and relative entropy in MCS. More specifically, a user-union matching scheme based on similarity calculation is constructed to achieve user-union and reduce data redundancy effectively. Then, considering the interval-valued influence, a user-union selection strategy with the lowest relative entropy is proposed. Extensive testing was conducted to investigate the impact of various parameters on user selection. The results obtained are encouraging and provide essential insights into the different aspects impacting the data redundancy and interval-valued estimation of MCS user selection.

关键词： mobile crowdsensing(MCS) user selection interval-value user-union relative entropy

来源：评论

学校读者我要写书评

暂无评论

HASHL: Dynamic Hash Verification for Detecting and Preventing Eclipse Attacks

引用

IEEE Internet of Things Journal 2025年第13期12卷 23524-23535页

作者： He, Daojing Gong, Wei Tu, Chen Chan, Sammy Harbin Institute of Technology School of Computer Science and Technology Shenzhen China Jiangxi University of Science and Technology School of Information Engineering Jiangxi Ganzhou China City University of Hong Kong Department of Electrical Engineering Hong Kong

With the rapid development of blockchain technology, P2P networks are facing increasing security threats, among which Eclipse attacks, as a type of network isolation attack, have seriously affected the normal operation of the network and the integrity of data. To address this challenge, this study implements node authentication and dynamic reputation evaluation by leveraging a dynamic hash computation mechanism that integrates challenge strings, node identifiers, and the latest active time, ensuring the uniqueness of node identities and the authenticity of operations. Based on a dynamic hash chain behavior evaluation mechanism, node behaviors are quantified across three dimensions: integrity, consistency, and temporal consistency, enabling precise identification of anomalous nodes. Furthermore, a network prevention repository framework is proposed, which dynamically adjusts the trust index of nodes by combining historical behavior with real-time data, effectively detecting and defending against stealthy Eclipse attacks. In addition, extensive testing on both Bitcoin and Ethereum platforms has shown that the method proposed in this study not only can effectively coexist on these two platforms, but also significantly improves the security and stability of the network, effectively reducing the occurrence of Eclipse attacks. © 2014 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Unraveling the role of NiSnPH@OOH/CC perovskite hydroxide for efficient electrocatalytic oxidation of methanol to formate

引用

Nano Research 2024年第4期17卷 2388-2399页

作者： Jing Shao Yusheng Fang Xiaobing Wu Muhammad Imran Abdullah Youkun Tao College of Chemistry and Environmental Engineering Shenzhen UniversityShenzhen 518060China School of Science Harbin Institute of TechnologyShenzhen 518055China

The sluggish kinetics of oxygen evolution reaction(OER)is the key tailback for hydrogen production from the water *** OER with thermodynamically auspicious methanol oxidation reaction(MOR)can significantly boost the H_(2) and value-added products ***,it is currently challenging to achieve a synergistic manipulation of product selectivity and performance for MOR ***,we report NiSnPH@OOH/CC(CC=carbon cloth)perovskite hydroxide nanosphere as an efficient MOR electrocatalyst with high activity,stability,and selectivity towards methanol oxidation to formate.A surface amorphous layer of defect rich NiOOH was generated in operando by selective Sn leaching with stable perovskite hydroxide bulk structure,which mitigates the oxidative power and optimizes the local coordination environment of the active NiOOH *** situ Raman combined with electrochemical studies further confirm the key active species,NiOOH,generated in operando enhance the MOR and blocking the over oxidation of methanol to CO_(2).As a result,NiSnPH@OOH/CC effectively masks the OER and attains>99%selectivity with 100%Faradic efficiency for *** results of this study show the advances of NiSnPH@OOH/CC as an efficient electrocatalyst for MOR and also suggest its potential applications for various small organic molecules oxidation.

关键词： perovskite hydroxide small organic molecules nickel oxy(hydroxide) value-added products methanol oxidation reaction

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal Learning for Route-Based Travel Time Estimation

引用

Journal of computer science & technology 2024年第5期39卷 1107-1122页

作者： Zi-Quan Fang Qi-Chen Sun Lu Chen Dan-Lei Hu Yun-Jun Gao School of Software Technology Zhejiang UniversityNingbo 315048China College of Computer Science Zhejiang UniversityHangzhou 310027China

Travel time estimation(TTE)is a fundamental task to build intelligent transportation ***,most existing TTE solutions design models upon simple homogeneous graphs and ignore the heterogeneity of traffic networks,where,e.g.,main roads typically contribute differently from side *** terms of spatial dimension,few studies consider the dynamic spatial correlations across road segments,e.g.,the traffic speed/volume on road segment A may correlate with the traffic speed/volume on road segment B,where A and B could be adjacent or non-adjacent,and such correlations may vary across *** terms of temporal dimension,even fewer studies consider the dynamic temporal dependences,where,e.g.,the historical states of road A may directly correlate with the recent state of A,and may also indirectly correlate with the recent state of road *** track all aforementioned issues of existing TTE approaches,we provide HDTTE,a solution that employs heterogeneous and dynamic spatio-temporal predictive ***,we first design a general multi-relational graph constructor that extracts hidden heterogeneous information of road segments,where we model road segments as nodes and model correlations as edges in the multi-relational ***,we propose a dynamic graph attention convolution module that aggregates dynamic spatial dependence of neighbor roads to focal *** also present a novel correlation-augmented temporal convolution module to capture the influence of states at past time steps on current traffic ***,in view of the periodic dependence of traffic,we develop a multi-scale adaptive fusion layer to enable HDTTE to exploit periodic patterns from recent,daily,and weekly traffic *** experimental study using real-life highway and urban datasets demonstrates the validity of the approach and its advantage over others.

关键词： heterogeneous traffic modeling spatio-temporal learning travel time estimation traffic speed prediction

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：