检索结果-内蒙古大学图书馆

Emerging Trends in engineering and Medical sciences (ICETEMS), International Conference on

作者： S. Baskar Meikandan Megaraj Karthick Manjunathan M. Chandrasekaran M. Anish P. Umamaheswarrao Jayant Giri Ahmad Abdelhafiz Ali Samhan Department of Automobile Engineering Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Mechanical Engineering Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai India Department of Mechanical Engineering Sathyabama Institute of Science and Technology Chenna Tamil Nadu India Department of Mechanical Engineering Bapatla Engineering College Bapatla A.P Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai TN India Department of Software Engineering Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331529352

ISBN: (纸本)9798331529390

Crankpin is a mechanical part which links the crankshaft to the connecting rod to each cylinder. Normally, crankpins are made up of low carbon material which results in unexpected fracture on the crankpin material due its chemical composition, high engine temperature, high operating oil temperature, improper lubrication and lower hardness. Recently, researchers are developing crankpins with different materials for the better performance such as alloy steel and the mild steel materials which have similar chemical compositions of low carbon material. The primary object of this study is to develop an improved crankpin which will alleviate the current crankpin used in the connecting rod. In this work we have selected 16MnCr5 as a replacement of the presently used crankpin in the connecting rod. 16MnCr5 is a low carbon steel widely used for several applications in many of the automobile industries. 16MnCr5 is hardened by a case hardening process which is carried out through the sealed quench furnace for the set of process parameters. The results of the prepared material were analyzed using hardness, microstructure examination and the economic conditions of the materials. In future, another set of two materials such as SCM420H and EN1A will be used for alternating material for crankpin which are processed with the same set of parameters and compared with the 16MnCr5 material to check the suitable crank pin material to avoid unexpected damage.

关键词： Industries Market research Lubricating oils Pins Lubrication Steel Microstructure Carbon Engines Chemicals

来源：评论

学校读者我要写书评

暂无评论

A Multi-tier Offloading Optimization Strategy for Consumer Electronics in Vehicular Edge Computing

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Lin, Haiyang Xiao, Bo Zhou, Xiaokang Zhang, Yonghong Liu, Xiaodong the School of Software Nanjing University of Information Science and Technology Nanjing210044 China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing210044 China the School of Chemistry and Materials Science Nanjing University of Information Science and Technology Nanjing210044 China the Faculty of Business Data Science Kansai University Osaka565-0823 Japan the School of Automation Nanjing University of Information Science and Technology Nanjing210044 China the School of Computing Edinburgh Napier University EdinburghEH10 5DT United Kingdom

—In the domain of consumer electronics, vehicular edge computing (VEC) technology is emerging as a novel data processing paradigm within vehicular networks. By sending tasks related to vehicular applications to the edge, this model makes it easier for computing power to be spread out. This lets interactive services respond quickly. Nevertheless, the computational resources at edge servers are inherently limited and often tasked with handling multiple concurrent operations. The inefficacious allocation of these resources significantly impairs the efficiency of task offloading. Additionally, indiscriminate offloading could overwhelm the servers, detrimentally impacting the performance of subsequent tasks. To circumvent these challenges, this study introduces a multi-tier offloading model predicated on game theory principles. This framework aims to optimize resource utilization at the edge while accounting for server load to ensure the timely execution of latency-sensitive tasks. To evaluate this model, this paper created a simulation environment specifically for video game tasks in consumer electronics. The experimental results show that the multi-tier offloading model can effectively relieve the load pressure on the edge server. The task failure rate of the multi-tier offloading model remains at the lowest level compared with several state-of-the-art algorithms, significantly reducing the execution delay of tasks and being able to meet the requirements of consumer electronics applications. © 2025 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Research on Deep Learning of Convolutional Neural Network for Action Recognition of Intelligent Terminals in the Big data Environment and its Intelligent software Application

Research on Deep Learning of Convolutional Neural Network fo...

引用

IEEE International Conference on Automation, Electronics and Electrical engineering (AUTEEE)

作者： Jiahan Sun Shengyuan Zhang Jieting Lian Lei Fu Zijie Zhou Yuxin Fan Kai Xu Shenyang Jianzhu University Shenyang China Master of Professional Science in Applied Statistics- Data Science College of Computing and Information Science Cornell University New York America Master of Science in Database Technology School of Professional Studies New York University New York America Master of Science in Computer Software Engineering College of Engineering Northeastern University Boston Massachusetts USA University of Pennsylvania Philadelphia Pennsylvania USA PipeChina Zhejiang Pipeline Network Co. LTD. Hangzhou China

ISBN: (数字)9798350377033

ISBN: (纸本)9798350377040

To enhance the accuracy and reliability of big data network traffic intrusion detection, an innovative detection model based on the two-branch convolution and gated recurrent unit was constructed, and its application effectiveness in the field of software engineering was thoroughly explored. This model first performs preprocessing operations on the original network traffic data, and then imports it as input information into the core architecture system jointly composed of the two-branch convolution and gated recurrent unit. Among them, the two-branch convolution focuses on quickly and accurately extracting the multi-dimensional features of the network traffic data, while the gated recurrent unit emphasizes on modeling and analyzing the long-term correlation patterns in the feature sequence. Through the organic combination of the two, the potential features of the data are deeply mined. Subsequently, the obtained feature output is directly transmitted to the classifier, so as to achieve accurate discrimination of various types of network traffic such as normal traffic, DoS attack traffic, DDoS attack traffic, port scanning traffic, and SQL injection attack traffic. The comparison experiment data shows that for network traffic data from different sources and with diverse patterns, the detection accuracy rate of this model is as high as 84.3%. This result strongly verifies its high efficiency and practicality in the field of big data network traffic intrusion detection, provides a solid technical guarantee foundation for the network security protection link in software engineering, has important theoretical and practical values, and is expected to promote the further development and application expansion of network security technologies.

关键词： Accuracy Convolution Telecommunication traffic Big data Logic gates Feature extraction data models software Convolutional neural networks software engineering

来源：评论

学校读者我要写书评

暂无评论

VAE Latent Space Quantization Methods for UAVs Video Stream

VAE Latent Space Quantization Methods for UAVs Video Stream

引用

Information, Control, and Communication Technologies (ICCT), International Conference on

作者： Alexander Chenskiy Alexander Berezkin Roman Vivchar Ruslan Kirichek Dmitry Kukunin Advanced Projects and Developments Department Bonch-Bruevich Saint-Petersburg University of Telecommunications Saint-Petersburg Russia Software Engineering and Computer Science Department Bonch-Bruevich Saint-Petersburg University of Telecommunications Saint-Petersburg Russia Communication Networks and Data Transmission Department Bonch-Bruevich Saint-Petersburg University of Telecommunications Saint-Petersburg Russia

ISBN: (数字)9798331517564

ISBN: (纸本)9798331517571

In FPV control of unmanned aerial vehicles, video frames are transmitted to the external pilot's station via a down link. Down links utilize mobile and hybrid orbital-terrestrial communication networks. The efficiency increase in their utilization is achieved by reducing the required bandwidth for each FPV-controlled unmanned aircraft. This requires ensuring a high compression rate of video stream frames, for which methods based on the application of variational autoencoders can be used. The principle of their operation is as follows: encoding frames into latent space, quantization and lossless compression. This paper presents new quantization algorithms and investigates the effect of applying different quantization algorithms to compression rate of latent space of VQ-D6 variational autoencoder from Stable Diffusion during further lossless compression using LZMA algorithm. In the result, the most effective quantization is selected to be used together with lossless compression.

关键词： Space vehicles Quantization (signal) Image coding Tensors Autoencoders Neural networks Bandwidth Streaming media Autonomous aerial vehicles Orbits

来源：评论

学校读者我要写书评

暂无评论

pFedLVM: A Large Vision Model (LVM)-Driven and Latent Feature-Based Personalized Federated Learning Framework in Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Kou, Wei-Bin Lin, Qingfeng Tang, Ming Xu, Sheng Ye, Rongguang Leng, Yang Wang, Shuai Li, Guofa Chen, Zhenyu Zhu, Guangxu Wu, Yik-Chung Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Shenzhen Research Institute of Big Data Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Research Institute of Electronic Science and Technology University of Electronic Science and technology Chengdu China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Mechanical and Vehicle Engineering Chongqing University Chongqing China

Deep learning-based Autonomous Driving (AD) semantic segmentation (SSeg) models often exhibit poor generalization due to data heterogeneity in an ever domain-shifting environment. While Federated Learning (FL) could improve the generalization of an AD SSeg model (known as FedAD system), conventional models often struggle with under-fitting as the amount of accumulated training data progressively increases. To address this issue, instead of conventional small models, employing Large Vision Models (LVMs) in FedAD is a viable option for better learning of representations from a vast volume of data. However, implementing LVMs in FedAD introduces three challenges: (I) the extremely high communication overheads associated with transmitting LVMs between participating vehicles and a central server;(II) lack of computing resource to deploy LVMs on each vehicle;(III) the performance drop due to LVM focusing on shared features but overlooking local vehicle characteristics. To overcome these challenges, we propose pFedLVM, a LVM-Driven, Latent Feature-Based Personalized Federated Learning framework. In this approach, the LVM is deployed only on central server, which effectively alleviates the computational burden on individual vehicles. Furthermore, the exchange between central server and vehicles are the learned features rather than the LVM parameters, which significantly reduces communication overhead. In addition, we utilize both shared features from all participating vehicles and individual characteristics from each vehicle to establish a personalized learning mechanism. This enables each vehicle’s model to learn features from others while preserving its personalized characteristics, thereby outperforming globally shared models trained in general FL. Extensive experiments demonstrate that pFedLVM outperforms the existing state-of-the-art approach by 18.47%, 25.60%, 51.03% and 14.19% in terms of mIoU, mF1, mPrecision and mRecall, respectively. © 2024, CC BY-NC-ND.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

CLDG: Contrastive Learning on Dynamic Graphs

CLDG: Contrastive Learning on Dynamic Graphs

引用

International Conference on data engineering

作者： Yiming Xu Bin Shi Teng Ma Bo Dong Haoyi Zhou Qinghua Zheng Department of Computer Science and Technology Xi’an Jiaotong University China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China Department of Distance Education Xi’an Jiaotong University China School of Software Beihang University China Advanced Innovation Center for Big Data and Brain Computing Beihang University China

The graph with complex annotations is the most potent data type, whose constantly evolving motivates further exploration of the unsupervised dynamic graph representation. One of the representative paradigms is graph contrastive learning. It constructs self-supervised signals by maximizing the mutual information between the statistic graph’s augmentation views. However, the semantics and labels may change within the augmentation process, causing a significant performance drop in downstream tasks. This drawback becomes greatly magnified on dynamic graphs. To address this problem, we designed a simple yet effective framework named CLDG. Firstly, we elaborate that dynamic graphs have temporal translation invariance at different levels. Then, we proposed a sampling layer to extract the temporally-persistent signals. It will encourage the node to maintain consistent local and global representations, i.e., temporal translation invariance under the timespan views. The extensive experiments demonstrate the effectiveness and efficiency of the method on seven datasets by outperforming eight unsupervised state-of-the-art baselines and showing competitiveness against four semi-supervised methods. Compared with the existing dynamic graph method, the number of model parameters and training time is reduced by an average of 2,001.86 times and 130.31 times on seven datasets, respectively. The code and data are available at: https://***/yimingxu24/CLDG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CancerAI: A Deep Learning Framework for Ovarian Cancer Prediction

CancerAI: A Deep Learning Framework for Ovarian Cancer Predi...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： G. Revathy P. Uma Maheswari S. Madhavi Vijay Anand P R. Vajubunnisa Begum H. Jasmin Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India Department of Computer science and Business systems K. Ramakrishnan college of Engineering Trichy India Department of Information Technology Vel tech Multi tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Electronics and Communication Science Justice Basheer Ahmed Sayeed College for Women Affiliated by University of Madras Chennai India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Ovarian cancer is the fifth most common cause of death from cancer in women. This is mainly because it is often diagnosed at a late stage, as the earliest symptoms are unclear and inconsistent. Existing diagnostic techniques, such as biomarkers, biopsies, and imaging tests, have notable drawbacks such as reliance on subjective interpretation, inconsistency across different observers, and time-consuming testing procedures. This research study introduces an innovative deep learning framework that employs a convolutional neural network (CNN) algorithm to accurately predict and diagnose ovarian cancer, thereby overcoming the existing constraints. The CNN was trained using a dataset of histopathology images. The dataset was partitioned into test and training subsets to enhance the model's performance. The algorithm demonstrated an impressive accuracy rate of 96%, successfully detecting 97.12% of malignant instances and precisely categorizing 95.02% of healthy cells. This method effectively mitigates the challenges related to human expert evaluation, including elevated rates of misclassification and variability across different observers, while also reducing the time required for analysis. The results underscore the capability of this CNN-based technique to offer a more precise, effective, and dependable strategy for forecasting and detecting ovarian cancer. Subsequent investigations will prioritize the integration of new breakthroughs in deep learning to further amplify the efficacy of the suggested approach.

关键词： Deep learning Training Accuracy Histopathology Transfer learning Observers Prediction algorithms Partitioning algorithms Convolutional neural networks Ovarian cancer

来源：评论

学校读者我要写书评

暂无评论

Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery

arXiv

引用

arXiv 2023年

作者： Liu, Jin Mao, Junbin Lin, Hanhe Kuang, Hulin Pan, Shirui Wu, Xusheng Xie, Shan Liu, Fei Pan, Yi Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830000 China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China School of Science and Engineering University of Dundee DundeeDD1 4HN United Kingdom School of Information and Communication Technology Griffith University Gold CoastQLD4215 Australia Shenzhen Health Development Research and Data Management Center Shenzhen518109 China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology. The source code will be available at https://***/yutian0315/MMKGL. © 2023, CC BY-NC-ND.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

data assimilation for particle and heat transport of LHD plasma 47

Data assimilation for particle and heat transport of LHD pla...

引用

47th EPS Conference on Plasma Physics, EPS 2021

作者： Morishita, Y. Murakami, S. Yokoyama, M. Ueno, G. Department of Nuclear Engineering Kyoto University Kyoto Japan National Institute for Fusion Science Toki Japan The Institute of Statistical Mathematics Tachikawa Japan The Graduate University for Advanced Studies SOKENDAI Toki and Tachikawa Japan The Joint Support Center for Data Science Research Tachikawa Japan

ISBN: (纸本)9781713837046

data assimilation techniques are applied to the integrated transport simulation in Large Helical Device (LHD). We employ the ensemble Kalman filter (EnKF) and the ensemble Kalman smoother (EnKS) as data assimilation methods. The time series data of measured temperature and density profiles are assimilated into the particle and heat transport simulation by TASK3D. We apply ASTI to the time series data sets of the 12 NBI heated plasmas in LHD. The obtained profiles and temporal variations of temperature and density by the EnKF and EnKS agree well with measured ones due to the optimization of the employed model parameters. These results indicate the effectiveness and validity of ASTI for accurate prediction and analysis of the behavior of fusion plasmas. © 2021 47th EPS Conference on Plasma Physics, EPS 2021. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Novel Explainable Artificial Intelligence Model in Image Classification problem

arXiv

引用

arXiv 2023年

作者： Cao, Hung Quoc Nguyen, Hung Truong Thanh Nguyen, Khang Vo Thanh Nguyen, Phong Xuan FSO.QNH.QAI.AIC FPT Software Binh Dinh Viet Nam FSO.QNH.QAI.AIC FPT Software Viet Nam Department of Computer Science Frankfurt University of Applied Sciences Frankfurt am Main Germany Graduate School of Engineering Advanced Interdisciplinary Studies The University of Tokyo Japan

In recent years, artificial intelligence is increasingly being applied widely in many different fields and has a profound and direct impact on human life. Following this is the need to understand the principles of the model making predictions. Since most of the current high-precision models are black boxes, neither the AI scientist nor the end-user deeply understands what’s going on inside these models. Therefore, many algorithms are studied for the purpose of explaining AI models, especially those in the problem of image classification in the field of computer vision such as LIME, CAM, GradCAM. However, these algorithms still have limitations such as LIME’s long execution time and CAM’s confusing interpretation of concreteness and clarity. Therefore, in this paper, we propose a new method called Segmentation - Class Activation Mapping (SeCAM) that combines the advantages of these algorithms above, while at the same time overcoming their disadvantages. We tested this algorithm with various models, including ResNet50, Inception-v3, VGG16 from ImageNet Large Scale Visual Recognition Challenge (ILSVRC) data set. Outstanding results when the algorithm has met all the requirements for a specific explanation in a remarkably concise time. © 2023, CC BY.

关键词： Machine learning

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：