检索结果-内蒙古大学图书馆

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Liu, Jie He, Mengting Shang, Xuequn Shi, Jieming Cui, Bin Yin, Hongzhi School of Computer Science Northwestern Polytechnical University Xi'an China The Hong Kong Polytechnic University Department of Computing Hong Kong Hong Kong School of Computer Science Peking University Beijing China School of Electrical Engineering & Computer Science The University of Queensland Brisbane Australia

ISBN: (纸本)9798350317152

Graph anomaly detection (GAD) has gained increasing attention in recent years due to its critical application in a wide range of domains, such as social networks, financial risk management, and traffic analysis. Existing GAD methods can be categorized into node and edge anomaly detection models based on the type of graph objects being detected. However, these methods typically treat node and edge anomalies as separate tasks, overlooking their associations and frequent co-occurrences in real-world graphs. As a result, they fail to leverage the complementary information provided by node and edge anomalies for mutual detection. Additionally, state-of-the-art GAD methods, such as CoLA and SL-GAD, heavily rely on negative pair sampling in contrastive learning, which incurs high computational costs, hindering their scalability to large graphs. To address these limitations, we propose a novel unified graph anomaly detection framework based on bootstrapped self-supervised learning (named BOURNE). We extract a subgraph (graph view) centered on each target node as node context and transform it into a dual hypergraph (hypergraph view) as edge context. These views are encoded using graph and hypergraph neural networks to capture the representations of nodes, edges, and their associated contexts. By swapping the context embeddings between nodes and edges and measuring the agreement in the embedding space, we enable the mutual detection of node and edge anomalies. Furthermore, BOURNE can eliminate the need for negative sampling, thereby enhancing its efficiency in handling large graphs. Extensive experiments conducted on six benchmark datasets demonstrate the superior effectiveness and efficiency of BOURNE in detecting both node and edge anomalies. © 2024 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Big Data Security Framework Based on AEFS-KENN Algorithms for the Detection of Cyber-Attacks from Smart Grid Systems

引用

Big Data Mining and Analytics 2024年第2期7卷 399-418页

作者： Sankaramoorthy Muthubalaji Naresh Kumar Muniyaraj Sarvade Pedda Venkata Subba Rao Kavitha Thandapani Pasupuleti Rama Mohan Thangam Somasundaram Yousef Farhaoui Department of Electrical and Electronics Engineering CMR College of Engineering&TechnologyHyderabad 501401India Department of Electronics and Communication Engineering Vardhaman College of Engineering KacharamShamshabad 501218India Department of Electronics and Communication Engineering Sreenidhi Institute of Science and TechnologyHyderabad 501301India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyChennai 600062India Department of Electrical and Electronics Engineering Bharat Institute of Engineering and TechnologyHyderabad 501510India Department of Computer Science and Engineering Amrita School of ComputingAmrita Vishwa VidhyapeethamBengaluru 560035India T-IDMS Department of Computer ScienceFaculty of Sciences and TechniquesMoulay Ismail UniversityErrachidia 52000Morocco

Big data has the ability to open up innovative and ground-breaking prospects for the electrical grid,which also supports to obtain a variety of technological,social,and financial *** is an unprecedented amount of heterogeneous big data as a consequence of the growth of power grid technologies,along with data processing and advanced *** main obstacles in turning the heterogeneous large dataset into useful results are computational burden and information *** original contribution of this paper is to develop a new big data framework for detecting various intrusions from the smart grid systems with the use of AI ***,an AdaBelief Exponential Feature Selection(AEFS)technique is used to efficiently handle the input huge datasets from the smart grid for boosting ***,a Kernel based Extreme Neural Network(KENN)technique is used to anticipate security vulnerabilities more *** Polar Bear Optimization(PBO)algorithm is used to efficiently determine the parameters for the estimate of radial basis ***,several types of smart grid network datasets are employed during analysis in order to examine the outcomes and efficiency of the proposed AdaBelief Exponential Feature Selection-Kernel based Extreme Neural Network(AEFS-KENN)big data security *** results reveal that the accuracy of proposed AEFS-KENN is increased up to 99.5%with precision and AUC of 99%for all smart grid big datasets used in this study.

关键词： smart grid Machine Learning(ML) big data analytics AdaBelief Exponential Feature Selection(AEFS) Polar Bear Optimization(PBO) Kernel Extreme Neural Network(KENN)

来源：评论

学校读者我要写书评

暂无评论

Robot Manipulation Strategy for Explosives Disposal in Cluttered Scenes 8th

Robot Manipulation Strategy for Explosives Disposal in Clutt...

引用

8th International Conference on Cognitive Systems and Information Processing, ICCSIP 2023

作者： Guo, Run Yuan, Yi Sun, Funchun Wen, Shuhuan Chen, Yang Li, Linxiang School of Electrical Engineering Yanshan University Qinhuangdao China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9789819980208

Compared to human operator, robotic arm possesses the advantages of high accuracy and controllability in handling and manipulating hazardous materials. Due to the complexity and variability of application scenarios, such as the objects are stacked, it is a great challenge to accurately select target objects and manipulation mode in the fields of security and demolition. To address these problems, robotic arm systems require capabilities in target object detection, object relationship reasoning, and manipulation strategy selection. In this paper, we propose a framework with the abilities of reasoning about the unknown relationships between target objects and interfering objects, predicting manipulation sequences, and adopting appropriate manipulation strategies for hazardous object detection and manipulation processing. We conduct a series of experiments in indoor single-target, multi-target, and outdoor scenarios to complete the assigned tasks with improved manipulation sequences. These results serve as evidence of the effectiveness of the proposed framework. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Experimental validation of multi-parameter diffuse optical tomography using deep-learning

Experimental validation of multi-parameter diffuse optical t...

引用

Optical Tomography and Spectroscopy, OT and S 2024 - Part of Optica Biophotonics Congress: Biomedical Optics

作者： Dale, Robin Zheng, Biao O’Sullivan, Thomas Dehghani, Hamid University of Birmingham School of Computer Science United Kingdom University of Notre Dame Department of Electrical Engineering United States

This study presents experimental validation of a deep-learning (DL) model for simultaneous 3D reconstruction of absolute absorption and reduced scattering. The model improved structural similarity and contrast, but in... 详细信息

ISBN: (纸本)9781957171340

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

VisionReli6G: Enhancing 6G Wireless Reliability with CNN-LSTM for LOS Blockage Prediction 2024

VisionReli6G: Enhancing 6G Wireless Reliability with CNN-LST...

引用

16th International Conference on Contemporary Computing, IC3 2024

作者： Bajaj, Sagar Patel, Dhaval K. Raval, Mehul S. Zaveri, Mukesh Merchant, Shabbir N. School of Engineering and Applied Science Ahmedabad University Ahmedabad India Department of Computer Science and Engineering SVNIT Surat India Department of Electrical Engineering IIT Bombay Mumbai India

ISBN: (纸本)9798400709722

The mmWave and sub-THz signals rely on Line-of-Sight (LOS) links for higher throughput. Blocking these links can lead to a sudden drop in the received SNR and increase the latency of the communication network. We propose a CNN-LSTM pipeline designed to enhance the reliability of 6G wireless networks by predicting LOS blockages in advance using a sequential stream of RGB images. The proposed solution's efficiency is demonstrated by comparing key performance indicators between the baseline (YOLO-GRU) and the developed pipelines (ResNet-LSTM, ResNeXt-LSTM). The results are validated on the first real-world 6G communication dataset, DeepSense 6G, which contains diverse data modalities captured at different locations and times of the day. The Top-1 accuracy for future 1, 5, and 10 instances of scenario 22 yields an average increase of 10.63% and 12.60% with the Resnet-LSTM and ResNeXt-LSTM pipelines respectively compared to the baseline YOLO-GRU model. The F1 score of scenarios 17-22 for future-1 time window prediction increased by an average of 7.58% and 8.13% for both pipelines respectively. © 2024 Copyright held by the owner/author(s).

关键词： Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

Edge AI-Driven Video Analytics: A Mobile Deep Learning Framework for Victim Detection in SAR robotics 3

Edge AI-Driven Video Analytics: A Mobile Deep Learning Frame...

引用

3rd FORTEI-International Conference on electrical engineering, FORTEI-ICEE 2024

作者： Ihsan, Muhammad Putra, Karisma Trinanda Mustar, Muhamad Yusvin Setyawan, Aufa Faiz Chu, Hsueh-Ting Chen, Hsing-Chung Department of Electrical Engineering Universitas Muhammadiyah Yogyakarta Bantul Indonesia Department of Electrical Engineering Center of Artificial Intelligence and Robotics Studies Universitas Muhammadiyah Yogyakarta Bantul Indonesia Department of Computer Science and Information Engineering Asia University Taichung Taiwan

ISBN: (纸本)9798331542207

In post-disaster search and rescue (SAR) missions, it is crucial for robots to distinguish between actual victims and dummy objects, despite their similar characteristics. Edge video analytics have demonstrated exceptional performance in such missions, however, the trade-off between high-performing deep learning models and computational complexity often results in inadequate computational efficiency for SAR robotics. This study tackles this challenge by deploying a deep learning (DL) algorithm, i.e., MobileNet Single Shot Detector (SSD), specifically tailored for embedded systems, to perform object detection and classification tasks on lab-scale SAR robots. The proposed algorithm is developed in Python and implemented on a low-powered edge computing device. The effectiveness of the proposed algorithm in object localization is highlighted by its mAP score of 0.6247 and an average IoU of 0.9036. Experimental tests using a confusion matrix showed that the model accurately predicted 42 dummy objects and 43 victim dolls. The model achieved an overall accuracy of 89.47%, with a precision of 1.0, a recall of 0.8947, and an F1 Score of 0.9444. Real-time testing confirmed the model’s robust performance, maintaining high accuracy and a stable frame rate of 47 FPS. These findings corroborate the efficacy of the MobileNet SSD algorithm in reliably detecting and differentiating objects within embedded SAR robotic operations. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

FREEnet: a dynamic deep-learning model for freehand diffuse optical tomography

FREEnet: a dynamic deep-learning model for freehand diffuse ...

引用

Microscopy Histopathology and Analytics, Microscopy 2024 - Part of Optica Biophotonics Congress: Biomedical Optics

作者： Dale, Robin O'Sullivan, Thomas Dehghani, Hamid University of Birmingham School of Computer Science United Kingdom University of Notre Dame Department of Electrical Engineering United States

A deep-learning (DL) model for handheld diffuse optical tomography is presented. The fully convolutional network can reconstruct 3D absorption and scattering from arbitrarily undersampled scan data at a rate of 18.5Hz... 详细信息

ISBN: (纸本)9781957171340

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

A Survey on Supervised,Unsupervised,and Semi-Supervised Approaches in Crowd Counting

引用

computers, Materials & Continua 2024年第12期81卷 3561-3582页

作者： Jianyong Wang Mingliang Gao Qilei Li Hyunbum Kim Gwanggil Jeon School of Electrical and Electronic Engineering Shandong University of TechnologyZibo255000China School of Electronic Engineering and Computer Science Queen Mary University of LondonLondonE14NSUK Department of Embedded Systems Engineering Incheon National UniversityIncheon22012Republic of Korea

Quantifying the number of individuals in images or videos to estimate crowd density is a challenging yet crucial task with significant implications for fields such as urban planning and public *** counting has attracted considerable attention in the field of computer vision,leading to the development of numerous advanced models and *** approaches vary in terms of supervision techniques,network architectures,and model ***,most crowd counting methods rely on fully supervised learning,which has proven to be ***,this approach presents challenges in real-world scenarios,where labeled data and ground-truth annotations are often *** a result,there is an increasing need to explore unsupervised and semi-supervised methods to effectively address crowd counting tasks in practical *** paper offers a comprehensive review of crowd counting models,with a particular focus on semi-supervised and unsupervised approaches based on their supervision *** summarize and critically analyze the key methods in these two categories,highlighting their strengths and ***,we provide a comparative analysis of prominent crowd counting methods using widely adopted benchmark *** believe that this survey will offer valuable insights and guide future advancements in crowd counting technology.

关键词： Crowd counting density estimation convolutional neural network(CNN) un/semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Reset-Free Reinforcement Learning via Multi-State Recovery and Failure Prevention for Autonomous Robots

引用

Tsinghua science and Technology 2024年第5期29卷 1481-1494页

作者： Xu Zhou Benlian Xu Zhengqiang Jiang Jun Li Brett Nener School of Mechanical Engineering Changshu Institute of TechnologyChangshu 215500China School of Automation Nanjing University of Science and TechnologyNanjing 210094China School of Electronic and Information Engineering Suzhou University of Science and TechnologySuzhou 215009China Faculty of Medicine and Health The University of SydneySydney 2006Australia Department of Electrical Electronic and Computer EngineeringThe University of Western AustraliaPerth 6009Australia

Reinforcement learning holds promise in enabling robotic tasks as it can learn optimal policies via trial and ***,the practical deployment of reinforcement learning usually requires human intervention to provide episodic resets when a failure *** manual resets are generally unavailable in autonomous robots,we propose a reset-free reinforcement learning algorithm based on multi-state recovery and failure prevention to avoid failure-induced *** multi-state recovery provides robots with the capability of recovering from failures by self-correcting its behavior in the problematic state and,more importantly,deciding which previous state is the best to return to for efficient *** failure prevention reduces potential failures by predicting and excluding possible unsafe actions in specific *** simulations and real-world experiments are used to validate our algorithm with the results showing a significant reduction in the number of resets and failures during the learning.

关键词： reinforcement learning manual reset multi-state recovery failure prediction

来源：评论

学校读者我要写书评

暂无评论

Posture Detection of Heart Disease Using Multi-Head Attention Vision Hybrid(MHAVH)Model

引用

computers, Materials & Continua 2024年第5期79卷 2673-2696页

作者： Hina Naz Zuping Zhang Mohammed Al-Habib Fuad A.Awwad Emad A.A.Ismail Zaid Ali Khan School of Computer Science and Engineering Central South UniversityChangsha410003China Department of Quantitative analysis College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh11587Saudi Arabia Electrical and Computer Engineering University of VictoriaVictoriaV9A1B8Canada

Cardiovascular disease is the leading cause of death *** disease causes loss of heart muscles and is also responsible for the death of heart cells,sometimes damaging their functionality.A person’s life may depend on receiving timely assistance as soon as ***,minimizing the death ratio can be achieved by early detection of heart attack(HA)*** the United States alone,an estimated 610,000 people die fromheart attacks each year,accounting for one in every four ***,by identifying and reporting heart attack symptoms early on,it is possible to reduce damage and save many lives *** objective is to devise an algorithm aimed at helping individuals,particularly elderly individuals living independently,to safeguard their *** address these challenges,we employ deep learning *** have utilized a vision transformer(ViT)to address this ***,it has a significant overhead cost due to its memory consumption and computational complexity because of scaling dot-product ***,since transformer performance typically relies on large-scale or adequate data,adapting ViT for smaller datasets is more *** response,we propose a three-in-one steam model,theMulti-Head Attention Vision Hybrid(MHAVH).Thismodel integrates a real-time posture recognition framework to identify chest pain postures indicative of heart attacks using transfer learning techniques,such as ResNet-50 and VGG-16,renowned for their robust feature extraction *** incorporatingmultiple heads into the vision transformer to generate additional metrics and enhance heart-detection capabilities,we leverage a 2019 posture-based dataset comprising RGB images,a novel creation by the author that marks the first dataset tailored for posture-based heart attack *** the limited online data availability,we segmented this dataset into gender categories(male and female)and conducted testing on both segmented and original dat

关键词： Image analysis posture of heart attack(PHA)detection hybrid features VGG-16 ResNet-50 vision transformer advance multi-head attention layer

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：