检索结果-内蒙古大学图书馆

Unsupervised Distributed Anomaly Detection Framework for IoT in Edge AI Network

IEEE Internet of Things Journal 2025年第12期12卷 22058-22072页

作者： Jiang, Xingguo Lu, Chang Luo, Hong Sun, Yan Beijing University of Posts and Telecommunications School of Computer Science National Pilot Software Engineering School Beijing100876 China

Anomaly detection of sensor data is crucial to ensure the stability and effectiveness of IoT system. The task requires high accuracy and low latency, which makes distributed anomaly detection gradually become a research hotspot. Edge AI networks further enhance the computing power of edge servers, allowing distributed anomaly detection to be gradually applied to complex scenarios under the Industrial Internet of Things (IIoT), such as smart factories. However, in such cases, the data reported by different sensors in different fields are not independent and identically distributed (non-IID). Simultaneously, during unsupervised training, anomaly data mixed into the training data will reduce the recognition ability of the anomaly detector. To address these challenges, we propose an unsupervised distributed anomaly detection framework. On the cloud, we train an unsupervised anomaly detection model with global factors, using global and local factors to learn the distribution patterns of different fields. At the edge, a multi-dimensional threshold and its automatic selection algorithm are proposed to overcome the problem of decreased anomaly recognition ability introduced by anomaly training data. Extensive experiments on six datasets show that our approach outperforms SOTA methods in F1-score, can detect anomalies with high accuracy and efficiency in distributed IoT scenarios. © 2014 IEEE.

关键词： Industrial internet of things (IIoT)

来源：评论

学校读者我要写书评

暂无评论

A Novel Unsupervised Anomaly Detection Approach Using Neural Transformation in Cloud Environment 1

引用

15th International Conference on Cloud Computing, CLOUD 2022, held as part of the Services Conference Federation, SCF 2022

作者： Zhang, Rui Chen, Juan Song, Yujia Shan, Wenyu Chen, Peng Xia, Yunni School of Computer and Software Engineering Xihua University Chengdu China College of Computer Science Chongqing University Chongqing China

ISBN: (数字)9783031234989

ISBN: (纸本)9783031234972

As a new way of computing on the Internet, cloud computing has completely changed the abstraction and utilization of computing infrastructure and is favored by users of significant enterprises. Therefore, various large-scale cloud computing systems have emerged. Cloud computing systems capture real-time indicators in the form of multivariate time series. Therefore, it is necessary and valuable to do multivariate time series anomaly detection in the cloud computing system. However, because the data monitored in the cloud computing system is massive, redundant, contains noise and missing values, and is accompanied by the randomness and scarcity of anomalies, anomaly detection in the cloud computing system will generate high computational costs and the challenge of uncertain detection results. To solve these problems, we use neural transformation (NT) for anomaly detection, that is, Neural Transformation-Encoding-Auto Regression (NT-E-AR). NT-E-AR uses NT to generate different transformation views from the input data. Convolutional Long-Short Term Memory (ConvLSTM) encoding network and Autoregressive Long-Short Term Memory (LSTM) are combined to extract Spatio-Temporal features of time series data to achieve better anomaly detection capability. Extensive experiments show that NT-E-AR consistently outperforms all baselines on three open datasets and achieves an average F1 (0.772), increasing the average accuracy by 16.52%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

A Ginkgo Detection Algorithm in Complex Environments Based on Improved YOLOv7

A Ginkgo Detection Algorithm in Complex Environments Based o...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Chi Ma Qiang Guo School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

Detections of Ginkgoes are prerequisites for later counting and harvesting. Due to the uneven distribution of samples, the detection speed and accuracy of existing algorithms cannot adapt to the impact of complex environments. Therefore, an enhanced model YOLOv7-DC based on YOLOv7 is proposed in this paper, which redesigns the detection network and introduces a new feature fusion method. DCNv2 is embedded in the efficient layer aggregation network (ELAN), while PConv is utilized instead of conventional convolution to reduce the parameter impact of DCNv2. Moreover, the attention mechanism CBAM is introduced during training to enhance spatial and channel information, and the ConvMixer architecture is employed to capture spatial and channel relationships within the features, which are transmitted to the detection head through attention mechanism, improving the model's detection accuracy for each specific classification sample. Experimental results show that our YOLOv7-DC achieves both excellent detection speed and recognition rate in various classification tasks. The improved model's average detection accuracy is increased by 6.2% compared to previous algorithms, and the model parameters are reduced by 13%. It is proved that YOLOv7-DC is more suitable for scenarios with imbalanced samples and complex environments.

关键词： Training Accuracy Attention mechanisms Convolution Signal processing algorithms Lighting Medical services Feature extraction Environmental factors Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

QoS-aware Dynamic Service Caching and Updating in Cost-efficient Multi-Access Edge Computing 22

QoS-aware Dynamic Service Caching and Updating in Cost-effic...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Lu, Shuaibing Jin, Xin Wu, Jie Zhou, Shuyang Wu, Shen Yang, Jackson Yan, Ran Beijing University of Technology College of Computer Science Beijing China Temple University Center for Networked Computing United States Beijing Jiaotong University School of Software Engineering Beijing China

ISBN: (纸本)9798331509712

In the context of mobile edge computing, achieving dynamic service caching and updating to guarantee the QoS of users and reduce system costs is a challenging problem. However, existing research still has certain deficiencies in considering the dynamic behavior of users and the limited storage resources of edge servers. To address this problem, this paper proposes three novel strategies for the different stages of service caching and updating to jointly optimize the delay and cost. At the initial service caching stage, we propose a caching strategy based on dynamic programming, taking into account the constraint of limited memory resources. Given the dynamic behavior of users, we formulate the joint optimization problem as a Markov Decision Process (MDP) and design a service extension strategy based on Q-learning at the service updating decision-making stage and a replacement strategy taking both the distribution of service replications and service access frequency into account at the service updating replacement stage to guarantee the QoS of users. We effectively tackle the challenges arising from the dynamic behavior of users and limited storage resources. Through extensive comparative experiments, our approach outperforms traditional strategies by significantly reducing user latency and system cost. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Accelerating Distributed Urban Traffic Simulation via Enhanced Stale Synchronous Parallelism

Accelerating Distributed Urban Traffic Simulation via Enhanc...

引用

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Haojia Zhu Ran Ma Jiahui Jin Hongru Lu School of Computer Science and Engineering Southeast University School of Software Engineering Southeast University School of Computer Science Nanjing Audit University Nanjing China

ISBN: (数字)9798331531904

ISBN: (纸本)9798331531911

Modeling urban mobility behaviours with micro-scopic traffic flow simulation is now crucial for studying intel-ligent urban decision-making algorithms, such as traffic light control and road congestion charging. However, in urban-scale traffic environments, simulation is computationally intensive. Most existing studies use distributed traffic simulations based on the Bulk Synchronous Parallel (BSP) model, leading to significant time and data transfer costs due to the need for coordination and data synchronization. To address these issues, we propose an enhanced Stale Synchronous Parallel (ESSP) model. Our model reduces the waiting time of the simulation compute nodes, and we design it to control and measure errors during simulation. We also develop a distributed traffic simulator to validate our model, and the results show a performance improvement of 30% to 50% compared to conventional synchronization methods.

关键词： Social computing Computational modeling Scalability Roads Distributed databases Traffic control Data models Time measurement Robustness Synchronization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Predictive Travel Planning: Challenges and Opportunities 25

Deep Learning for Predictive Travel Planning: Challenges and...

引用

Proceedings of the 2025 International Conference on Big Data, Communication Technology and computer Applications

作者： Rui Shi Dongmei Wei Lizhou Wang Chunli Li School of Computer Science and Software Engineering Xihua University Chengdu Sichuan China School of Computer Science and Software Engineering Xihua University Chengdu Sichuan China School of Management Science and Engineering Southwest University of Finance Ecnomics Chengdu Sichuan China

ISBN: (纸本)9798400713620

With the rapid development of artificial intelligence technology, deep learning has shown great potential in many fields, and travel planning is no exception. This paper explores the diverse applications of deep learning in travel planning, covering weather forecasting, route planning, and travel destination recommendations. By comparing and analyzing various deep learning-based algorithm models, this study reveals their significant advantages and potential challenges in enhancing the accuracy, personalization, and efficiency of travel planning. It aims to provide innovative ideas and practical references for the field of travel planning, and to help achieve smarter, more convenient, and more efficient travel planning services.

关键词： Algorithm models

来源：评论

学校读者我要写书评

暂无评论

Deep3DSketch-im:rapid high-fidelity AI 3D model generation by single freehand sketches

引用

Frontiers of Information Technology & Electronic engineering 2024年第1期25卷 149-159页

作者： Tianrun CHEN Runlong CAO Zejian LI Ying ZANG Lingyun SUN College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China School of Software Technology Zhejiang UniversityHangzhou 310027China School of Information Engineering Huzhou UniversityHuzhou 313000China

The rise of artificial intelligence generated content(AIGC)has been remarkable in the language and image fields,but artificial intelligence(AI)generated three-dimensional(3D)models are still under-explored due to their complex nature and lack of training *** conventional approach of creating 3D content through computer-aided design(CAD)is labor-intensive and requires expertise,making it challenging for novice *** address this issue,we propose a sketch-based 3D modeling approach,Deep3DSketch-im,which uses a single freehand sketch for *** is a challenging task due to the sparsity and ***3DSketch-im uses a novel data representation called the signed distance field(SDF)to improve the sketch-to-3D model process by incorporating an implicit continuous field instead of voxel or points,and a specially designed neural network that can capture point and local *** experiments are conducted to demonstrate the effectiveness of the approach,achieving state-of-the-art(SOTA)performance on both synthetic and real ***,users show more satisfaction with results generated by Deep3DSketch-im,as reported in a user *** believe that Deep3DSketch-im has the potential to revolutionize the process of 3D modeling by providing an intuitive and easy-to-use solution for novice users.

关键词： Content creation Sketch Three-dimensional(3D)modeling 3D reconstruction Shape from X Artificial intelligence(AI)

来源：评论

学校读者我要写书评

暂无评论

A PSO Improved with Imbalanced Mutation and Task Rescheduling for Task Offloading in End-Edge-Cloud Computing

引用

computer Systems science & engineering 2023年第11期47卷 2259-2274页

作者： Kaili Shao Hui Fu Ying Song Bo Wang Faculty of Engineering Huanghe Science and Technology UniversityZhengzhou 450003China Computer School Beijing Information Science and Technology UniversityBeijing100192China Software Engineering College Zhengzhou University of Light IndustryZhengzhou450001China

To serve various tasks requested by various end devices with different requirements,end-edge-cloud(E2C)has attracted more and more attention from specialists in both academia and industry,by combining both benefits of edge and cloud *** nowadays,E2C still suffers from low service quality and resource efficiency,due to the geographical distribution of edge resources and the high dynamic of network topology and user *** address these issues,this paper focuses on task offloading,which makes decisions that which resources are allocated to tasks for their *** paper first formulates the problem into binary non-linear programming and then proposes a particle swarm optimization(PSO)-based algorithm to solve the *** proposed algorithm exploits an imbalance mutation operator and a task rescheduling approach to improve the performance of *** proposed algorithm concerns the resource heterogeneity by correlating the probability that a computing node is decided to process a task with its capacity,by the imbalance *** task rescheduling approach improves the acceptance ratio for a task offloading solution,by reassigning rejected tasks to computing nodes with available *** simulated experiments are *** the results show that the proposed offloading algorithm has an 8.93%–37.0%higher acceptance ratio than ten of the classical and up-to-date algorithms,and verify the effectiveness of the imbalanced mutation and the task rescheduling.

关键词： Cloud computing edge computing edge cloud task scheduling task offloading particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Implementation of a continuous-time quantum walk on a sparse graph

引用

Physical Review A 2024年第5期110卷 052215-052215页

作者： Zhaoyang Chen Guanzhong Li Lvzhou Li Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou 510006 China

Continuous-time quantum walks (CTQWs) play a crucial role in quantum computing, especially for designing quantum algorithms. However, how to efficiently implement CTQWs is a challenging issue. In this paper, we study the implementation of CTQWs on sparse graphs, i.e., constructing efficient quantum circuits for implementing the unitary operator e−iHt, where H=γA (γ is a constant and A corresponds to the adjacency matrix of a graph). Our result is, for a d-sparse graph with N vertices and evolution time t, we can approximate e−iHt by a quantum circuit with gate complexity (d3∥H∥tNlog2(N))1+o(1), compared to the general Pauli decomposition, which scales like (∥H∥tN4log2(N))1+o(1). For sparse graphs, for instance, d=O(1), we obtain a noticeable improvement. Interestingly, our technique is related to graph decomposition. More specifically, we decompose the graph into a union of star graphs, and correspondingly, the Hamiltonian H can be represented as the sum of some Hamiltonians Hj, where each e−iHjt is a CTQW on a star graph which can be implemented efficiently.

关键词： Quantum algorithms & computation Quantum computation Quantum walks

来源：评论

学校读者我要写书评

暂无评论

Iot monitoring lathe machine performance

引用

Materials Today: Proceedings 2023年 80卷 3570-3574页

作者： Sharma, Rupak Sharma, Rajeev Prabha, Y.B. Rema Devi, S. Saxena, Pankaj Rajasanthosh kumar, T. Department of Computer Applications Faculty of Science& Humanities SRM Institute of Science & Technology NCR Campus Delhi NCR Campus Meerut-Delhi Road Modinagar UP Ghaziabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Vaddeswaram India Department of English School of Liberal Arts and Special Education Kalasalingam Academy of Research and Education Krishnankoil Virudhunagar District India R.B.S. Management Technical Campus Agra India Department of Mechanical Engineering Oriental Institute of Science & Technology Bhopal India

Machines have to operate effectively and free from faults in order to enhance productivity, increase quality, and decrease costs. With automated and flexible action, this is far more likely. An accurate identification of the underlying cause Causes of failure that need repairs and the time for restoration include: A lot of Various monitoring methods are available to track the experimentally-recorded machine health. Maintaining instruments and sensors. The vibration monitoring methods in this list. It is the right fit, and it has shown itself over time. Measuring vibrations in this job three different locations resembling the stock of a gun: headstock, tailstock. When conducting turning operation with mild steel, the tool post of the lathe machine is made of metal. Data that is gathered through sensors is sent straight to the cloud in this case, such as Ubidots IoT platform. via way of nodeMCU. Whether a task is impacted or a tool is impacted, mission failure has occurred. Thus, in either instance, early warning is provided by a signature, thus the development does not progress as quickly machining. If the tail-stock seems to be broken, and this appears to be a consistent problem, then the whole batch must be inspected for errors to be inspected closely is anything that has been created under such circumstances. An optimal decision-making procedure light may be thrown on CM so processes may be machine-wise instituted in a shop there. Tools while talking about lathes that are large, medium, or tiny. Overall it is a method which is easy but yet capable of benefitting people at all levels, from the absolute beginner to experts Floor productivity is aided by training elements that are almost unnecessary. © 2021

关键词： Lathes

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：