检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Zhou, Hao Guo, Xuanru Ji, Mingcheng Jiang, Jielin Xiang, Haolong Xue, Shengjun University of Science and Technology Beijing Beijin China Nanjing University of Information Science and Technology Nanjing China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services China Silicon Lake College Suzhou China

ISBN: (纸本)9798331509712

Anomaly detection is a critical aspect of industrial production processes. Most of the self-supervised training system utilise Convolutional neural networks (CNNs) for feature extraction. However, these methods often exhibit poor detection performance on small structural anomalies due to the limited receptive field of CNN. The prompt learning method has been demonstrated to be an effective means of enhancing the global information extraction abilities of the model. However, this approach necessitates the input of a significant number of manual prompts. To address these issues, we propose a Memory And Prompt Learning Based network (MPLNet) for anomaly detection. MPLNet obtains the differences information between normal and detected images by comparing their features and then uses these differences to generate prompts. By automatically generating prompts, it reduces the workload of manually entering prompts in prompt learning. At the same time, it effectively enhances the model's ability to extract and use global information. Extensive experiments have shown that the proposed MPLNet achieves state-of-the-art anomaly detection performance on the widely used and challenging MVTec AD dataset and MVTec AD-3D dataset. Index Terms - Anomaly detection, U-Net, Transformer, Prompt, artificial intelligence System © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Lower Bounds and Nearly Optimal Algorithms in distributed Learning with Communication Compression 36

Lower Bounds and Nearly Optimal Algorithms in Distributed Le...

引用

36th Conference on neural Information processing Systems (NeurIPS)

作者： Huang, Xinmeng Chen, Yiming Yin, Wotao Yuan, Kun Univ Penn Philadelphia PA USA Alibaba Grp DAMO Acad Hangzhou Peoples R China MetaCarbon New York NY USA Peking Univ Beijing Peoples R China

ISBN: (纸本)9781713871088

Recent advances in distributed optimization and learning have shown that communication compression is one of the most effective means of reducing communication. While there have been many results for convergence rates with compressed communication, a lower bound is still missing. Analyses of algorithms with communication compression have identified two abstract properties that guarantee convergence: the unbiased property or the contractive property. They can be applied either unidirectionally (compressing messages from worker to server) or bidirectionally. In the smooth and non-convex stochastic regime, this paper establishes a lower bound for distributed algorithms whether using unbiased or contractive compressors in unidirection or bidirection. To close the gap between this lower bound and the best existing upper bound, we further propose an algorithm, NEOLITHIC, that almost reaches our lower bound (except for a logarithm factor) under mild conditions. Our results also show that using contractive compressors in bidirection can yield iterative methods that converge as fast as those using unbiased compressors unidirectionally. We report experimental results that validate our findings.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Predicting Temperature of Molten Steel in LF-Refining Process Using IF-ZCA-DNN Model

引用

METALLURGICAL AND MATERIALS TRANSACTIONS B-PROCESS METALLURGY AND MATERIALS processing SCIENCE 2023年第3期54卷 1181-1194页

作者： Xin, Zi-Cheng Zhang, Jiang-Shan Zhang, Jun-Guo Zheng, Jin Jin, Yu Liu, Qing Univ Sci & Technol Beijing State Key Lab Adv Met Beijing Peoples R China Hebei Iron & Steel Co Ltd Tangshan Branch Tangshan Hebei Peoples R China

Controlling the temperature of molten steel in ladle furnace (LF)-refining process is one of the main tasks to ensure that the steelmaking-continuous casting process runs smoothly. In this work, a hybrid model based on metallurgical mechanism, isolation forest (IF), zero-phase component analysis whitening (ZCA whitening), and a deep neural network (DNN) was established to predict the temperature of molten steel in LF-refining process. The metallurgical mechanism, Pearson correlation coefficient, ZCA whitening, IF, and t-distributed stochastic neighbor embedding (t-SNE) were used to obtain the main factors affecting the temperature, analyze the correlation between two random variables, eliminate the correlation among the input variables, reduce the abnormal data of the original datasets, and visualize high-dimensional data, respectively. The single-machine-learning (ML) models, ZCA-ML models, and IF-ZCA-DNN model were comparatively examined by evaluating the coefficient of determination (R-2), root-mean-square error (RMSE), mean absolute error (MAE), and hit ratio. The optimal structure of IF-ZCA-DNN model had 4 hidden layers, 45 hidden layer neurons, a learning rate of 0.03, regularization coefficient of 2 x 10(-4), batch size of 128, leaky-rectified linear unit activation function, and an optimization algorithm of mini-batch stochastic gradient descent with momentum. The R-2, RMSE, and MAE of the IF-ZCA-DNN model were 0.916, 2.827, and 2.048, respectively. Meanwhile, the prediction hit ratio for the temperature of IF-ZCA-DNN model in the error ranges of [- 3, 3], [- 5, 5], and [- 10, 10] were 77.9, 92.3, and 99.6 pct, respectively. This study will be beneficial to realize precise control of temperature of molten steel in LF-refining process.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Enabling Variable High Spatial Resolution Retrieval From a Long Pulse BOTDA Sensor

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第2期10卷 1813-1821页

作者： Ge, Zhao Shen, Li Zhao, Can Wu, Hao Zhao, Zhiyong Tang, Ming Huazhong Univ Sci & Technol Sch Opt & Elect Informat Wuhan 430074 Peoples R China

resolution (SR) is one of the most important parameters of Brillouin optical time-domain analysis (BOTDA) sensors, which determines the minimum length that a perturbation event can be distinguished. In the field of Internet of Things (IoT), there is an urgent need for sensors with large-scale high-precision sensing capability for scenarios, such as intelligent monitoring of production lines and urban infrastructure. Conventionally, the SR is normally restricted to be longer than 1 m due to the similar to 10-ns acoustic lifetime limitation in silica optical fibers. For long-distance smart monitoring systems, the SR is generally on the order of several meters or even worse. However, it does not meet the needs of many applications. Therefore, there is an urgent need to achieve SR in the submeter magnitude. In this work, for the first time to the best of our knowledge, we propose a convolutional neural network (CNN) to process the data of conventional BOTDA sensors, which achieves unprecedented performance improvement that allows to directly retrieve submeter SR from the sensing system that use long pump pulses. By using the simulated Brillouin gain spectrums (BGSs) as the CNN input and the corresponding high SR Brillouin frequency shift (BFS) as the output target, the trained CNN is able to obtain an SR higher than the theoretical value determined by the pump pulse width. In the experiment, the CNN accurately retrieves 0.5-m hotspots from the measured BGS with pump pulses from 20 to 50 ns, and the acquired BFS is in great agreement with 45/40 ns differential pulse-width pair (DPP) measurement results. Compared with the DPP technique, the proposed CNN demonstrates a twofold improvement in BFS uncertainty with only half the measurement time. In addition, by changing the training data sets, the proposed CNN can obtain tunable high SR retrieval based on conventional BOTDA sensors that use long pulses without any requirement of hardware modifications. It is worth mentioning

关键词： Brillouin scattering convolutional neural network (CNN) distributed optical fiber sensors signal processing

来源：评论

学校读者我要写书评

暂无评论

EdgeShield: Hybrid Real-Time Attack Detection in IOTA Tangle via Edge Devices 15

EdgeShield: Hybrid Real-Time Attack Detection in IOTA Tangle...

引用

15th International Conference on Computing Communication and networking Technologies, ICCCNT 2024

作者： Arunodhai, V. Susan, Leena P. Kannimoola, Jinesh M. Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Applications Amritapuri India

ISBN: (纸本)9798350370249

The Internet of Things (IoT) revolutionizes technology interaction by enabling seamless connectivity and automation, but it introduces significant security challenges. A distributed ledger technology (DLT) called IOTA Tangle, a utilizing a Directed Acyclic Graph (DAG), enables secure and feeless transactions among IoT devices. Despite its advantages, the IOTA Tangle faces threats such as replay attacks and double spending, which highlight vulnerabilities in distributed ledger technologies. To address these security concerns, we initially developed EdgeGuard, a rule-based system for spam detection within the IOTA ecosystem. However, its reliance on predetermined rulesets limited its adaptability. We have now enhanced our approach with EdgeShield, incorporating a neural network for superior threat *** enhances adaptability over EdgeGuard in threat detection for the IOTA Tangle by integrating machine learning. EdgeShield analyzes network packets to identify threats, leveraging machine learning to adapt to evolving risks. Trained using the MQTTSet dataset, it detects network-based threats such as denial-of-service (DoS) attacks and packet flooding. Tested with simulated IoT data, EdgeShield demonstrates effectiveness across various domains, particularly in healthcare IoT. Its decentralized processing on edge devices like the Raspberry Pi 4 enables immediate network traffic analysis, reducing reliance on centralized servers and improving system resilience. Additionally, real-time alerts empower administrators to proactively secure IoT deployments and maintain transaction integrity within the IOTA Tangle. This paper traces our research evolution from EdgeGuard to EdgeShield, highlighting advancements and demonstrating the enhanced security of IoT transactions on the IOTA Tangle. © 2024 IEEE.

关键词： and Decentralised Security Measures distributed Ledger Edge Computing Edge Devices Internet of Things (IoT) IOTA Tangle Machine Learning network Packet Analysis Real-Time Security

来源：评论

学校读者我要写书评

暂无评论

Task Partitioning and Offloading in DNN-Task Enabled Mobile Edge Computing networks

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2023年第4期22卷 2435-2445页

作者： Gao, Mingjin Shen, Rujing Shi, Long Qi, Wen Li, Jun Li, Yonghui Chinese Acad Sci Inst Comp Technol Beijing 100864 Peoples R China Beijing Key Lab Mobile Comp & Pervas Device Beijing 100190 Peoples R China Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Nanjing Univ Sci & Technol Sch Elect & Opt Engn Nanjing Peoples R China China Telecom Res Inst Beijing Peoples R China Univ Sydney Camperdown NSW Australia

Deep neural network (DNN)-task enabled mobile edge computing (MEC) is gaining ubiquity due to outstanding performance of artificial intelligence. By virtue of characteristics of DNN, this paper develops a joint design of task partitioning and offloading for a DNN-task enabled MEC network that consists of a single server and multiple mobile devices (MDs), where the server and each MD employ the well-trained DNNs for task computation. The main contributions of this paper are as follows: First, we propose a layer-level computation partitioning strategy for DNN to partition each MD's task into the subtasks that are either locally computed at the MD or offloaded to the server. Second, we develop a delay prediction model for DNN to characterize the computation delay of each subtask at the MD and the server. Third, we design a slot model and a dynamic pricing strategy for the server to efficiently schedule the offloaded subtasks. Fourth, we jointly optimize the design of task partitioning and offloading to minimize each MD's cost that includes the computation delay, the energy consumption, and the price paid to the server. In particular, we propose two distributed algorithms based on the aggregative game theory to solve the optimization problem. Finally, numerical results demonstrate that the proposed scheme is scalable to different types of DNNs and shows the superiority over the baseline schemes in terms of processing delay and energy consumption.

关键词： Task analysis Servers Delays Computational modeling Energy consumption Resource management Pricing Deep neural networks mobile edge computing task partitioning and offloading aggregative game

来源：评论

学校读者我要写书评

暂无评论

Multi-Head Self-Attention Enhanced Convolutional neural network for Driver Fatigue Detection using EEG Signals 21

Multi-Head Self-Attention Enhanced Convolutional Neural Netw...

引用

21st IEEE International Symposium on Parallel and distributed processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Gao, Kai Jia, Wenhao Zhou, Yuxiang Du, Ronghua Changsha University of Science &technology College of Automotive and Mechanical Engineering Changsha China

ISBN: (纸本)9798350329223

Extended periods or intensive sessions of driving can lead to driver fatigue, affecting not just their reaction time and decision-making capacity, but also resulting in diminished concentration and potential episodes of drowsiness or even falling asleep. In response to this challenge, we have developed a convolutional neural network model incorporating a multi-head self-attention mechanism. To quantify the relationship between electroencephalogram (EEG) signals and driver fatigue, we commence by collecting raw EEG data from 40 channels in the brain using an EEG device. Subsequently, we apply filtering to the raw signals to eliminate physiological disturbances like electrocardiogram signals and non-physiological interferences such as power frequency noise. Thereafter, we employ continuous wavelet transform to extract α and β signals from the EEG data, along with features like spectral entropy, sample entropy, and fuzzy entropy from distinct subbands. Finally, we employ a convolutional neural network featuring a multi-head self-attention mechanism for classification. Additionally, we compare the performance of this model against existing classification methods, validating its efficacy. Our results demonstrate that this model can serve as an effective means for detecting driver fatigue, achieving an average accuracy of 98.3% across both testing and validation datasets. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

WDMoE: Wireless distributed Large Language Models with Mixture of Experts

WDMoE: Wireless Distributed Large Language Models with Mixtu...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Xue, Nan Sun, Yaping Chen, Zhiyong Tao, Meixia Xu, Xiaodong Qian, Liang Cui, Shuguang Zhang, Ping Shanghai Jiao Tong University Cooperative Medianet Innovation Center Shanghai200240 China Peng Cheng Laboratory Department of Broadband Communication Shenzhen518000 China Shenzhen518172 China Beijing University of Posts and Telecommunications Beijing100876 China Shenzhen518172 China

ISBN: (纸本)9798350351255

Large Language Models (LLMs) have achieved significant success in various natural language processing tasks, but how wireless networks can support LLMs has not been extensively studied. In this paper, we propose a wireless distributed LLMs paradigm based on Mixture of Experts (MoE), named WDMoE, through server-device collaboration at the wireless network edge. Specifically, we decompose the MoE layer in LLMs by deploying the gating network and the preceding neural network layer at the edge server of the base station (BS), while distributing the expert networks across the mobile devices. This arrangement leverages the parallel capabilities of expert networks on distributed devices. Moreover, to overcome the instability of wireless communications, we design an expert selection policy by taking into account both the performance of the model and the end-to-end latency, which includes both transmission delay and inference delay. Evaluations conducted across various LLMs and multiple datasets demonstrate that WDMoE not only outperforms existing models, such as Llama 2 with 70 billion parameters, but also significantly reduces end-to-end latency. © 2024 IEEE.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

A Review of Machine Learning Methods for IoT network-Centric Anomaly Detection 47

A Review of Machine Learning Methods for IoT Network-Centric...

引用

47th International Conference on Telecommunications and Signal processing, TSP 2024

作者： Nag, Anindya Hassan, Md. Mehedi Mandal, Dishari Chand, Nisarga Islam, Md Babul Meena, V.P. Benedetto, Francesco Khulna University Computer Science and Engineering Discipline Khulna9208 Bangladesh Adamas University Department of Cse Kolkata India University of Calabria Department of Dimes Cosenza Italy Amrita School of Engineering Amrita Vishwa Vidyapeetham Dept of Eee Bangalore India University of Roma Tre SP4TE - Laboratory Economics Department Via Silvio D'Amico 77 Rome00145 Italy

ISBN: (纸本)9798350365597

Anomaly detection in IoT infrastructure is a growing idea in the IoT area. The IoT enables the linking of many devices through the use of wireless and mobile communication technologies. Data received from distributed sensing devices in a certain location is relayed to a central processing center, where it is collected and processed. Data dependability and the quality of IoT services are strongly related. To discover abnormalities, one alternative is to employ Machine Learning (ML) models that have been trained on both normal and aberrant behavior. Only a few are the methods effectively used to discover and evaluate anomalous data with varying degrees of success including Artificial neural networks (ANN), Support Vector Machine (SVM), Long Short-Term Memory (LSTM), Convolutional neural networks (CNN), and the Unsupervised Machine Learning. The findings of the study indicate that, with an accuracy of 99.87%, Unsupervised Machine Learning exceeds the other strategies in terms of performance. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive ResNet Architecture for distributed Inference in Resource-Constrained IoT Systems 19

Adaptive ResNet Architecture for Distributed Inference in Re...

引用

19th IEEE International Wireless Communications and Mobile Computing (IEEE IWCMC)

作者： Khan, Fazeela Mazhar Baccour, Emna Erbad, Aiman Hamdi, Mounir Hamad Bin Khalifa Univ Qatar Fdn Coll Sci & Engn Doha Qatar

ISBN: (纸本)9798350333398

As deep neural networks continue to expand and become more complex, most edge devices are unable to handle their extensive processing requirements. Therefore, the concept of distributed inference is essential to distribute the neural network among a cluster of nodes. However, distribution may lead to additional energy consumption and dependency among devices that suffer from unstable transmission rates. Unstable transmission rates harm real-time performance of IoT devices causing low latency, high energy usage, and potential failures. Hence, for dynamic systems, it is necessary to have a resilient DNN with an adaptive architecture that can downsize as per the available resources. This paper presents an empirical study that identifies the connections in ResNet that can be dropped without significantly impacting the model's performance to enable distribution in case of resource shortage. Based on the results, a multi-objective optimization problem is formulated to minimize latency and maximize accuracy as per available resources. Our experiments demonstrate that an adaptive ResNet architecture can reduce shared data, energy consumption, and latency throughout the distribution while maintaining high accuracy.

关键词： optimization distributed inference neural networks resilience ResNet

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：