检索结果-内蒙古大学图书馆

29th IEEE International Conference on Parallel and distributed Systems, ICPADS 2023

作者： Wang, Min Li, Peng Cheng, Zhang Liu, Wenmao Nie, Lei Bao, Haizhou Liu, Qin Zhang, Kai Wuhan University of Science and Technology School of Computer Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China Nsfocus Technologies Group Co. Ltd China Wuhan University School of Cyber Science and Engineering China

ISBN: (纸本)9798350330717

5G Core network (5GC) employs a Service Based Architecture (SBA). This architecture decomposes the control plane into multiple independent network Functions (NFs). NFs open interfaces to provide services to other NFs, which makes the control plane more susceptible to external malicious attacks. However, existing anomaly detection methods focus more on traffic statistics features and are difficult to apply to the 5GC control plane. In this paper, we proposed GSAD, a Graph-Sequence analysis-based Anomaly Detection method for 5GC control plane traffic. We model control plane traffic as a directed graph to depict topological and NF interaction information. Further, we use the normalizing flows with temporal dependencies to mine the sequential information in the traffic. GSAD combines the topological and sequential information to provide fine-grained detection. We evaluate our proposed framework on the 5GC testbed using Free5GC and UERANSIM in various scenarios. Experimental results demonstrate that our framework outperforms the baselines significantly in terms of detection performance. © 2023 IEEE.

关键词： 5G core network anomaly detection control plane graph neural network normalizing flows

来源：评论

学校读者我要写书评

暂无评论

Comparison of Deep-neural-network-Based Models for Estimating distributed Representations of Compound Words

引用

Procedia Computer Science 2021年 192卷 1294-1303页

作者： An Dao Natthawut Kertkeidkachorn Ryutaro Ichise The University of Tokyo Japan Japan Advanced Institute of Science and Technology Japan National Institute of Informatics Japan National Institute of Advanced Industrial Science and Technology Japan

Word embeddings or word vectors have become fundamental in language processing techniques, especially deep learning approaches. Although many languages have compound words (e.g., “robot arm” and “maple leaf”), such words have not received much attention from researchers. Most research on compound word embeddings considered only two-word compounds; there has been little detailed analysis on the learning representations of arbitrary-length compound words. This paper discusses the necessity for learning-based approaches for estimating the distributed representations of compound words instead of a simple average of the representations of constituents. An evaluation of two downstream tasks confirms the effectiveness of compositional models in encoding useful information into vector spaces. The experimental results suggest that complex architectures such as long short-term memory, gated recurrent units, and transformers learn better representations for long entities, whereas simpler models such as recurrent neural networks are more applicable for downstream tasks where there are only short compounds (two or three words in length), as in the noun compound interpretation task.

关键词： compound word distributional models of semantics multi-word expressions

来源：评论

学校读者我要写书评

暂无评论

Multi-objective biogeography-based optimization and reinforcement learning hybridization for network-on chip reliability improvement

引用

JOURNAL OF PARALLEL AND distributed COMPUTING 2022年 161卷 20-36页

作者： Kadri, Nassima Koudil, Mouloud Ecole Natl Super Informat ESI Lab Methodes Concept Syst LMCS BP 68M Oued Smar 16270 Alger Algeria

Reliability is increasingly a major concern in network-on-a-chip (NoC) design, alongside increased performance demands from new applications and the need for continued miniaturization of silicon technology. In this article, we look at the task migration mechanism, used to recover from permanent processing element (PE) failures in NoCs, by remapping tasks performed on faulty cores to spare ones. An innovative reliability-aware task mapping technique is presented, based on a hybridization between Multi-Objective Optimization (MOO) and Reinforcement Learning (RL). It takes place in two steps. In the first, a set of optimal remapping solutions for different failure scenarios is generated at design-time, using a Biogeography-Based Multi-Objective Optimization algorithm, while considering communication energy and migration costs. In the second step, an artificial neural network agent is trained to select the best remapping solution, from those generated at design-time, to recover from execution failures at run-time. Experiments were carried out to evaluate our technique for different sizes of networks and on different benchmarks. The results obtained show that the technique based on the hybridization MOO_RL brings a great improvement in the reliability of the NoC and achieves a good compromise between reliability and performance. It also guarantees a reduction of the overhead caused by the storage space of the remapping solutions, compared to the existing solutions. (C) 2021 Elsevier Inc. All rights reserved.

关键词： network-on chip Reliability Task migration Spare placement Multi-objective optimization Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection with Graph Attention network for Multimodal IoT Data Monitoring 29

Anomaly Detection with Graph Attention Network for Multimoda...

引用

29th IEEE International Conference on Parallel and distributed Systems, ICPADS 2023

作者： Li, Haoyu Gao, Yi Dong, Wei Zhejiang University College of Computer Science China

ISBN: (纸本)9798350330717

The popularity of the wireless network and the embedded system has promoted the widespread application of the Internet of Things (IoT) monitoring system which detects anomalies for discovering emergency events to avoid losses by deploying various sensors. In the face of anomaly detection algorithms for multi-dimensional data in the IoT monitoring system, the currently popular method is to implement a model based on the graph neural network (GNN). Graph attention network (GAT), a mutant of GNN, is widely used because of the attention mechanism in capturing multi-dimensional nonlinear features between nodes. However, the GAT's weakness in processing complex temporal features leads to the fact that anomalies with distinctive temporal features are hard to detect. In this paper, we propose Time-Series Graph Attention network (TSGAT), an innovative GAT-based model for anomaly detection. Given the simplified attention mechanism of the GAT and its weakness in extracting temporal pattern features, we embed the time-series layer to enhance the ability to process time-series data. In addition, we designed the loss function and anomaly scoring mechanism based on data reconstruction features, multidimensional features, and temporal features. TSGAT achieves the improvement of 7%-8% F1 score on two classical public datasets for IoT monitoring: SWaT and WADI, compared with the state-of-the-art GNN-based anomaly detection model. © 2023 IEEE.

关键词： anomaly detection GAT multimodal IoT data

来源：评论

学校读者我要写书评

暂无评论

A Cascaded Structure for Generalized Graph Filters

引用

IEEE TRANSACTIONS ON SIGNAL processing 2022年 70卷 3499-3513页

作者： Coutino, Mario Leus, Geert Delft Univ Technol Fac Elect Engn Math & Comp Sci NL-2826 CD Delft Netherlands TNO Radar Technol NL-2597 AK The Hague Netherlands

One of the main challenges of graph filters is the stability of their design. While classical graph filters allow for a stable design using optimal polynomial approximation theory, generalized graph filters tend to suffer from the ill-conditioning of the involved system matrix. This issue, accentuated for increasing graph filter orders, naturally leads to very large (small) filter coefficients or error saturation, casting a shadow on the benefits of these richer graph filter structures. In addition to this, data-driven design/learning of graph filters with large filter orders, even in the case of classical graph filters, suffers from the eigenvalue spread of the input data covariance matrix and mode coupling, leading to convergence-related issues as the ones observed when identifying time-domain filters with large orders. To alleviate these conditioning and convergence problems, and to reduce the overall design complexity, in this work, we propose a cascaded implementation of generalized graph filters and an efficient algorithm for designing the graph filter coefficients in both model- and data-driven settings. Further, we establish the connections of this implementation with so-called graph convolutional neural networks and demonstrate the performance of the proposed structure in different network applications. By the proposed approach, further error reduction and better design stability are achieved.

关键词： Time-domain analysis Convergence Signal processing Eigenvalues and eigenfunctions Laplace equations Transforms Iterative methods Cascaded filters distributed optimization graph filtering graph signal processing signal processing on graphs

来源：评论

学校读者我要写书评

暂无评论

Security Analysis of Accounting Computerized Information System based on Data Mining and neural networks

Security Analysis of Accounting Computerized Information Sys...

引用

distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： Yan Wang Xi 'an Mingde Institute of Technology Xi 'an Shaanxi China

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

The security issue of accounting by electronic data processing information systems is a complex system engineering. How to extract useful data from the massive amount of accounting by electronic data processing information and provide decision-making basis for enterprise decision-makers is a key issue. The article is based on data mining and neural network technology, and studies a security analysis method for accounting by electronic data processing information systems based on data mining and neural networks. This method extracts useful information from data and establishes corresponding models through neural networks to identify key factors that affect the security of accounting by electronic data processing information systems. The results show that the average reliability of the accounting computerization information system based on data mining is 84.38%. The average security of the accounting computerization information system based on neural networks is 94.86%. This article combines the two to create a better accounting by electronic data processing information system.

关键词： neural networks Decision making Electric variables measurement distributed databases Data processing Data models Security

来源：评论

学校读者我要写书评

暂无评论

AirPose: Multi-View Fusion network for Aeria 3D Human Pose and Shape Estimation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 4805-4812页

作者： Saini, Nitin Bonetto, Elia Price, Eric Ahmad, Aamir Black, Michael J. Max Planck Inst Intelligent Syst D-72076 Tubingen Germany Univ Stuttgart Inst Flight Mech & Controls Fac Aerosp Engn & Geodesy D-70569 Stuttgart Germany

In this letter, we present a novel markerless 3D human motion capture (MoCap) system for unstructured, outdoor environments that uses a team of autonomous unmanned aerial vehicles (UAVs) with on-hoard RGB cameras and computation. Existing methods are limited by calibrated cameras and off-line processing. Thus, we present the first method (AirPose) to estimate human pose and shape using images captured by multiple extrinsically uncalibrated flying cameras. AirPose itself calibrates the cameras relative to the person instead of relying on any pre-calibration. It uses distributed neural networks running on each UAV that communicate viewpoint-independent information with each other about the person (i.e., their 3D shape and articulated pose). The person's shape and pose are parameterized using the SMPL-X body model, resulting in a compact representation, that minimizes communication between the UAVs. The network is trained using synthetic images of realistic virtual environments, and fine-tuned on a small set of real images. We also introduce an optimization-based post-processing method (AirPose+) for offline applications that require higher MoCap quality. We make our method's code and data available for research at https://***/robot-perception-group/AirPose. A video describing the approach and results is available at https://***/xLYelTNHsfs.

关键词： Aerial systems deep learning for visual perception datasets for human motion human detection and tracking perception and autonomy sensor fusion

来源：评论

学校读者我要写书评

暂无评论

A novel Deep-Learning model for RDTS signal denoising based on graph neural networks

引用

OPTICAL FIBER TECHNOLOGY 2022年 74卷

作者： Wang, Sibo Wang, Honghui Wang, Yiru Wang, Yuhang Zeng, Shangkun Chengdu Univ Technol Key Lab Earth Explorat & Informat Technol Minist Educ Chengdu 610059 Peoples R China Chengdu Univ Technol State Key Lab Geohazard Prevent & Geoenvironm Prot Chengdu 610059 Peoples R China Chengdu Univ Technol Coll Comp Sci & Cyber Secur Dept Artificial Intelligence Chengdu 610059 Peoples R China

Focusing on the problem of increasing the deviation of temperature measurement for Raman-based distributed temperature sensor (RDTS) caused by random noise, a new method of applying a three-layer GraphSAGE-based graph neural network (3L-GraphSAGE) to noise reduction is proposed, where the spatial relationship between each signal is first constructed, and then the effective denoised results are obtained from the developed 3L-GraphSAGE model. First, an experimental setup is built for collecting fiber signals. Then, the datasets are input into the 3L-GraphSAGE to train the model. Finally, the test datasets are input into the well-trained 3L-GraphSAGE model to obtain effective denoised signals. To evaluate the performance of 3L-GraphSAGE, three evaluation indexes are calculated, including maximum deviation (MD), root mean square error (RMSE) and smoothness. The experimental results show that it can efficiently suppress the random noise and reduce the temperature measurement deviation in RDTS compared with direct demodulation of the raw data, and signifi-cantly improve the curve smoothness compared with wavelet transform by soft threshold function (WT-soft) and fast waveform type (FWT). Therefore, 3L-GraphSAGE model can provide an available method for improving the performance of RDTS.

关键词： Raman-based distributed temperature sensor Noise reduction Sensor signal processing GraphSAGE

来源：评论

学校读者我要写书评

暂无评论

Question Classification Method based on Self-Attention Mechanism and BiLSTM-AlexNet Model 29

Question Classification Method based on Self-Attention Mecha...

引用

29th IEEE International Conference on Parallel and distributed Systems, ICPADS 2023

作者： Wang, Yumeng Jia, Yinshan LiaoNing Petrochemical University School of Artificial Intelligence and Software Fushun China

ISBN: (纸本)9798350330717

With the rapid development of Natural Language processing and deep learning algorithms, research and applications based on intelligent question answering have gained widespread attention from researchers and the industry. As the primary step in intelligent question answering, the accuracy of question classification is crucial to answer generation. In order to solve the problems of single model and poor classification performance in Chinese question classification, this paper proposes a question classification model based on self-attention mechanism combined with BiLSTM-AlexNet model (named A-Bi-Al). Firstly, word2vec-based word vector representation is performed, and then the local features of the question text are extracted using convolutional neural network (AlexNet). Secondly,bidirectional long short-term memory network (BiLSTM) is used to extract semantic crrelation information of context to obtain high-level feature expression at the sentence level, then feature weighting is performed through self-attention mechanism to reduce the influence of noise features. Finally, classification is performed through the output layer. In addition, the more smooth and adaptive Mish function is used instead of traditional activation function to enrich local feature representation in AlexNet, BiLSTM, and self-attention layers. Relevant experiments were conducted based on LTP and THUC- News datasets. The experimental results show that the model achieves good performance and can effectively improve the effect of question classification. © 2023 IEEE.

关键词： AlexNet bidirectional long short-term memory network question classification SelfAttention

来源：评论

学校读者我要写书评

暂无评论

24th International Conference on Parallel and distributed Computing, Applications and Technologies, PDCAT 2023

24th International Conference on Parallel and Distributed Co...

引用

24th International Conference on Parallel and distributed Computing, Applications and Technologies, PDCAT 2023

ISBN: (纸本)9789819982103

The proceedings contain 28 papers. The special focus in this conference is on Parallel and distributed Computing, Applications and Technologies. The topics include: Insider Trading Detection Algorithm in Industrial Chain Based on Logistics Time Interval Characteristics;link Attributes Based Multi-service Routing for Software-Defined Satellite networks;A Fuzzy Logical RAT Selection Scheme in SDN-Enabled 5G HetNets;SSR-MGTI: Self-attention Sequential Recommendation Algorithm Based on Movie Genre Time Interval;fine Time Granularity Allocation Optimization of Multiple networks Industrial Chains in Task processing Systems;Ε-Maximum Critic Deep Deterministic Policy Gradient for Multi-agent Reinforcement Learning;effective Density-Based Concept Drift Detection for Evolving Data Streams;an End-to-End Multiple Hyper-parameters Prediction Method for distributed Constraint Optimization Problem;Formalization and Verification of the Zab Protocol Using CSP;dynamic Priority Coflow Scheduling in Optical Circuit Switched networks;Deep Reinforcement Learning Based Multi-WiFi Offloading of UAV Traffic;Triple-Path RNN network: A Time-and-Frequency Joint Domain Speech Separation Model;design of Query Based Gallery Selector and Mask-Aware Loss for Person Search;a Privacy-Preserving Blockchain Scheme for the Reliable Exchange of IoT Data;R-RPT-A Reliable Routing Protocol for Industrial Wireless Sensor networks;action Segmentation Based on Encoder-Decoder and Global Timing Information;Security Challenges and Lightweight Cryptography in IoT: Comparative Study and Testing Method for PRESENT-32bit Cipher;The Prediction Model of Water Level in Front of the Check Gate of the LSTM neural network Based on AIW-CLPSO;Using MPIs Non-Blocking Allreduce for Health Checks in Dynamic Simulations;parallelizable Loop Detection using Pre-trained Transformer Models for Code Understanding;list-Based Workflow Scheduling Utilizing Deep Reinforcement Learning.

关键词：

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：