检索结果-内蒙古大学图书馆

Neural Network Model-Based Control for Manipulator: An autoencoder Perspective

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第6期34卷 2854-2868页

作者： Li, Zhan Li, Shuai Univ Elect Sci & Technol China Sch Automat Engn Chengdu 610054 Peoples R China Swansea Univ Dept Comp Sci Swansea SA2 7QL W Glam Wales Swansea Univ Fac Sci & Engn Swansea SA2 7QL W Glam Wales Swansea Univ Coll Engn Swansea W Glam Wales

Recently, neural network model-based control has received wide interests in kinematics control of manipulators. To enhance learning ability of neural network models, the autoencoder method is used as a powerful tool to achieve deep learning and has gained success in recent years. However, the performance of existing autoencoder approaches for manipulator control may be still largely dependent on the quality of data, and for extreme cases with noisy data it may even fail. How to incorporate the model knowledge into the autoencoder controller design with an aim to increase the robustness and reliability remains a challenging problem. In this work, a sparse autoencoder controller for kinematic control of manipulators with weights obtained directly from the robot model rather than training data is proposed for the first time. By encoding and decoding the control target though a new dynamic recurrent neural network architecture, the control input can be solved through a new sparse optimization formulation. In this work, input saturation, which holds for almost all practical systems but usually is ignored for analysis simplicity, is also considered in the controller construction. Theoretical analysis and extensive simulations demonstrate that the proposed sparse autoencoder controller with input saturation can make the end-effector of the manipulator system track the desired path efficiently. Further performance comparison and evaluation against the additive noise and parameter uncertainty substantiate robustness of the proposed sparse autoencoder manipulator controller.

关键词： Manipulators Neural networks Manipulator dynamics Kinematics Optimization Recurrent neural networks Computational modeling autoencoder manipulator neural network control

来源：评论

学校读者我要写书评

暂无评论

Human Motion Enhancement via Tobit Kalman Filter-Assisted autoencoder

引用

IEEE ACCESS 2022年 10卷 29233-29251页

作者： Lannan, Nate Zhou, Le Fan, Guoliang Oklahoma State Univ Sch Elect & Comp Engn Stillwater OK 74078 USA

We present a novel approach to enhance the quality of human motion data collected by low-cost depth sensors, namely D-Mocap, which suffers from low accuracy and poor stability due to occlusion, interference, and algorithmic limitations. Our approach takes advantage of a large set of high-quality and diverse Mocap data by learning a general motion manifold via the convolutional autoencoder. In addition, the Tobit Kalman filter (TKF) is used to capture the kinematics of each body joint and handle censored measurement distribution. The TKF is incorporated with the autoencoder via latent space optimization, maintaining adherence to the motion manifold while preserving the kinematic nature of the original motion data. Furthermore, due to the lack of an open source benchmark dataset for this research, we have developed an extension of the Berkeley Multimodal Human Action Database (MHAD) by generating D-Mocap data from RGB-D images. The newly extended MHAD dataset is skeleton-matched and time-synced to the corresponding Mocap data and is publicly available. Along with simulated D-Mocap data generated from the CMU Mocap dataset and our self-collected D-Mocap dataset, the proposed algorithm is thoroughly evaluated and compared with different settings. Experimental results show that our approach can improve the accuracy of joint positions and angles as well as skeletal bone lengths by over 50%.

关键词： Manifolds Kinematics Filtering Kalman filters Bones Optimization Deep learning autoencoder human motion manifold depth sensors motion capture Tobit Kalman filter

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based Fault Diagnosis for Grinding System 29

Autoencoder-based Fault Diagnosis for Grinding System

引用

第29届中国控制与决策会议

作者： QU Xing-yu ZENG Peng Fu Dong-dong Xu chengcheng Key Lab of Networked Control System Shenyang Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Northern Heavy Industries Group Co.Itd College of Information Science and Engineering Northeastern University

ISBN: (纸本)9781509046584

At present, most fault diagnosis for grinding system is based on artificial judgments, which is inefficient, low accurate, high cost and easy to cause casualties. The traditional neural network has an unsatisfying performance to predict on high dimensional dataset, and is hard to extract crucial features, which brings about terrible classification results. To solve the above problems, the paper present a deep learning based on autoencoder to realize the intelligent diagnosis for grinding system. The algorithm applies autoencoder to extract features from fault dataset, and transit the non-linearized features to Softmax classification to recognize the fault category. This paper compares autoencoder-based deep learning networks and the traditional BP neural networks in experiments, and it is concluded that the autoencoderbased deep learning outperforms BP networks in the unbalanced classification. The classification precision is up to 92.4% by using the proposed method.

关键词： Fault Diagnosis autoencoder Softmax Classifier Deep Learning

来源：评论

学校读者我要写书评

暂无评论

autoencoder as Feature Extraction Technique for Financial Distress Classification 29th

Autoencoder as Feature Extraction Technique for Financial Di...

引用

29th International Conference on Information and Software Technologies (ICIST)

作者： Kuiziniene, Dovile Savickas, Paulius Krilavicius, Tomas Vytautas Magnus Univ Univ Str 10-202Akad LT-53361 Kaunas Lithuania

ISBN: (纸本)9783031489808;9783031489815

Financial statements are typical financial distress identification data for the enterprise. However, nowadays, the valuable data source characterizing enterprise could be expanded, including data from legal events, macro, industry, government register center, etc. This data creates valuable information, which could lead to more accurate financial distress classification model creation. On the other hand, the new data source involvement expands the dimensional space of features and increases the data sparsity. In order to reduce dimensions and have maximum information retention from the initial data space is used feature extraction techniques. This study uses an autoencoder as a nonlinear feature extraction method. Moreover, we compared several structure composition strategies for autoencoders: 1) all data compress;2) union of the several autoencoders (i.e. data compress of each data type separately and the union of these separate autoencoders). After implementing different autoencoder strategies, eight machine-learning models for financial distress classification were used. The results demonstrated that features retrieved from the union data source strategy outperform the features extracted all at once. These findings create a novelty of autoencoder usage as a feature extraction technique for financial distress key feature's identification and better financial distress issue classification.

关键词： autoencoder Feature extraction Bankruptcy Financial distress

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based One-class Classification Technique for Event Prediction 19

Autoencoder-based One-class Classification Technique for Eve...

引用

4th International Conference on Cloud Computing and Internet of Things (CCIOT) / International Conference on Emerging Networks Technologies (ICENT)

作者： Shin, Seung Yeop Kim, Han-joon Univ Seoul Sch Elect & Comp Engn 163 Seoulsiripdaero Seoul 02504 South Korea

ISBN: (纸本)9781450372411

This paper proposes an autoencoder-based one-class classification technique to predict a specific event such as the occurrence of a fire in a specific building. Basically, a binary classification system that uses machine learning to identify fire-risk buildings requires 'positive' fire data and 'negative' non-fire data. However, the fire-risk building data that can be actually obtained have a single class data that includes only the data of the occurrence of the fire and does not include the data of the 'non-occurrence'. In this situation, PU (Positive-Unlabeled) learning which uses 'unlabeled' data can be an effective way of generating the fire prediction model. The autoencoder generates new features from the unlabeled data, with which a predictive model for predicting the fire-risk buildings is built through PU learning.

关键词： Machine Learning autoencoder Deep Learning One-class Classification Feature Extraction

来源：评论

学校读者我要写书评

暂无评论

autoencoder via DCNN and LSTM Models for Intrusion Detection in Industrial Control Systems of Critical Infrastructures 4

Autoencoder via DCNN and LSTM Models for Intrusion Detection...

引用

IEEE/ACM 4th International Workshop on Engineering and Cybersecurity of Critical Systems (EnCyCriS)

作者： Saheed, Yakub Kayode Misra, Sanjay Chockalingam, Sabarathinam Amer Univ Nigeria Dept Comp Sci Yola Nigeria Ostfold Univ Coll Dept Comp & Commun Halden Norway Inst Energy Technol Dept Risk & Secur Halden Norway

ISBN: (纸本)9798350338140

Industrial Control Systems (ICS) are widely used to carry out the fundamental functions of a society and are frequently employed in Critical Infrastructures (CIs). Consequently, protection against cyber-attacks is essential for these systems. Over the years, numerous cyber-attack detection system concepts have been proposed, each employing a distinct set of processes and methodologies. Despite this, there is a significant gap in the field of techniques for detecting cyber-attacks on ICS. Most existing studies used device logs, which require considerable pre-processing and understanding before they can be utilized for intrusion detection in an ICS environment. In this paper, we proposed an intrusion detection using an autoencoder for feature dimensionality reduction trained on network flow data via a Deep Convolutional Neural Network (DCNN) and Long Short-Term Memory (LSTM), which does not require prior knowledge of the underlying architecture and network's topology. The experimental analysis was performed on the ICS dataset and gas pipeline data given by Mississippi State University (MSU). The LSTM model achieved an accuracy greater than 99% and an AUC-ROC of 99.50% on the ICS data, whereas the DCNN model achieved an accuracy of 96.0% and an AUC-ROC of 97.20% on the gas pipeline network data, with extremely low false negatives and false positives. The results of the study showed that LSTM is superior to DCNN in detecting anomalies in ICS. In addition, the results disclosed that LSTM and DCNN are effective at time series prediction tasks. This observation is encouraging, as DCNN and LSTM are smaller, faster, and more straightforward than the deep neural network and recurrent neural networks utilized in previous research. The proposed IDS architecture is a low-cost, network-based solution that requires minimal processing, performs unsupervised, and is straightforward to implement in a real-world environment.

关键词： autoencoder Critical infrastructures Deep convolution neural network Industrial control systems Intrusion detection system Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based intra prediction with auxiliary feature

Autoencoder-based intra prediction with auxiliary feature

引用

IEEE International Conference on Visual Communications and Image Processing (VCIP)

作者： Xu, Luhang Yu, Yue Yu, Haoping Wang, Dong OPPO Dept Stand Res Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781665475921

A set of autoencoders is trained to perform intra prediction for block-based video coding. Each autoencoder consists of an encoding network and a decoding network. Both encoding network and decoding networks are jointly optimized and integrated into the state-of-the-art VVC reference software VTM-11.0 as an additional intra prediction mode. The simulation is conducted under common test conditions with all intra configurations and the test results show 1.55%, 1.04%, and 0.99% of Y, U, V components Bjontegaard-Delta bit rate saving compared to VTM-11.0 anchor, respectively. The overall relative decoding running time of proposed autoencoder-based intra prediction mode on top of VTM-11.0 are 408% compared to VTM-11.0.

关键词： Intra prediction video coding autoencoder neural networks

来源：评论

学校读者我要写书评

暂无评论

autoencoder based Friendly Jamming

Autoencoder based Friendly Jamming

引用

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Bui Minh Tuan Ta Duc Tuyen Nguyen Linh Trung Nguyen Viet Ha Vietnam Natl Univ VNU Univ Engn & Technol AVITECH Hanoi Vietnam Univ Technol Sydney Sch Elect & Data Engn Sydney NSW Australia Vietnam Acad Mil Sci & Technol Hanoi Vietnam

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131061

Physical layer security (PLS) provides lightweight security solutions in which security is achieved based on the inherent random characteristics of the wireless medium. In this paper, we consider the PLS approach called friendly jamming (FJ), which is more practical thanks to its low computational complexity. State-of-the-art methods require that legitimate users have full channel state information (CSI) of their channel. Thanks to the recent promising application of the autoencoder (AE) in communication, we propose a new FJ method for PLS using AE without prior knowledge of the CSI. The proposed AE-based FJ method can provide good secrecy performance while avoiding explicit CSI estimation. We also apply the recently proposed tool for mutual information neural estimation (MINE) to evaluate the secrecy capacity. Moreover, we leverage MINE to avoid end-to-end learning in AE-based FJ.

关键词： Physical layer security autoencoder friendly jamming wiretap channel mutual information neural estimation

来源：评论

学校读者我要写书评

暂无评论

autoencoder and Matching-based Resource Allocation Scheme for D2D Communication

Autoencoder and Matching-based Resource Allocation Scheme fo...

引用

IEEE International Conference on Communications (IEEE ICC)

作者： Rathod, Tejal Tanwar, Sudeep Nirma Univ Inst Technol Dept Comp Sci & Engn Ahmadabad Gujarat India

ISBN: (纸本)9798350333077

A fifth-generation (5G) mobile network facilitates key enable technology for future communication systems known as device-to-device (D2D) communication, where two nearby devices communicate with each other without any involvement of the base station (BS). Here, the device's physical proximity establishes a communication link that enhances the system's spectral efficiency. However, it faces interference issues from the other device. In this paper, we proposed an efficient resource allocation scheme using a matching theory-based Hungarian algorithm. We resolve the random weight selection (when they are the same consecutive weight) issue in the Hungarian algorithm using a vanilla autoencoder. For the performance evaluation of the adopted scheme, we considered different parameters such as loss function, accuracy, and sum rate. The simulation results reveal the proposed autoencoder scheme recreates original input data with minimum reconstruction loss with 88% accuracy. Further, the Hungarian algorithm efficiently allocates D2D resources by maximizing the system's overall sum rate.

关键词： D2D communication Artificial intelligence Resource allocation autoencoder Hungarian algorithm

来源：评论

学校读者我要写书评

暂无评论

autoencoder performance analysis with adaptive and trainable activation function to compress images 8

Autoencoder performance analysis with adaptive and trainable...

引用

IEEE Latin American Conference on Computational Intelligence (LA-CCI)

作者： De Medeiros Delgado, Joao Henrique Ferreira, Tiago A. E. Univ Fed Rural Pernambuco UFRPE Dept Estatistia & Informat Recife PE Brazil

ISBN: (数字)9781665488587

ISBN: (纸本)9781665488587

Activation functions are essential keys to good performance in a neural network. Many functions can be used, and the choice of which one to use depends on the issues addressed. New adaptable and trainable activation functions have been studied lately, which are used to increase network performance. This study intends to evaluate the performance of an artificial neuron that uses adaptive and trainable functions in an autoencoder network for image compression problems. The tested neuron, known as Global-Local Neuron, comprises two complementary components, one with global characteristics and the other with local characteristics. The global component is given by a sine function and the local component by the hyperbolic tangent function. The experiment was carried out in two stages. In the first one, different activation functions, GLN, Tanh, and Sine, were tested in an MLP-type autoencoder neural network model. Different compression ratios were considered when varying the size of the autoencoder bottleneck layer, and 48 samples were obtained for each value of this layer. The metrics used for the evaluation were the loss value obtained in the test set and the number of epochs necessary to reach a stopping criterion. In the second step, the classification accuracy of the images compressed by the encoder block of the previous model was evaluated, using a Wide Residual Networks (WRN) network and the Support Vector Machines (SVM) method. The results obtained indicated that the use of Global-Local Neuron improved the network training speed, obtained better classification accuracy for compression up to 50% in a WRN network, and proved the adaptability in image classification problems.

关键词： activation functions autoencoder neural network

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：