检索结果-内蒙古大学图书馆

An adversarial contrastive autoencoder for robust multivariate time series anomaly detection

EXPERT SYSTEMS WITH APPLICATIONS 2024年 245卷

作者： Yu, Jiahao Gao, Xin Zhai, Feng Li, Baofeng Xue, Bing Fu, Shiyuan Chen, Lingli Meng, Zhihang Beijing Univ Posts & Telecommun Sch Artificial intelligence Beijing 100876 Peoples R China Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China China Elect Power Res Inst Co Ltd Beijing 100192 Peoples R China

Multivariate time series (MTS), whose patterns change dynamically, often have complex temporal and dimensional dependence. Most existing reconstruction-based MTS anomaly detection methods only learn the point-wise information while ignoring the overall trend of time series, resulting in their incompetence in extracting high-level semantic information. Although a few contrastive learning-based approaches have been proposed recently to solve this problem, they forcibly increase the difference between the features of normal data, leading to the loss of useful information. This paper proposes an adversarial contrastive autoencoder (ACAE) for MTS anomaly detection. ACAE conducts feature combination and decomposition as the contrastive learning proxy task, which introduces adversarial training to learn the transformation-invariant representation of data, achieving a robust representation of MTS. Firstly, ACAE constructs positive and negative sample pairs through the multi-scale timestamp mask and random sampling. Secondly, the features of the original samples are combined with those of the positive and negative samples to generate the positive and negative composite features. Finally, ACAE trains the encoder and discriminator to decompose the negative composite features cooperatively to decrease the similarity between the features of negative pairs. In contrast, it adversarially decomposes the positive composite features to increase the similarity between the features of positive pairs. Experimental results show that ACAE outperforms 14 state-of-the-art baselines on five real-world datasets from different fields.

关键词： Multivariate time series Anomaly detection autoencoder Contrastive learning Adversarial training Feature combination and decomposition

来源：评论

学校读者我要写书评

暂无评论

GRAPH LEARNING BASED autoencoder FOR HYPERSPECTRAL BAND SELECTION 47

GRAPH LEARNING BASED AUTOENCODER FOR HYPERSPECTRAL BAND SELE...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Zhang, Yongshan Wang, Xinxin Wang, Zhenyu Jiang, Xinwei Zhou, Yicong China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China Univ Macau Dept Comp & Informat Sci Macau 999078 Peoples R China

ISBN: (纸本)9781665405409

Hyperspectral band selection aims to identify an optimal subset of bands from hyperspectral images (HSIs). Most existing methods explore the relationships between pair-wise pixels in a fixed graph. However, the quality of the initial fixed graph may be influenced by noises and user-defined parameters that may not be optimal for HSI analysis. In this paper, we propose a graph learning based autoencoder (GLAE) to achieve unsupervised hyperspectral band selection. Using the relationships of pair-wise pixels within HSIs, GLAE constructs the initial graph to characterize the geometric structures of HSIs and then adjusts the graph to adapt the band selection process. To solve the proposed model, we intoduce an alternative optimization algorithm. Experiments and comparisons on three HSI datasets demonstrate that the proposed GLAE achieves better results over the state-of-the-art methods.

关键词： Hyperspectral image band selection autoencoder graph learning

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Toward Feature Reconstruction using Huber Conditional Variational autoencoder 36

Intrusion Detection Toward Feature Reconstruction using Hube...

引用

36th International Conference on Information Networking (ICOIN)

作者： Razafimahatratra, Fenohasina Lova Rakotomandimby, Miora Fifaliana Wajira, Prasad De Silva Wuhan Univ Technol Sch Informat Engn Wuhan Peoples R China Boroughmarkets Sydney NSW Australia

ISBN: (纸本)9781665413329

autoencoder is recently one of the widely used machine learning approaches where the network is trained to learn the data representation. This paper considers autoencoder for Feature Reconstruction in Intrusion Detection System. Two networks are used to form an autoencoder;the left part, an Encoder network used to learn and compress data in order to reduce feature dimension, and the right part Decoder network, which can be used to reconstruct content into its original format instead of categorizing the data. However, the ability to approximate data reconstructed to the original one in an accurate manner is still a challenging process. Thus, we propose a Conditional Variational autoencoder with an adaptive loss function named Adaptive Huber CVAE (AH-CVAE). We replace the classical reconstruction loss function with a flexible loss function in order to minimize reconstruction error. Then, this approach is proposed to make an optimal estimation of Intrusion Detection data and achieve an accurate approximation. We conduct our experiment on two datasets, NSL-KDD and UNSW-NB15 Dataset, and compare results with other existing approaches. AH-CVAE can better approximate the original and the reconstructed feature in the intrusion detection dataset.

关键词： Feature Reconstruction Dimensionality reduction autoencoder Conditional Variational autoencoder Intrusion Detection

来源：评论

学校读者我要写书评

暂无评论

DEEP LEARNING OF RADIATIVE ATMOSPHERIC TRANSFER WITH AN autoencoder 12

DEEP LEARNING OF RADIATIVE ATMOSPHERIC TRANSFER WITH AN AUTO...

引用

12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)

作者： Basener, A. Abigail Basener, B. Bill Virginia Mil Inst Student in Appl Math Lexington VA USA Univ Virginia Sch Data Sci Charlottesville VA USA

ISBN: (数字)9781665470698

ISBN: (纸本)9781665470698

As electro-optical energy from the sun propagates through the atmosphere it is affected by radiative transfer effects including absorption, emission, and scattering. Modeling these affects is essential for scientific remote sensing measurements of the earth and atmosphere. For example, hyperspectral imagery is a form of digital imagery collected with many, often hundreds, of wavelengths of light in pixel. The amount of light measured at the sensor is the result of emitted sunlight, atmospheric radiative transfer, and the reflectance off the materials on the ground, all of which vary per wavelength resulting from multiple physical phenomena. Therefore measurements of the ground spectra or atmospheric constituents requires separating these different contributions per wavelength. In this paper, we create an autoencoder similar to denoising autoencoders treating the atmospheric affects as 'noise' and ground reflectance as truth per spectrum. We generate hundreds of thousands of training samples by taking random samples of spectra from laboratory measurements and adding atmospheric affects using physics-based modelling via MOD-TRAN (http://***/modtran_home) by varying atmospheric inputs. This process ideally could create an autoencoder that would separate atmospheric effects and ground reflectance in hyperspectral imagery, a process called atmospheric compensation which is difficult and time-consuming requiring a combination of heuristic approximations, estimates of physical quantities, and physical modelling. While the accuracy of our method is not as good as other methods in the field, this an important first step in applying the growing field of deep learning of physical principles to atmospheric compensation in hyperspectral imagery and remote sensing.

关键词： Machine Learning Deep Learning autoencoder Radiative Transfer Atmospheric Compensation

来源：评论

学校读者我要写书评

暂无评论

Atypical Sample Regularizer autoencoder for Cross-Domain Human Activity Recognition

引用

INFORMATION SYSTEMS FRONTIERS 2021年第1期23卷 71-80页

作者： Prabono, Aria Ghora Yahya, Bernardo Nugroho Lee, Seok-Lyong Hankuk Univ Foreign Studies 81 Oedae Ro Yongin 17035 Gyeonggi Do South Korea

The sensor-based human activity recognition (HAR) using machine learning requires a sufficiently large amount of annotated data to realize an accurate classification model. This requirement stimulates the advancement of the transfer learning research area that minimizes the use of labeled data by transferring knowledge from the existing activity recognition domain. Existing approaches transform the data into a common subspace between domains which theoretically loses information, to begin with. Besides, they are based on the linear projection which is bound to linearity assumption and its limitations. Some recent works have already incorporated nonlinearity to find a latent representation that minimizes domain discrepancy based on an autoencoder that includes statistical distance minimization. However, such approach discovers latent representation for both domains at once, which causes sub-optimal representation because both domains compensate each other's reconstruction error during the training. We propose an autoencoder-based approach on domain adaptation for sensor-based HAR. The proposed approach learns a latent representation which minimizes the discrepancy between domains by reducing statistical distance. Instead of learning representation of both domains simultaneously, our method is a two-phase approach which first learns the representation for the domain of interest independently to ensure its optimality. Subsequently, the useful information from the existing domain is transferred. We test our approach on the publicly available sensor-based HAR datasets, using cross-domain setup. The experimental result shows that our approach significantly outperforms the existing ones.

关键词： Transfer learning autoencoder Human activity recognition Machine learning

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based Malware Analysis: An Imagery Analysis Approach to Enhance the Security of Smart City IoT 23

Autoencoder-based Malware Analysis: An Imagery Analysis Appr...

引用

Proceedings of the 2023 2nd International Symposium on Computing and Artificial Intelligence

作者： Huiyao Dong Igor Kotenko Faculty of information security ITMO University Russia Federation Research laboratory of computer security problems SPC RAS Russia Federation

ISBN: (纸本)9798400708954

Abstract. Smart Cities, the modern digital urban landscapes, are primarily facilitated by the Internet of Things (IoT) infrastructures for information communication. Despite Smart Cities' benefits, risks revolving around data privacy and security within the IoT sphere raise concern. Particularly, malware attacks significantly threaten IoT systems, demanding proactive research into malware prevention techniques. This paper presents a study on autoencoder (AE)-based methodologies for efficient imagery analysis-based malware classification, aiming to enhance the Smart Cities IoT security. It focuses on effective malware classification utilizing various AE structures applied to grayscale or RGB malware derived images, contributing to improved malware detection and analysis. We conduct experiments with different input shapes and multi-label classification output to ascertain the robustness and generalizability of the proposed method. By analysing the classification capabilities of different AE types, we prove that variational AE built with convolutional neural network can achieve effective malware imagery classification in Smart City IoT environments.

关键词： autoencoder IoT Malware analysis Smart city

来源：评论

学校读者我要写书评

暂无评论

Graph t-SNE multi-view autoencoder for joint clustering and completion of incomplete multi-view data

引用

KNOWLEDGE-BASED SYSTEMS 2024年 284卷

作者： Li, Ao Feng, Cong Xu, Shibiao Cheng, Yuan Harbin Univ Sci & Technol Sch Comp Sci & Technol Heilongjiang 150080 Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing 100876 Peoples R China

In recent years, incomplete multi-view clustering has attracted much attention and achieved promising performances through the use of deep learning. However, only a few prior methods are concerned with joint missing data recovery and clustering. In this paper, we present a graph t-SNE multi-view autoencoder (GTSNEMvAE) for this task. We formulate the view completion problem as a multi-view multivariate regression and reconsider the autoencoder for this task. First, a multi-view encoder augmented with graph-convolutional layers and the t-SNE regularization loss extracts unified representations from incomplete multi-view features. Then, the representations are fed into view-specific decoders to regress the features of views, through which the missing views are recovered. Notably, the unified representations learned by our model are cluster-friendly. Our simple method achieves competitive clustering performances on 9 challenging public benchmarks while keeping a stable training process and hyperparameter insensitivity.

关键词： Incomplete multi-view clustering Data recovery autoencoder Graph t-SNE

来源：评论

学校读者我要写书评

暂无评论

Surface defect detection of stay cable sheath based on autoencoder and auxiliary anomaly location

引用

ADVANCED ENGINEERING INFORMATICS 2024年 62卷

作者： Liu, Qi He, Deqiang Shen, Yixin Lao, Zhenpeng Ma, Rui Li, Jianhui Guangxi Univ Sch Mech Engn Guangxi Key Lab Mfg Syst & Adv Mfg Technol Nanning 530004 Peoples R China Guangxi Acad Sci Inst Adv Equipment Mfg Nanning 530007 Peoples R China

As the critical protection component of stay cables, the stay cable sheath's reliability relates to cable-stayed bridges' operation safety. Due to the scarcity of defect samples, the subtlety of defect characteristics, and the high annotation cost in the actual industrial scene, existing methods are still challenging in automating the stay cable sheath's surface defect detection. To solve these problems, a semi-supervised deep learning method based on autoencoder and assisted anomaly location (AEAL) is proposed. The defect detection and localization task can be performed end-to-end with only normal samples used for training. The model learns the differences between normal and abnormal samples by constructing effective positive and negative sample pairs. Meanwhile, it fuses and fine-adjusts image features in combination with the proposed auxiliary anomaly location module and multi- scale feature fusion module, thereby achieving accurate location of defects. The experimental results demonstrate that AEAL outperforms other advanced unsupervised and semi-supervised defect detection networks, yielding superior defect location results. It achieves the highest pixel-level detection accuracy in the dataset of stay cable sheath surfaces, making it well-suited for practical applications.

关键词： Stay cable Image defect detection Semi-supervised deep learning autoencoder Anomaly location

来源：评论

学校读者我要写书评

暂无评论

An Integration of TextGCN and autoencoder into Aspect-Based Sentiment Analysis 1

引用

24th International Conference on Big Data Analytics and Knowledge Discovery (DaWaK)

作者： Tsai, Yi-Hang Chang, Chia-Ming Chen, Kun-Hsiang Hwang, San-Yih Natl Sun Yat Sen Univ Dept Informat Management Kaohsiung Taiwan

ISBN: (数字)9783031126703

ISBN: (纸本)9783031126703;9783031126697

Due to the rapid increase in User-Generated Content (UGC) data, opinion mining, also called sentiment analysis, has attracted much attention in both academia and industry. Aspect-Based Sentiment Analysis (ABSA), a subfield of sentiment analysis, aims to extract the aspect and the corresponding sentiment simultaneously. Previous works in ABSA may generate undesired aspects, require a large amount of training data, or produce unsatisfactory results. This paper proposes a Graph Neural Network based method to automatically generate aspect-specific sentiment words using a small number of aspect seed words and general sentiment words. It subsequently leverages the aspect-specific sentiment words to improve the Joint Aspect-Sentiment autoencoder (JASA) model. We conduct experiments on two datasets to verify the proposed model. It shows that our approach has better performance in the ABSA task when compared with previous works.

关键词： Aspect-based sentiment analysis Attention mechanism autoencoder Text graph convolution network Text mining

来源：评论

学校读者我要写书评

暂无评论

A Fault Detection Framework Based on LSTM autoencoder: A Case Study for Volvo Bus Data Set 1

引用

20th International Symposium on Intelligent Data Analysis (IDA)

作者： Davari, Narjes Pashami, Sepideh Veloso, Bruno Fan, Yuantao Pereira, Pedro Mota Ribeiro, Rita P. Gama, Joao Nowaczyk, Slawomir INESC TEC Porto Portugal Halmstad Univ Ctr Appl Intelligent Syst Res Halmstad Sweden Univ Porto Fac Sci Porto Portugal Univ Porto Sch Econ Porto Portugal Univ Portucalense Porto Portugal Metro Porto Porto Portugal RISE Res Inst Sweden Kista Sweden

ISBN: (数字)9783031013331

ISBN: (纸本)9783031013331;9783031013324

This study applies a data-driven anomaly detection frame-work based on a Long Short-Term Memory (LSTM) autoencoder network for several subsystems of a public transport bus. The proposed frame-work efficiently detects abnormal data, significantly reducing the false alarm rate compared to available alternatives. Using historical repair records, we demonstrate how detection of abnormal sequences in the signals can be used for predicting equipment failures. The deviations from normal operation patterns are detected by analysing the data collected from several on-board sensors (e.g., wet tank air pressure, engine speed, engine load) installed on the bus. The performance of LSTM autoencoder (LSTM-AE) is compared against the multi-layer autoencoder (mlAE) network in the same anomaly detection framework. The experimental results show that the performance indicators of the LSTM-AE network, in terms of F1 Score, Recall, and Precision, are better than those of the mlAE network.

关键词： Fault detection Outliers Time series LSTM autoencoder

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：