检索结果-内蒙古大学图书馆

SpATr: MoCap 3D human action recognition based on spiral auto-encoder and transformer network

COMPUTER VISION AND IMAGE UNDERSTANDING 2024年 241卷

作者： Bouzid, Hamza Ballihi, Lahoucine Mohammed V Univ Rabat Fac Sci LRIT CNRSTURAC 29 Rabat Morocco

Recent technological advancements have significantly expanded the potential of human action recognition through harnessing the power of 3D data. This data provides a richer understanding of actions, including depth information that enables more accurate analysis of spatial and temporal characteristics. In this context, We study the challenge of 3D human action recognition. Unlike prior methods, that rely on sampling 2D depth images, skeleton points, or point clouds, often leading to substantial memory requirements and the ability to handle only short sequences, we introduce a novel approach for 3D human action recognition, denoted as SpATr (Spiral auto-encoder and Transformer Network), specifically designed for fixed-topology mesh sequences. The SpATr model disentangles space and time in the mesh sequences. A lightweight autoencoder, based on spiral convolutions, is employed to extract spatial geometrical features from each 3D mesh. These convolutions are lightweight and specifically designed for fix-topology mesh data. Subsequently, a temporal transformer, based on self-attention, captures the temporal context within the feature sequence. The self-attention mechanism enables long-range dependencies capturing and parallel processing, enabling scalability for long sequences. The proposed method is evaluated on three prominent 3D human action datasets: Babel, MoVi, and BMLrub, from the Archive of Motion Capture As Surface Shapes (AMASS). Our results analysis demonstrates the competitive performance of our SpATr model in 3D human action recognition while maintaining efficient memory usage. The code and the training results are publicly available at https: //***/h-bouzid/spatr.

关键词： Human action recognition auto-encoder Transformer Spiral convolution AMASS Geometric deep learning

来源：评论

学校读者我要写书评

暂无评论

Federated auto-encoder and XGBoost schemes for multi-omics cancer detection in distributed fog computing paradigm

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2023年第1期241卷

作者： Mohammed, Mazin Abed Lakhan, Abdullah Abdulkareem, Karrar Hameed Garcia-Zapirain, Begonya Univ Anbar Coll Comp Sci & Informat Technol Anbar 31001 Iraq Dawood Univ Engn & Technol Dept Comp Sci Karachi Pakistan Al Muthanna Univ Coll Agr Samawah 66001 Iraq Univ Warith Al Anbiyaa Coll Engn Karbala Iraq Univ Deusto eVIDA Lab Bilbao 48007 Spain

The digital healthcare paradigm has significantly improved based on distributed fog and cloud networks for cancer detection with multiple classes in recent years. The paradigm allows the collecting and training of cancer data on various computing nodes to make optimal cancer detection with their classes. In paradigm, multiomics approaches (such as RNA, miRNA, and methylation) and machine learning techniques have achieved remarkable results in predicting cancer with different features. However, the digital healthcare paradigm for cancer detection concerning infrastructure still faces challenges related to security, execution delay, and improving the accuracy of cancer prediction in existing studies. These limitations affect the overall cancer detection results with more accuracy. In this paper, we are handling the research mentioned above limitations. We present a new paradigm for cancer detection with more accuracy, less processing delay, and more security based on fog cloud heterogeneous computing nodes. We present the Multi-Cancer Multi-Omics Clinical Dataset Laboratories (MCMOCL) Schemes to predict multi-cancers with multiple classes and consist of federated learning, auto-encoder, and XGBoost methods. The main objective of this study is to improve accuracy, reduce execution delay, and improve the security among heterogeneous cancer clinics in the architecture. Simulation results show that MCMOCL outperformed all existing machine models in terms of accuracy by 98% , processing delay by 61%, and security for the multi-classes types of cancers in heterogeneous fog cloud paradigm.

关键词： Multi-cancers MCMOCL Omics XGBoost auto-encoder Federated learning Fog cloud Security Accuracy Processing delay

来源：评论

学校读者我要写书评

暂无评论

Broad auto-encoder for machinery intelligent fault diagnosis with incremental fault samples and fault modes

引用

MECHANICAL SYSTEMS AND SIGNAL PROCESSING 2022年 178卷 1页

作者： Fu, Yang Cao, Hongrui Chen, Xuefeng Ding, Jianming Xi An Jiao Tong Univ State Key Lab Mfg Syst Engn Xian 710049 Peoples R China Southwest Jiaotong Univ State Key Lab Tract Power Chengdu 610031 Peoples R China

Intelligent fault diagnosis (IFD) has been a widely concerned topic in the field of prognostics and health management. Existing machinery IFD approaches are generally developed based on the one-time learning manner. Therefore, they are powerless to deal with the data stream issue in which new fault samples and fault modes will be progressively collected for model training. To overcome this drawback, this paper proposes a broad auto-encoder (BAE) with incremental learning capabilities for on-line IFD of machinery. The BAE is constructed by stacking a series of auto-encoders in the width direction. Then, the output weight matrix of the BAE is calculated by the ridge regression algorithm. After that, the capabilities of sample-incremental learning and class-incremental learning are developed, so that the BAE can easily update itself to accommodate the new fault samples and fault modes without model retraining. With the two incremental learning capabilities, the BAE can be first trained using limited historical fault samples, and then incrementally learn new diagnosis knowledge from the newly coming fault samples and fault modes. In this way, the BAE will be more and more powerful over time. Finally, the proposed BAE is applied to diagnose faults for high-speed train wheelset bearings and disc components. The results show that the proposed BAE offers an efficient solution for machinery IFD to deal with the continuous data stream issue.

关键词： Intelligent fault diagnosis auto-encoder Broad learning system Incremental learning

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Anomaly Detection with auto-encoder and Independent Target

引用

REMOTE SENSING 2023年第22期15卷 5266页

作者： Chen, Shuhan Li, Xiaorun Yan, Yunfeng Zhejiang Univ Dept Elect Engn Hangzhou 310027 Peoples R China

As an unsupervised data representation neural network, auto-encoder (AE) has shown great potential in denoising, dimensionality reduction, and data reconstruction. Many AE-based background (BKG) modeling methods have been developed for hyperspectral anomaly detection (HAD). However, their performance is subject to their unbiased reconstruction of BKG and target pixels. This article presents a rather different low rank and sparse matrix decomposition (LRaSMD) method based on AE, named auto-encoder and independent target (AE-IT), for hyperspectral anomaly detection. First, the encoder weight matrix, obtained by a designed AE network, is utilized to construct a projector for generating a low-rank component in the encoder subspace. By adaptively and reasonably determining the number of neurons in the latent layer, the designed AE-based method can promote the reconstruction of BKG. Second, to ensure independence and representativeness, the component in the encoder orthogonal subspace is made into a sphere and followed by finding of unsupervised targets to construct an anomaly space. In order to mitigate the influence of noise on anomaly detection, sparse cardinality (SC) constraint is enforced on the component in the anomaly space for obtaining the sparse anomaly component. Finally, anomaly detector is constructed by combining Mahalanobi distance and multi-components, which include encoder component and sparse anomaly component, to detect anomalies. The experimental results demonstrate that AE-IT performs competitively compared to the LRaSMD-based models and AE-based approaches.

关键词： low rank and sparse decomposition (LRaSMD) auto-encoder unsupervised independent target sparsity cardinality (SC) independent target subspace (ITS)

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Adversarial auto-encoder to Expedite Human Activity Recognition

引用

SENSORS 2023年第2期23卷 683-683页

作者： Thapa, Keshav Seo, Yousung Yang, Sung-Hyun Kim, Kyong Daegu Haany Univ Dept Rehabil Med Engn Gyongsan 38610 South Korea Daegu Haany Univ Dept Geriatr Rehabil Gyongsan 38610 South Korea Kwangwoon Univ Dept Elect Engn Seoul 01897 South Korea

The study of human activity recognition concentrates on classifying human activities and the inference of human behavior using modern sensing technology. However, the issue of domain adaptation for inertial sensing-based human activity recognition (HAR) is still burdensome. The existing requirement of labeled training data for adapting such classifiers to every new person, device, or on-body location is a significant barrier to the widespread adoption of HAR-based applications, making this a challenge of high practical importance. We propose the semi-supervised HAR method to improve reconstruction and generation. It executes proper adaptation with unlabeled data without changes to a pre-trained HAR classifier. Our approach decouples VAE with adversarial learning to ensure robust classifier operation, without newly labeled training data, under changes to the individual activity and the on-body sensor position. Our proposed framework shows the empirical results using the publicly available benchmark dataset compared to state-of-art baselines, achieving competitive improvement for handling new and unlabeled activity. The result demonstrates SAA has achieved a 5% improvement in classification score compared to the existing HAR platform.

关键词： semi-supervised auto-encoder human activity recognition adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Deep Belief Echo State Network with a Sensitivity Analysis Input Scaling auto-encoder algorithm

引用

KNOWLEDGE-BASED SYSTEMS 2020年 191卷 105257-105257页

作者： Wang, Heshan Wu, Q. M. Jonathan Xin, Jianbin Wang, Jie Zhang, Heng Zhengzhou Univ Coll Elect Engn Zhengzhou 450001 Peoples R China Univ Windsor Dept Elect & Comp Engn Windsor ON N9B 3P4 Canada

Echo State Network (ESN) is a specific class of recurrent neural networks, which displays very rich dynamics owing to its reservoir based hidden neurons. ESN has been viewed as a powerful approach to model real-valued time series processes. In order to integrate with deep learning theory, Deep Belief Echo State Network (DBESN) is employed to address the slow convergence in Deep Belief Network (DBN). In DBESN, the DBN part is employed for feature learning in an unsupervised fashion and the ESN part is utilized as a regression layer of DBN. However, the ESN input layer is still not working in an unsupervised status in DBESN. Moreover, ESN's input dimension increases dramatically because of the DBN layer in DBESN. Namely, the DBN layer in DBESN makes the ESN more difficult to construct the input scaling parameters. For purpose of constructing an optimal input weights matrix and input scaling parameters in the ESN layer of DBESN, a novel Sensitivity Analysis Input Scaling auto-encoder (SAIS-AE) algorithm is employed in this paper through an unsupervised pre-training process. Initially, the output weights matrix of ESN layer is pre-trained by total input data set. Then, the pretrained output weights matrix is injected into the input weights matrix of the ESN layer to ensure the specificity of AE. Finally, the input scaling parameters of ESN layer are tuned based on a sensitivity analysis algorithm. Two multivariable sequence tasks and one univariate sequence benchmark are applied to demonstrate the advantage and superiority of SAIS-AE. Extensive experimental results show that our SAIS-AE-DBESN model can effectively improve the performance of DBESN. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Echo State Network Reservoir computing Recurrent neural network Sensitivity Analysis Input Scaling auto-encoder Time-series prediction

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Anomaly Detection in High-Voltage Transformer Bushings with LSTM auto-encoder

引用

SENSORS 2021年第21期21卷 7426-7426页

作者： Mitiche, Imene McGrail, Tony Boreham, Philip Nesbitt, Alan Morison, Gordon Glasgow Caledonian Univ Sch Comp Engn & Built Environm Dept Comp Glasgow G4 0BA Lanark Scotland Doble Engn Bere Regis BH20 7LA England Glasgow Caledonian Univ Dept Elect & Elect Engn Sch Comp Engn & Built Environm Glasgow G4 0BA Lanark Scotland

The reliability and health of bushings in high-voltage (HV) power transformers is essential in the power supply industry, as any unexpected failure can cause power outage leading to heavy financial losses. The challenge is to identify the point at which insulation deterioration puts the bushing at an unacceptable risk of failure. By monitoring relevant measurements we can trace any change that occurs and may indicate an anomaly in the equipment's condition. In this work we propose a machine-learning-based method for real-time anomaly detection in current magnitude and phase angle from three bushing taps. The proposed method is fast, self-supervised and flexible. It consists of a Long Short-Term Memory auto-encoder (LSTMAE) network which learns the normal current and phase measurements of the bushing and detects any point when these measurements change based on the Mean Absolute Error (MAE) metric evaluation. This approach was successfully evaluated using real-world data measured from HV transformer bushings where anomalous events have been identified.

关键词： transformer bushings insulation failure anomaly detection LSTM auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised auto-encoder Graph Network for Diabetic Retinopathy Grading

引用

IEEE ACCESS 2021年 9卷 140759-140767页

作者： Li, Yujie Song, Zhang Kang, Sunkyoung Jung, Sungtae Kang, Wenpei Weifang Univ Sci & Technol Weifang Key Lab Blockchain Agr Vegetables Weifang 262700 Shandong Peoples R China Wonkwang Univ Dept Comp Software Engn Iksan 54538 Jeonbuk South Korea Qingdao Univ Affiliated Hosp Qingdao 266000 Peoples R China Southwest Univ Business Coll Chongqing 402460 Peoples R China

Diabetic Retinopathy (DR) causes quite a few blindness worldwide, which can be refrained by the timely diagnosis on retinal images. Recently, researches on deep learning-based retinal image classification have accelerated outstanding improvements in DR grading task. However, existing DR grading works are mostly limited to a supervised manner. They require accurately annotated data labeled by professional experts, and the annotating work is very laborious and time-consuming. We propose a Semi-supervised auto-encoder Graph Network (SAGN) for the challenging DR diagnosis to relax this constraint. Precisely, SAGN consists of three major modules: auto-encoder feature learning, neighbor correlation mining, and graph representation. Firstly, our model learns to extract representations from retinal images and reconstruct them as close to original inputs as possible. Then neighbor correlations among labeled and unlabeled samples are established by their similarities, calculated by the radial basis function. Finally, we operate Graph Convolutional Neural Network (GCN) to grade retinal samples from extracted features and their correlations. To evaluate the performance of SAGN, we conduct sufficient comparative experiments on APTOS 2019 dataset, trained from EyePACS. Results demonstrate that our SAGN model can achieve comparable performance with limited labeled retinal images with the help of large amounts of unlabeled data.

关键词： Retina Feature extraction Correlation Training Task analysis Annotations Convolutional neural networks Diabetic retinopathy grading semi-supervised learning auto-encoder graph convolutional network

来源：评论

学校读者我要写书评

暂无评论

Event log anomaly detection method based on auto-encoder and control flow

引用

MULTIMEDIA SYSTEMS 2024年第1期30卷 29-29页

作者： Kan, Daoyu Fang, Xianwen Anhui Univ Sci & Technol Coll Math & Big Data 168 Taifeng St Huainan 232001 Anhui Peoples R China Anhui Prov Engn Lab Big Data Anal & Early Warning Huainan Peoples R China

Anomaly detection is widely used in the field of business process management, and researchers have proposed various anomaly detection algorithms to detect anomalies in event logs. However, existing research focuses on detecting anomalies in event logs at the data level, ignoring the problem of anomalies caused by event log control flow, especially behavioral relationships, and identifying behavioral anomalies as normal, leading to an increase in the false-negative rate of anomaly detection results, which negatively affects the performance of process mining. To solve the above problems, this article proposes an auto-encoder-based anomaly detection approach to achieve the detection of behavioral relationship anomalies in event logs through the reconstruction error between images. The approach first considers event logs containing behavioral relationships, converts the logs into images as input to the auto-encoder, and analyses the reconstruction error between images to propose a reconstruction error threshold for anomaly detection. The algorithm is able to achieve anomaly detection of behavioral relationships in event logs and reduce the false-negative rate of anomaly detection results. Experiments on synthetic datasets and real datasets show that the proposed approach can improve the recall rate and F1-score of event log anomaly detection effectively.

关键词： Control flow Anomaly detection auto-encoder Business process Reconstruction error

来源：评论

学校读者我要写书评

暂无评论

On Improving the accuracy with auto-encoder on Conjunctivitis

引用

APPLIED SOFT COMPUTING 2019年 81卷 105489-000页

作者： Li, Wei Liu, Xiao Liu, Jin Chen, Ping Wan, Shaohua Cui, Xiaohui Wuhan Univ Sch Cyber Sci & Engn Wuhan 430079 Hubei Peoples R China Deakin Univ Sch Informat Technol Geelong Vic 3216 Australia Wuhan Univ Sch Comp Wuhan 430079 Hubei Peoples R China Univ Massachusetts Dept Engn Boston MA 02125 USA Zhongnan Univ Econ & Law Sch Informat & Safety Engn Wuhan 430073 Hubei Peoples R China

Applying the classification approach in machine learning to medical field is a promising direction as it could potentially save a large amount of medical resources and reduce the impact of error-prone subjective diagnosis. However, low accuracy is currently the biggest challenge for classification. So far many approaches have been developed to improve the classification performance and most of them are focusing on how to extend the layers or the nodes in the Neural Network (NN), or combining a classifier with the domain knowledge of the medical field. These extensions may improve the classification performance. However, these classifiers trained on one datasets may not be able to adapt to another dataset. Meanwhile, the layers and the nodes of the neural network cannot be extended infinitely in practice. To overcome these problems, in this paper, we propose an innovative approach which is to employ the auto-encoder (AE) model to improve the classification performance. Specifically, we make the best of the compression capability of the encoder to generate the latent compressed vector which can be used to represent the original samples. Then, we use a regular classifier to perform classification on those compressed vectors instead of the original data. In addition, we explore the classification performance on different extracted features by enumerating the number of hidden nodes which are used to save the extracted features. Comprehensive experiments are conducted to validate our proposed approach with the medical dataset of conjunctivitis and the STL-10 dataset. The results show that our proposed AE-based model can not only improve the classification accuracy but also be beneficial to solve the problem of False Positive Rate. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Classification auto-encoder Neural networks Medical diagnosis

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：