检索结果-内蒙古大学图书馆

10th International Joint Conference on Biomedical Engineering Systems and Technologies

作者： Moucek, Roman Hnojsky, Lukas Vareka, Lukas Prokop, Tomas Bruha, Petr Univ West Bohemia Dept Comp Sci & Engn Univ 8 Plzen Czech Republic Univ West Bohemia NTIS Fac Appl Sci Univ 8 Plzen Czech Republic

ISBN: (纸本)9789897582134

Attention of drivers is very important for road safety and it is worth observing even in laboratory conditions during a simulated drive. This paper deals with design of an experiment investigating driver's attention, validation of collected data, and first preprocessing and processing steps used within data analysis. Brain activity is considered as a primary biosignal and is measured and analyzed using the techniques and methods of electroencephalography and event related potentials. Respiration is considered as a secondary biosignal that is captured together with brain activity. Validation of collected data using a stacked autoencoder is emphasized as an important step preceding data analysis.

关键词： Neuroinformatics Brain Activity Electroencephalography Event Related Potentials Respiration Rate Driver's Attention Simulated Drive Data Validation Deep Learning stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Robust Feature Learning by Improved Auto-encoder From non-Gaussian Noised Images 12

Robust Feature Learning by Improved Auto-encoder From non-Ga...

引用

IEEE International Conference on Imaging Systems and Techniques (IST)

作者： Zhao, Dan Guo, Baolong Wu, Jinfu Ning, Weikang Yan, Yunyi Xidian Univ Sch Aerosp Sci & Technol Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781479986330

Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks(DBN) and stacks of auto-encoder variants, with impressive results obtained in several areas, mostly on vision and languages datasets. These learning algorithms aim to find good representations for data, which can be used for classification, reconstruction, visualization and so on. Despite the progress, most existing algorithms would be fragile to non-Gaussian noises and outliers due to the criterion of mean square error(MSE) and cross entropy(CE). In this paper, we propose a robust autoencoder called correntropy-based contractive auto-encoder(CCAE) to learn robust features from data with non-Gaussian noises and outliers. The maximum correntropy criterion(MCC) is adopted as reconstruction cost function and a well chosen penalty term is added to the reconstruction cost function. By replacing cross entropy with MCC, the proposed method can learn robust features from the data containing non-Gaussian noises and outliers. The penalty term corresponds to the Frobenius norm of the Jacobian matrix of the encoder activations with respect to the input. By adding the penalty term, the antinoise ability of the proposed method is improved. The proposed method is evaluated using the MNIST benchmark dataset. Experimental results show that, compared with the traditional auto-encoders, the proposed method learns robust features, improves classification accuracy and reduces the reconstruction error, which demonstrates that the proposed method is capable of learning robust features on noisy data.

关键词： feature learning stacked autoencoder correntropy

来源：评论

学校读者我要写书评

暂无评论

Online Non-linear Prediction of Financial Time Series Patterns

Online Non-linear Prediction of Financial Time Series Patter...

引用

作者： da Costa, Joel University of Cape Town

学位级别：硕士

We consider a mechanistic non-linear machine learning approach to learning signals in financial time series data. A modularised and decoupled algorithm framework is established and is proven on daily sampled closing time-series data for JSE equity markets. The input patterns are based on input data vectors of data windows preprocessed into a sequence of daily, weekly and monthly or quarterly sampled feature measurement changes (log feature fluctuations). The data processing is split into a batch processed step where features are learnt using a stacked autoencoder (SAE) via unsupervised learning, and then both batch and online supervised learning are carried out on Feedforward Neural Networks (FNNs) using these features. The FNN output is a point prediction of measured time-series feature fluctuations (log differenced data) in the future (ex-post). Weight initializations for these networks are implemented with restricted Boltzmann machine pretraining, and variance based initializations. The validity of the FNN backtest results are shown under a rigorous assessment of backtest overfitting using both Combinatorially Symmetrical Cross Validation and Probabilistic and Deflated Sharpe Ratios. Results are further used to develop a view on the phenomenology of financial markets and the value of complex historical data under unstable dynamics.

关键词： online learning feedforward neural network restricted Boltzmann machine variance weight initialization stacked autoencoder pattern prediction JSE non-linear financial time series combinatorially symmetrical cross validation backtest overfitting deflated Sharpe ratio probabilistic Sharpe ratio

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Deep Embedding Clustering for High--Dimensional Visual Features of Fashion Images

Unsupervised Deep Embedding Clustering for High--Dimensional...

引用

作者： Malhi,Umar Subhan 东华大学

学位级别：硕士

Can a computer algorithm detect images of pants,shirts,sneakers,clothes,and dresses automatically?It turns out that it is amazingly simple to do correctly classifying pictures of fashion products,considering the quality training data,to begin *** in real-world fashion datasets areconsist of products of various kinds.(***,top,hat,footwear).We have to describe fashion product characteristics manually based on their pattern,color,look,material,*** such cases,data become noisy because of human error and it also a quite expensive *** problem leads to unsupervised learning,where we train our model without an object *** this thesis,we will use the real-world amazon dataset to build a machine-learning model to recognize cluster of fashion objects.　　The currently widely used feature extraction methods based on deep learning such as a convolutional neural network(CNN)can generate feature vector up to4096dimensions,which provides a guarantee for accurate image ***,high dimensions can lead to the curse of dimensionality,which makes subsequent clustering *** fashion images oriented deep clustering(FIDC)method is proposed in *** method uses CNNto generate a4096-dimensional feature vector for each fashion image through migration learning,and then performs dimensionality reduction through a deep-stacked auto-encoder model,and finally does clustering on these low-dimensional *** dimensional vectors are capable of representing image features and dimensionality reduction avoids the curse of dimensionality during clustering tasks.　　While for feature encoding,we employ a suitable encoding method to perform efficient clustering *** jointly perform dimension reduction with optimal parameter and clustering assignments.　　A special point in the method is the joint learning and optimization of the dimensionality reduction process and the clustering *** optimize the cluster centroid byusing back-propagation a

关键词： clustering algorithm dimensionality reduction fashionimages deep embedding stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Dynamic System Based on SAE-LDS Model for Fault Diagnosis 13

Nonlinear Dynamic System Based on SAE-LDS Model for Fault Di...

引用

13th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2024

作者： Tang, Xiaochu Zhang, Yi Zhang, Xinmin Song, Zhihuan School of Automation Shenyang Aerospace University Liaoning Province Shenyang110136 China College of Control Science and Engineering Zhejiang University State Key Laboratory of Industrial Control Technology Zhejiang Province Hangzhou310027 China

ISBN: (纸本)9798350361674

Dynamic, uncertainty and nonlinearity are three very important characteristics of complex industrial process data. In this paper, a method of fault detection and classification based on stacked autoencoder-linear dynamic system (SAE-LDS) model is proposed. This method aims to simultaneously consider multiple characteristics of industrial process data for fault detection and classification. Firstly, the deep learning algorithm SAE is used to mine the nonlinear characteristic of process data. On this basis, the SAE model is embedded into the LDS model. The LDS model is used to further extract the dynamics and uncertainty, so as to establish a SAE-LDS model that can comprehensively consider multiple characteristics of data. Finally, the SAE-LDS model is applied to the TE process, compared with the traditional method for fault detection and fault classification. The experimental results show that SAE- LDS model has good effectiveness. © 2024 IEEE.

关键词： data-driven fault classification fault detection linear dynamic system stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Deep-Learning-Based Health Indicator Constructor Using Kullback-Leibler Divergence for Predicting the Remaining Useful Life of Concrete Structures

引用

SENSORS 2022年第10期22卷 3687-3687页

作者： Nguyen, Tuan-Khai Ahmad, Zahoor Kim, Jong-Myon Univ Ulsan Dept Elect Elect & Comp Engn Ulsan 44610 South Korea

This paper proposes a new technique for the construction of a concrete-beam health indicator based on the Kullback-Leibler divergence (KLD) and deep learning. Health indicator (HI) construction is a vital part of remaining useful lifetime (RUL) approaches for monitoring the health of concrete structures. Through the construction of a HI, the deterioration process can be processed and portrayed so that it can be forwarded to a prediction module for RUL prognosis. The degradation progression and failure can be identified by predicting the RUL based on the situation of the current specimen;as a result, maintenance can be planned to reduce safety risks, reduce financial costs, and prolong the specimen's useful lifetime. The portrayal of deterioration through HI construction from raw acoustic emission (AE) data is performed using a deep neural network (DNN), whose parameters are obtained by pretraining and fine tuning using a stack autoencoder (SAE). Kullback-Leibler divergence, which is calculated between a reference normal-conditioned signal and a current unknown signal, was used to represent the deterioration process of concrete structures, which has not been investigated for the concrete beams so far. The DNN-based constructor then learns to generate HI from raw data with KLD values as the training label. The HI construction result was evaluated with run-to-fail test data of concrete specimens with two measurements: fitness analysis of the construction result and RUL prognosis. The results confirm the reliability of KLD in portraying the deterioration process, showing a large improvement in comparison to other methods. In addition, this method requires no adept knowledge of the nature of the AE or the system fault, which is more favorable than model-based approaches where this level of expertise is compulsory. Furthermore, AE offers in-service monitoring, allowing the RUL prognosis task to be performed without disrupting the specimen's work.

关键词： acoustic emission deep neural network concrete structures health indicator Kullback-Leibler divergence remaining useful life stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Threat Alert Prioritization Using Isolation Forest and stacked Auto Encoder With Day-Forward-Chaining Analysis

引用

IEEE ACCESS 2020年 8卷 217977-217986页

作者： Aminanto, Muhamad Erza Ban, Tao Isawa, Ryoichi Takahashi, Takeshi Inoue, Daisuke Natl Inst Informat & Commun Technol Tokyo 1848795 Japan Univ Indonesia Grad Sch Strateg & Global Studies Jakarta 16424 Indonesia

Security Incident and Event Manager (SIEM) is a security management approach designed to identify possible threats within a real-time enterprise environment. The main challenge for SIEM is to find critical security incidents among a huge number of less critical alerts coming from separate security products. The continuously growing number of internet-connected devices has led to the alert fatigue problem, which is defined as the inability of security operators to investigate each incoming alert from intrusion detection systems. This fatigue can lead to human errors and leave many alerts being not investigated. Aiming at reducing the number of less important threat alerts presented to security operators, this paper presents a new method for highlighting critical alerts with a minimal number of false negatives. The proposed method employs isolation forest to ensure unsupervised performance and adaptability to different types of networks. Furthermore, it takes the advantage of day-forward-chaining analysis to ensure the detection of highly important alerts in real time. The number of false positive cases is reduced by employing an autoencoder. The proposed method achieved a recall score of 95.89% and a false positive rate of 5.86% on a dataset comprising more than half a million alerts collected in a real-world enterprise environment over ten months. This study highlights the importance of addressing the alert fatigue problem and validates the effectiveness of unsupervised learning in filtering out less important threat alerts.

关键词： Security Fatigue Forestry Real-time systems Task analysis Monitoring Intrusion detection Threat alert fatigue stacked autoencoder isolation forest intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

A Scheme with Acoustic Emission Hit Removal for the Remaining Useful Life Prediction of Concrete Structures

引用

SENSORS 2021年第22期21卷 7761-7761页

作者： Tuan-Khai Nguyen Ahmad, Zahoor Kim, Jong-Myon Univ Ulsan Dept Elect Elect & Comp Engn Ulsan 44610 South Korea PD Technol Co Ulsan 44610 South Korea

In this study, a scheme of remaining useful lifetime (RUL) prognosis from raw acoustic emission (AE) data is presented to predict the concrete structure's failure before its occurrence, thus possibly prolong its service life and minimizing the risk of accidental damage. The deterioration process is portrayed by the health indicator (HI), which is automatically constructed from raw AE data with a deep neural network pretrained and fine-tuned by a stacked autoencoder deep neural network (SAE-DNN). For the deep neural network structure to perform a more accurate construction of health indicator lines, a hit removal process with a one-class support vector machine (OC-SVM), which has not been investigated in previous studies, is proposed to extract only the hits which matter the most to the portrait of deterioration. The new set of hits is then harnessed as the training labels for the deep neural network. After the completion of the health indicator line construction, health indicators are forwarded to a long short-term memory recurrent neural network (LSTM-RNN) for the training and validation of the remaining useful life prediction, as this structure is capable of capturing the long-term dependencies, even with a limited set of data. Our prediction result shows a significant improvement in comparison with a similar scheme but without the hit removal process and other methods, such as the gated recurrent unit recurrent neural network (GRU-RNN) and the simple recurrent neural network.

关键词： acoustic emission deep neural network hit removal long short-term memory one-class support vector machine remaining useful life stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Remaining useful life prediction for space bearing with cage friction fault based on data pre-screening and gated recurrent unit

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2023年第12期34卷 125049-125049页

作者： Wang, Jianwen Pan, Qiang He, Tian Wang, Hong Qing, Tao Beihang Univ Sch Transportat Sci & Engn Beijing 100191 Peoples R China Beijing Inst Control Engn Beijing Key Lab Long life Technol Precise Rotat & Beijing 100194 Peoples R China

The remaining useful life (RUL) of bearings in space inertia actuators is crucial for performance maintenance requirements. But it is quite difficult to accurately predict the RUL of space bearings due to the significant intermittency and nonstationary properties caused by cage friction faults commonly occurring during the operation of the actuator. This paper proposes a data-driven method for RUL prediction of space bearings by incorporating the gated recurrent unit network with a novel data pre-screening approach. In the proposed method, a stacked autoencoder and clustering approach are introduced into the data pre-processing method, and a health index called Overrun-Distance is constructed for lifetime assessment. To verify the proposed method, a series of vibration tests on flywheels equipped with space bearings are conducted and used for RUL evaluation. The results show that the proposed RUL prediction method is applicable to space bearings for RUL prediction with high accuracy and effectiveness.

关键词： space bearing cage friction fault remaining useful life prediction stacked autoencoder gated recurrent unit

来源：评论

学校读者我要写书评

暂无评论

Aeroengine Remaining Life Prediction Based on Advanced Health Index Construction and Gray Similarity Multiscale Matching

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Sun, Shilong Huang, Haodong Ding, Jian Wang, Dong Xu, Wenfu Harbin Inst Technol Sch Mech Engn & Automat Shenzhen 518055 Peoples R China Shanghai Jiao Tong Univ State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China Key Univ Lab Mech & Machine Theory & Intelligent U Shenzhen 518055 Guangdong Peoples R China

In this article, we address the challenge of predicting the remaining useful life (RUL) of aeroengines, which are critical components of aircraft that operate under increasingly extreme conditions as engine performance enhances. Ensuring the safety and reliability of these engines is paramount. To this end, we introduce a novel RUL prediction methodology that leverages gray similarity multiscale matching. This approach employs the robust capabilities of long short-term memory (LSTM) networks for processing time-series data. First, an LSTM stacked autoencoder (L-SAE) is designed to extract pivotal operational features of the engine, thereby delineating its degradation trajectory. Furthermore, the gray correlation analysis is utilized to assess the similarity between these degradation trajectories, which are complemented by a multitime scale sliding window technique for enhanced similarity matching. Subsequently, kernel density estimation (KDE) is applied to gauge the uncertainty associated with the prediction outcomes. The efficacy and superiority of our proposed method are demonstrated through the validation of the experiment study. Comparative analysis reveals that our method outperforms existing techniques in key evaluation metrics, underscoring its potential applicability to large-scale datasets. This validation confirms not only the method's effectiveness but also its advantage in predicting the RUL of aeroengines with greater accuracy and reliability.

关键词： Sensors Degradation Time series analysis Trajectory Predictive models Information entropy Engines Sensor phenomena and characterization Indexes Aircraft propulsion Gray correlation analysis remaining useful life (RUL) similarity matching stacked 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：