检索结果-内蒙古大学图书馆

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

作者： Xia, Rui Deng, Jun Schuller, Bjoern Liu, Yang Univ Texas Dallas Dept Comp Sci Dallas TX 75230 USA Tech Univ Munich MMK Machine Intelligence & Signal Proc Grp Munich Germany Imperial Coll London Dept Comp London England

ISBN: (纸本)9781479928934

The denoising autoencoder (DAE) has been successfully applied to acoustic emotion recognition lately. In this paper, we adopt the framework of the modified DAE introduced in [1] that projects the input signal to two different hidden representations, for neutral and emotional speech respectively, and uses the emotional representation for the classification task. We propose to model gender information for more robust emotional representation in this work. For neutral representation, male and female dependent DAEs are built using non-emotional speech with the aim of capturing distinct information between the two genders. The emotional hidden representation is shared for the two genders in order to model more emotion specific characteristics, and is used as features in a back-end classifier for emotion recognition. We propose different optimization objectives in training the DAEs. Our experimental results show improvement on unweighted accuracy compared with previous work using the modified DAE method and the classifiers using the standard static features. Further performance gain can be achieved by structural level system combination.

关键词： Emotion recognition denoising autoencoder Gender

来源：评论

学校读者我要写书评

暂无评论

Bathymetric Data Processing based on denoising autoencoder Wasserstein Generative Adversarial Network

Bathymetric Data Processing based on Denoising Autoencoder W...

引用

Global Intelligent Industry Conference (GIIC)

作者： Zhang, Ruichen Chen, Yongbing Bian, Shaofeng Gao, Duanyang Naval Univ Engn Dept Nav Wuhan 430033 Hubei Peoples R China

ISBN: (数字)9781510623002

ISBN: (纸本)9781510623002

In view of the complexity and variability of bathymetric data, the paper introduces a new algorithm named DAE-WGAN to construct sea bottom trend surface. This new model is an alternative to traditional GAN training method, combined with the advantages of denoising autoencoder (DAE) and Wasserstein Generative Adversarial Network (WGAN). Firstly, the network structure is introduced in detail, in which the critic (or 'discriminator') estimates the Wasserstein-1 distance between the generated-sample distributions and the real-sample distributions, and optimizes the generator to approximate the minimum Wasserstein-1 distance, which effectively improves the stability of the adversarial training. Moreover, the generalized denoising autoencoder algorithm is added to train the back-propagation process, having a better ability of dimensionality reduction, which improves the robustness of the whole algorithm. Then, using two different types of bathymetric data (seabed tiny-terrain data and Electronic Nautical Chart data), we had long-time experiments to train the DAE-WGAN till optimality, and got the better sea bottom trend surface. Finally, by comparison with other GAN models (such as InFoGAN, LSGAN), the results show that the proposed method has an obvious improvement in accuracy, stability and robustness, and further illustrate the feasibility of this method in bathymetric precise data processing area.

关键词： denoising autoencoder Wasserstein generative adversarial network Bathymetric data processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

DAEimp: denoising autoencoder-Based Imputation of Sleep Heart Health Study for Identification of Cardiovascular Diseases 2nd

DAEimp: Denoising Autoencoder-Based Imputation of Sleep Hear...

引用

2nd Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Dong, Xiaoyun Zhang, Jingjing Wang, Gang Xia, Yong Northwestern Polytech Univ ShenZhen Res & Dev Inst Shenzhen 518057 Peoples R China Xi An Jiao Tong Univ Affiliated Hosp 2 Dept Crit Care Med Xian 710004 Peoples R China Northwestern Polytech Univ Sch Comp Sci & Engn Natl Engn Lab Integrated AeroSp Ground Ocean Big Xian 710072 Peoples R China

ISBN: (纸本)9783030316532;9783030316549

Since it has been recognized that the disordered breathing during sleep is related to cardiovascular diseases, it is possible to predict cardiovascular diseases from sleep breathing data, which however is usually inevitable to have missing data, resulted probability from the loss to follow-up, failure to attend medical appointments, lack of measurements, failure to send or retrieve questionnaires, and inaccurate data transfer. In this paper, we propose a denoising autoencoder-based imputation (DAEimp) algorithm to impute the missing values in the sleep heart health study (SHHS) dataset for the predication of cardiovascular diseases. This algorithm consists of three major steps: (1) based on the missing completely at random assumption, the random uniform noise is added to the positions of missing values to convert missing data imputation into a denoising problem, (2) feed the noisy data and a missing position indicator matrix into an autoencoder model and use the reconstruction error, divided into observation positions reconstruction error and missing positions error, for denoising, and (3) the logistic regression is applied to the generated complete dataset for the identification of cardiovascular diseases. Our results on the SHHS dataset indicate that the proposed DAEimp algorithm achieves state-of-the-art performance in missing data imputation and sleep breathing data-based identification of cardiovascular diseases.

关键词： Missing data denoising autoencoder Sleep heart health study Cardiovascular disease identification

来源：评论

学校读者我要写书评

暂无评论

Anomaly Root Cause Analysis forWind Turbines Based on denoising autoencoder and Sparse Estimation 12

Anomaly Root Cause Analysis forWind Turbines Based on Denois...

引用

IEEE 12th Data Driven Control and Learning Systems Conference (DDCLS)

作者： Du, Songtao Wan, Yiming Zhang, Cong Zhang, Sihang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Beijing Inst Control Engn Beijing 100094 Peoples R China

ISBN: (纸本)9798350321050

Wind turbine condition monitoring has been extensively studied to reduce maintenance costs. Although there exist a vast amount of literature on anomaly detection for wind turbine, anomaly root cause analysis has not been fully addressed so far. To cope with this problem, we propose a denoising autoencoder (DAE) based anomaly detector and performs anomaly root cause analysis using sparse estimation. For anomaly detection, deep denoising autoencoder is learned with normal history data, with enhanced robustness compared to the conventional autoencoder. The reconstruction error from the DAE is further evaluated by the exponentially weighted moving average control chart (EWMA) to reduce the false positive rate. After anomaly detection, root cause analysis performs sparse fault estimation, with the assumption that a small number of observed variables are affected under the abnormal condition. The fault estimates are then leveraged to identify the variables most relevant to the underlying anomaly root causes. Real cases on a public dataset demonstrate the effectiveness of the proposed method.

关键词： anomaly detection root cause analysis denoising autoencoder sparse fault estimation wind turbine

来源：评论

学校读者我要写书评

暂无评论

Improved Automatic Speech Recognition using Subband Temporal Envelope Features and Time-delay Neural Network denoising autoencoder 18

Improved Automatic Speech Recognition using Subband Temporal...

引用

18th Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2017)

作者： Cong-Thanh Do Stylianou, Yannis Toshiba Res Europe 208 Cambridge Sci Pk Cambridge England

ISBN: (纸本)9781510848764

This paper investigates the use of perceptually-motivated sub band temporal envelope (STE) features and time-delay neural network (TDNN) denoising autoencoder (DAE) to improve deep neural network (DNN)-based automatic speech recognition (ASR). STEs are estimated by full-wave rectification and low-pass filtering of band-passed speech using a Gammatone filter-bank. TDNNs are used either as DAE or acoustic models. ASR experiments are performed on Aurora-4 corpus. STE features provide 2.2% and 3.7% relative word error rate (WER) reduction compared to conventional log-mel filter-bank (FBANK) features when used in ASR systems using DNN and TDNN as acoustic models, respectively. Features enhanced by TDNN DAE are better recognized with ASR system using DNN acoustic models than using TDNN acoustic models. Improved ASR performance is obtained when features enhanced by TDNN DAE are used in ASR system using DNN acoustic models. In this scenario, using STE features provides 9.8% relative WER reduction compared to when using FBANK features.

关键词： Subband temporal envelope denoising autoencoder time-delay neural network deep neural network acoustic features

来源：评论

学校读者我要写书评

暂无评论

Unsupervised adaptation of a denoising autoencoder by Bayesian Feature Enhancement for reverberant asr under mismatch conditions 40

Unsupervised adaptation of a denoising autoencoder by Bayesi...

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Heymann, Jahn Haeb-Umbach, Reinhold Golik, Pavel Schluter, Ralf University of Paderborn Department of Communications Engineering Paderborn Germany RWTH Aachen University Human Language Technology and Pattern Recognition Computer Science Department Aachen Aachen Germany

ISBN: (纸本)9781467369978

The parametric Bayesian Feature Enhancement (BFE) and a datadriven denoising autoencoder (DA) both bring performance gains in severe single-channel speech recognition conditions. The first can be adjusted to different conditions by an appropriate parameter setting, while the latter needs to be trained on conditions similar to the ones expected at decoding time, making it vulnerable to a mismatch between training and test conditions. We use a DNN backend and study reverberant ASR under three types of mismatch conditions: different room reverberation times, different speaker to microphone distances and the difference between artificially reverberated data and the recordings in a reverberant environment. We show that for these mismatch conditions BFE can provide the targets for a DA. This unsupervised adaptation provides a performance gain over the direct use of BFE and even enables to compensate for the mismatch of real and simulated reverberant data. © 2015 IEEE.

关键词： deep neuronal networks denoising autoencoder feature enhancement robust speech recognition

来源：评论

学校读者我要写书评

暂无评论

A Pruned-CELP Speech Codec Using denoising autoencoder with Spectral Compensation for Quality and Intelligibility Enhancement

A Pruned-CELP Speech Codec Using Denoising Autoencoder with ...

引用

1st IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Lo, Yu-Ting Wang, Syu-Siang Tsao, Yu Peng, Sheng-Yu Natl Taiwan Univ Sci & Technol Dept Elect Engn Taipei Taiwan Acad Sinica Res Ctr Informat Technol Innovat Taipei Taiwan

ISBN: (纸本)9781538678848

A codec based on the excited linear prediction (CELP) speech compression method adopting a denoising autoencoder with spectral compensation (DAE-SC) for quality and intelligibility enhancement is proposed in this paper. The sizes of CELP parameters in the encoder are carefully pruned to achieve a higher compression rate. To recover the speech quality and intelligibility degradation due to the pruned CELP parameters, a DAE-SC network with three hidden layers is employed in the *** with the conventional CELP codec at a 9.6k bps transmission rate, the proposed speech codec achieves extra 21.9% bit rate reduction with comparable speech quality and intelligibility that are evaluated by four commonly used speech performance metrics.

关键词： speech codec speech compression code excited linear prediction denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Survival prediction for patients with glioblastoma multiforme using a Cox proportional hazards denoising autoencoder network

引用

FRONTIERS IN COMPUTATIONAL NEUROSCIENCE 2023年 16卷 916511页

作者： Yan, Ting Yan, Zhenpeng Liu, Lili Zhang, Xiaoyu Chen, Guohui Xu, Feng Li, Ying Zhang, Lijuan Peng, Meilan Wang, Lu Li, Dandan Zhao, Dong Shanxi Med Univ Dept Pathol Key Lab Cellular Physiol Minist Educ Taiyuan Shanxi Peoples R China Taiyuan Univ Technol Coll Informat & Comp Taiyuan Peoples R China Shanxi Prov Peoples Hosp Taiyuan Peoples R China Capital Med Univ Beijing Chaoyang Hosp Dept Stomatol Beijing Peoples R China

ObjectivesThis study aimed to establish and validate a prognostic model based on magnetic resonance imaging and clinical features to predict the survival time of patients with glioblastoma multiforme (GBM). MethodsIn this study, a convolutional denoising autoencoder (DAE) network combined with the loss function of the Cox proportional hazard regression model was used to extract features for survival prediction. In addition, the Kaplan-Meier curve, the Schoenfeld residual analysis, the time-dependent receiver operating characteristic curve, the nomogram, and the calibration curve were performed to assess the survival prediction ability. ResultsThe concordance index (C-index) of the survival prediction model, which combines the DAE and the Cox proportional hazard regression model, reached 0.78 in the training set, 0.75 in the validation set, and 0.74 in the test set. Patients were divided into high- and low-risk groups based on the median prognostic index (PI). Kaplan-Meier curve was used for survival analysis (p = < 2e-16 in the training set, p = 3e-04 in the validation set, and p = 0.007 in the test set), which showed that the survival probability of different groups was significantly different, and the PI of the network played an influential role in the prediction of survival probability. In the residual verification of the PI, the fitting curve of the scatter plot was roughly parallel to the x-axis, and the p-value of the test was 0.11, proving that the PI and survival time were independent of each other and the survival prediction ability of the PI was less affected than survival time. The areas under the curve of the training set were 0.843, 0.871, 0.903, and 0.941;those of the validation set were 0.687, 0.895, 1.000, and 0.967;and those of the test set were 0.757, 0.852, 0.683, and 0.898. ConclusionThe survival prediction model, which combines the DAE and the Cox proportional hazard regression model, can effectively predict the prognosis of patients with GBM.

关键词： glioblastoma multiforme deep learning survival prediction denoising autoencoder time-dependent ROC curve Cox proportional hazard regression

来源：评论

学校读者我要写书评

暂无评论

An Efficient Convolutional denoising autoencoder-Based BDS NLOS Detection Method in Urban Forest Environments

引用

SENSORS 2024年第6期24卷 1959页

作者： Qin, Yahang Li, Zhenni Xie, Shengli Zhao, Haoli Wang, Qianming Guangdong Univ Technol Sch Automat Guangzhou 510006 Peoples R China Guangdong HongKong Macao Joint Lab Smart Discrete Guangzhou 510006 Guangdong Peoples R China 111 Ctr Intelligent Batch Mfg Based IoT Technol G Guangzhou 510006 Peoples R China Minist Educ Key Lab Intelligent Informat Proc & Syst Integrat Guangzhou 510006 Peoples R China Guangdong Key Lab IoT Informat Technol GDUT Guangzhou 510006 Peoples R China Taidou Microelect Technol Co Ltd Guangzhou 510663 Peoples R China

The BeiDou Navigation Satellite System (BDS) provides real-time absolute location services to users around the world and plays a key role in the rapidly evolving field of autonomous driving. In complex urban environments, the positioning accuracy of BDS often suffers from large deviations due to non-line-of-sight (NLOS) signals. Deep learning (DL) methods have shown strong capabilities in detecting complex and variable NLOS signals. However, these methods still suffer from the following limitations. On the one hand, supervised learning methods require labeled samples for learning, which inevitably encounters the bottleneck of difficulty in constructing databases with a large number of labels. On the other hand, the collected data tend to have varying degrees of noise, leading to low accuracy and poor generalization performance of the detection model, especially when the environment around the receiver changes. In this article, we propose a novel deep neural architecture named convolutional denoising autoencoder network (CDAENet) to detect NLOS in urban forest environments. Specifically, we first design a denoising autoencoder based on unsupervised DL to reduce the long time series signal dimension and extract the deep features of the data. Meanwhile, denoising autoencoders improve the model's robustness in identifying noisy data by introducing a certain amount of noise into the input data. Then, an MLP algorithm is used to identify the non-linearity of the BDS signal. Finally, the performance of the proposed CDAENet model is validated on a real urban forest dataset. The experimental results show that the satellite detection accuracy of our proposed algorithm is more than 95%, which is about an 8% improvement over existing machine-learning-based methods and about 3% improvement over deep-learning-based approaches.

关键词： denoising autoencoder BDS NLOS time series features urban forest

来源：评论

学校读者我要写书评

暂无评论

RunDAE model: Running denoising autoencoder models for denoising ECG signals

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2023年 166卷 107553-107553页

作者： Samann, Fars Schanze, Thomas TH Mittelhessen THM Inst Biomed Tech IBMT FB Life Sci Engn LSE Giessen Germany Univ Duhok Dept Biomed Engn Duhok Iraq

Background: The denoising autoencoder (DAE) is commonly used to denoise bio-signals such as electrocar-diogram (ECG) signals through dimensional reduction. Typically, the DAE model needs to be trained using correlated input segments such as QRS-aligned segments or long ECG segments. However, using long ECG segments as an input can result in a complex deep DAE model that requires many hidden layers to achieve a low-dimensional representation, which is a major ***: This work proposes a novel DAE model, called running DAE (RunDAE), for denoising short ECG segments without relying on the R-peak detection algorithm for alignment. The proposed RunDAE model employs a sample-by-sample processing approach, considering the correlation between consecutive, overlapped ECG segments. The performance of both the classical DAE and RunDAE models with convolutional and dense layers, respectively, is evaluated using corrupted QRS-aligned and non-aligned ECG segments with physical noise such as motion artifacts, electrode movement, baseline wander, and simulated noise such as Gaussian white ***: The simulation results indicate that 1. QRS-aligned segments are preferable to non-aligned segments, 2. the RunDAE model outperforms the classical DAE model in denoising ECG signals, especially when using dense layers and QRS-aligned segments, 3. training the RunDAE models with normal and arrhythmic ECG signals enhance model's properties/capabilities, and 4. the RunDAE is a multistage, non-causal, nonlinear adaptive ***: A shallow learning model, which consists of a couple of hidden layers, could achieve outstanding denoising performance using only the correlation among neighboring samples.

关键词： denoising autoencoder Convolutional denoising autoencoder Running denoising autoencoder Non-aligned ECG segments QRS-aligned ECG segments Overlapping ECG segments Multistage nonlinear adaptive filter

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：