检索结果-内蒙古大学图书馆

IEEE 7th International Conference on Advanced Technologies, Signal and Image Processing (ATSIP)

作者： Qahmash, Ayman AlQahtani, Basmah Misfer King Khalid Univ Informat & Comp Syst Dept Abha Saudi Arabia

ISBN: (纸本)9798350351491;9798350351484

The utilization of Artificial Intelligence 'AI' techniques for analyzing speech signals is so promising nowadays especially for various medical applications. In our proposed research, dealing with early diagnosis of Parkinson's disease using speech analysis is a highly promising and innovative approach that has demonstrated considerable potential in identifying the disease during its initial phases. This study uses a combined methodology that utilizes deep Learning 'DL' approach for speech features' extraction followed by one Machine Learning approach as for final classification. In order to cultivate these profound features, a deep auto-encoder was hence utilized as a technique for feature extraction, while a multi-layer perceptron (MLP) was employed as a classifier. Our empirical findings indicate that the DL models proposed in this study yielded favorable outcomes, achieving a success rate of 90%. The preliminary findings of this study indicate that the proposed approach has the potential to early identifying Parkinson's disease through the analysis of speech signals. Such an important finding will not only help neurologists and considerably during their clinical investigations but also will enrich medical further assessments. A clinical aided tool could be conceived consequently in correlation with the future clinical feedback.

关键词： Parkinson's Disease deep auto-encoder multi-layer perceptron (MLP) Voice Diagnosis speech signals

来源：评论

学校读者我要写书评

暂无评论

A deep Learning Method for Rough Surface Clutter Reduction in GPR Image

A Deep Learning Method for Rough Surface Clutter Reduction i...

引用

IEEE Radar Conference (RadarConf)

作者： Zhang, Yan Huston, Dryver Xia, Tian Univ Vermont Burlington VT 05405 USA

ISBN: (纸本)9781665436694

The major clutter in a typical ground penetrating radar (GPR) B-scan image is the ground surface clutter. It can severely obscure or distort the subsurface target response, especially when the surface profile variation is large and the target reflection signal is overlapped with the surface clutter. In this paper, we propose a deep auto-encoder based method for reducing the rough surface clutter in GPR images. In our method, the rough surface clutter reduction is formulated as an anomaly detection problem. The rough surface region in a Bscan image is splitted into small patches which are used as the training data set to train a deep auto-encoder. The trained auto-encoder captures the patterns of the rough surface patches. After training, the whole B-scan image is divided into small patches of the same size as the training patches and each of which is fed into the auto-encoder to compute an anomaly score. To reduce the clutter, we design a novel method that adopts a weighted sum approach to aggregate all patches based on their anomaly scores. For performance evaluation, simulation and laboratory tests are conducted, and the clutter-to-rest ratios (CRR) are computed to quantify the clutter reduction effectiveness. The CRR of the simulated B-scan image is reduced from 4.24 dB to -14.06 dB, and the CRRs of two measured B-scans are reduced from 3.71 dB to -20.45 dB, and from 8.62 dB to -8.07 dB, respectively.

关键词： deep auto-encoder rough surface clutter reduction ground penetrating radar

来源：评论

学校读者我要写书评

暂无评论

A New Cooperative deep Learning Method for Underwater Acoustic Target Recognition

A New Cooperative Deep Learning Method for Underwater Acoust...

引用

OCEANS - Marseille Conference

作者： Yang, Honghui Xu, Guanghui Yi, Shuzhen Li, Yiqing Northwestern Polytech Univ Sch Marine Sci & Technol Xian Peoples R China

ISBN: (纸本)9781728114507

Underwater acoustic target recognition is a difficult task due to the complicated and changeable environment. In this paper, a new cooperative deep learning method is proposed to get a better result. This new method combines deep long short-term memory network (DLSTM) and deep auto-encoder neural network (DAE) together. Firstly, we pre-train a DLSTM model in a LSTM based DAE network via unsupervised learning. Then, we utilize the pre -trained DLSTM model and softmax classifier to classify ship radiated noise. Experiments based on acquired data show that the proposed method can achieve a better classification performance compared with only using DAE network and DLSTM network.

关键词： underwater acoustic target recognition deep learning deep long short-term memory network deep auto-encoder cooperative deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards Unknown Traffic Identification via Embeddings and deep autoencoders 26

Towards Unknown Traffic Identification via Embeddings and De...

引用

26th International Conference on Telecommunications (ICT)

作者： Zhao, Shuyuan Zhang, Yongzheng Sang, Yafei Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9781728102733

Traffic classification, as a fundamental tool for network management and security, is suffering from a critical problem, namely "unknown traffic". The unknown traffic is defined as network traffic generated by previously unknown applications (i.e., zero-day applications) in a traffic classification system. The ability to divide the mixed unknown traffic into clusters, each of which contains only one application traffic as far as possible, is the key to solve this problem. This paper reports our recent exploration of the n-gram embeddings strategy, deep neural networks and clustering algorithms for constructing an unsupervised scheme for unknown network traffic identification. Experimental results on real-world traces demonstrate that our method gains average clustering purity rate about 97.35% when we use DNS, DHCP, BitTorrent, SSH, HTTP, IMAP, MySQL, and Github to simulate unknown traffic.

关键词： unknown traffic identification deep auto-encoder embedding network measurement

来源：评论

学校读者我要写书评

暂无评论

Learning to Compress Using deep autoencoder 57

Learning to Compress Using Deep AutoEncoder

引用

57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)

作者： Li, Qing Chen, Yang Western Digital Res Milpitas CA 95035 USA Univ Michigan Dept Stat Ann Arbor MI 48109 USA Univ Michigan Michigan Inst Data Sci Ann Arbor MI 48109 USA

ISBN: (纸本)9781728131511

A novel deep learning framework for lossy compression is proposed. The framework is based on deep autoencoder (DAE) stacked of Restricted Boltzmann Machines (RBMs), which form deep Belief Networks (DBNs). The proposed DAE compression scheme is one variant of the known fixed-distortion scheme, where the distortion is fixed and the compression rate is left to optimize. The fixed distortion is achieved by the DBN Blahut-Arimoto algorithm to approximate the Nth-order rate distortion approximating posterior. The trained DBNs are then unrolled to create a DAE, which produces an encoder and a reproducer. The unrolled DAE is fine-tuned with back-propagation through the whole autoencoder to minimize reconstruction errors.

关键词： rate distortion lossy source coding Restricted Boltzmann Machine deep auto-encoder deep Belief Network Blahut-Arimoto algorithm

来源：评论

学校读者我要写书评

暂无评论

deep Learning-Based Dependability Assessment Method for Industrial Wireless Network 5th

Deep Learning-Based Dependability Assessment Method for Indu...

引用

5th IFAC Symposium on Telematics Applications (TA)

作者： Sun, Danfeng Willmann, Sarah Inst F Automat & Kommunikat eV D-39106 Magdeburg Germany

Techniques on 5G and Internet of things bring a strong potential paradigm shift to wireless communication applications in industrial domain. Hence, there is a strong need for quantitative dependability assessment in these applications. However, with the ever-growing complexity and amount of wireless communication systems, their dependability relevant parameters also increase rapidly. In addition, the deep neural network has advantages on high dimensional data process. Hence, a deep learning-based dependability assessment method is proposed to address the issue, wherein a deep auto-encoder based approach is proposed to reduce data dimension and to obtain the data codes, and DBSCAN is used to cluster these codes. An experimental environment is built for collecting data set on the Multifaces, and a rough classification method is proposed to obtain a superior deep encoder model. Based on the superior model and DBSCAN, the data set are mainly divided into four dependability clusters. Copyright (C) 2019. The Authors. Published by Elsevier Ltd. All rights reserved.

关键词： DBSCAN deep auto-encoder dependability assessment machine learning industrial wireless network

来源：评论

学校读者我要写书评

暂无评论

Structure learning with similarity preserving

引用

NEURAL NETWORKS 2020年 129卷 138-148页

作者： Kang, Zhao Lu, Xiao Lu, Yiwei Peng, Chong Chen, Wenyu Xu, Zenglin Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 611731 Sichuan Peoples R China Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen Peoples R China

Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications. However, in many applications the data can display structures beyond simply being low-rank or sparse. Fully extracting and exploiting hidden structure information in the data is always desirable and favorable. To reveal more underlying effective manifold structure, in this paper, we explicitly model the data relation. Specifically, we propose a structure learning framework that retains the pairwise similarities between the data points. Rather than just trying to reconstruct the original data based on self-expression, we also manage to reconstruct the kernel matrix, which functions as similarity preserving. Consequently, this technique is particularly suitable for the class of learning problems that are sensitive to sample similarity, e.g., clustering and semisupervised classification. To take advantage of representation power of deep neural network, a deep auto-encoder architecture is further designed to implement our model. Extensive experiments on benchmark data sets demonstrate that our proposed framework can consistently and significantly improve performance on both evaluation tasks. We conclude that the quality of structure learning can be enhanced if similarity information is incorporated. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Similarity preserving Clustering Semisupervised classification Similarity measure deep auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A novel performance degradation prognostics approach and its application on ball screw

引用

MEASUREMENT 2022年 195卷

作者： Zhang, Xiaochen Luo, Tianjian Han, Te Gao, Hongli Fujian Normal Univ Coll Comp & Cyber Secur Fuzhou 350117 Fujian Peoples R China Minist Educ Engn Res Ctr Adv Energy Saving Driving Technol Chengdu 610031 Sichuan Peoples R China Tsinghua Univ Dept Ind Engn Beijing 100084 Peoples R China Southwest Jiaotong Univ Sch Mech Engn Chengdu 610031 Sichuan Peoples R China

The performance degradation prognostics of ball screw means important economic value and engineering application prospect. This paper proposes a performance degradation prognostics method which can be applied on ball screw. A clustering-based ensemble deep auto-encoders (EDAEs) was designed based on the selective ensemble and majority voting to extract features from the acceleration data. Then the sensitive feature distributions of different degradation cycles constitute the Gaussian mixture model (GMM), and the overlap degree of these distributions can be calculated to construct the health indicator. Finally, deep forest algorithm was introduced to achieve trend prognosis of health indicator. Meanwhile, the validity of the proposed method is confirmed by whole life cycle data of ball screw. The experimental results demonstrate that the proposed method can accurately identify the risk level of performance and realize the performance degradation prognostics.

关键词： deep auto-encoder deep forest Gaussian mixture model Health indicator Performance degradation

来源：评论

学校读者我要写书评

暂无评论

Relation-Guided Representation Learning

引用

NEURAL NETWORKS 2020年 131卷 93-102页

作者： Kang, Zhao Lu, Xiao Liang, Jian Bai, Kun Xu, Zenglin Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Sichuan Peoples R China Trusted Cloud Comp & Big Data Key Lab Sichuan Pro Chengdu Sichuan Peoples R China Tencent Cloud & Smart Ind Grp Beijing Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Shenzhen Peoples R China Peng Cheng Lab Ctr Artificial Intelligence Shenzhen Peoples R China

deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data from a latent space and neglect rich latent structural information. In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning. Different from previous work, our framework well preserves the relations between samples. Since the prediction of pairwise relations themselves is a fundamental problem, our model adaptively learns them from data. This provides much flexibility to encode real data manifold. The important role of relation and representation learning is evaluated on the clustering task. Extensive experiments on benchmark data sets demonstrate the superiority of our approach. By seeking to embed samples into subspace, we further show that our method can address the large-scale and out-of-sample problem. Our source code is publicly available at: https://***/nbShawnLu/RGRL. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： deep auto-encoder Unsupervised representation learning Subspace clustering Pairwise relation

来源：评论

学校读者我要写书评

暂无评论

Learning Graph Enhanced Spatial-Temporal Coherence for Video Anomaly Detection

引用

IEEE SIGNAL PROCESSING LETTERS 2023年 30卷 314-318页

作者： Cheng, Kai Liu, Yang Zeng, Xinhua Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China

Video Anomaly Detection (VAD) is a critical yet challenging task in the signal processing community. Since part abnormal events cannot be detected by analyzing spatial or temporal information alone, learning spatial-temporal coherence has been proven the key to effective VAD. To this end, we propose a Graph Enhanced Spatial-Temporal Attention (GESTA) to address unsupervised VAD by learning the spatial-temporal coherence of normal events. Firstly, we propose a Dynamic Graph Recurrent Neural Network (DGRNN) to extract the motion patterns. Then, we propose a Spatial-Temporal Attention Module (STAM) to better model spatial-temporal coherence by integrating the prototypical spatial and temporal information. Finally, the fused spatial-temporal features are fed into the decoder to predict future frames. In testing phase, the anomaly with irregular information will result in poor prediction results. Experiments on three benchmarks demonstrate that our GESTA performs comparably to the state-of-the-art methods, and extensive analysis proves the effectiveness of DGRNN and STAM.

关键词： Optical signal processing Decoding Benchmark testing Task analysis Optical computing Coherence Predictive models Video anomaly detection unsupervised learning spatial-temporal attention deep auto-encoder graph 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：