检索结果-内蒙古大学图书馆

A novel multi-scale and sparsity auto-encoder for classification

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2022年第12期13卷 3909-3925页

作者： Wang, Huiling Sun, Jun Gu, Xiaofeng Song, Wei Jiangnan Univ Sch IoT Engn Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Jiangsu Peoples R China

The inspiration for generating the multi-scale feature representation originates from the basic observation that multi-scale is closely related to human visual physiological characteristics. Also, since the increase of hidden layer neurons and the amount of data leads to the rise of redundant information, a large amount of calculation makes a model more complex. This paper proposes a novel learning method, namely, multi-scale feature consistency regularization and L-21-norm minimization sparse auto-encoder (LR21-MSAE). The multi-scale feature consistency regularization can achieve the latent representations and the visual details while retaining multi-scale information. This method ensures that LR21-MSAE can get valid information for better classification accuracy. By implementing the L-21-norm minimization constraint, the LR21-MSAE can adaptively eliminate the potential noise and redundant neurons by enforcing some rows and columns of the weight matrix to be reduced to zero. It can reduce the complexity of the learning model and promote learning sparsity features to generate a compact network. Moreover, introducing the Wasserstein distance in the sparse auto-encoder to measure the difference between the two distributions allows for a more stable training process and faster convergence. To complete the test of the LR21-MSAE model, we choose to conduct the experiments on some publicly available datasets MNIST, Fashion-MNIST, CIFAR-10, USPS, ISOLET, Pendigits, and Ecoli. We demonstrate the advantages of LR21-MSAE, through the experimental results, compared with state-of-the-art feature extraction methods.

关键词： Feature representation auto-encoder Multi-scale feature L-21-norm Classification

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based auto-encoder for Time-Offset Sub-Faster-Than-Nyquist Downlink NOMA With Timing Errors and Imperfect CSI

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2024年第7期18卷 1178-1193页

作者： Aboutaleb, Ahmed Torabi, Mohammad Belzer, Benjamin Sivakumar, Krishnamoorthy Marvell Technol Inc Santa Clara CA 95054 USA Washington State Univ Sch EECS Pullman WA 99164 USA

This paper presents architecture designs and performance evaluations for the encoding and decoding of transmitted and received sequences for downlink time-offset sub-faster-than-Nyquist non-orthogonal multiple access signaling (TO-sFTN-NOMA). A conventional singular value decomposition (SVD)-based scheme for TO-sFTN-NOMA is employed as a benchmark. While this SVD scheme provides reliable communication, our findings reveal that it is not optimal in terms of bit error rate (BER) performance. Moreover, the SVD scheme is sensitive to timing offset errors, and its complexity increases quadratically with the sequence length. To overcome these limitations and improve the TO-sFTN-NOMA's performance, we propose a convolutional neural network (CNN) auto-encoder (AE) technique for encoding and decoding with linear time complexity. We explain the design of the encoder and decoder architectures and the training criteria. By considering several variants of the proposed CNN AE, we show that the proposed CNN AE can achieve an excellent trade-off between performance and complexity. The proposed CNN AE surpasses the SVD method by approximately 10 dB in a TO-sFTN-NOMA system with no timing offset errors and no channel state information (CSI) estimation errors. In the presence of CSI error with variance of 1% and uniform timing error at +/- 4% of the symbol interval, the proposed CNN AE provides up to 16 dB SNR gain over the SVD method. We also propose a novel modified training objective function consisting of a weighted summation of the cross-entropy (CE) loss and a Q-function metric related to the BER. Simulations show that the modified objective loss function achieves SNR gains of up to 1 dB over the CE loss function alone.

关键词： NOMA Decoding Symbols Downlink Timing Interference cancellation Convolutional neural networks Asynchronous transmission auto-encoder deep learning faster-than Nyquist signaling neural networks non-orthogonal multiple access

来源：评论

学校读者我要写书评

暂无评论

Premature Ventricular Contractions Detection by Multi-Domain Feature Extraction and auto-encoder-based Feature Reduction

引用

CIRCUITS SYSTEMS AND SIGNAL PROCESSING 2024年第5期43卷 3279-3296页

作者： Ebrahimpoor, Maryam Taghizadeh, Mehdi Fatehi, Mohammad Hossein Mahdiyar, Omid Jamali, Jasem Islamic Azad Univ Dept Biomed Engn Kazerun Branch Kazerun Iran Islamic Azad Univ Dept Elect Engn Kazerun Branch Kazerun Iran

Cardiovascular disorders are known to be among the most severe diseases and the leading causes of mortality all over the globe. Premature ventricular contractions (PVC) are one of the most prevalent types of cardiac arrhythmia. Recording and analyzing electrocardiogram (ECG) signals is one of the most popular methods (the least intrusive and least expensive) for investigating cardiac disorders. In this study, a new supervised approach for the automated detection of PVC has been developed through a combination of handcrafted feature extraction from ECG signals and deep-learning-based feature reduction. The proposed approach utilized multiple methodologies, namely statistical and chaos analysis in the time domain and time-frequency domain, and morphological assessment, to extract numerous features from ECG signals. Then, a variational autoencoder network is developed as a deep learning-based feature reduction technique to reduce the number of extracted features and obtain the most discriminating features. Finally, a support vector machine, k-nearest neighbor, and neural network classifiers with fivefold cross-validation are utilized to classify ECG signals. The MIT-BIH database is used to evaluate the proposed approach. The numerical results show that the proposed approach performs better than the current state-of-the-art studies.

关键词： Premature ventricular contraction (PVC) Electrocardiogram (ECG) Machine learning Feature extraction auto-encoder Feature reduction

来源：评论

学校读者我要写书评

暂无评论

An Imputation Method for Missing Data Based on an Extreme Learning Machine auto-encoder

引用

IEEE ACCESS 2018年 6卷 52930-52935页

作者： Lu, Cheng-Bo Mei, Ying Lishui Univ Coll Engn Lishui 323000 Peoples R China

This paper proposes an imputation method for missing data based on an extreme learning machine auto-encoder (ELM-AE). The imputation chooses a set of plausible values determined by ELM-AE and then substitutes the average of these plausible values for the missing values. To compare the performance of ELM-AE imputation with the three other widely used imputation techniques, we conducted comprehensive experiments using seven UCI benchmark data sets. The proposed ELM-AE imputation approach proved to be superior to the other three methods based on the results using these data sets.

关键词： Imputation extreme learning machine auto-encoder generalized mean absolute deviation purity K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale auto-encoder for Edge Detection

引用

IEEE ACCESS 2022年 10卷 116253-116260页

作者： Shi, Changyou Lu, Jianping Sun, Qiang Zhou, Jing Huang, Wei Xia, Rongze Army Engn Univ PLA Sch Commun Sergeant Chongqing 400035 Peoples R China

A multi-scale encoder algorithm is proposed for image edge detection, which takes the auto-encoder as basic backbone structure. Three auto-encoders, each is responsible for processing an image of one scale, are organized together to perform image-to-image prediction by combining all multi-scale convolutional features. Taking the advantage of the multi-scale strategy and self-attention mechanism, the algorithm detects image edges from coarse to fine gradually, and succeeds in detecting edges missed easily in other works. Two types of skip connections designed in the model structure. One is connected between encoder and decoder within an auto-encoder, worked as the residual function, the other is between auto-encoders, providing multi-scale knowledge about the edges. The loss function is composed of cross-entropy function and Dice coefficient term which is used to handle imbalanced training data. Experimental results evaluated from BSDS500 and BIPED datasets show the algorithm achieves scores of 0.847, 0.858, 0.884 on ODS, OIS, AP indices and output high-quality edges.

关键词： Image edge detection Feature extraction Deep learning Symbols Image resolution Detectors Decoding Edge computing Deep learning auto-encoder edge detection multi-scale technology

来源：评论

学校读者我要写书评

暂无评论

Appearance-Motion United auto-encoder Framework for Video Anomaly Detection

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第5期69卷 2498-2502页

作者： Liu, Yang Liu, Jing Lin, Jieyu Zhao, Mengyang Song, Liang Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China Univ Toronto Dept Elect & Comp Engn Toronto ON M5S 1A1 Canada

The key to video anomaly detection is understanding the appearance and motion differences between normal and abnormal events. However, previous works either considered the characteristics of appearance or motion in isolation or treated them without distinction, making the model fail to exploit the unique characteristics of both. In this brief, we propose an appearance-motion united auto-encoder (AMAE) framework to jointly learn the prototypical spatial and temporal patterns of normal events. The AMAE framework includes a spatial auto-encoder to learn appearance normality, a temporal auto-encoder to learn motion normality, and a channel attention-based spatial-temporal decoder to fuse the spatial-temporal features. The experimental results on standard benchmarks demonstrate the validity of the united appearance-motion normality learning. The proposed AMAE framework outperforms the state-of-the-art methods with AUCs of 97.4%, 88.2%, and 73.6% on the UCSD Ped2, CUHK Avenue, and ShanghaiTech datasets, respectively.

关键词： Decoding Convolutional codes Task analysis Loss measurement Image reconstruction Convolution Feature extraction Video anomaly detection deep learning auto-encoder spatial-temporal features channel attention

来源：评论

学校读者我要写书评

暂无评论

Adversarial auto-encoder for rating prediction with ratings and reviews

引用

WEB INTELLIGENCE 2020年第4期18卷 285-294页

作者： Yi, Jin Huang, Jiajin Qin, Jin Guizhou Univ Coll Comp Sci & Technol Guiyang 550025 Peoples R China Beijing Univ Technol Int WIC Inst Beijing 100124 Peoples R China

Recommender systems have been widely used in our life in recent years to facilitate our life. And it is very important and meaningful to improve recommendation performance. Generally, recommendation methods use users' historical ratings on items to predict ratings on their unrated items to make recommendations. However, with the increase of the number of users and items, the degree of data sparsity increases, and the quality of recommendations decreases sharply. In order to solve the sparsity problem, other auxiliary information is combined to mine users' preferences for higher recommendation quality. Similar to rating data, review data also contain rich information about users' preferences on items. This paper proposes a novel recommendation model, which harnesses an adversarial learning among auto-encoders to improve recommendation quality by minimizing the gap of the rating and review relation between a user and an item. The empirical studies on real-world datasets show that the proposed method improves the recommendation performance.

关键词： Review recommendation adversarial learning auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Applying adversarial auto-encoder for estimating human walking gait abnormality index

引用

PATTERN ANALYSIS AND APPLICATIONS 2019年第4期22卷 1597-1608页

作者： Trong-Nguyen Nguyen Meunier, Jean Univ Montreal Image Proc Lab DIRO Room 2340Pavillon Andre Aisenstadt Montreal PQ H3T 1J4 Canada

This paper proposes an approach that estimates a human walking gait abnormality index using an adversarial auto-encoder (AAE), i.e., a combination of auto-encoder and generative adversarial network (GAN). Since most GAN-based models have been employed as data generators, our work introduces another perspective of their application. This method directly works on a sequence of 3D point clouds representing the walking postures of a subject. By fitting a cylinder onto each point cloud and feeding cylindrical histograms to an appropriate AAE, our system is able to provide different measures that may be used as gait abnormality indices. The combinations of such quantities are also investigated to obtain improved indicators. The ability of our method is demonstrated by experimenting on a large dataset of nearly 100 thousands point clouds, and the results outperform related approaches that employ different input data types.

关键词： Gait Adversarial auto-encoder Point cloud Posture Depth camera Kinect Mirror

来源：评论

学校读者我要写书评

暂无评论

Joint Design of Measurement Matrix and Sparse Support Recovery Method via Deep auto-encoder

引用

IEEE SIGNAL PROCESSING LETTERS 2019年第12期26卷 1778-1782页

作者： Li, Shuaichao Zhang, Wanqing Cui, Ying Cheng, Hei Victor Yu, Wei Shanghai Jiao Tong Univ Shanghai 200240 Peoples R China Univ Toronto Toronto ON M5S 3G4 Canada

Sparse support recovery arises in many applications in communications and signal processing. Existing methods tackle sparse support recovery problems for a given measurement matrix, and cannot flexibly exploit the properties of sparsity patterns for improving performance. In this letter, we propose a data-driven approach to jointly design the measurement matrix and support recovery method for complex sparse signals, using auto-encoder in deep learning. The proposed architecture includes two components, an auto-encoder and a hard thresholding module. The proposed auto-encoder successfully handles complex signals using standard auto-encoder for real numbers. The proposed approach can effectively exploit properties of sparsity patterns, and is especially useful when these underlying properties do not have analytic models. In addition, the proposed approach can achieve sparse support recovery with low computational complexity. Experiments are conducted on an application example, device activity detection in grant-free massive access for massive machine type communications (mMTC). Numerical results show that the proposed approach achieves significantly better performance with much less computation time than classic methods, in the presence of extra structures in sparsity patterns.

关键词： Sparse support recovery auto-encoder deep learning device activity detection grant-free massive access

来源：评论

学校读者我要写书评

暂无评论

Spatial and temporal prediction of secondary crashes combining stacked sparse auto-encoder and long short-term memory

引用

ACCIDENT ANALYSIS AND PREVENTION 2023年第1期191卷 107205页

作者： Li, Haojie Gao, Qi Zhang, Ziqian Zhang, Yingheng Ren, Gang Southeast Univ Sch Transportat Nanjing Peoples R China Jiangsu Key Lab Urban ITS Nanjing Peoples R China Jiangsu Prov Collaborat Innovat Ctr Modern Urban T Nanjing Peoples R China

Secondary crashes occur within the spatial and temporal impact area of primary crashes, resulting in traffic delays and safety problems. While most existing studies focus on the likelihood of secondary crashes, predicting the spatio-temporal location of secondary crashes could offer valuable insights for implementing prevention strategies. This includes guiding the deployment of emergency response measures and determining appropriate speed limits. The main objective of this study is to develop a prediction method for the spatial and temporal locations of secondary crashes. A hybrid deep learning model SSAE-LSTM is proposed by combining stacked sparse auto-encoder (SSAE) and long short-term memory network (LSTM). Traffic and crash data on the California I-880 highway covering the period of 2017-2021 are collected. The identification of secondary crashes is performed by the speed contour map method. The time and distance gaps between primary and secondary crashes are modeled using multiple 5-minute interval traffic variables as inputs. Multiple models are developed for benchmarking purposes, including PCA-LSTM, which incorporates principal component analysis (PCA) and LSTM, SSAE-SVM, which incorporates SSAE and support vector machine (SVM), and back propagation neural network (BPNN). The performance comparison indicates that the hybrid SSAE-LSTM model outperforms the other models in terms of both spatial and temporal prediction. In particular, SSAE4-LSTM1 (with 4 SSAE layers and 1 LSTM layer) demonstrates superior spatial prediction performance, while SSAE4-LSTM2 (with 4 SSAE layers and 2 LSTM layers) excels in temporal prediction. A joint spatio-temporal evaluation is also conducted to measure the overall accuracy of the optimal models over different permitted spatio-temporal ranges. Finally, practical suggestions are provided for secondary crash prevention.

关键词： Road safety Secondary crash Spatial and temporal gaps auto-encoder Long short-term memory 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：