检索结果-内蒙古大学图书馆

Collaborative filtering in dynamic networks based on deep auto-encoder

JOURNAL OF SUPERCOMPUTING 2022年第5期78卷 7410-7427页

作者： Jalali, Shiva Hosseini, Monireh KN Toosi Univ Technol Dept Ind Engn Tehran Iran

The collaborative filtering method in recommender systems can produce suggestions with good quality. However, this method suffers from the issues of cold start and data sparsity. To overcome these problems, other data sources must be used to identify users. As a source of information, social relationships between users can help solve these problems. Recommender systems, on the other hand, are set in environments where data are generated continuously and with high dimension over time. For example, users have new rates and new relationships. These are indicative of the dynamic nature of system data, the changes in which classical models are unable to manage in order to provide appropriate suggestions to users. Then a dynamic model is needed. In this research, a new hybrid dynamic recommender model, which utilizes deep auto-encoder networks, is described to close these gaps. In this model, users' rating information and social relationships between them are used simultaneously to calculate similarity matrices between users at different timestamps. In each timestamp, the similarity matrix is given as input to the deep neural network, in which users are divided into different clusters. Users' new behaviors over time will help update matrices values. The use of social relationships data and the consideration of users' new behaviors over time solves the problems of classical methods, reduces recommending error, and increases user satisfaction. The proposed model is compared with state-of-the-art models;based on evaluation metrics. The results of execution on the real dataset show that the proposed model outperforms them.

关键词： Collaborative filtering Social network Dynamic networks deep auto-encoder Clustering

来源：评论

学校读者我要写书评

暂无评论

Segmentation of shoulder muscle MRI using a new Region and Edge based deep auto-encoder

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第10期82卷 14963-14984页

作者： Khan, Saddam Hussain Khan, Asifullah Lee, Yeon Soo Hassan, Mehdi Jeong, Woong Kyo Pakistan Inst Engn & Appl Sci Dept Comp & Informat Sci Pattern Recognit Lab Islamabad 45650 Pakistan Univ Engn & Appl Sci UEAS Dept Comp Syst Engn Swat 19060 Pakistan Pakistan Inst Engn & Appl Sci PIEAS Artificial Intelligence Ctr PAIC Islamabad 45650 Pakistan Pakistan Inst Engn & Appl Sci Ctr Math Sci Islamabad 45650 Pakistan Catholic Univ Daegu Coll Med Sci Dept Biomed Engn Daegu South Korea Air Univ Dept Comp Sci Islamabad Pakistan Korea Univ Coll Med Dept Orthopaed Surg Seoul South Korea

automatic segmentation of shoulder muscle MRI is challenging due to the high variation in muscle size, shape, texture, and spatial position of tears. Manual segmentation of tear and muscle portion is hard, time-consuming, and subjective to pathological expertise. This work proposes a new Region and Edge-based deep auto-encoder (RE-DAE) for shoulder muscle MRI segmentation. The proposed RE-DAE harmoniously employs average and max-pooling operations in the Convolutional encoder and decoder blocks. The DAE's region and edge-based segmentation encourage the network to extract homogenous and anatomical information, respectively. These two concepts, systematically combined in a DAE, generate a discriminative and sparse hybrid feature space (exploiting both region homogeneity and boundaries). Moreover, the concept of static attention is exploited in the proposed RE-DAE that helps effectively learn the tear region. The performances of the proposed RE-DAE architectures have been tested using a 3D MRI shoulder muscle dataset using the hold-out cross-validation technique. The MRI data has been collected from the Korea University Anam Hospital, Seoul, South Korea. Experimental comparisons have been conducted by employing innovative custom-made and existing pre-trained CNN architectures using transfer learning and fine-tuning. Objective evaluation on the muscle datasets using the proposed SA-RE-DAE showed a dice similarity of 85.58% and 87.07%, an accuracy of 81.57% and 95.58% for tear and muscle regions, respectively. The high visual quality and the objective result suggest that the proposed SA-RE-DAE can correctly segment tear and muscle regions in shoulder muscle MRI for better clinical decisions.

关键词： MRI Shoulder muscle deep auto-encoder Segmentation Transfer learning CNN

来源：评论

学校读者我要写书评

暂无评论

Unsupervised deep learning approach using a deep auto-encoder with an one-class support vector machine to detect structural damage

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2021年第1期20卷 406-425页

作者： Wang, Zilong Cha, Young-Jin Univ Manitoba Dept Civil Engn SP427 Stanley Pauley Engn Bldg15 Gillson St Winnipeg MB R3T 6B3 Canada

This article proposes an unsupervised deep learning-based approach to detect structural damage. Supervised deep learning methods have been proposed in recent years, but they require data from an intact structure and various damage scenarios of monitored structures for their training processes. However, the labeling work on the training data is typically time-consuming and costly, and sometimes collecting sufficient training data from various damage scenarios of infrastructures in service is impractical. In this article, the proposed unsupervised deep learning method based on a deep auto-encoder with an one-class support vector machine only uses the measured acceleration response data acquired from intact or baseline structures as training data, which enables future structural damage to be detected. The major contributions and novelties of the proposed method are as follows. First, an appropriate deep auto-encoder is carefully designed through comparative studies on the depth of neural networks. Second, the designed deep auto-encoder is taken as an extractor to obtain damage-sensitive features from the measured acceleration response data, and an one-class support vector machine is used as a damage detector. Third, experimental and numerical studies validate the high accuracy of the proposed method for damage detection: a 97.4% mean average for a 12-story numerical building model and a 91.0% accuracy for a laboratory-scaled steel bridge. Fourth, the proposed method also detects light damage (i.e. a 10% reduction in stiffness) with 96.9% to 99.0% accuracy, which shows its superior performance compared with the current state of the art. Fifth, it provides stable and more robust damage detection performance with reduced tuning parameters.

关键词： Unsupervised learning deep learning deep auto-encoder one-class support vector machine structural damage detection

来源：评论

学校读者我要写书评

暂无评论

A new deep auto-encoder using multiscale reconstruction errors and weight update correlation

引用

INFORMATION SCIENCES 2021年 559卷 130-152页

作者： Song, Wei Li, Wei Hua, Ziyu Zhu, Fuxin Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Jiangsu Prov Engn Lab Pattern Recognit & Computat Wuxi 214122 Jiangsu Peoples R China

deep auto-encoder (DAE) is a promising deep learning model to extract the features of data. However, it is difficult to achieve the desired network parameters by training due to the issue of inappropriate learning rate, which usually affects its performance of extracting features. In order to solve such an issue, in this paper we propose a new Variable Learning Speed DAE (VLSDAE) using Multiscale Reconstruction Errors (MRE) and Weights Update Correlation (WUC) to adaptively adjust its learning rate. Specifically, the reconstruction errors based on the multiscales, i.e. mini-batch, epoch and phase, are considered to reflect the macroscopic training effect. Moreover, for the sake of further representing the microscopic training state, WUC is proposed to depict the training effect of each neuron. We first give the complexity analysis and the theoretical proof for the convergence of VLSDAE. To further exhibit its performance, a parameter sensitivity analysis is then provided to investigate the effects of two key parameters. In addition, the proposed MRE, WUC and our integrated method are studied individually to reveal their learning effects. Finally, we compare VLSDAE with eight state-of-the-art algorithms. The experimental results demonstrate that VLSDAE outperforms the other eight competitors in terms of training error, classification accuracy, precision, recall and macro-F1. (C) 2021 Elsevier Inc. All rights reserved.

关键词： deep learning deep auto-encoder Multiscale reconstruction errors Weights update correlation Learning rate

来源：评论

学校读者我要写书评

暂无评论

Performance degradation assessment of slewing bearings based on deep auto-encoder and optimized particle filtering

引用

JOURNAL OF VIBRATION AND CONTROL 2019年第17期25卷 2380-2394页

作者： Pan, Yubin Hong, Rongjing Chen, Jie Wu, Weiwei Nanjing Tech Univ 30Puzhu Rd S Nanjing 211800 Jiangsu Peoples R China Yangzhou Univ Yangzhou Jiangsu Peoples R China

Due to the low speed and heavy load conditions of slewing bearings, extracting of effective features for fault diagnosis and prediction is difficult but crucial. Moreover, challenges such as large data volumes, unlabeled and multi-source bring more difficulties for advanced prognosis and health management methods. To solve these problems, a novel method for performance degradation assessment of bearings based on raw signals is proposed. In this methodology, a combination of deep auto-encoder (DAE) algorithm and particle filter algorithm is utilized for feature extraction and remaining useful life (RUL) prediction. First, the raw vibration signal is employed to train parameters of a restricted Boltzmann machine to build the DAE model. Through encoding and decoding multi-source data, root mean square error of reconstruction error between the raw signal and reconstructed signal is employed to detect incipient faults of slewing bearings. Then, degradation trend model is established by particle filtering to predict RUL of bearings. The effectiveness of proposed method is validated using simulated and experimental vibration signals. Results illustrate that proposed method can evaluate the performance degradation process and RUL of slewing bearings.

关键词： Slewing bearing deep auto-encoder feature extraction particle filter remaining useful life prediction

来源：评论

学校读者我要写书评

暂无评论

Real-time drive-by bridge damage detection using deep auto-encoder

引用

STRUCTURES 2023年 47卷 1167-1181页

作者： Li, Zhenkun Lin, Weiwei Zhang, Youqi Aalto Univ Dept Civil Engn Rakentajanaukio 4 Espoo 02150 Finland

Structural health condition monitoring of bridge structures has been a concern in the last decades due to their aging and deterioration, in which the core task is damage detection. Recently, the drive-by method has gained much attention as it only needs several sensors installed on the passing vehicle. In this paper, we proposed an automatic damage detection method, which can be exploited in real time when the vehicle is passing the bridge. There are three steps in the proposed method: (1) The vehicle's framed short-time vibrations instead of full-length data are utilized for training a deep auto-encoder model;at this stage, not commonly used time-domain accelerations of the passing vehicle, but its selected frequency-domain responses are employed to circumvent the influence of noises, (2) For the bridge with unknown health conditions, damage indicators can be extracted from its passing vehicle's short-time vibration data using the trained model, and (3) The bridge's health states are determined by real-time extracted damage indicators. To verify the proposed idea, a U-shaped continuous beam and a model truck are used to simulate the vehicle bridge interaction system in engineering. Results showed that the proposed method could identify the bridge's damage with an accuracy of 86.2% when different severity was considered. In addition, it was observed that higher damage severity could not be revealed by greater values of damage indicators in the laboratory test. Instead, a novel index called identified damage ratios was employed as a reference for assessing the severity of the bridge's damage. It was shown that with the increase in damage severity, the index would increase and gradually approach 100%.

关键词： Structural health monitoring Damage detection Drive-by Short-time Fourier transform deep auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A new framework using deep auto-encoder and energy spectral density for medical waveform data classification and processing

引用

BIOCYBERNETICS AND BIOMEDICAL ENGINEERING 2019年第1期39卷 148-159页

作者： Karim, Ahmad M. Guzel, Mehmet S. Tolun, Mehmet R. Kaya, Hilal Celebi, Fatih, V Aksaray Univ Elect & Elect Engn Aksaray Turkey Ankara Univ Dept Comp Engn TR-06830 Ankara Turkey Baskent Univ Dept Comp Engn Ankara Turkey AYBU Dept Comp Engn Ankara Turkey

This paper proposes a new framework for medical data processing which is essentially designed based on deep autoencoder and energy spectral density (ESD) concepts. The main novelty of this framework is to incorporate ESD function as feature extractor into a unique deep sparse auto-encoders (DSAEs) architecture. This allows the proposed architecture to extract more qualified features in a shorter computational time compared with the conventional frameworks. In order to validate the performance of the proposed framework, it has been tested with a number of comprehensive medical waveform datasets with varying dimensionality, namely, Epilepsy Serious Detection, SPECTF Classification and Diagnosis of Cardiac Arrhythmias. Overall, the ESD function speeds up the deep auto-encoder processing time and increases the overall accuracy of the results which are compared to several studies in the literature and a promising agreement is achieved. (C) 2018 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.

关键词： Energy spectral density deep auto-encoder deep learning Medical waveform data process

来源：评论

学校读者我要写书评

暂无评论

Spatial Fuzzy Clustering and deep auto-encoder for Unsupervised Change Detection in Synthetic Aperture Radar Images 38

Spatial Fuzzy Clustering and Deep Auto-encoder for Unsupervi...

引用

38th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Li, Yangyang Zhou, Linhao Peng, Cheng Jiao, Licheng Xidian Univ Key Lab Intelligent Percept & Image Understanding Joint Int Res Lab Intelligent Percept & Computat Minist EducInt Res Ctr Intelligent Percept & Com Xian 710071 Shaanxi Peoples R China

ISBN: (纸本)9781538671504

Change detection in synthetic aperture radar (SAR) images is to detect the changes happening during a period of time in the same area, which has important application research value. In this paper, we propose a novel method based on spatial fuzzy clustering (SFCM) and deep auto-encoder for the change-detection of SAR. In this method, the difference image (DI) is generated by the log-ratio operator. Then, the spatial fuzzy clustering (SFCM) algorithm is used to analyze the DI. The spatial fuzzy clustering (SFCM) algorithm adds spatial information to the fuzzy cluster, which effectively reduces the influence of speckle noise. Finally, we choose appropriate samples to train the deep auto-encoder. Real data and theoretical analysis show the effectiveness and robustness of the proposed method.

关键词： change detection spatial fuzzy clustering deep auto-encoder synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

A deep auto-encoder BASED LOW-DIMENSIONAL FEATURE EXTRACTION FROM FFT SPECTRAL ENVELOPES FOR STATISTICAL PARAMETRIC SPEECH SYNTHESIS 41

A DEEP AUTO-ENCODER BASED LOW-DIMENSIONAL FEATURE EXTRACTION...

引用

41st IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Takaki, Shinji Yamagishi, Junichi Natl Inst Informat Tokyo Japan Univ Edinburgh Ctr Speech Technol Res Edinburgh EH8 9YL Midlothian Scotland

ISBN: (纸本)9781479999880

In the state-of-the-art statistical parametric speech synthesis system, a speech analysis module, e.g. STRAIGHT spectral analysis, is generally used for obtaining accurate and stable spectral envelopes, and then low-dimensional acoustic features extracted from obtained spectral envelopes are used for training acoustic models. However, a spectral envelope estimation algorithm used in such a speech analysis module includes various processing derived from human knowledge. In this paper, we present our investigation of deep auto-encoder based, non-linear, data-driven and unsupervised low-dimensional feature extraction using FFT spectral envelopes for statistical parametric speech synthesis. Experimental results showed that a text-to-speech synthesis system using deep auto-encoder based low-dimensional feature extraction from FFT spectral envelopes is indeed a promising approach.

关键词： Statistical parametric speech synthesis deep auto-encoder Spectral envelope Vocoder

来源：评论

学校读者我要写书评

暂无评论

Towards Unknown Traffic Identification Using deep auto-encoder and Constrained Clustering 19th

Towards Unknown Traffic Identification Using Deep Auto-Encod...

引用

19th Annual International Conference on Computational Science (ICCS)

作者： Zhang, Yongzheng Zhao, Shuyuan 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)9783030227340;9783030227333

Nowadays, network traffic identification, as the fundamental technique in the field of cybersecurity, suffers from a critical problem, namely "unknown traffic". The unknown traffic refers to network traffic generated by previously unknown applications ( i.e., zero-day applications) in a pre-constructed traffic classification system. The ability to divide the mixed unknown traffic into multiple clusters, each of which contains only one application traffic as far as possible, is the key to solve this problem. In this paper, we propose the DePCK to improve the clustering purity. There are two main innovations in our framework: (i) It learns to extract bottleneck features via deep auto-encoder from traffic statistical characteristics;(ii) It uses the flow correlation to guide the process of pairwise constrained k-means. To verify the effectiveness of our framework, we make contrast experiments on two real-world datasets. The experimental results show that the clustering purity rate of DePCK can exceed 94.81% on the ISP-data and 91.48% on the WIDE-data [1], which outperform the state-of-the-art methods: RTC [20], and k-means with log data [15].

关键词： Unknown traffic deep auto-encoder Bottleneck features Pairwise constrained k-means

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：