检索结果-内蒙古大学图书馆

12th International Conference on Graphics and Image Processing (ICGIP)

作者： Tang, Yue Liang, Zhuonan Shi, Huaze Fu, Peng Sun, Quansen Nanjing Univ Sci & Technol Nanjing Peoples R China

ISBN: (纸本)9781510642782;9781510642775

Overfitting is a common problem in training of neural network with small training sets, which leads to worse performance on the new samples. Dropout has been proved to be an effective method to avoid overfitting, which prevents co-adaptation of features detectors by randomly discarding nodes from hidden layers of network. Inspired by dropout, we proposed a ranked dropout method to remove randomness of standard dropout mask, which discards a part of active nodes and forces the inactive nodes to learn more features to improve generalization ability. We apply the proposed ranked dropout to a stacked autoencoder network and compare it with standard dropout, gaussian dropout, uniform dropout and DropConnect on MNIST dataset. Experimental results of handwritten digit recognition demonstrate that the ranked strategy leads to better classification performance and the proposed ranked dropout can effectively reduce interference of overfitting and improve model's generalization ability.

关键词： Overfitting dropout stacked autoencoder handwritten digit recognition

来源：评论

学校读者我要写书评

暂无评论

Tourism demand forecasting: An ensemble deep learning approach

引用

TOURISM ECONOMICS 2022年第8期28卷 2021-2049页

作者： Sun, Shaolong Li, Yanzhao Guo, Ju-e Wang, Shouyang Xi An Jiao Tong Univ Sch Management 28 Xianning West Rd Xian 710049 Peoples R China Chinese Acad Sci Acad Math & Syst Sci Management Sci Beijing Peoples R China Univ Chinese Acad Sci Management Sci & Engn Beijing Peoples R China Chinese Acad Sci Ctr Forecasting Sci Beijing Peoples R China

The availability of tourism-related big data increases the potential to improve the accuracy of tourism demand forecasting but presents significant challenges for forecasting, including curse of dimensionality and high model complexity. A novel bagging-based multivariate ensemble deep learning approach integrating stacked autoencoder and kernel-based extreme learning machine (B-SAKE) is proposed to address these challenges in this study. By using historical tourist arrival data, economic variable data, and search intensity index (SII) data, we forecast tourist arrivals in Beijing from four countries. The consistent results of multiple schemes suggest that our proposed B-SAKE approach outperforms the benchmark models in terms of level accuracy, directional accuracy, and even statistical significance. Both bagging and stacked autoencoder can effectively alleviate the challenges brought by tourism big data and improve the forecasting performance of the models. The ensemble deep learning model we propose contributes to tourism demand forecasting literature and benefits relevant government officials and tourism practitioners.

关键词： bagging economic variables ensemble deep learning search intensity index stacked autoencoder tourism demand forecasting

来源：评论

学校读者我要写书评

暂无评论

A Convolutional Neural Network Model-Based Approach for Multi-Fault Diagnosis of Asynchronous Motors

A Convolutional Neural Network Model-Based Approach for Mult...

引用

IEEE/IAS Industrial and Commercial Power System Asia (IEEE I and CPS Asia)

作者： Shi, Jun Li, Jiangnan Wang, Tao Shenzhen Power Supply Bur Co Ltd Shenzhen Peoples R China CSG Elect Power Res Inst Guangzhou Peoples R China

ISBN: (纸本)9798350339345

In view of the low accuracy of fault diagnosis for asynchronous motors, this paper constructs an stacked fault diagnosis model based on stacked autoencoder and convolutional neural network. The model uses stacked autoencoder to reduce the dimensionality and noise of the asynchronous motor fault data, and inputs the processed data into the convolutional neural network for fault diagnosis. By removing the pooling layer in the traditional convolutional neural network and using LeakyRelu activation function, the robustness and generalization of the diagnosis model are further improved, and the accurate diagnosis of fault types is realized. The experimental results show that the proposed method can effectively improve the accuracy of multi-fault diagnosis for asynchronous motors, and has excellent performance.

关键词： convolutional neural network asynchronous motor fault diagnosis stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Fault and Performance Management in Multi-Cloud Based NFV using Shallow and Deep Predictive Structures 26

Fault and Performance Management in Multi-Cloud Based NFV us...

引用

26th International Conference on Computer Communication and Networks (ICCCN)

作者： Gupta, Lav Samaka, M. Jain, Raj Erbad, Aiman Bhamare, Deval Chan, H. Anthony WUSTL Dept CSE St Louis MO 63110 USA Qatar Univ Dept CSE Doha Qatar Huawei Technol Plano TX USA

ISBN: (纸本)9781509029914

Deployment of Network Function Virtualization (NFV) over multiple clouds accentuates its advantages like flexibility of virtualization, proximity to customers and lower total cost of operation. However, NFV over multiple clouds has not yet attained the level of performance to be a viable replacement for traditional networks. One of the reasons is the absence of a standard based Fault, Configuration, Accounting, Performance and Security (FCAPS) framework for the virtual network services. In NFV, faults and performance issues can have complex geneses within virtual resources as well as virtual networks and cannot be effectively handled by traditional rulebased systems. To tackle the above problem, we propose a fault detection and localization model based on a combination of shallow and deep learning structures. Relatively simpler detection has been effectively shown to be handled by shallow machine learning structures like Support Vector Machine (SVM). Deeper structure, i. e., the stacked autoencoder has been found to be useful for a more complex localization function where a large amount of information needs to be worked through to get to the root cause of the problem. We provide evaluation results using a dataset adapted from fault datasets available on Kaggle and another based on multivariate kernel density estimation and Markov sampling.

关键词： NFV Network Function Virtualization Virtual Network Service Virtual Network Function Service Function Chain Multi-cloud FCAPS Fault Detection Fault Localization Machine Learning Deep Learning Support Vector Machine stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Recognition of Underwater Target

Deep Learning-Based Recognition of Underwater Target

引用

IEEE International Conference on Digital Signal Processing (DSP)

作者： Cao, Xu Zhang, Xiaomin Yu, Yang Niu, Letian Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

ISBN: (纸本)9781509041657

Underwater target recognition remains a challenging task due to the complex and changeable environment. There have been a huge number of methods to deal with this problem. However, most of them fail to hierarchically extract deep features. In this paper, a novel deep learning framework for underwater target classification is proposed. First, instead of extracting features relying on expert knowledge, sparse autoencoder (AE) is utilized to learn invariant features from the spectral data of underwater targets. Second, stacked autoencoder (SAE) is used to get high-level features as a deep learning method. At last, the joint of SAE and softmax is proposed to classify the underwater targets. Experiment results with the received signal data from three different targets on the sea indicated that the proposed approach can get the highest classification accuracy compared with support vector machine (SVM) and probabilistic neural network (PNN).

关键词： Deep learning Underwater target recognition Sparse autoencoder stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Unsupervised Pre-training Approaches in Regression Problems 8

An Empirical Study on Unsupervised Pre-training Approaches i...

引用

8th IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Saikia, Pallabi Baruah, Rashmi Dutta Indian Inst Technol Guwahati Comp Sci & Engn Dept Gauhati India

ISBN: (纸本)9781538692769

Unsupervised pre-training allows for efficient training of deep architectures. It provides a good set of initialised weights to the deep architecture that can provide better generalisation of the data. In this paper, we aim to empirically analyse the effect of different unsupervised pre-training approaches for the task of regression on different datasets. We have considered two most common pre-training methods namely deep belief network and stacked autoencoder, and compared the results with the standard training algorithm without pretraining. The models with pretraining performed better than the model without pretraining in terms of error, convergence and the prediction of pattern. The results of the experiments also show the importance of hyperparameters tuning, specially learning rate, in providing a better prediction result. This study once again confirmed the effectiveness and potential of pretraining approach in nonlinear regression problem.

关键词： Deep Architecture Multilayer perceptron Deep learning Unsupervised pre-training Deep belief network Restricted Boltzmann machine Contrastive divergence stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Study on Deep Neural Networks Framework

A Study on Deep Neural Networks Framework

引用

2016 IEEE Advanced Information Management,Communicates,Electronic and Automation Control Conference(IMCEC 2016)

作者： Huang Yi Duan Xiusheng Sun Shiyu Chen Zhigang Department of Electronic and Optical Engineering Ordnance Engineering College 68129 Army

ISBN: (纸本)9781509001668

Deep neural networks(DNN) is an important method for machine learning,which has been widely used in many *** with the shallow neural networks(NN),DNN has better feature expression and the ability to fit the complex *** this paper,we first introduce the background of the development of the DNN,and then introduce several typical DNN model,including deep belief networks(DBN),stacked autoencoder(SAE) and deep convolution neural networks(DCNN),finally research its applications from three aspects and prospects the development direction of DNN.

关键词： deep neural networks deep belief networks stacked autoencoder deep convolution neural networks

来源：评论

学校读者我要写书评

暂无评论

The Comparison of deep learning recognition methods based on SAR image

The Comparison of deep learning recognition methods based on...

引用

IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

作者： Zhai, Jia Zhu, Sha Chen, Feng Xie, Xiaodan Zhu, Yong Yin, Hongcheng Sci & Technol Electromagnet Scattering Lab Beijing Peoples R China Beijing Inst Remote Sensing Informat Beijing Peoples R China Sci & Technol Opt Radiat Lab Beijing Peoples R China

ISBN: (纸本)9781728117089

Aiming at the problem of Synthetic Aperture Radar (SAR) target recognition, a new deep learning method is proposed. The stacked Auto Encoder (SAE) network and the convolutional Neural Network (CNN) have remarkable performance. Through the implementation and comparison of these methods, it is shown that the proposed deep learning recognition method has strong adaptability to different situations and has robustness to attitude angle, background and noise.

关键词： Synthetic Aperture Radar (SAR) target recognition principle component analysis stacked autoencoder convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Enhancing Speech and Music Discrimination Through the Integration of Static and Dynamic Features 25

Enhancing Speech and Music Discrimination Through the Integr...

引用

25th Interspeech Conference

作者： Chen, Liangwei Zhou, Xiren Tut, Qiang Chen, Huanhuan Univ Sci & Technol China Hefei Peoples R China Anhui Prov Hosp Hefei Peoples R China

Audio is inherently temporal data, where features extracted from each segment evolve over time, yielding dynamic traits. These dynamics, relative to the acoustic characteristics inherent in raw audio features, primarily serve as complementary aids for audio classification. This paper employs the reservoir computing model to fit the audio feature sequences efficiently, capturing feature-sequence dynamics into the readout models, and without the need for offline iterative training. Additionally, stacked autoencoders further integrate the extracted static features (i.e., raw audio features) with the captured dynamics, resulting in more stable and effective classification performance. The entire framework is called Static-Dynamic Integration Network (SDIN). The conducted experiments demonstrate the effectiveness of SDIN in speech-music classification tasks.

关键词： reservoir computing model stacked autoencoder speech-music classification audio processing

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Interaction Prediction in Coronavirus Disease 2019 Case Using Deep Semi-Supervised Learning Model 12

Drug-Target Interaction Prediction in Coronavirus Disease 20...

引用

12th International Conference on Advanced Computer Science and Information Systems (ICACSIS)

作者： Sulistiawan, Faldi Kusuma, Wisnu Ananta Ramadhanti, Nabila Sekar Tedjo, Aryo IPB Univ Fac Math & Nat Sci Dept Comp Sci Bogor Indonesia IPB Univ Dept Comp Sci Bogor Indonesia IPB Univ Trop Biopharmaca Res Ctr Bogor Indonesia Univ Indonesia Fac Med Dept Med Chem Jakarta Indonesia

ISBN: (纸本)9781728192796

Coronavirus disease 2019 (COVID-19) is an infectious disease of the respiratory system that caused a pandemic in 2020. There is still not any effective special treatment to cure it. Drug repositioning is used to find an effective drug for curing new diseases by finding new efficacy of registered drug. The new efficacy can be conducted by elaborating the interactions between compounds and proteins (DTI). Deep Semi-Supervised Learning (DSSL) is used to overcome the lack of DTI information. DSSL utilizes unsupervised learning algorithms such as stacked Auto Encoder (SAE) as pre-training for initializing weights on the Deep Neural Network (DNN). This study uses DSSL with a feature-based chemogenomics approach on the data resulted from the exploration of potential anti-coronavirus treatment. This study finds that the use of fingerprints for compound features and Dipeptide Composition (DC) for protein features gives the best results on accuracy (0.94), recall (0.83), precision (0.817), F-measure (0.822), and AUROC (0.97). From the test data predictions, 1766 and 929 positive interactions are found on the test data and herbal compounds, respectively.

关键词： coronavirus disease 2019 drug repositioning deep semi-supervised learning stacked autoencoder deep neural 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：