检索结果-内蒙古大学图书馆

Multi-Channel and Fusion Encoding Strategy Based auto encoder Model for Video Recommendation

IEEE ACCESS 2019年 7卷 86004-86017页

作者： Yan, Wenjie Wang, Dong Liu, Jing Ma, Liang Li, Zhi Hebei Univ Technol Sch Artificial Intelligence Tianjin 300401 Peoples R China Hebei Prov Key Lab Big Data Calculat Tianjin 300401 Peoples R China

Recommendation techniques are widely used in many areas to deal with the information overload problem. However, the recommendation theory has suffered from the sparseness problem, which decreases the precision of the recommendation algorithms heavily. Deep learning theory has proven to be a very efficient tool to mine the latent information of data. In this paper, a novel scalable multi-channel and fusion encoding strategy-based auto encoder (MCFE-AE) model is introduced to make recommendations by deeply mining the latent features of users and video items of the data. The detail of the proposed algorithm is summarized as follows. First, the rating data that represent the users' preference are sent to the input port of the proposed MCFE-AE model as raw input data. Second, the latent features of users and items have been deeply mined by the multi-channel and fusion encoding process of the proposed MCFE-AE model. Third, the final rating prediction result has been obtained by the decoding process of the proposed MCFE-AE model. The extensive experiments have shown the benefits of the proposed algorithm on the measure of mean absolute error (MAE) and root mean square error (RMSE) compared with the state-of-the-art algorithms. Besides, the number of channels of the MCFE-AE, the L-1 and L-2 regularization method, the learning rate, and the important regularization parameter lambda have been studied thoroughly in this paper.

关键词： Deep learning multi-channel auto encoder video recommendation

来源：评论

学校读者我要写书评

暂无评论

Droidencoder: Malware detection using auto-encoder based feature extractor and machine learning algorithms

引用

COMPUTERS & ELECTRICAL ENGINEERING 2023年第1期110卷

作者： Bakir, Halit Bakir, Rezan Sivas Univ Sci & Technol Fac Engn & Nat Sci Comp Engn Dept Sivas Turkiye

Android Malware detection became a hot topic over the last several years. Although considerable studies have been conducted utilizing machine learning-based methods, little attention has been dedicated to the feature extraction importance which considers an essential factor when using machine learning methods. Thus, in this study, we proposed a new feature extraction method based on the auto-encoder structure. Particularly, we propose Droidencoder, a novel autoencoder-based model to classify Android malware applications. On the grounds of this, an image-based Android app dataset composed of 3000 malicious apps and 3000 benign apps is constructed. Then, three different auto-encoders, namely ANN-based auto-encoder, CNN-based auto-encoder, and VGG19-based auto-encoder have been proposed to extract features from the visualized Malware dataset. Three different experiments were conducted for extracting features in order to train multiple machine learning algorithms, such as decision tree, extra tree, k-nearest neighbors, LightGBM, XGBoost, Random forest, linear regression, and support vector machine. Furthermore, cross-validation alongside multiple metrics was used for evaluating the performance of the proposed models. According to the obtained results, the proposed method approved its affectivity with superior performance in terms of all metrics.

关键词： auto encoder Malware detection Android application Code analysis

来源：评论

学校读者我要写书评

暂无评论

RUNNING STATE ASSESSMENT FOR INDUCED DRAFT FANS USING auto encoder MODEL COMBINED WITH FUZZY SYNTHETIC

引用

ASME Power Conference 2019

作者： Yang, Jiawei Hu, Di Yang, Tao Gao, Wei Li, Chunmei Huang, Zhihui Huazhong Univ Sci & Technol Sch Energy & Power Engn Wuhan 430074 Peoples R China Guangdong Yudean Grp Co Ltd Shajiao C Power Plant Dongguan 523936 Peoples R China

ISBN: (纸本)9780791859100

In order to explore the operation and maintenance characteristics of important auxiliary machines in large-scale power plant coal-fired boilers, a running state assessment model for auxiliary equipment is established. In this paper, taking the complex variability of the operating conditions of thermal power equipment into consider, auto encoder model combined with fuzzy synthetic is proposed. Based on the residual of the model results and the actual power plant operation data, combined with the fuzzy evaluation model to establish a state assessment model, and analyze the actual situation of the induced draft fan of the power plant, to make a real-time assessment of operation status. The evaluation results show the advantages of the state assessment strategy proposed in this paper;and it can reflect the deterioration of the induced draft fan status in time, providing guidance for the operation and maintenance of the equipment.

关键词： Running state assessment Induced draft fan auto encoder Fuzzy synthetic

来源：评论

学校读者我要写书评

暂无评论

Anomaly-based Intrusion Detection Using auto-encoder 27

Anomaly-based Intrusion Detection Using Auto-encoder

引用

27th International Conference on Software, Telecommunications and Computer Networks (SoftCOM)

作者： Nguimbous, Yves Nsoga Ksantini, Riadh Bouhoula, Adel Higher Sch Commun Tunis Digital Secur Res Lab Tunis Tunisia

ISBN: (纸本)9789532900880

Intrusion detection systems do not perform well when it comes to detecting new attacks. Therefore improving their performance in that regard is an active research topic. In this study, to detect unknown attacks with high accuracy, we have proposed an anomaly detection model based on auto encoder. Generally speaking, the key factor that directly affects the accuracy of the proposed relevant anomaly detection models, is the threshold value estimation. For this reason, we propose an efficient anomaly detection model based on auto-encoder and novel thresholding procedure, using training data reconstruction error percentiles and parameters fine-tuning, rather than the relevant state-of-the-art thresholding approaches in the current literature. The proposed method has been evaluated and compared to the widely used anomaly detection thresholding methods, on the KDDCUP'99 network traffic connections testing and training sets. Our experimental results have demonstrated that our method has outperformed the other methods, in term of classification performance, with amelioration of up to 7% of the Area Under the ROC Curve.

关键词： Networking security Intrusion Detection auto encoder Thresholding Procedure

来源：评论

学校读者我要写书评

暂无评论

Robust Facial Alignment with Internal Denoising auto-encoder 16

Robust Facial Alignment with Internal Denoising Auto-Encoder

引用

16th Conference on Computer and Robot Vision (CRV)

作者： Aspandi, Decky Martinez, Oriol Sukno, Federico Binefa, Xavier Pompeu Fabra Univ Dept Informat & Commun Technol Barcelona Spain

ISBN: (纸本)9781728118383

The development of facial alignment models is growing rapidly thanks to the availability of large facial land-marked datasets and powerful deep learning models. However, important challenges still remain for facial alignment models to work on images under extreme conditions, such as severe occlusions or large variations in pose and illumination. Current attempts to overcome this limitation have mainly focused on building robust feature extractors with the assumption that the model will be able to discard the noise and select only the meaningful features. However, such an assumption ignores the importance of understanding the noise that characterizes unconstrained images, which has been shown to benefit computer vision models if used appropriately on the learning strategy. Thus, in this paper we investigate the introduction of specialized modules for noise detection and removal, in combination with our state-of-the-art facial alignment module and show that this leads to improved robustness both to synthesized noise and in-the-wild conditions. The proposed model is built by combining two major subnetworks: internal image denoiser (based on the auto-encoder architecture) and facial landmark localiser (based on the inception-resnet architecture). Our results on the 300-W and Menpo datasets show that our model can effectively handle different types of synthetic noise, which also leads to enhanced robustness in real-world unconstrained settings, reaching top state-of-the-art accuracy.

关键词： Facial Alignment auto encoder Noise Normalization

来源：评论

学校读者我要写书评

暂无评论

auto-encoder generative adversarial networks

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2018年第3期35卷 3043-3049页

作者： Zhai, Zhonghua Zhejiang Univ Sch Math Sci Hangzhou Zhejiang Peoples R China

Generative Adversarial Networks have demonstrated potential on a variety of generative tasks, although they are regarded as unstable and sometimes they miss modes. We propose auto-encoder Generative Adversarial Networks a convolutional neural network combining auto-encoders with Generative Adversarial Networks. The former brings more information to Generative Adversarial Networks to reduce problems of miss modes and the latter makes the picture generated more coherent because it can better handle multiple modes in the output. We also show that image composition is available for auto-encoder Generative Adversarial Networks so that it can be used for many feature-based tasks. Besides, we can generate different samples by adding a random noise to a feature vector.

关键词： Generative adversarial networks auto encoder joint loss image composition

来源：评论

学校读者我要写书评

暂无评论

ELM-Based Signal Detection Scheme of MIMO System Using auto encoder 24th

ELM-Based Signal Detection Scheme of MIMO System Using Auto ...

引用

24th International Conference on Neural Information Processing (ICONIP)

作者： Long, Fei Yan, Xin Guizhou Inst Technol Sch Elect & Informat Engn Guiyang 550001 Peoples R China Guizhou Univ Coll Big Data & Informat Engn Guiyang 550025 Peoples R China

ISBN: (纸本)9783319701363;9783319701356

Signal detection scheme is the key technology to the implementation of multiple-input multiple-output (MIMO) wireless communication system, while the spatial-multiplexing coded MIMO systems cause a severe design challenge for signal detection algorithms. Although many researches focus on searching the solution space for optimal solution based on more efficient searching algorithm, the signal detection of MIMO system does not regarded as a classification problem. In this paper, the detection problem is considered as a feature classification, and a novel signal detection scheme of MIMO system based on extreme learning machine auto encoder (ELM-AE) is proposed. The proposed algorithm can efficiently extract the features of input data by ELM-AE and classify these representations to corresponding groups rapidly by using extreme learning machine (ELM). This paper has constructed a theoretical model of the proposed signal detector for MIMO system and carried out simulations to evaluating its performance. Simulation results indicate that the proposed detector outperforms many traditional schemes and state-of-the-art algorithms.

关键词： MIMO Signal detection Extreme learning machine auto encoder Feature classification

来源：评论

学校读者我要写书评

暂无评论

The prediction of protein secondary structure based on auto encoder 13

The prediction of protein secondary structure based on auto ...

引用

13th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)

作者： Zhang Shuai-yan Liu Yi-hui Cheng Jin-yong Qilu Univ Technol Sch Informat Jinan 250353 Shandong Peoples R China

ISBN: (纸本)9781538621653

In this paper, a new encoding method composed of radical group encoding and position specific scoring matrix(PSSM) is proposed. The radical group encoding contains 42 features, it is formed according to amino acids composition. To combine the radical group encoding with the evolution matrix Blosum62, this will form a new encoding method. The Bayes classifier, single-layer auto encoder and stacked auto encoder with two hidden layers are used to predict the secondary structure. The auto encoder is mainly used to extract features, the single-layer auto encoder extracts 1500 features. The stacked auto encoder extracts features in two layers, in the first layer, it extracts 1500 features, in the second layer, it extracts 800 features. The accuracies will be compared. According to the comparision of the accuracies, the accuracy of stacked auto encoder is higher 1.39% than the accuracy of single-layer auto encoder. The accuracy of single-layer auto encoder is higher 1.23% than Bayes classifier.

关键词： protein secondary structure prediction radical group encoding PSSM Bayes classifier auto encoder

来源：评论

学校读者我要写书评

暂无评论

Signal Detection of MIMO-OFDM System Based on auto encoder and Extreme Learning Machine

Signal Detection of MIMO-OFDM System Based on Auto Encoder a...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yan, Xin Long, Fei Wang, Jingshuai Fu, Na Ou, Weihua Liu, Bin Guizhou Univ Coll Big Data & Informat Engn Guiyang Guizhou Peoples R China Guizhou Normal Univ Sch Big Data & Comp Sci Guiyang Guizhou Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Sichuan Peoples R China

ISBN: (纸本)9781509061822

In this paper, we address the problem of signal detection in multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) system by using auto-encoder (AE) network and extreme learning machine (ELM). The existing signal detection algorithms, such as zero-forcing successive-interference-cancellation (ZF-SIC), minimum-mean-square-error successive-interference-cancellation (MMSE-SIC), maximum likelihood detection (MLD) and quantum-genetic radial-basis-function (QGA-RBF) etc., haven't considered the characteristics invariance of signals in the process of transmission. Combined AE network with ELM, a novel signal detection scheme for MIMO-OFDM system is proposed. The proposed algorithm can obtain the features of received signals effectively through AE and recognize the corresponding original signals quickly via ELM. Moreover, the channel matrix is not required in the process of signal detection. We have derived a theoretically model and analyze the feasibility of feature extraction in received signals, and simulations are also carried out to evaluate the performance and compare that with some traditional and state-of-the-art algorithms. The simulation results confirm that the performance of the proposed scheme outperforms that of many detection schemes such as zero-forcing (ZF), ZF-SIC, minimum-mean-square-error (MMSE), MMSE-SIC, and reaches the similar bit-error-rate (BER) performance of MLD and QGA-RBF with much lower complexity.

关键词： Deep Learning auto encoder Extreme Learning Machine Feature Extraction MIMO Signal Detection

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Japanese Handwritten Images Using auto-encoder with Residual Block in Parallel Computing

Reconstructing Japanese Handwritten Images Using Auto-Encode...

引用

International Conference on Electrical Engineering and Informatics (ICELTICs)

作者： Pratama, M. Octaviano Kareen, Pamela Univ Indonesia CCIT Fac Engn Depok Indonesia Univ Indonesia Fac Comp Sci Depok Indonesia

ISBN: (纸本)9781538629345

Unsupervised learning is essential for reconstructing a model without target label such as Reconstructing handwritten character that usually used as benchmarking in deep learning tasks. auto-encoder is one of unsupervised algorithm with purpose of dimensionality reduction and data reconstruction. auto-encoder with deep architecture layer will produce noise higher than shallow architecture. In this research, existing auto-encoder algorithm augmented with Residual Block is performed in parallel computing to reconstruct Japanese handwritten images. Residual block can strengthen deep layer connection. The result is compared with classical auto-encoder.

关键词： auto encoder Residual Blocks Japanese Handwritten Images Parallel Computing

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：