检索结果-内蒙古大学图书馆

A network intrusion detection method based on deep learning with higher accuracy

Procedia Computer Science 2020年 174卷 50-54页

作者： Yuening Zhang Yiming Zhang Nan Zhang Mingzhong Xiao College of Information Science and Technology Beijing Normal University Bei Jing China

The traditional network intrusion detection methods have the problem of long distance dependency. It is easy to ignore contextual information. Moreover, the current data dimension is too high and the feature extraction process is complex, which is not conducive to the requirements of real-time and accuracy of intrusion detection. For the above two problems, this paper presents a new network intrusion detection method based on auto-encoder network(AN) and long-term memory neural network (LSTM). First, KDDcup99 data set is used and pre-processed. And an auto-encoder network model is constructed by superimposing multiple auto-encoder networks to map high-dimensional data to low-dimensional space. Then the LSTM model optimized the cell structure was used to extract features, train data and predict intrusion detection types. The experimental results show that compared with several classical methods, the accuracy of network intrusion detection is improved by 2% on average, and the false alarm rates are lower.

关键词： network intrusion detection auto encoder LSTM

来源：评论

学校读者我要写书评

暂无评论

Cross-Subject Motor Imagery Tasks EEG Signal Classification Employing Multiplex Weighted Visibility Graph and Deep Feature Extraction

IEEE SENSORS LETTERS

引用

IEEE SENSORS LETTERS 2020年第1期4卷 1页

作者： Samanta, Kaniska Chatterjee, Soumya Bose, Rohit Techno India Univ Dept Elect Engn Kolkata 700091 India Carnegie Mellon Univ Dept Bioengn Pittsburgh PA 15213 USA

This letter presents a novel technique for classification of motor imagery (MI) electroencephalogram (EEG) signals employing a multiplex weighted visibility graph (MWVG) algorithm. A weighted visibility graph (WVG) is an effective tool to map a univariate time series into a graphical representation while preserving its temporal characteristics. In this contribution, the concept of WVG of univariate time series is extended to analyze multivariate EEG time series known as a MWVG algorithm. From the graphical representation of the transformed EEG time series, a new method for construction of complex functional brain connectivity network using clustering co-efficient was proposed based on mutual correlation between different electrodes. An auto encoder based deep feature extraction technique was employed to extract meaningful features from the images of brain connectivity matrix and classification of different MI tasks was performed using different benchmark classifiers. In this contribution, a cross-subject classification is performed to address the problem of lack of generalized features from EEG signals across different subjects. It was observed that an average classification accuracy of 99.92% and 99.96% is obtained using the Random Forest classifier. Experimental investigations on two publicly available databases revealed that the proposed model can be implemented to develop a robust and effective brain computer interface system.

关键词： Sensor signal processing auto encoder brain computer interface electroencephalogram (EEG) motor imagery (MI) multiplex visibility graph random forest (RF)

来源：评论

学校读者我要写书评

暂无评论

A Face Replacement Neural Network for Image and Video 19

A Face Replacement Neural Network for Image and Video

引用

11th International Conference on Machine Learning and Computing (ICMLC)

作者： Guo, YanHui Ke, Xue Ma, Jie Huazhong Univ Sci & Technol Sch Automat Inst Image Recognit & Artificial Intelligence Luo Yu Rd 1037 Wuhan Hubei Peoples R China

ISBN: (纸本)9781450366007

We propose a method to solve the problem of face replacing for image and video. This approach is enabled to transform an input identity into a target identity, including the facial expression, facial organs and the facial skin colour. To this end, we make the following contributions. (a)We elaborately design a simple auto encoder network to reconstruct the face. (b)Building on recent research in this area, we integrate a weight mask into the loss function to improve the performance of the network during training. (c)Unlike the previous work, we can transform the face not only in image, but also merging video after we adjust the results. We make it easier to replace a people's face with another one in image or video by combining neural networks with simple processing steps.

关键词： Face replacement auto encoder convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Learning to Design Constellation for AWGN Channel Using auto-encoders 33

Learning to Design Constellation for AWGN Channel Using Auto...

引用

33rd IEEE International Workshop on Signal Processing Systems (IEEE SiPS)

作者： Huang, Qisheng Jiang, Ming Zhao, Chunming Southeast Univ Natl Mobile Commun Res Lab Purple Mt Lab Nanjing Peoples R China

ISBN: (纸本)9781728119274

This paper proposes a novel constellation design in AWGN channel through learning based auto-encoder (AE). Additionally, this paper illustrates the reason why learning based constellation has better performance than the classical square-shaped QAM design by analyzing the Euclidean distance distribution and the bound of symbol error rate between learning designed symbols and other constellations. Moreover, the performance of learning based constellation will be compared to constellation based on convex optimization design. To solve the hit mapping problem of the learning based constellation, Q-ary LDPC encoding is applied to these specifically designed QAM modulation systems, where the soft decoding of Q-ary LDPC codes can be carried out with the symbol-level soft outputs of demodulation.

关键词： auto encoder constellations neural networks Q-ary LDPC AWGN

来源：评论

学校读者我要写书评

暂无评论

Targeted unsupervised features learning for gene expression data analysis to predict cancer stage 19

Targeted unsupervised features learning for gene expression ...

引用

Proceedings of the Tenth International Conference on Computational Systems-Biology and Bioinformatics

作者： Imene Zenbout Abdelkrim Bouramoul Souham Meshoul Abedlhamid Mehri University Algeria Princess Nourah bint Abdulrahman University Riyadh Saudi Arabia

ISBN: (纸本)9781450372152

The intensive explosion in the generation of large scale cancer gene expression data brought several computational challenges, yet opened great opportunities in exploring different pathways in order to improve cancer prognosis, diagnosis and treatment. In this paper, we propose a targeted unsupervised learning model, based on deep autoencoders (TAE) to learn significant cancer representation based on the gene expression omnibus(GEO) integrated expO data set, for the ultimate goal of constructing an accurate cancer stage predictive model. Where, the trained model was tested on two gene expression cancer data sets namely, lung cancer for clinical stage and intensive breast cancer (IBC) for pathological stage. In which, the model extracted new features space for the two cancer type based on the knowledge built from the expO data set. The generated features were used to train classifiers to predict the cancer stage of each sample. We evaluated the effectiveness of our proposal by comparison to the principal component analysis (PCA) unsupervised dimensionality reduction, as well as to the supervised univariate features selection method. The experimental results, show a promising performance of our analysis model to build a collaborative knowledge from different cancer type to enhance the prediction rate of different cancer stage.

关键词： gene expression feature selection deep learning bioinformatics auto encoder unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Application of deep autoencoder model for structural condition monitoring

引用

Journal of Systems Engineering and Electronics 2018年第4期29卷 873-880页

作者： PATHIRAGE Chathurdara Sri Nadith LI Jun LI Ling HAO Hong LIU Wanquan Department of Computing Curtin University Centre for Infrastructural Monitoring and Protection Curtin University

Damage detection in structures is performed via vibra-tion based structural identification. Modal information, such as fre-quencies and mode shapes, are widely used for structural dama-ge detection to indicate the health conditions of civil *** deep learning algorithm that works on a multiple layer neuralnetwork model termed as deep autoencoder is proposed to learnthe relationship between the modal information and structural stiff-ness parameters. This is achieved via dimension reduction of themodal information feature and a non-linear regression against thestructural stiffness parameters. Numerical tests on a symmetri-cal steel frame model are conducted to generate the data for thetraining and validation, and to demonstrate the efficiency of theproposed approach for vibration based structural damage detec-tion.

关键词： auto encoder non-linear regression deep auto en-coder model damage identification vibration structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

A deep stochastic weight assignment network and its application to chess playing

引用

JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING 2018年 117卷 205-211页

作者： Wang, Zhi Wang, Xizhao Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Hebei Univ Coll Comp Sci & Technol Baoding 071002 Peoples R China

Chinese chess is an ancient game in which the chess situation is the information ensemble of chess pieces' spatial locations and interrelations. The situation evaluation plays an extremely important role in the policy decisions of Chinese chess game. However, the situation evaluation is too complex for human to cover every detail with naked eyes. The deep stochastic weight assignment network (DSWAN) proposed in this paper to classify the situations in advantages and disadvantages can solve the above problem. DSWAN is a type of multi-layer perception (MLP) which is divided into two main components: unsupervised feature extractor formed by multi-layer auto encoder and supervised classifier trained by stochastic weight assignment network (SWAN). We summarize a series of chess situation features by gathering specialized knowledges of Chinese chess, and these features are proved valid to estimate the situation. Another highlight of this paper is that the auto encoder is constrained by L-1/2 regularization. By doing so, it can bring more sparsity to data set, make situation features more representative and ease the overfitting trouble of SWAN. (C) 2017 Elsevier Inc. All rights reserved.

关键词： Chinese chess game Chess situation analysis Deep stochastic weight assignment network (DSWAN) auto encoder L-1/2 regularization Stochastic weight assignment network (SWAN)

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Collaborating Filtering Approach using Extended Matrix Factorization and autoencoder in Recommender System

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2019年第6期10卷 505-513页

作者： Hasan, Mahamudul Roy, Falguni Hasan, Tasdikul Jamal, Lafifa East West Univ Dept Comp Sci & Engn Dhaka Bangladesh Noakhali Sci & Technol Univ Inst Informat Technol Noakhali Bangladesh Univ Dhaka Dept Robot & Mechatron Engn Dhaka Bangladesh

Recommender system is an approach where users get suggestions based on their previous preferences. Nowadays, people are overwhelmed by the huge amount of information that is being present in any system. Sometimes, it is difficult for a user to find an appropriate item by searching the desired content. Recommender system assists users by providing suggestions of required information or items based on the similar features among the users. Collaborative filtering is one of the most re-known process of recommender system where the recommendation is done by similar users or similar items. Matrix factorization is an approach which can be used to decompose a matrix into two or more matrix to generate features. Again, autoencoder is a deep learning based technique which is used to find hidden features of an object. In this paper, features are calculated using extended matrix factorization and autoencoder and then a new similarity metric has been introduced that can calculate the similarity efficiently between each pair of users. Then, an improvement of the prediction method is introduced to predict the rating accurately by using the proposed similarity measure. In the experimental section, it has been shown that our proposed method outperforms in terms of mean absolute error, precision, recall, f-measures, and average reciprocal hit rank.

关键词： Recommender system deep learning auto encoder matrix factorization similarity measures

来源：评论

学校读者我要写书评

暂无评论

Text Sentiment Polarity Classification Method Based on Word Embedding 18

Text Sentiment Polarity Classification Method Based on Word ...

引用

2nd International Conference on Algorithms, Computing and Systems (ICACS)

作者： Sun, Xiaojie Du, Menghao Shi, Hua Huang, Wenming Guilin Univ Elect Technol Guilin Peoples R China

ISBN: (纸本)9781450365093

Most of the machine learning algorithms for text sentiment analysis use the word embedding obtained by word2vec training as their inputs. However, the word embedding of word2vec training contains only semantic information. An algorithm for text sentiment analysis is proposed solve the problem of text containing semantics, syntax, sentiment and other information. It begins with the learning of original text-multi word embedding in the semantic, syntactic, and sentiment information, followed by proceeding the word embedding fusion. The improved convolution neural network is applied for sentiment analysis. Thus, it solves the problem that the word embedding contains monotonous text information. K-means text clustering is applied by dividing similar text into the same cluster, thus improving the classification accuracy. The application of the Principal Component Analysis (PCA) dimensionality not only extracts the principal component information, but also solves the problem of redundancy embedding and improves the computational performance of classification model. The experiment results show that the presented method has a significant improvement in the accuracy, recall rate and F value of the sentiment polarity analysis of the critical text in comparison with other fusion algorithms.

关键词： Word Embedding Convolution Neural Network Sentiment Analysis auto encoder

来源：评论

学校读者我要写书评

暂无评论

Adaptive Threshold for Outlier Detection on Data Streams 5

Adaptive Threshold for Outlier Detection on Data Streams

引用

5th IEEE International Conference on Data Science and Advanced Analytics (IEEE DSAA)

作者： Clark, James P. Liu, Zhen Japkowicz, Nathalie Lockheed Martin Centralized Super Comp Facil Herndon VA 20171 USA Guangdon Pharmaceut Univ Sch Med Inofrmat Engn Guangzhou Guangdong Peoples R China Amer Univ Comp Sci Dept Washington DC 20016 USA

ISBN: (纸本)9781538650905

As the distribution of a data stream evolves over time, a learner must adapt to its distributional shifts in order to make accurate predictions. In the context of anomaly detection, it is crucial for the learner to distinguish between natural changes in distribution and true anomalies in the data stream. This is the problem we focus on in this study which considers the situation where only normal data are available for initial training, but subsequent data can be either normal or anomalous. In that context, it is necessary to train a one-class learning anomaly detection system on the normal data and let the system output a score representing the degree of normalcy or outlierness that each data point in the subsequent data stream exhibits. The system then uses a threshold to discriminate between normal and anomalous instances. In the case of data stream, the data distribution may shift overtime, and a fixed threshold could develop a high false alarm rate or a low outlier detection rate in case of concept drift. To this end, we designed an adaptive sliding window approach which updates the threshold when necessary based on the scores distribution. Experimental results show that our method improves the performance of base anomaly detectors by dynamically updating the threshold of the scores when needed rather than using a fixed threshold or an adaptive threshold with fixed window sizes.

关键词： outlier detection threshold setting one class learning auto encoder LOF

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：