检索结果-内蒙古大学图书馆

10th International Conference on Digital Image Processing (ICDIP)

作者： Zhang, Guodong Guo, Mao Gong, Zhaoxuan Bi, Jing Kim, Yoohwan Guo, Wei Shenyang Aerosp Univ Sch Comp Sci Shenyang 110136 Liaoning Peoples R China Chinese Acad Sci Shenyang Inst Comp Technol Shenyang 110168 Liaoning Peoples R China Univ Nevada Dept Comp Sci Las Vegas NV 89154 USA

ISBN: (数字)9781510622005

ISBN: (纸本)9781510622005

In this paper, we proposed a semi-automatic pulmonary nodule segmentation algorithm, which is operated within a region of interest for each nodule. It mainly includes two parts: the unsupervised training of auto-encoder and the supervised training of segmentation network. Applying an auto-encoder's unsupervised learning, we obtain a feature extractor that consists of its encoded part. Through adding some new neural network layers behind the feature extractor and do supervised learning on it, we get the final segmentation neural network. Compared with the traditional maximum two-dimensional entropy threshold segmentation algorithm, the dice correlation coefficient of this algorithm is 1% - 9% higher in 36 regions of interest segmentation experiments.

关键词： Pulmonary nodule segmentation auto-encoder feature extraction medical image process

来源：评论

学校读者我要写书评

暂无评论

A New Approach for an End-to-end Communication System Using Variational auto-encoder (VAE)

A New Approach for an End-to-end Communication System Using ...

引用

IEEE Global Communications Conference (GLOBECOM)

作者： Alawad, Mohamad A. Hamdan, Mutasem Q. Hamdi, Khairi A. Foh, Chuan Heng ul Quddus, Atta Univ Manchester Sch Elect & Elect Engn Manchester Lancs England Univ Surrey ICS 5GIC & 6GIC Guildford Surrey England

ISBN: (纸本)9781665435406

In this paper, a new approach has been proposed and investigated with the help of variational auto-encoder (VAE) as a probabilistic model to reconstruct the transmitted symbol without sending the data bits out of the transmitter. The novelty of the proposed End-to-end (E2E) wireless system is in representing the symbol as a image hot vector (IHV) that contains the features of the shape such as spikes, closed squared frame, pixels index location and pixels grey-scale colours. The previously mentioned features are inferred by latent random variables (LRVs). The LRVs are used for fronthaul and backhaul data representation. The LRVs parameters have only been transmitted through the physical wireless channel instead of the original bits as in the classical modulations or the hot vectors in the autoencoders (AE) E2E systems. The new proposed VAE architecture achieved the reconstruction of the symbol from the received LRV. The results show that the VAE with a simple classifier can provide a better symbol error rate (SER) than both AE baseline and classical Hamming code with hard decision decoding, especially at high E-b/N-o.

关键词： Variational auto-encoder Machine Learning auto-encoder Hamming code Latent variable probabilistic models wireless communications Fronthaul Backhaul

来源：评论

学校读者我要写书评

暂无评论

Predicting metabolite-disease associations based on auto-encoder and non-negative matrix factorization

引用

BRIEFINGS IN BIOINFORMATICS 2023年第5期24卷 bbad259页

作者： Gao, Hongyan Sun, Jianqiang Wang, Yukun Lu, Yuer Liu, Liyu Zhao, Qi Shuai, Jianwei Univ Sci & Technol Liaoning Anshan Peoples R China Linyi Univ Linyi Peoples R China Univ Chinese Acad Sci Wenzhou Inst Wenzhou 325001 Peoples R China Chongqing Univ Chongqing Peoples R China Univ Chinese Acad Sci Wenzhou Inst Biomed Phys Ctr Wenzhou Peoples R China Univ Sci & Technol Liaoning Sch Comp Sci & Software Engn Anshan 114051 Peoples R China Univ Chinese Acad Sci Wenzhou Key Lab Phys Wenzhou 325001 Peoples R China

Metabolism refers to a series of orderly chemical reactions used to maintain life activities in organisms. In healthy individuals, metabolism remains within a normal range. However, specific diseases can lead to abnormalities in the levels of certain metabolites, causing them to either increase or decrease. Detecting these deviations in metabolite levels can aid in diagnosing a disease. Traditional biological experiments often rely on a lot of manpower to do repeated experiments, which is time consuming and labor intensive. To address this issue, we develop a deep learning model based on the auto-encoder and non-negative matrix factorization named as MDA-AENMF to predict the potential associations between metabolites and diseases. We integrate a variety of similarity networks and then acquire the characteristics of both metabolites and diseases through three specific modules. First, we get the disease characteristics from the five-layer auto-encoder module. Later, in the non-negative matrix factorization module, we extract both the metabolite and disease characteristics. Furthermore, the graph attention auto-encoder module helps us obtain metabolite characteristics. After obtaining the features from three modules, these characteristics are merged into a single, comprehensive feature vector for each metabolite-disease pair. Finally, we send the corresponding feature vector and label to the multi-layer perceptron for training. The experiment demonstrates our area under the receiver operating characteristic curve of 0.975 and area under the precision-recall curve of 0.973 in 5-fold cross-validation, which are superior to those of existing state-of-the-art predictive methods. Through case studies, most of the new associations obtained by MDA-AENMF have been verified, further highlighting the reliability of MDA-AENMF in predicting the potential relationships between metabolites and diseases.

关键词： metabolites diseases auto-encoder non-negative matrix factorization feature splicing multi-layer perceptron

来源：评论

学校读者我要写书评

暂无评论

A Convolutional auto-encoder Method for Anomaly Detection on System Logs

A Convolutional Auto-encoder Method for Anomaly Detection on...

引用

IEEE International Conference on Systems, Man, and Cybernetics (SMC)

作者： Cui, Yu Sun, Yiping Hu, Jinglu Sheng, Gehao Waseda Univ Grad Sch Informat Prod & Syst 2-7 Hibikino Kitakyushu Fukuoka Japan Shanghai Jiao Tong Univ Sch Elect Informat & Elect Engn 800 Dongchuan Rd Shanghai Peoples R China

ISBN: (纸本)9781538666500

Anomaly detection on system logs is to report system failures with utilization of console logs collected from devices, which ensures the reliability of systems. Most previous researches split logs into sequential time windows and regarded each window as an independent instance for classification using popular machine learning methods like support vector machine(SVM), however, neglected the time patterns under logs. Those approaches also suffer from information loss due to the vector representation, and high dimensionality if there is a large number of log events. To make up these deficiencies, unlike most traditional methods that used a vector to represent a period behavior at the macro level, we construct a 2D matrix to reveal more detailed system behaviors in the time period by dividing each window into sequential subwindows. To provide a more efficient representation, we further use the ant colony optimization algorithm to find a highly-coupled event template as the horizontal index of the 2D window matrix to replace the disordered one. To capture time dependencies, a multi-module convolutional auto-encoder is configured as that different paralleled modules scan among different time intervals to extract information respectively. These features are then concatenated in latent space as the final input, which contains diversified time information, for classification by SVM. The experiments on Blue Gene/L log dataset showed that our proposed method outperforms the state-of-art SVM method.

关键词： Log Analysis Anomaly Detection Feature Extraction auto-encoder Ant Colony Optimization

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Rolling Element Bearings Based on a Second Order Cyclic autocorrelation and a Deep auto-encoder

Fault Diagnosis of Rolling Element Bearings Based on a Secon...

引用

International Conference of The Efficiency and Performance Engineering Network (TEPEN)

作者： Shang, Yajun Lin, Tianran Qingdao Univ Technol Sch Mech & Automot Engn Qingdao 266520 Peoples R China

ISBN: (纸本)9783031261954;9783031261930;9783031261923

A rolling element bearing fault diagnosis technique based on a secondorder cyclic autocorrelation and a deep auto-encoder is proposed in this study aiming to deal with strong noise interference and weak fault characteristics often encountered in signals acquired under practical industrial environment. In this approach, second-order cycle statistical features of the vibration signals are estimated using a second-order cycle autocorrelation algorithm to highlight the periodic impulse characteristics generated by a bearing defect, and to suppress the random noise to a certain extent. The preprocessed feature set is then used as an input in a deep auto-encoder combining a stacked constriction auto-encoder and a denoising auto-encoder to fully utilize the advantages of both denoising auto-encoder and constriction auto-encoder. The effectiveness of the proposed technique in rolling element bearing fault diagnosis is verified by a set of experimental data acquired from a rolling element bearing test rig. The result shows that the proposed technique can produce a better diagnosis accuracy comparing with other commonly employed techniques for rolling element bearing fault diagnosis.

关键词： Rolling element bearings Second-order cyclic autocorrelation auto-encoder Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

3D Shape and Texture Features Fusion using auto-encoder for Efficient Face Recognition 26

3D Shape and Texture Features Fusion using Auto-Encoder for ...

引用

26th International Conference on Pattern Recognition / 8th International Workshop on Image Mining - Theory and Applications (IMTA)

作者： Bahroun, Sahbi Abed, Rahma Zagrouba, Ezzeddine Univ Tunis ElManar Inst Super Informat Lab Limtic 2 Rue Abou Rayhane Bayrouni Ariana Tunisia

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Face recognition is one of the most widely used biometrics for identifying people. However, face images suffer from several issues that could affect the achieved results, especially in a crowded environment. Such as facial expression, occlusion, low resolution, noise, illumination and pose variation. In this paper, we propose a robust image representation system for face recognition. First, 3D face data reconstructed from 2D images are used instead of 3D capture. This is accomplished by modeling the difference in the texture map of the 3D aligned input and reference images. Then, fusing shape and texture local binary patterns (LBP) on a mesh for face recognition using the Mesh-LBP. Finally, we used a deep auto-encoder to create a compact data representation based on the obtained face images descriptors from the Mesh-LBP. Through experiments conducted on the Multi-PIE and Bosphorus databases, we show that our method is very competitive against state-of-the-art methods.

关键词： 3D morphable model Face recognition Mesh-LBP feature fusion auto-encoder

来源：评论

学校读者我要写书评

暂无评论

PATCH-WISE auto-encoder FOR VISUAL ANOMALY DETECTION 30

PATCH-WISE AUTO-ENCODER FOR VISUAL ANOMALY DETECTION

引用

30th IEEE International Conference on Image Processing (ICIP)

作者： Cui, Yajie Liu, Zhaoxiang Lian, Shiguo China Unicom Unicom Digital Technol Beijing 100013 Peoples R China

ISBN: (纸本)9781728198354

Anomaly detection without priors of the anomalies is challenging. In the field of unsupervised anomaly detection, traditional auto-encoder (AE) tends to fail based on the assumption that by training only on normal images, the model will not be able to reconstruct abnormal images correctly. On the contrary, we propose a novel patch-wise auto-encoder (Patch AE) framework, which aims at enhancing the reconstruction ability of AE to anomalies instead of weakening it. Each patch of image is reconstructed by corresponding spatially distributed feature vector of the learned feature representation, i.e., patch-wise reconstruction, which ensures anomaly-sensitivity of AE. Our method is simple and efficient. It advances the state-of-the-art performances on Mvtec AD benchmark, which proves the effectiveness of our model. It shows great potential in practical industrial application scenarios.

关键词： Anomaly detection auto-encoder Patchwise Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Corporate Tax Compliance and Fraud Prevention System by Principal Component Analysis and auto-encoder 3

Corporate Tax Compliance and Fraud Prevention System by Prin...

引用

International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI)

作者： Vedapuri, Samvarthini Evangeline, Sharon Genitha, C. Heltin St Josephs Coll Engn Dept Informat Technol Chennai Tamil Nadu India

ISBN: (纸本)9798350389432;9798350389449;9798350389456

Almost all tax authorities prioritize the detection of tax fraud as a means of optimizing their earnings and upholding strict compliance standards. When devising standard tax models and their outcomes, it is imperative for every nation to take into account the prevalence of tax evasion and avoidance, as they can significantly skew tax arrangements. Early models in this field focused on tax evasion, as it was perceived as a challenge to the state's ability to enforce the law. This study expands on earlier research on tax fraud detection, which used a variety of machine learning models to look at all tax kinds. This model finds a number of variables that are important for identifying income tax fraud in both small and corporate enterprises, such as the length of the firm, its size, and whether it works locally or internationally. Notably, this study compares several parameters including taxable income, tax rate, deductions to discover the best settings for obtaining improved accuracy. It is the first to use Principal Component Analysis and auto-encoder to detect corporate tax fraud. The findings of this work will assist scrutinizers in comprehending the elements that lead to corporate tax fraud, hence decreasing the duration and expenses of audits and facilitating the recovery of lost revenue from corporate tax fraud.

关键词： Fraud Detection Corporate Tax Tax Fraud Principal Component Analysis auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A Mobile Network Performance Evaluation Method Based on Multivariate Time Series Clustering with auto-encoder 2018

A Mobile Network Performance Evaluation Method Based on Mult...

引用

2nd International Conference on Telecommunications and Communication Engineering (ICTCE)

作者： Wang, Xiaoyu Jin, Yuehui Yu, Yanping Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China Yunnan Univ Finance & Econ Int Language & Culture Inst Kunming Yunnan Peoples R China

ISBN: (纸本)9781450365857

With the extensive use of smartphones, the amount of collected mobile data and types of mobile network performance evaluation indicators are rapidly expanding. This has resulted in a challenge for the mobile network providers of how to assess the mobile network performance quickly and precisely. This paper proposes a mobile network performance evaluation method based on multivariate time series clustering with auto-encoder. In this method, firstly, we remove a part of indicators with high redundancy by combining Pearson's correlation coefficient and lightgbm. Secondly, we consider the changes in indicators over time as multivariate time series, the distance matrices of which are measured by fastDTW and auto-encoder. Finally, the indicators data under different periods are clustered into three categories by using k-medoids on matrices. We apply this method to the indicator data provided by a mobile network provider and discover that the clusters refer to different levels of mobile network performance according to the mobile network provider' KPI standards.

关键词： Multivariate Time Series Mobile Network Performance Evaluation Clustering auto-encoder Distance Measure

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Dimension Reduction for Image Classification Using Regularized Convolutional auto-encoder

Unsupervised Dimension Reduction for Image Classification Us...

引用

Computer Vision Conference (CVC)

作者： Xu, Chaoyang Wu, Ling Wang, Shiping Putian Univ Sch Informat Engn Putian 351100 Peoples R China Fuzhou Univ Sch Econ & Management Fuzhou 350116 Fujian Peoples R China Fuzhou Univ Coll Math & Comp Sci Fuzhou 350116 Fujian Peoples R China

ISBN: (纸本)9783030177959;9783030177942

Unsupervised dimension reduction has gained widespread attention. Most of previous work performed poorly on image classification due to taking no account of neighborhood relations and spatial localities. In this paper, we propose the 'regularized convolutional auto-encoder', which is a variant of auto-encoder that uses the convolutional operation to extract low-dimensional representations. Each auto-encoder is trained with cluster regularization terms. The contributions of this work are presented as follows: First, we perform different sized filter convolution in parallel and abstract a low-dimensional representation from images cross scales simultaneously. Second, we introduce a cluster regularized rule on auto-encoders to reduce the classification error. Extensive experiments conducted on six publicly available datasets demonstrate that the proposed method significantly reduces the classification error after dimension reduction.

关键词： Deep learning auto-encoder Convolutional neural network Dimension reduction Unsupervised learning

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：