检索结果-内蒙古大学图书馆

37th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Maji, Debapriya Santara, Anirban Ghosh, Sambuddha Sheet, Debdoot Mitra, Pabitra Indian Inst Technol Kharagpur Kharagpur 721302 W Bengal India North Bengal Med Coll & Hosp Dept Ophthalmol Darjeeling India

ISBN: (纸本)9781424492701

Vision impairment due to pathological damage of the retina can largely be prevented through periodic screening using fundus color imaging. However the challenge with large-scale screening is the inability to exhaustively detect fine blood vessels crucial to disease diagnosis. In this work we present a computational imaging framework using deep and ensemble learning based hybrid architecture for reliable detection of blood vessels in fundus color images. A deep neural network (DNN) is used for unsupervised learning of vesselness dictionaries using sparse trained denoising auto-encoders (DAE), followed by supervised learning of the DNN response using a random forest for detecting vessels in color fundus images. In experimental evaluation with the DRIVE database, we achieve the objective of vessel detection with max. avg. accuracy of 0.9327 and area under ROC curve of 0.9195.

关键词： Computational imaging deep learning denoising auto-encoder random forests vessel detection

来源：评论

学校读者我要写书评

暂无评论

REAL-TIME RADIO MODULATION CLASSIFICATION WITH AN LSTM auto-encoder

REAL-TIME RADIO MODULATION CLASSIFICATION WITH AN LSTM AUTO-...

引用

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

作者： Ke, Ziqi Vikalo, Hanis Univ Texas Austin Dept Elect & Comp Engn Austin TX 78712 USA

ISBN: (纸本)9781728176055

Identifying modulation type of a received radio signal is a challenging problem encountered in many applications including radio interference mitigation and spectrum allocation. This problem is rendered challenging by the existence of a large number of modulation schemes and numerous sources of interference. Existing methods for monitoring spectrum readily collect large amounts of radio signals. However, existing state-of-the-art approaches to modulation classification struggle to reach desired levels of accuracy with computational efficiency practically feasible for implementation on low-cost computational platforms. To this end, we propose a learning framework based on an LSTM denoising auto-encoder designed to extract robust and stable features from the noisy received signals, and detect the underlying modulation scheme. The method uses a compact architecture that may be implemented on low-cost computational devices while achieving or exceeding state-of-the-art classification accuracy. Experimental results on realistic synthetic and over-the-air radio data show that the proposed framework reliably and efficiently classifies radio signals, and often significantly outperform state-of-the-art approaches.

关键词： modulation classification denoising auto-encoder LSTM

来源：评论

学校读者我要写书评

暂无评论

Research on Intrusion Detection Model Based on DAE-XGBoost 10

Research on Intrusion Detection Model Based on DAE-XGBoost

引用

IEEE 10th International Conference on Information, Communication and Networks (ICICN)

作者： Gao Minghui Zhao Hang Ma Li Zhang Zhijun Lu Kai Cui Xudong He Jicheng Ning Zhiyan Beijing Kedong Elect Power Control Syst Co Ltd Beijing Peoples R China

ISBN: (纸本)9781665490825

The DAE-XGBoost detection model designed in this paper solves the problem that the detection effect of rare attack types in massive network data is not ideal. First, extract information from large-scale high-dimensional data through DAE (denoising auto-encoder) neural ***, a trade-off factor is introduced into the XGBoost (eXtrame Gradient Boosting)model to balance the detection ability and improve the detection accuracy of rare attack types. The experiment uses the NSL-KDD data set for simulation verification. The results show that the detection accuracy of the proposed model for the two rare attack types "U2R" and "R2L" is 13.32% higher than the comparison method on average.

关键词： network intrusion detection sample imbalance rare attack type detection denoising auto-encoder extrame gradient boosting

来源：评论

学校读者我要写书评

暂无评论

VConv-DAE: Deep Volumetric Shape Learning Without Object Labels 14

VConv-DAE: Deep Volumetric Shape Learning Without Object Lab...

引用

14th European Conference on Computer Vision (ECCV)

作者： Sharma, Abhishek Grau, Oliver Fritz, Mario Intel Visual Comp Inst Saarbrucken Germany Intel Saarbrucken Germany Max Planck Inst Informat Saarbrucken Germany

ISBN: (纸本)9783319494098;9783319494081

With the advent of affordable depth sensors, 3D capture becomes more and more ubiquitous and already has made its way into commercial products. Yet, capturing the geometry or complete shapes of everyday objects using scanning devices (e.g. Kinect) still comes with several challenges that result in noise or even incomplete shapes. Recent success in deep learning has shown how to learn complex shape distributions in a data-driven way from large scale 3D CAD Model collections and to utilize them for 3D processing on volumetric representations and thereby circumventing problems of topology and tessellation. Prior work has shown encouraging results on problems ranging from shape completion to recognition. We provide an analysis of such approaches and discover that training as well as the resulting representation are strongly and unnecessarily tied to the notion of object labels. Thus, we propose a full convolutional volumetric auto encoder that learns volumetric representation from noisy data by estimating the voxel occupancy grids. The proposed method outperforms prior work on challenging tasks like denoising and shape completion. We also show that the obtained deep embedding gives competitive performance when used for classification and promising results for shape interpolation.

关键词： denoising auto-encoder 3D deep learning Shape completion Shape blending

来源：评论

学校读者我要写书评

暂无评论

A hybrid learning model based on auto-encoders 12

A hybrid learning model based on auto-encoders

引用

12th IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Zhou, Ju Ju, Li Zhang, Xiaolong Wuhan Univ Sci & Technol Sch Comp Sci & Technol Hubei Key Lab Intelligent Informat Proc & Real Ti Wuhan 430065 Hubei Peoples R China

ISBN: (纸本)9781509061617

The existing auto-encoder algorithm has been used to do deep learning. A variety of improved auto-encoder algorithms still have their disadvantages. In order to improve the learning accuracy of the auto-encoder algorithm, a hybrid learning model with a classifier is proposed. This model constructs a new depth auto-encoder model (SDCAE) by mixing a denoising auto-encoder (DAE) and a contractive auto-encoder (CAE). The weights are initialized by the construction method of the stacking auto-encoders, which is optimized by the gradient descent method. Therefore, the model has robustness to the reconstruction input of DAE and to the hidden layer representation of the CAE at the same time in the pre-training process. The learning model uses Softmax regression as a classification layer. The experimental results show that the classifier based on SDCAE has higher classification accuracy compared to existing auto-encoder on the given data sets.

关键词： deep learning auto-encoder denoising auto-encoder contractive auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Imputing missing indoor air quality data with inverse mapping generative adversarial network

引用

BUILDING AND ENVIRONMENT 2022年 215卷 108896-108896页

作者： Wu, Zejun Ma, Chao Shi, Xiaochuan Wu, Libing Dong, Yi Stojmenovic, Milos Wuhan Univ Sch Cyber Sci & Engn Wuhan Peoples R China Chinese Acad Sci Inst Rock & Soil Mech Wuhan Peoples R China Lab Geomech & Geotech Engn Wuhan Peoples R China Singidunum Univ Dept Comp Sci & Elect Engn Belgrade Serbia

Sensors deployed all over the buildings are nowadays collecting a large amount of data, such as the Indoor Air Quality (IAQ) data which can provide valuable suggestions on improving indoor environments and energy consumption strategies. However, as treated as Multivariate Time Series (MTS), IAQ data often contain missing values that severely limit further analysis on them. Unfortunately, most of the existing methods fail to handle a couple of technical issues due to the complexity of MTS data, such as data distribution approximation, removing the redundancy, and so on. In this paper, we formulate the IAQ missing data imputation problem and propose an Inverse Mapping Generative Adversarial Network (IM-GAN) to tackle that problem. IM-GAN takes advantage of Bi-directional Recurrent Neural Network (BRNN), denoising auto-encoder (DAE), and Generative Adversarial Network (GAN) to overcome the aforementioned technical issues. To validate the effectiveness of our proposed IM-GAN, we conduct comprehensive experiments on two public IAQ datasets GAMS and Gainesville. Results show that our IM-GAN achieves the new state-of-the-art performance in accurately estimating missing values in indoor air quality time series data, with the average performance of 0.1566 and 0.0789 in terms of Mean Relative Error, and 17.2884 and 2.7434 in terms of Mean Absolute Error on GAMS and Gainesville respectively at different missing rates. Our ablation study and visualization also validate that IM-GAN effectively overcomes the aforementioned technical issues by capturing data distribution, eliminating network saturation, and so on for IAQ data imputation.

关键词： Indoor air quality Missing data imputation Generative adversarial network denoising auto-encoder Bi-directional recurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Boosted Multifeature Learning for Cross-Domain Transfer

引用

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 2015年第3期11卷 35-35页

作者： Yang, Xiaoshan Zhang, Tianzhu Xu, Changsheng Yang, Ming-Hsuan Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing 100190 Peoples R China China Singapore Inst Digital Media Singapore 119613 Singapore Univ Calif Dept Elect Engn & Comp Sci Merced CA 95334 USA

Conventional learning algorithm assumes that the training data and test data share a common distribution. However, this assumption will greatly hinder the practical application of the learned model for cross-domain data analysis in multimedia. To deal with this issue, transfer learning based technology should be adopted. As a typical version of transfer learning, domain adaption has been extensively studied recently due to its theoretical value and practical interest. In this article, we propose a boosted multifeature learning (BMFL) approach to iteratively learn multiple representations within a boosting procedure for unsupervised domain adaption. The proposed BMFL method has a number of properties. (1) It reuses all instances with different weights assigned by the previous boosting iteration and avoids discarding labeled instances as in conventional methods. (2) It models the instance weight distribution effectively by considering the classification error and the domain similarity, which facilitates learning new feature representation to correct the previously misclassified instances. (3) It learns multiple different feature representations to effectively bridge the source and target domains. We evaluate the BMFL by comparing its performance on three applications: image classification, sentiment classification and spam filtering. Extensive experimental results demonstrate that the proposed BMFL algorithm performs favorably against state-of-the-art domain adaption methods.

关键词： Algorithms Experimentation Performance Domain adaptation multifeature boosting denoising auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Hybrid -task learning for robust automatic speech recognition

引用

COMPUTER SPEECH AND LANGUAGE 2020年 64卷 101103-101103页

作者： Pironkov, Gueorgui Wood, Sean U. N. Dupont, Stephane Univ Mons Circuit Theory & Signal Proc Lab Mons Belgium Univ Sherbrooke Dept Elect & Comp Engn NECOTIS Sherbrooke PQ J1K 2R1 Canada

In order to properly train an automatic speech recognition system, speech with its annotated transcriptions is most often required. The amount of real annotated data recorded in noisy and reverberant conditions is extremely limited, especially compared to the amount of data than can be simulated by adding noise to clean annotated speech. Thus, using both real and simulated data is important in order to improve robust speech recognition, as this increases the amount and diversity of training data (thanks to the simulated data) while also benefiting from a reduced mismatch between training and operation of the system (thanks to the real data). Another promising method applied to speech recognition in noisy and reverberant conditions is multi-task learning. The idea is to train one acoustic model to solve simultaneously at least two tasks that are different but related, with speech recognition being the main task. A successful auxiliary task consists of generating clean speech features using a regression loss (as a denoising auto-encoder). This auxiliary task though uses as targets clean speech, which implies that real data cannot be used. In order to tackle this problem a Hybrid-Task Learning system is proposed. This system switches frequently between multi and single-task learning depending on whether the input is real or simulated data respectively. Having a hybrid architecture allows us to benefit from both real and simulated data while using a denoising auto-encoder as auxiliary task of a multi-task setup. We show that the relative improvement brought by the proposed hybrid-task learning architecture can reach up to 4.4% compared to the traditional single-task learning approach on the CHiME4 database. We also demonstrate the benefits of the hybrid approach compared to multi-task learning or adaptation.

关键词： Multi-task learning Robust speech recognition Hybrid-task learning denoising auto-encoder Real & simulated data training Noise & reverberation CHiME4

来源：评论

学校读者我要写书评

暂无评论

JLGBMLoc-A Novel High-Precision Indoor Localization Method Based on LightGBM

引用

SENSORS 2021年第8期21卷 2722-2722页

作者： Yin, Lu Ma, Pengcheng Deng, Zhongliang Beijing Univ Posts & Telecommun Sch Elect Engn Beijing 100876 Peoples R China

Wi-Fi based localization has become one of the most practical methods for mobile users in location-based services. However, due to the interference of multipath and high-dimensional sparseness of fingerprint data, with the localization system based on received signal strength (RSS), is hard to obtain high accuracy. In this paper, we propose a novel indoor positioning method, named JLGBMLoc (Joint denoising auto-encoder with LightGBM Localization). Firstly, because the noise and outliers may influence the dimensionality reduction on high-dimensional sparseness fingerprint data, we propose a novel feature extraction algorithm-named joint denoising auto-encoder (JDAE)-which reconstructs the sparseness fingerprint data for a better feature representation and restores the fingerprint data. Then, the LightGBM is introduced to the Wi-Fi localization by scattering the processed fingerprint data to histogram, and dividing the decision tree under leaf-wise algorithm with depth limitation. At last, we evaluated the proposed JLGBMLoc on the UJIIndoorLoc dataset and the Tampere dataset, the experimental results show that the proposed model increases the positioning accuracy dramatically compared with other existing methods.

关键词： indoor localization Wi-Fi fingerprint denoising auto-encoder JLGBMLoc

来源：评论

学校读者我要写书评

暂无评论

An integrated data-driven scheme for the defense of typical cyber-physical attacks

引用

RELIABILITY ENGINEERING & SYSTEM SAFETY 2022年第0期220卷 108257-108257页

作者： Wu, Shimeng Jiang, Yuchen Luo, Hao Zhang, Jiusi Yin, Shen Kaynak, Okyay Harbin Inst Technol Sch Astronaut Dept Control Sci & Engn Harbin Peoples R China Norwegian Univ Sci & Technol Fac Engn Dept Mech & Ind Engn N-7033 Trondheim Norway Bogazici Univ Dept Elect & Elect Engn Istanbul Turkey

With the frequent occurrence of safety incidents in cyber-physical systems (CPSs), great significance has been attached to the study of defense schemes against cyber-physical attacks. In this paper, an integrated data-driven defense scheme is proposed, which can sensitively detect data integrity attacks such as false data injection (FDI) attacks, denial-of-service (DoS) attacks, and replay attacks, and ensures secure transmission against eavesdropping attacks. Specifically, a novel deep learning model is designed so that both the online detection task and the encryption/decryption task can be completed under the same framework. The main idea is inspired by denoising auto-encoders whereas necessary changes are made to adapt to the challenges in the context of CPS attacks, and in light of this, the proposed approach is called modified denoising auto-encoder (MDAE). Unlike supervised classifier-based detectors, the proposed detector can retain sensitivity to unknown attacks because it is trained to learn the normal operation behavior. Moreover, to improve the detectability of the DoS and replay attacks on all data, the check code is designed. Encrypting the transmitted data through nonlinear mapping is achieved using the same MDAE, which prevents the attackers from recording useful information. Benefiting from the fact that the dimension of the variables is reduced after encryption, the transmission traffic can be saved. Simulation results on the measurement data instances generated by the IEEE 118-bus system validate the encryption effects and detection accuracy of the proposed scheme and show the superiority by comparison study.

关键词： Cyber-physical attacks Safety denoising auto-encoder Secure transmission Attack detection

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：