检索结果-内蒙古大学图书馆

deep neural network based approach for ECG classification using hybrid differential features and active learning

IET SIGNAL PROCESSING 2019年第2期13卷 165-175页

作者： Hanbay, Kazim Bingol Univ Comp Engn Dept TR-12000 Bingol Turkey

A novel active learning-based electrocardiogram (ECG) signal classification method using eigenvalues and deep learning is proposed. Six statistical features relating to ECG beat intervals are calculated separately for each heartbeat. Both statistical features and eigenvalues of ECG beats are combined into a single feature vector. The eigenvalues of ECG beats are used as an input to denoising autoencoder (DAE). Weighted ECG beat intervals are calculated by using ten-fold cross-validation approach. To learn an efficient feature representation from the hybrid feature vector, DAE is used in an unsupervised way. After completing the feature learning procedure, a softmax regression layer is added on the top of the resulting hidden layer of DAE, and thus a suitable deep neural network (DNN) architecture is built. The learned features obtained from the autoencoder layers are fed to the softmax regression layer for classification. To update weights of the proposed eigenvalues-based DNN model, ECG beats are labelled by the medical expert are used. In order to determine the most informative beats, entropy and Breaking-Ties are also used as selection criteria. The proposed method is evaluated in terms of ECG beats classes. The classification performance of the authors' proposed model is also compared with the several conventional machine learning classifiers.

关键词： medical signal processing feature extraction signal classification eigenvalues and eigenfunctions regression analysis neural nets learning (artificial intelligence) electrocardiography neural network based approach ECG classification hybrid differential features active learning-based electrocardiogram signal classification method deep learning statistical features ECG beats single feature vector DAE weighted ECG beat intervals cross-validation approach hybrid feature vector feature learning procedure softmax regression layer eigenvalues-based DNN model informative beats feature representation deep neural network architecture

来源：评论

学校读者我要写书评

暂无评论

Data-driven sensor fault detection and isolation of nonlinear systems: deep neural-network Koopman operator

引用

IET CONTROL THEORY AND APPLICATIONS 2023年第2期17卷 123-132页

作者： Bakhtiaridoust, Mohammadhosein Irani, Fatemeh Negar Yadegar, Meysam Meskin, Nader Qom Univ Technol Dept Elect & Comp Engn Qom Iran Qatar Univ Dept Elect Engn Doha Qatar

This paper proposes a data-driven sensor fault detection and isolation approach for the general class of nonlinear systems. The proposed method uses deep neural network architecture to obtain an invariant set of basis functions for the Koopman operator to form a linear predictor for a nonlinear system. Then, the obtained Koopman predictor has been used in a geometric framework for sensor fault detection and isolation purposes without relying on a priori knowledge about the underlying dynamics as well as requiring faulty data, leading to a data-driven sensor fault detection and isolation framework for nonlinear systems. Finally, the approach's efficacy is demonstrated using simulation case study on a two-degree of freedom robot arm.

关键词： data-driven sensor fault detection fault diagnosis Nonlinear control systems faulty data data-driven sensor fault isolation manipulators Koopman predictor deep neural network architecture sensors neural nets deep neural-network Koopman operator Control engineering computing nonlinear systems deep learning (artificial intelligence) nonlinear control systems control engineering computing two-degree of freedom robot arm Manipulators linear predictor

来源：评论

学校读者我要写书评

暂无评论

Power consumption model based on feature selection and deep learning in cloud computing scenarios

引用

IET COMMUNICATIONS 2020年第10期14卷 1610-1618页

作者： Liang, Yang Hu, Zhigang Li, Keqin Cent South Univ Sch Comp Sci & Engn Changsha Peoples R China Hunan Univ Chinese Med Sch Informat Changsha Peoples R China SUNY Coll New Paltz Dept Comp Sci New Paltz NY USA

High power consumption of cloud data centres is a crucial challenge in modern cloud computing. To comply with the conceptions of green computing, power consumption prediction of the computing cluster has a major role to play in these energy conservation efforts. However, due to complexity and heterogeneity in cloud computing scenarios, it is difficult to accurately predict the power consumption using conventional approaches. To this end, this study presents a power consumption model based on feature selection and deep learning to powerfully cope with low energy efficiency. Different from other methods focusing on only a few performance attributes, the proposed method takes into account up to 12 energy-related features and introduces deep neural network architecture, aiming at making full use of massive data to train model completely. In particular, this approach is composed of three main phases including (i) performance monitoring and energy-related feature acquisition, (ii) essential feature selection, and (iii) model establishment and optimisation. Representative results of comprehensive experiments, in terms of the relative error, reveal that the proposed power consumption model can undoubtedly achieve state-of-the-art predictive capability when compared with other models in most cases.

关键词： learning (artificial intelligence) power aware computing computer centres green computing power consumption cloud computing neural nets feature selection power consumption model deep learning cloud computing scenarios high power consumption cloud data centres modern cloud computing green computing power consumption prediction computing cluster energy conservation efforts energy-related feature acquisition feature selection deep neural network architecture

来源：评论

学校读者我要写书评

暂无评论

Capturing the spatio-temporal continuity for video semantic segmentation

引用

IET IMAGE PROCESSING 2019年第14期13卷 2813-2820页

作者： Chen, Xin Wu, Aming Han, Yahong Tianjin Univ Coll Intelligence & Comp Yaguan Rd Tianjin Peoples R China

In recent years, image semantic segmentation based on a convolutional neural network has achieved many advances. However, the development of video semantic segmentation is relatively slow. Directly applying the image segmentation algorithms to each video frame separately may ignore the temporal region continuity inherent in videos. In this study, the authors propose a novel deep neural network architecture with a newly devised spatio-temporal continuity (STC) module for video semantic segmentation. Particularly, the architecture includes an encoding network, an STC module, and a decoding network. The encoding network is used to extract a high-level feature map. The STC module then uses the high-level feature map as input to extract the STC feature map. For decoding, they use four dilated convolutional layers to obtain more abstract representation and a deconvolutional layer to increase the size of the representation. Finally, they fuse the current feature representation and the previous feature representation and get the class probabilities. Thus, this architecture receives a sequence of consecutive video frames and outputs the segmentation result of the current frame. They extensively evaluate the proposed approach on the CamVid and KITTI datasets. Compared with other methods, the authors' approach not only achieves competitive performance but also has lower complexity.

关键词： feature extraction image segmentation image representation video signal processing neural nets probability video semantic segmentation image semantic segmentation convolutional neural network image segmentation algorithms video frame temporal region continuity inherent videos deep neural network architecture newly devised spatio-temporal continuity encoding network STC module decoding network high-level feature map STC feature map current feature representation consecutive video frames segmentation result

来源：评论

学校读者我要写书评

暂无评论

Macro-pixel-wise CNN-based filtering for quality enhancement of light field images

引用

ELECTRONICS LETTERS 2020年第25期56卷 1413-1416页

作者： Huang, H. Schiopu, I. Munteanu, A. Vrije Univ Brussel Dept Elect & Informat Pl Laan 2 B-1050 Brussels Belgium

The Letter introduces a novel filtering method based on convolutional neural networks (CNNs) for quality enhancement of light field (LF) images captured by a plenoptic camera and compressed using high-efficiency video coding (HEVC). The method takes advantage of the macro-pixel (MP) structure specific to the LF images and proposes a novel MP-wise filtering approach based on a novel deep neural network architecture. The proposed CNN-based method achieves an outstanding performance when HEVC is employed without its in-loop filters. Experimental results show high luminance-peak signal-to-noise ratio (Y-PSNR) gains and average Y-BjOntegaard delta (BD)-rate savings of 25.6% over HEVC on a large data set.

关键词： filtering theory image enhancement cameras video coding convolutional neural nets macro-pixel-wise CNN-based quality enhancement light field images novel filtering method convolutional neural networks plenoptic camera high-efficiency video coding HEVC macro-pixel structure LF images novel MP-wise filtering approach deep neural network architecture CNN-based method in-loop filters

来源：评论

学校读者我要写书评

暂无评论

Robust detection of small and dense objects in images from autonomous aerial vehicles

引用

ELECTRONICS LETTERS 2021年第16期57卷 611-613页

作者： Lee, Joo Chan Yoo, JeongYeop Kim, Yongwoo Moon, SungTae Ko, Jong Hwan Sungkyunkwan Univ Dept Artificial Intelligence Suwon South Korea Sungkyunkwan Univ Dept Elect & Comp Engn Suwon South Korea Sangmyung Univ Dept Syst Semicond Engn Cheonan South Korea Korea Aerosp Res Inst Artificial Intelligence Res Div Daejeon South Korea Sungkyunkwan Univ Coll Informat & Commun Engn Suwon South Korea

Aerial images obtained from autonomous aerial vehicles have lots of small and densely distributed objects because of the capture distance. This paper proposes a deep neural network architecture and training/inference techniques for robust detection of objects in the aerial images. Based on cascade R-CNN, the proposed model adopts the recursive feature pyramid and switchable atrous convolution for robust detection of dense objects. A patch-level division and multi-scale inference techniques are applied to effectively detect small objects. The results show that the proposed approach achieves the highest performance on the VisDrone test-dev dataset, in the official ECCV VisDrone2020-DET challenge.

关键词： learning (artificial intelligence) dense objects aerial images neural nets robust detection Aerospace control densely distributed objects remotely operated vehicles multiscale inference techniques capture distance object detection computer vision Optical, image and video signal processing Computer vision and image processing techniques feature extraction autonomous aerial vehicles Mobile robots deep neural network architecture recursive feature pyramid

来源：评论

学校读者我要写书评

暂无评论

Grammatically Recognizing Images with Tree Convolution 20

Grammatically Recognizing Images with Tree Convolution

引用

26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

作者： Wang, Guangrun Wang, Guangcong Wang, Keze Liang, Xiaodan Lin, Liang Sun Yat Sen Univ Guangzhou Guangdong Peoples R China Univ Calif Los Angeles Los Angeles CA USA DarkMatter AI Res Guangzhou Guangdong Peoples R China

ISBN: (纸本)9781450379984

Similar to language, understanding an image can be considered as a hierarchical decomposition process from scenes to objects, parts, pixels, and the corresponding spatial/contextual relations. However, the existing convolutional networks concentrate on stacking redundant convolutional layers with a large number of kernels in a hierarchical organization to implicitly approximate this decomposition. This may limit the network to learn the semantic information conveyed in the internal feature maps that may reveal minor yet crucial differences for visual understanding. Attempting to tackle this problem, this paper proposes a simple yet effective tree convolution (TreeConv) operation for deep neural networks. Specifically, inspired by the image grammar techniques [73] that serve as a unified framework of object representation, learning, and recognition, our TreeConv designs a generative image grammar, i.e., tree generation rule, to parse the hierarchy of internal feature maps by generating tree structures and implicitly learning the specific visual grammars for each object category. Extensive experiments on a variety of benchmarks, i.e., classification (ImageNet / CIFAR), detection & segmentation (COCO 2017), and person re-identification (CUHK03), demonstrate the superiority of our TreeConv in both boosting the accuracy and reducing the computational cost. The source code will be available at https://***/wanggrun/TreeConv.

关键词： deep neural network architecture hierarchical representation learning image grammar image classification object detection person re-identification

来源：评论

学校读者我要写书评

暂无评论

deepLCZChange: A REMOTE SENSING deep LEARNING MODEL architecture FOR URBAN CLIMATE RESILIENCE^CRediT

DeepLCZChange: A REMOTE SENSING DEEP LEARNING MODEL ARCHITEC...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Sun, Wenlu Sun, Yao Liu, Chenying Albrecht, Conrad M. Tech Univ Munich Data Sci Earth Observat Munich Germany German Aerosp Ctr Remote Sensing Technol Inst Cologne Germany

ISBN: (纸本)9798350320107

Urban land use structures impact local climate conditions of metropolitan areas. To shed light on the mechanism of local climate wrt. urban land use, we present a novel, data-driven deep learning architecture and pipeline, deepLCZChange, to correlate airborne LiDAR data statistics with the Landsat 8 satellite's surface temperature product. A proof-of-concept numerical experiment utilizes corresponding remote sensing data for the city of New York to verify the cooling effect of urban forests.

关键词： urban planning local climate zones climate resilience LiDAR Landsat 8 deep neural network architecture explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection on Medical Images using Autoencoder and Convolutional neural network

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2021年第7期12卷 148-156页

作者： Siddalingappa, Rashmi Kanagaraj, Sekar Indian Inst Sci Dept Computat & Data Sci CV Raman Rd Bangalore 560012 Karnataka India

Detection of anomalies from the medical image dataset improves prognosis by discovering new facts hidden in the data. The present study aims to discuss anomaly detection using autoencoders and convolutional neural networks. The autoencoder identifies the imbalance between normal and abnormal samples. They create learning models flexible and accurate on training data. The problem is addressed in four stages: 1) training: an autoencoder is initialized with the hyperparameters and trained on the lung cancer CT scan images, 2) test: the autoencoder reconstructs the input from the latent space representation with a slight variation from the original data, indicated by a reconstruction error as Mean Squared Error (MSE), 3) evaluate: the MSE value of the training and test dataset are compared. The MSE values of anomalous data are higher than a base threshold, detecting those as anomalies, 4) validate: the efficiency metrics such as accuracy and MSE scores are used at both training and validation phases. The dataset was further classified as benign and malignant. The accuracy reported for outlier detection and the classification task is 98% and 97.2% Thus, the proposed autoencoder-based anomaly detection could positively isolate anomalies from the CT scan images of lung cancer.

关键词： Anomalies autoencoder convolutional neural networks (CNN) (ConvNets) deep neural network architecture regularization

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：