检索结果-内蒙古大学图书馆

Energy-Efficient ECG Signals Outlier Detection Hardware Using a Sparse Robust Deep autoencoder

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2021年第8期E104D卷 1121-1129页

作者： Soga, Naoto Sato, Shimpei Nakahara, Hiroki Tokyo Inst Technol Dept Informat & Commun Engn Tokyo 1528552 Japan

Advancements in portable electrocardiographs have allowed electrocardiogram (ECG) signals to be recorded in everyday life. Machine-learning techniques, including deep learning, have been used in numerous studies to analyze ECG signals because they exhibit superior performance to conventional methods. A mobile ECG analysis device is needed so that abnormal ECG waves can be detected anywhere. Such mobile device requires a real-time performance and low power consumption, however, deep-learning based models often have too many parameters to implement on mobile hardware, its amount of hardware is too large and dissipates much power consumption. We propose a design flow to implement the outlier detector using an autoencoder on a low-end FPGA. To shorten the preparation time of ECG data used in training an autoencoder, an unsupervised learning technique is applied. Additionally, to minimize the volume of the weight parameters, a weight sparseness technique is applied, and all the parameters are converted into fixed-point values. We show that even if the parameters are reduced converted into fixed-point values, the outlier detection performance degradation is only 0.83 points. By reducing the volume of the weight parameters, all the parameters can be stored in on-chip memory. We design the architecture according to the CRS format, which is the well-known data structure of a sparse matrix, minimizing the hardware size and reducing the power consumption. We use weight sharing to further reduce the weight-parameter volumes. By using weight sharing, we could reduce the bit width of the memories by 60% while maintaining the outlier detection performance. We implemented the autoencoder on a Digilent Inc. ZedBoard and compared the results with those for the ARM mobile CPU for a built-in device. The results indicated that our FPGA implementation of the outlier detector was 12 times faster and 106 times more energy-efficient.

关键词： FPGA autoencoder outlier detection unsupervised training

来源：评论

学校读者我要写书评

暂无评论

Homodyned K-Distribution Parameter Estimation in Quantitative Ultrasound: autoencoder and Bayesian Neural Network Approaches

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 2024年第3期71卷 354-365页

作者： Tehrani, Ali K. Z. Cloutier, Guy Tang, An Rosado-Mendez, Ivan M. Rivaz, Hassan Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada Univ Montreal Dept Radiol Radiooncol & Nucl Med Montreal PQ H2L 2W5 Canada Univ Montreal Inst Biomed Engn Montreal PQ H2L 2W5 Canada Univ Wisconsin Dept Med Phys Madison WI 53792 USA

Quantitative ultrasound (QUS) analyzes the ultrasound (US) backscattered data to find the properties of scatterers that correlate with the tissue microstructure. Statistics of the envelope of the backscattered radio frequency (RF) data can be utilized to estimate several QU Sparameters. Different distributions have been proposed to model envelope data. The homodyned K-distribution(HK-distribution) is one of the most comprehensive distributions that can model US backscattered envelope data under diverse scattering conditions (varying scatterer number density and coherent scattering). The scatterer clustering parameter (alpha) and the ratio of the coherent to diffuse scattering power (k) are the parameters of this distribution that have been used extensively for tissue characterization in diagnostic US. The estimation of these two parameters (which we refer to as HK parameters) is done using optimization algorithms in which statistical features such as the envelope point-wise signal-to-noise ratio (SNR), skewness, kurtosis, and the log-based moments have been utilized as input tosuch algorithms. The optimization methods minimize the difference between features and their theoretical value from the HK model. We propose that the true value of these statistical features is a hyperplane that covers a small portion of the feature space. In this article, we follow two approaches to reduce the effect of sample features'error. We propose a model projection neural network based on denoising autoencoders to project the noisy features into this space based on this assumption. We also investigate if the noise distribution can be learned by the deep estimators. We compare the proposed methods with conventional methods using simulations, an experimental phantom, and data from an in vivo animal model of hepatic steatosis. The network weight and a demo code are available online at ***://***.

关键词： autoencoder deep learning (DL) homodyned K-distribution quantitative ultrasound (QUS)

来源：评论

学校读者我要写书评

暂无评论

Physical Layer Key Generation Scheme for MIMO System Based on Feature Fusion autoencoder

引用

IEEE INTERNET OF THINGS JOURNAL 2023年第16期10卷 14886-14895页

作者： Chen, Yanru Chen, Zhengyu Zhang, Yuanyuan Luo, Zhiyuan Li, Yang Xing, Bin Guo, Bing Chen, Liangyin Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Inst Ind Internet Res Chengdu 610065 Peoples R China Inst Southwestern Commun Sci & Technol Secur Commun Lab Chengdu 610041 Peoples R China Ind Big Data Applicat Technol Natl Engn Lab Beijing 100040 Peoples R China Univ Elect Sci & Technol China Chengdu 611731 Peoples R China

Recently, the use of wireless channel state information (CSI) to generate encryption keys in the physical layer has gained significant attention from researchers. Unlike classical cryptography, this approach relies on the variability of the wireless channel, channel reciprocity, and spatial decorrelation to ensure security, making it more lightweight and providing strong randomness. This article proposes a physical layer key generation scheme for wireless LAN MIMO systems based on feature fusion autoencoder (FFAEncoder) to address the issue of a high key disagreement rate (KDR). Our approach involves extracting amplitude and phase features separately, fusing them through multiplication operator in a neural network, and using an autoencoder to extract common features. The proposed scheme was evaluated on multiple data sets in different real-world scenarios, and it was found that the transmitter and receiver codeword's mean squared error (MSE) and mean absolute error (MAE) were smaller than those of the current models, indicating better key generation performance. Additionally, the proposed scheme's KDR was smaller, with a decay rate faster than that of the other two models in the same environment, and the primary key bits were 1/2 and 1/3 that of the other models, respectively, as the signal-to-noise ratio (SNR) increased.

关键词： autoencoder channel reciprocity feature fusion MIMO physical layer key generation

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Translation Learning Method Utilizing autoencoder Pre-Training for Super-Resolution of Radar Sparse Sensor Arrays

引用

IEEE ACCESS 2023年 11卷 61773-61785页

作者： Kim, Jong-Hoon Hong, Ic-Pyo Kongju Natl Univ Smart Nat Space Res Ctr Cheonan 31080 South Korea Kongju Natl Univ Dept Smart Informat Technol Engn Cheonan 31080 South Korea

This study proposes a convolutional neural network based image translation framework to faithfully realize the super-resolution of radar sensor sparse measurement. We exploited the autoencoder model able to learn a latent representation of input domain data via the iteration of encoding and decoding processes. Based on the belief that the low resolution data retains an essential measurement to fully represent the sparse information of the high resolution counterpart, we assumed that input (source domain of low-resolution denoted by X) and output (target domain of high-resolution denoted by Y) share a common latent code. On the other hand, from the observation that the recovery quality of Y-to-Y translation is far more favorable than the outcome from X-to-Y translation, we performed the pre-training for finding the latent code (z(y)) of the Y domain data, and subsequently the acquired z(y) serving as a label for predicting the latent code (z(x)) of X domain data. As a result, in our proposed network, encoder and decoder parts were trained with separate minimization strategies relative to respective loss functions. For the sake of verifying the effect of the pre-training scheme, we introduced hyper-parameters, alpha and beta, to regulate the training rate for the encoder and decoder parts respectively. As metrics for quantitative assessment, detection rate (DR), false alarm rate (FAR) and ROC curve were utilized. Our network set with 0.9 of alpha and 0.1 of beta showed a higher ROC curve plot across the whole range of DR and FAR than a basic autoencoder. DRs of the proposed network and comparative model were respectively 92.23% and 91.00% at FAR of 2%.

关键词： Super-resolution radar sensor arrays sparse measurement autoencoder pre-training latent representation image-to-image translation

来源：评论

学校读者我要写书评

暂无评论

GAAE: a novel genetic algorithm based on autoencoder with ensemble classifiers for imbalanced healthcare data

引用

JOURNAL OF SUPERCOMPUTING 2023年第1期79卷 541-572页

作者： Ram, Pintu Kumar Kuila, Pratyay Natl Inst Technol Dept Comp Sci & Engn Sikkim 737139 India

With the advancement of artificial intelligence (AI) and machine learning techniques, the diseases can be early diagnosed and detected with the help of known healthcare data of similar diseases. However, the analysis of healthcare data becomes challenging due to the imbalance behavior of such data. Such behavior has a skewed nature and the samples of imbalanced dataset contain the majority and minority instances. The quantity of majority instances is much higher than that of the minority instances. Thus, the classifier always gets biased toward the majority instances while classifying an unknown instance. This is not a perfect deal by any of the classifiers especially for disease diagnosis. Therefore, it is important to balance the dataset by considering both the majority and minority class samples. In this context, Genetic Algorithm based on autoencoder (GAAE) model is proposed to process the imbalance data. Initially, an autoencoder is trained by the help of genetic operators and both the majority and minority samples. The chromosome is efficiently designed to represent an autoencoder. The error function is designed as the fitness function with the help of ensemble of classifiers. The optimized autoencoder generates the synthetic data of minority class to balance the data. Once the imbalanced data is balanced using the proposed GAAE, then the feature selection is done based on the correlation coefficient. Then various classifiers, multi-layer perceptron (MLP), k-nearest neighbor (k-NN), C4.5 decision tree (DT) and random forest (RF) are employed for the data classification. An extensive simulation is performed on the proposed approach and comparison is done with the existing approaches. It is observed that consideration of both the majority and minority samples to generate the synthetic data helps the classifiers to perform better. In addition, statistical analysis has also been performed.

关键词： Imbalanced data GAAE autoencoder Ensemble classifier Feature selection

来源：评论

学校读者我要写书评

暂无评论

Operational performance evaluation of bridges using autoencoder neural network and clustering

引用

SMART STRUCTURES AND SYSTEMS 2024年第3期33卷 189-199页

作者： Jiang, Huachen Xie, Liyu Fang, Da Wan, Chunfeng Gao, Shuai Yang, Kang Ding, Youliang Xue, Songtao Shanghai Key Lab Engn Struct Safety SRIBS Shanghai 200032 Peoples R China Tongji Univ Dept Disaster Mitigat Struct Shanghai 200092 Peoples R China Southeast Univ Key Lab Concrete & Prestressed Concrete Struct Minist Educ Nanjing 210096 Peoples R China Shanghai Inst Technol Sch Railway Transportat Shanghai 201418 Peoples R China Tohoku Inst Technol Dept Architecture Sendai Miyagi 9828577 Japan

To properly extract the strain components under varying operational conditions is very important in bridge health monitoring. The abnormal sensor readings can be correctly identified and the expected operational performance of the bridge can be better understood if each strain components can be accurately quantified. In this study, strain components under varying load conditions, i.e., temperature variation and live-load variation are evaluated based on field strain measurements collected from a real concrete box-girder bridge. Temperature-induced strain is mainly regarded as the trend variation along with the ambient temperature, thus a smoothing technique based on the wavelet packet decomposition method is proposed to estimate the temperature-induced strain. However, how to effectively extract the vehicle-induced strain is always troublesome because conventional threshold setting-based methods cease to function: if the threshold is set too large, the minor response will be ignored, and if too small, noise will be introduced. Therefore, an autoencoder framework is proposed to evaluate the vehicleinduced strain. After the elimination of temperature and vehicle-induced strain, the left of which, defined as the model error, is used to assess the operational performance of the bridge. As empirical techniques fail to detect the degraded state of the structure, a clustering technique based on Gaussian Mixture Model is employed to identify the damage occurrence and the validity is verified in a simulation study.

关键词： autoencoder early warning Gaussian mixture model strain measurement structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Graph autoencoder Anomaly Detection for E-Commerce Application by Contextual Integrating Contrast With Reconstruction and Complementarity

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 1623-1630页

作者： Wu, Jinjie Qiu, Zhipeng Zeng, Zhixia Xiao, Ruliang Rida, Imad Zhang, Shi Fujian Normal Univ Coll Comp & Cyber Secur Fuzhou 350117 Peoples R China Univ Technol Compiegne Ctr Rech Royallieu Lab Biomecan & Bioingn UMR7338 F-60200 Compiegne France

Considering the personalized characteristics and behavior patterns of users, quickly and accurately identifying abnormal users is crucial in the realm of E-commerce applications. However, existing methods fall short in integrating local and global structural information. Meanwhile, contextual information can serve effectively as a supervisory signal for anomaly detection. This paper proposes a Graph autoencoder Anomaly Detection model, GAAD, that leverages context-integrated contrast and reconstruction complementarity. This model utilizes local information of target nodes and adopts a contrastive learning module based on graph neural networks to capture anomalies in the structure space;simultaneously, a context subgraph of the global information of the target node is constructed and anomalies in the attribute space are captured through the autoencoder-based reconstruction module. The GAAD model integrates two complementary modules, contrast and reconstruction, to enhance the accuracy of anomaly node detection. The experimental results showcase the superior performance of the proposed model over existing baseline methods across all seven benchmark datasets, thereby highlighting its efficiency in anomaly detection within E-commerce applications. Our code is available at https://***/jinjiewu2000/GAAD.

关键词： Anomaly detection Graph neural networks Context modeling Self-supervised learning Feature extraction Electronic commerce Decoding autoencoder graph neural network contextual integrating anomaly detection

来源：评论

学校读者我要写书评

暂无评论

ABAE: Auxiliary Balanced autoencoder for class-imbalanced semi-supervised learning

引用

PATTERN RECOGNITION LETTERS 2024年 182卷 118-124页

作者： Tang, Qianying Wei, Xiang Su, Qi Zhang, Shunli Beijing Jiaotong Univ Sch Software Engn 3 Shangyuancun Beijing 100044 Peoples R China

Semi -supervised learning has achieved extraordinary success in prevalent image -classification benchmarks. However, a class -balanced distribution that differs notably from real -world data distribution is required. In general, models trained under class-imbalanced semi -supervised learning conditions are severely biased towards the majority classes. To address this issue, we propose a novel framework called ABAE by implanting an Auxiliary Balanced autoencoder branch into existing semi -supervised learning algorithms. Considering that adaptive feature augmentation for different classes can alleviate confirmation bias, we devise a class -aware reconstruction loss to train the autoencoder module. To further smooth the output, we adopt a graph -based label propagation scheme at the end of the autoencoder. Extensive experiments on CIFAR-10/100-LT, SVHN-LT and Small demonstrate the effectiveness of ABAE.

关键词： Class-imbalanced learning Semi-supervised learning autoencoder Label propagation

来源：评论

学校读者我要写书评

暂无评论

AE-LGBM: Sequence-based novel approach to detect interacting protein pairs via ensemble of autoencoder and LightGBM

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2020年 125卷 103964-103964页

作者： Sharma, Abhibhav Singh, Buddha Jawaharlal Nehru Univ Sch Comp & Syst Sci New Delhi 110067 India

Protein-protein interactions (PPIs) play a crucial role in biological processes of living organisms. Correct prediction of PPI can prove to be extremely valuable in probing protein functions which can aid in the development of new and powerful therapies for disease prevention. Many experimental studies have been previously performed to investigate PPIs. However, in-vitro techniques to investigate PPIs are resource-extensive and time-consuming. Although various in-silico approaches to predict PPI have been developed in recent years, they could be fallible in terms of accuracy and false-positive rate. To overcome these shortcomings, we propose a novel approach, AE-LGBM to predict the PPIs more accurately. It employs LightGBM classifier and utilizes the autoencoder, which is an artificial neural network, to efficiently produce lower-dimensional, discriminative, and noise-free features. We incorporate conjoint triad (CT) and Composition-Transition-Distribution (CTD) features into the AE-LGBM framework. On performing ten-fold cross-validation, the prediction accuracies obtained by AE-LGBM for Human and Yeast datasets are 98.7% and 95.4% respectively. AE-LGBM was further evaluated on independent datasets and has achieved excellent accuracies of 100%, 100%, 99.9%, 99.3%, 99.2% on E. coli, M. musculus, C. elegans, H. pylori and H. sapiens respectively. AE-LGBM has also obtained the best accuracy when tested over three important PPI networks namely single-core network (CD9), the multiple-core network (The Ras/Raf/MEK/ERK pathway) and the cross-connection network (Wnt Network). The outstanding generalization ability of AE-LGBM makes it a versatile, efficient, and robust PPIs prediction model.

关键词： Protein-protein interaction Prediction model Machine learning Neural network autoencoder LightGBM Accuracy PPI Protein

来源：评论

学校读者我要写书评

暂无评论

Graph dynamic autoencoder for fault detection

引用

CHEMICAL ENGINEERING SCIENCE 2022年 254卷

作者： Liu, Lu Zhao, Haitao Hu, Zhengwei East China Univ Sci & Technol Sch Informat Sci & Engn Automat Dept Shanghai Peoples R China

Dynamic information is a non-negligible part of time-correlated process data, and its full utilization can improve the performance of fault detection. Traditional dynamic methods concatenate the current process data with a certain number of previous process data into an extended vector before performing feature extraction. However, this simple way of using dynamic information inevitably increases the input dimensionality and it is inappropriate to treat previous process data as equally important. To address these problems, this paper proposes a novel nonlinear dynamic method, called graph dynamic autoencoder (GDAE), for fault detection. GDAE utilizes a graph structure to model the dynamic information between different data points. GDAE firstly embeds the current data point and previous data points as the features of the central node and its neighbors, respectively, then convolves the feature of the central node with the features of its neighbors to derive the updated feature for the central node, and finally, an encoder-decoder structure is adopted to extract the key low-dimensional feature. Due to the utilization of the graph structure, the extended high-dimensional vectors utilized by traditional dynamic fault detection methods are avoided in GDAE. Furthermore, with the dynamically constructed graph, GDAE is able to adaptively assign different weights to its neighbors by updating the adjacency matrix of the graph. Experimental results obtained from a numerical simulation and the Tennessee Eastman process illustrate the superiority of GDAE in terms of missed detection rate (MDR) and false alarm rate (FAR). The source code of GDAE can be found in https://***/luliu-fighting/Graph-Dynamic-autoencoder. (c) 2022 Elsevier Ltd. All rights reserved.

关键词： Process monitoring Dynamic fault detection Graph convolution autoencoder

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：