检索结果-内蒙古大学图书馆

BLER performance evaluation of an enhanced channel autoencoder

COMPUTER COMMUNICATIONS 2021年 176卷 173-181页

作者： Njoku, Judith Nkechinyere Morocho-Cayamcela, Manuel Eugenio Lim, Wansu Kumoh Natl Inst Technol Dept Aeronaut Mech & Elect Convergence Engn Gumi South Korea Yachay Tech Univ Sch Math & Computat Sci San Miguel De Urcuqui Ecuador

The concept of using autoencoders (AEs) to represent wireless communication systems as an end-to-end reconstruction task that optimizes the transmitter and receiver components simultaneously in a single process has attracted the attention of wireless practitioners worldwide. This is attributable to the flexibility, and convenience of representing complex channel models. However, owing to the characteristics of deep neural networks (DNNs), as the AE learns the representation of the channel, overfitting limits its performance. In this paper, we propose RegAE, a regularized DNN architecture that overcomes the overfitting limitation in AEs and reduces their training complexity, which are characteristics of models with higher dimensions. We demonstrate that RegAE improves the block error rate (BLER) as compared with equivalent models from the literature. Thereby, it achieves a performance (1) better than that of a 4/7 rate Hamming code with a 16 phase-shift keying (16PSK) modulation under an additive white Gaussian noise (AWGN) channel, (2) comparable to that of a 4/7 rate maximum likelihood decoding (MLD) with a E-b/N-0 range from 1 dB to 5 dB, and (3) equivalent to that of an uncoded binary phase-shift keying (BPSK) modulation over a E-b/N-0 range from 0 dB to 10 dB.

关键词： autoencoder Deep learning Neural network Wireless communications Modulation End-to-end learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Outlier Detection Applied to a Doppler Velocity Log Sensor Based on Hybrid autoencoder and Recurrent Neural Network

引用

IEEE JOURNAL OF OCEANIC ENGINEERING 2021年第4期46卷 1288-1301页

作者： Davari, Narjes Aguiar, A. Pedro Univ Porto Fac Engn P-4200465 Porto Portugal

This article presents a real-time outlier detection deep-learning (OD-DL)-based method using a hybridized artificial neural network (ANN) approach. We propose an unsupervised ANN scheme that runs in parallel, a denoising autoencoder (DAE) and a recurrent neural network (RNN). The DAE aims to reconstruct relevant/normal input data, whereas it seeks to ignore outliers;the RNN, with a recursive structure, is used to predict time-series data. As measurements arrive, two tasks are performed: 1) the outlier decision, which is based on a reconstruction error and an energy score criteria from the output difference between the DAE and the RNN;and 2) the training procedure for both DAE and RNN. The proposed OD-DL scheme is specifically targeted to address the outlier problem of the data generated by a Doppler velocity log (DVL) sensor installed on board of an autonomous underwater vehicle (AUV) to enhance the AUV navigation system performance. In particular, the DVL data enter into the OD-DL scheme whose output is fed into an AUV navigation system that runs an error-state Kalman filter that integrates the corrected DVL data with the measurements of an inertial measurement unit and a depth meter. The experimental results show that the AUV navigation system with the OD-DL method outperforms in terms of a more accurate estimated position when compared with the case that there is no outlier detection and with the case of a navigation system using a conventional outlier detection method, or other simpler deep-learning methods.

关键词： Navigation Neurons Recurrent neural networks Kalman filters Training Real-time systems Anomaly detection autoencoder autonomous underwater vehicle (AUV) error-state Kalman filter (ESKF) integrated navigation system outlier detection (OD) recurrent neural network (RNN)

来源：评论

学校读者我要写书评

暂无评论

EXTRACTING RELEVANCE FROM SAR TEMPORAL PROFILES ON A GLACIER AND AN ALPINE WATERSHED BY A DEEP autoencoder 24

EXTRACTING RELEVANCE FROM SAR TEMPORAL PROFILES ON A GLACIER...

引用

24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow

作者： Charrier, Laurane di Martino, Thomas Koeniguer, Elise Colin Weissgerber, Flora Plyer, Aurelien Univ Paris Saclay DTIS ONERA Gif Sur Yvette France Univ Savoie Mt Blanc LISTIC Annecy France Univ Paris Saclay Cent Supelec SONDRA Gif Sur Yvette France

This paper proposes to use methods for compressing the temporal profiles of Sentinel-1 images, in order to be able to evaluate and analyze the richness of the temporal dynamics, both on a glacier and on a watershed. We propose to use unsupervised deep learning to auto-encode the temporal information in 3 dimensions, allowing to use the three descriptors as three RGB components to produce a colored composition synthesizing the information. We compare this Convolutional autoencoder (CAE) approach with a dimensionality reduction based on a Principal Component Analysis (PCA) of the temporal profiles. The two methods, CAE and PCA, are applied to a time series over the Kyagar Glacier before and after a surge event, and on an alpine watershed to compare the differences in dynamic evolution associated with different terrain classes with and without snow. On the one hand, on the glacier, the stacks of 10 images used are too short for CAE to extract more than two really significant axes. On the other hand, with longer profiles available over the alpine watershed, the CAE is interesting to improve the clustering results obtained from the decomposition.

关键词： deep learning autoencoder glacier visualization surge clustering

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Recognition of Aquatic Invasive Species Larvae Using autoencoder-Based Feature Averaging 17th

Recognition of Aquatic Invasive Species Larvae Using Autoenc...

引用

17th International Symposium on Visual Computing (ISVC)

作者： Chowdhury, Shaif Hamerly, Greg Baylor Univ Waco TX 76798 USA

ISBN: (纸本)9783031207129;9783031207136

The spread of invasive aquatic species disrupts ecological balance, damages natural resources, and adversely affects agricultural activity. There is a need for automated systems that can detect and classify invasive and non-invasive aquatic species using underwater videos without human supervision. In this paper, we intend to classify the larvae of invasive species like Zebra and Quagga mussels. These organisms are native to eastern Europe, but are invasive in United States waterways. It's important to identify invasive species at the larval stage when they are mobile in the water and before they have established a presence, to avoid infestations. Video-based underwater species classification has several challenges due to variation of illumination, angle of view and background noise. In the case of invasive larvae, there is added difficulty due to the microscopic size and small differences between aquatic species larvae. Additionally, there are challenges of data imbalance since invasive species are typically less abundant than native species. In video-based surveillance methods, each organism may have multiple video frames offering different views that show different angles, conditions, etc. Since, there are multiple images per organism, we propose using image set based classification which can accurately classify invasive and non-invasive organisms based on sets of images. Image set classification can often have higher accuracy even if single image classification accuracy is lower. Our system classifies image sets with a feature averaging pipeline that begins with an autoencoder to extract features from the images. These features are then averaged for each set corresponding to a single organism. The final prediction is made by a classifier trained on the image set features. Our experiments show that feature averaging provides a significant improvement over other models of image classification, achieving more than 97% F1 score to predict invasive organisms on our v

关键词： Invasive species Quagga mussels Classification Image set autoencoder Feature averaging

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL IMAGE CHANGE DETECTION BASED ON MULTI-SCALE 3D CONVOLUTION autoencoder

HYPERSPECTRAL IMAGE CHANGE DETECTION BASED ON MULTI-SCALE 3D...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Tang, Yingjie Fan, Yuanze Feng, Shou Zhao, Chunhui Luo, Tianfang Harbin Engn Univ Coll Informat & Commun Engn Harbin Peoples R China

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

(1)Change detection has always been a hot research area in the field of hyperspectral image (HSI) processing. However, in the current change detection methods, most of them need to train a large number of labeled data to extract representative features. In this paper, a hyperspectral change detection method based on multi-scale three-dimensional (3D) convolution autoencoder network (M3CAN) is proposed. Firstly, the multi-scale 3D convolution block is adopted in the autoencoder which can extract effective spectral-spatial joint features of HSIs. Then, the autoencoder is pre-trained to obtain the trained encoder as the feature extractor. Finally, the feature maps of the bi-temporal data are obtained by the encoder and then sent to the Softmax classifier to obtain the final change detection result. In this paper, unsupervised training of autoencoder is combined with supervised training of classifier. Therefore, only a small amount of data is needed to complete the training, which avoids the difficulty of requiring many labeled training data. Experiments show that the proposed method has good results on two datasets.

关键词： Hyperspectral image Change detection Multi-scale 3D convolution autoencoder

来源：评论

学校读者我要写书评

暂无评论

Design of autoencoder Algorithm for Compression of Lightweight EEG Signals Based on 2-D Rhythm Feature Maps

IEEE SENSORS LETTERS

引用

IEEE SENSORS LETTERS 2025年第3期9卷

作者： Ma, Peijun Yao, Cong Shi, Jiangyi Zhao, Gongzhi Ma, Mingyu Xidian Univ Sch MicroElect Xian 710000 Peoples R China

In recent years, with the development of brain science, the value of electroencephalography (EEG) data has become prominent. However, due to the characteristics of real-time transmission and large amounts of data, there is an urgent need for efficient and lightweight EEG compression algorithms. The existing EEG compression methods have many shortcomings, such as limited compression ratio (CR), poor reconstruction signal quality, and too large model scale, which cannot meet the developmental needs of portable wearable EEG detection devices. In this letter, a method of EEG signal compression based on 2-D rhythm feature maps is proposed. Through discrete wavelet transformation (DWT) extraction of the signal rhythm characteristics, the signal is compressed and reconstructed using encoding and reconstruction channels based on an autoencoder network. At the output end of the encoding channel, entropy coding is carried out to further compress the data volume. Through the discussion of several coding algorithms, JPEG2000 is selected as the local optimal coding algorithm. In addition, based on the idea of grouping convolution and void convolution kernel, a lightweight structure is designed to simplify the process of the proposed network and greatly reduce the number of model parameters. Experiments show that, compared with other similar algorithms, the percentage-root-mean-square distortion and mean squared error (MSE) of the proposed algorithm are 14.76% and 2.95%, respectively, at a relatively high CR (CR is about 16). And only 87.9-k parameters are used, which is more suitable for embedded scenarios and wearable devices.

关键词： Convolution Electroencephalography Feature extraction Transform coding Rhythm Kernel autoencoders Brain modeling Sleep Signal processing algorithms Sensor signal processing 2-D rhythm profile autoencoder electroencephalography (EEG) JPEG2000 lightweight signal compression

来源：评论

学校读者我要写书评

暂无评论

Enhanced autoencoder-based LiDAR localization in self-driving vehicles

引用

APPLIED SOFT COMPUTING 2024年 152卷

作者： Charroud, Anas El Moutaouakil, Karim Palade, Vasile Yahyaouy, Ali Univ Sidi Mohamed Ben Abdellah Engn Sci Lab ESL FST Fes Fes 30000 Morocco Coventry Univ Ctr Computat Sci & Math Modelling Coventry England Sidi Mohamed Ben Abdellah Univ Sci Fac Dhar Mahraz Comp Sci Automat & Cognitivism Lab Fes 30000 Morocco

The ability of self -driving vehicles to carry out navigation tasks successfully relies heavily on the implementation of a strong localization system. Global navigation satellite systems have been used to provide such information to the vehicle. However, this faces challenges related to the position computation in certain environments, such as in tunnels, under bridges, or in urban canyons. This paper proposes an autoencoder based method to predict a vehicle's position based on a LiDAR point cloud (converted into a reference system) without using additional sensors. The proposed model modifies the objective function of the autoencoder to include an additional objective responsible for adapting the output of the encoder layer (the latent space) to predict the position. Moreover, a penalty parameter was used in the objective function to emphasize the learning in the latent space. The convergence of the proposed method was proven by showing that it is a stochastic -local -quasi -convex function, which ensures the effectiveness of the Stochastic Normalized Gradient Descent algorithm in achieving convergence. The NCLT dataset was used to train our model in PyTorch. In comparison to various advanced registration techniques, our method achieves excellent results for the majority of the Kitti dataset sequences as well. The method achieved a mean absolute error of about 0.5, which is desirable for autonomous -driving vehicles.

关键词： Self-driving vehicles Localization Mapping Optimization autoencoder Latent space

来源：评论

学校读者我要写书评

暂无评论

Recurrent graph convolutional multi-mesh autoencoder for unsteady transonic aerodynamics

引用

JOURNAL OF FLUIDS AND STRUCTURES 2024年 131卷

作者： Massegur, David Da Ronch, Andrea Univ Southampton Fac Engn & Phys Sci Southampton SO16 7QF England

Unsteady, high-fidelity aerodynamic load predictions around a three-dimensional configuration will remain computationally expensive for the foreseeable future. Data-driven algorithms based on deep-learning are an attractive option for reduced order modelling of complex, nonlinear systems. However, a dedicated approach is needed for applicability to large and unstructured domains that are typical in engineering. This work presents a geometric-deep-learning multi- mesh autoencoder framework to predict the spatial and temporal evolution of aerodynamic loads for a finite-span wing undergoing different types of motion. The novel framework leverages on: (a) graph neural networks for aerodynamic surface grids embedded with a multi- resolution algorithm for dimensionality reduction;and (b) a recurrent scheme for time-marching the aerodynamic loads. The test case is for the BSCW wing in transonic flow undergoing a combination of forced-motions in pitch and plunge. A comprehensive comparison between a quasi-steady and a recurrent approach is provided. The model training requires four unsteady, high-fidelity aerodynamic analyses which require each about two days of HPC computing time. For any common engineering task that involves more than four cases, a clear benefit in computing costs is achieved using the proposed framework as an alternative predictive tool: new cases are computed in seconds on a standard GPU.

关键词： Geometric deep learning Recurrent neural network autoencoder Computational fluid dynamics Unsteady aerodynamics Graph convolutional network Multi mesh BSCW wing

来源：评论

学校读者我要写书评

暂无评论

A convolutional autoencoder architecture for robust network intrusion detection in embedded systems

引用

JOURNAL OF SYSTEMS ARCHITECTURE 2024年 156卷

作者： Borgioli, Niccolo Aromolo, Federico Phan, Linh Thi Xuan Buttazzo, Giorgio Scuola Super Sant Anna Pisa Italy Univ Penn Philadelphia PA USA

Security threats are becoming an increasingly relevant concern in cyber-physical systems. Cyber attacks on these systems are not only common today but also increasingly sophisticated and constantly evolving. One way to secure the system against such threats is by using intrusion detection systems (IDSs) to detect suspicious or abnormal activities characteristic of potential attacks. State-of-the-art IDSs exploit both signature-based and anomaly-based strategies to detect network threats. However, existing solutions mainly focus on the analysis of statically defined features of the traffic flow, making them potentially less effective against new attacks that cannot be properly captured by analyzing such features. This paper presents an anomaly-based IDS approach that leverages unsupervised neural models to learn the expected network traffic, enabling the detection of unknown novel attacks (as well as previously-known ones). The proposed solution uses an autoencoder to reconstruct the received packets and detect malicious packets based on the reconstruction error. A careful optimization of the model architecture allowed improving detection accuracy while reducing detection time. The proposed solution has been implemented on a real embedded platform, showing that it can support modern high-performance communication interfaces, while significantly outperforming existing approaches in both detection accuracy, inference time, generalization capability, and robustness to poisoning (which is commonly ignored by state-of-the-art IDSs). Finally, a novel mechanism has been developed to explain the detection performed by the proposed IDS through an analysis of the reconstruction error.

关键词： Intrusion detection Artificial neural networks autoencoder Unsupervised learning Poisoning robustness Explainable AI

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：