检索结果-内蒙古大学图书馆

Patch-Wise autoencoder Based on Transformer for Radar High-Resolution Range Profile Target Recognition

IEEE SENSORS JOURNAL 2023年第23期23卷 29406-29414页

作者： Zhang, Xianwen Wei, Yao Wang, Wenying Nanjing Res Inst Elect Technol Nanjing 210039 Peoples R China

High-resolution range profile (HRRP) is indispensable for modern radar automatic target recognition (RATR) systems and commonly has noisy background and misalignment along the range dimension. In this article, we propose a novel algorithm for HRPP recognition with the improvement of recognition accuracy, stability against range translation, and robustness to noise background. This method divides the HRRP into patches and encodes the patches to latent feature vectors via a multihead attention mechanism, modeling the spatial dependence, eliminating the influence of range translation, and focusing on the target area. A decoder is adopted to reconstruct the HRRP and improve the robustness against the noise. Experiments on measured data prove that the proposed algorithm outperforms other existing methods with recognition accuracy increased significantly, sensitivity to the range translation eliminated, and noise robustness improved. This study provides a promising and effective approach for HRRP target recognition.

关键词： autoencoder high-resolution range profile (HRRP) multihead self-attention (MSA) radar automatic target recognition (RART) transformer

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based Data Augmentation for Deepfake Detection 23

Autoencoder-based Data Augmentation for Deepfake Detection

引用

2nd ACM International Workshop on Multimedia AI against Discrimination (MAD)

作者： Stanciu, Dan-Cristian Ionescu, Bogdan Univ Politehn Bucuresti AI Multimedia Lab Bucharest Romania

ISBN: (纸本)9798400701870

Image generation has seen huge leaps in the last few years. Less than 10 years ago we could not generate accurate images using deep learning at all, and now it is almost impossible for the average person to distinguish a real image from a generated one. In spite of the fact that image generation has some amazing use cases, it can also be used with ill intent. As an example, deepfakes have become more and more indistinguishable from real pictures and that poses a real threat to society. It is important for us to be vigilant and active against deepfakes, to ensure that the false information spread is kept under control. In this context, the need for good deepfake detectors feels more and more urgent. There is a constant battle between deepfake generators and deepfake detection algorithms, each one evolving at a rapid pace. But, there is a big problem with deepfake detectors: they can only be trained on so many data points and images generated by specific architectures. Therefore, while we can detect deepfakes on certain datasets with near 100% accuracy, it is sometimes very hard to generalize and catch all real-world instances. Our proposed solution is a way to augment deepfake detection datasets using deep learning architectures, such as autoencoders or U-Net. We show that augmenting deepfake detection datasets using deep learning improves generalization to other datasets. We test our algorithm using multiple architectures, with experimental validation being carried out on state-of-the-art datasets like CelebDF and DFDC Preview. The framework we propose can give flexibility to any model, helping to generalize to unseen datasets and manipulations.

关键词： deepfake deep learning digital video forensics face manipulation data augmentation generalization autoencoder

来源：评论

学校读者我要写书评

暂无评论

Vector-Quantized Variational autoencoder for pansharpening

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2023年第20期44卷 6329-6349页

作者： Talbi, Farid Elmezouar, Miloud Chikr Boutellaa, Elhocine Alim, Fatiha Univ Djillali Liabes Sidi Bel Abbes Dept Elect Commun Networks Architecture & Multimedia Lab Sidi Bel Abbes Algeria Ctr Dev Technol Avancees Div Architecture & Syst Multimedia Algiers Algeria Univ MHamed BOUGARA Inst Genie Elect & Elect Boumerdes Algeria

Pansharpening refers to the fusion of a multispectral image (MS) and a panchromatic image (PAN) to obtain a new image with the same spatial resolution as the PAN image and the same spectral resolution as the MS image. This paper describes a new, efficient, and accurate pansharpening architecture. The Vector-Quantized Variational autoencoder (VQ-VAE) is the foundation of the proposed method. The VQ-VAE model is trained to learn the non-linear mapping of degraded panchromatic image patches to high-resolution patches. This approach ensures that high-resolution patches can be recovered from low-resolution ones. After training on PAN patches, the VQ-VAE estimates high-resolution multispectral patches for each band of the original multispectral image before reconstructing the high-resolution multispectral image from the patches. The original multispectral image, the panchromatic image, and the estimated high-resolution multispectral image are combined through a modified Component Substitution (CS) process to obtain the pansharpened image. Three large satellite datasets from urban areas with 4-band spectral resolution (blue, green, red, and near-infrared) were used to evaluate the proposed pansharpening method's performance. The effectiveness of the proposed method is demonstrated by the quantitative and visual results obtained compared to several literature approaches.

关键词： Pansharpening multispectral images panchromatic images fusion autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on Denoising from Facial Images Using Convolutional autoencoder

引用

GAZI UNIVERSITY JOURNAL OF SCIENCE 2023年第3期36卷 1122-1138页

作者： Darici, Muazzez Buket Erdem, Zeki Kadir Has Univ Dept Elect Elect Engn Istanbul Turkiye Kadir Has Univ Dept Management Informat Syst Istanbul Turkiye

Denoising is one of the most important preprocesses in image processing. Noises in images can prevent extracting some important information stored in images. Therefore, before some implementations such as image classification, segmentation, etc., image denoising is a necessity to obtain good results. The purpose of this study is to compare the deep learning techniques and traditional techniques on denoising facial images considering two different types of noise (Gaussian and Salt&Pepper). Gaussian, Median, and Mean filters have been specified as traditional methods. For deep learning methods, deep convolutional denoising autoencoders (CDAE) structured on three different optimizers have been proposed. Both accuracy metrics and computational times have been considered to evaluate the denoising performance of proposed autoencoders, and traditional methods. The utilized standard evaluation metrics are the peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM). It has been observed that overall, while the traditional methods gave results in shorter times in terms of computation times, the autoencoders performed better concerning the evaluation metrics. The CDAE based on the Adam optimizer has been shown the best results in terms of PSNR and SSIM metrics on removing both types of noise.

关键词： Denoising autoencoder Salt&pepper noise Gaussian noise

来源：评论

学校读者我要写书评

暂无评论

Multi-criteria- Recommendations using autoencoder and Deep Neural Networks with Weight Optimization using Firefly Algorithm

引用

INTERNATIONAL JOURNAL OF ENGINEERING 2023年第1期36卷 130-138页

作者： Spoorthy, G. Sanjeevi, S. G. NIT Warangal Dept CSE Warangal India

Demand for personalized recommendation systems elevated recently by e-commerce, news portals etc., to grab the customer interest on the sites. Collaborative filtering proves to be powerful technique but it always suffers from data sparsity, cold-start and robustness issues. These issues have been tackled by some approaches resulting in higher accuracy. Few of them take user profiles, item attributes and rating time as the side information along with ratings to give interpretative personalized recommendations. These type of approaches tries to find which factors mainly impacted the user to rate an item. Another approach extends the single-criteria ratings of collaborative filtering to multi-criteria ratings. Our approach exploits non-linear interpretative recommendations by exploring Multi-criteria ratings by combination of autoencoders with dropout layer and firefly algorithm optimized weights for deep neural networks. Our approach solves data sparsity, scalability issues and fetch accurate recommendations. Experimental evaluations have been done using Yahoo! Movie and MovieLens datasets. Our approach outperforms in robustness and accuracy with respect to previous research works.

关键词： Multi-Criteria Recommendation Systems autoencoder Firefly Algorithm Deep Neural Networks Deep Learning

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Deep autoencoder Scheme for Cyberattack Detection in the Internet of Things

引用

Computer Systems Science & Engineering 2023年第7期46卷 57-72页

作者： Maha Sabir Jawad Ahmad Daniyal Alghazzawi Information Systems Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah80200Saudi Arabia School of Computing Edinburgh Napier UniversityEdinburgh EH105DYUK

The Internet of things(IoT)is an emerging paradigm that integrates devices and services to collect real-time data from surroundings and process the information at a very high speed to make a *** several advantages,the resource-constrained and heterogeneous nature of IoT networks makes them a favorite target for cybercriminals.A single successful attempt of network intrusion can compromise the complete IoT network which can lead to unauthorized access to the valuable information of consumers and *** overcome the security challenges of IoT networks,this article proposes a lightweight deep autoencoder(DAE)based cyberattack detection *** proposed approach learns the normal and anomalous data patterns to identify the various types of network *** most significant feature of the proposed technique is its lower complexity which is attained by reducing the number of *** optimally train the proposed DAE,a range of hyperparameters was determined through extensive experiments that ensure higher attack detection *** efficacy of the suggested framework is evaluated via two standard and open-source *** proposed DAE achieved the accuracies of 98.86%,and 98.26%for NSL-KDD,99.32%,and 98.79%for the UNSW-NB15 dataset in binary class and multi-class *** performance of the suggested attack detection framework is also compared with several state-of-the-art intrusion detection *** outcomes proved the promising performance of the proposed scheme for cyberattack detection in IoT networks.

关键词： autoencoder cybersecurity deep learning intrusion detection IoT

来源：评论

学校读者我要写书评

暂无评论

TransGAD: A Transformer-Based autoencoder for Graph Anomaly Detection 29th

TransGAD: A Transformer-Based Autoencoder for Graph Anomaly ...

引用

29th International Conference on Database Systems for Advanced Applications (DASFAA)

作者： Guo, Zehao Wu, Nannan Zhao, Yiming Wang, Wenjun Tianjin Univ Coll Intelligence & Comp Tianjin Peoples R China

ISBN: (纸本)9789819755714;9789819755721

Graph anomaly detection, aimed at identifying anomalous patterns that significantly differ from other nodes, has drawn widespread attention in recent years. Due to the complex topological structures and attribute information inherent in graphs, conventional methods often struggle to effectively identify anomalies. Deep anomaly detection methods based on Graph Neural Networks (GNNs) have achieved significant success. However, they face the challenge of not only obtaining limited neighborhood information but over-smoothing. Over-smoothing is the phenomenon where the representations of nodes gradually become similar and flattened across multiple convolutional layers, thereby limiting the comprehensive learning of neighborhood information. Therefore, we propose a novel anomaly detection framework, TransGAD, to address these challenges. Inspired by the Graph Transformer, we introduce a Transformer-based autoencoder. Treating each node as a sequence and its neighborhood as tokens in the sequence, this autoencoder captures both local and global information. We incorporate cosine positional encoding and masking strategy to obtain more informative node representations and leverage reconstruction error for improved anomaly detection. Experimental results on seven datasets demonstrate that our approach outperforms the state-of-the-art methods.

关键词： Graph anomaly detection Transformer autoencoder

来源：评论

学校读者我要写书评

暂无评论

Recursive autoencoder network for prediction of CAD model parameters from STEP files 5

Recursive autoencoder network for prediction of CAD model pa...

引用

5th International Conference on Industry 4.0 and Smart Manufacturing (ISM)

作者： Miles, Victoria Giani, Stefano Vogt, Oliver Kafieh, Raheleh Univ Durham Dept Engn Stockton Rd Durham DH1 3LE England

Databases of 3D CAD (computer aided design) models are often large and lacking in meaningful organisation. Effective tools for automatically searching for, categorising and comparing CAD models, therefore, have many potential applications in improving efficiency within design processes. This paper presents a novel asymmetric autoencoder model, consisting of a recursive encoder network and fully-connected decoder network, for the reproduction of CAD models through prediction of the parameters necessary to generate a 3D part design. Inputs to the autoencoder are STEP (standard for the exchange of product data) files, an ISO standard CAD model format, compatible with all major CAD software. A complete 3D model can be accurately reproduced using a STEP file, meaning that all geometric information can be used to contribute to the final encoded vector, with no loss of small detail. In a CAD model of overall size 10 x 10 x 10 units, for 90% of models, the class of an added feature is estimated with maximum error of 0.6 units, feature size with maximum error of 0.4 units and coordinate values representing position with maximum error of 0.3 units. These results demonstrate the successful encoding of complex geometric information, beyond merely the shape of the 3D object, with potential application in the design of search engine functionality. (c) 2023 The Authors. Published by Elsevier B.V.

关键词： CAD models STEP files recursive neural network autoencoder

来源：评论

学校读者我要写书评

暂无评论

Dual autoencoder based zero shot learning in special domain

引用

PATTERN ANALYSIS AND APPLICATIONS 2023年第2期26卷 797-808页

作者： Li, Qiong Rigall, Eric Sun, Xin Lam, Kin Man Dong, Junyu Qingdao Agr Univ Dept Sci & Informat Sci 700 Changcheng Rd Qingdao 266109 Shandong Peoples R China Ocean Univ China Dept Comp Sci & Technol 238 Songling Rd Qingdao 266100 Shandong Peoples R China Hong Kong Polytech Univ Dept Elect & Informat Engn Hung Hom Kowloon Hong Kong 999077 Peoples R China Tech Univ Munich Dept Aerosp & Geodesy D-80333 Munich Germany

Zero-shot learning aims to learn a visual classifier for a category which has no training samples leveraging its semantic information and its relationship to other categories. It is common, yet vital, in practical visual scenarios, and particularly prominent in the uncharted ocean field. Phytoplankton plays an important part in the marine ecological environment. It is common to encounter the zero-shot recognition problem during the in situ observation. Therefore, we propose a dual autoencoder model, which contains two similar encoder-decoder structures, to tackle the zero-shot recognition problem. The first one is used for the projection from the visual feature space to a latent space, then to the semantic space. Inversely, the second one projects from the semantic space to another latent space, then back to the visual feature space. This structure guarantees the projection from the visual feature space to the semantic space to be more effective, through the stable mutual mapping. Experimental results on four benchmarks demonstrate that the proposed dual autoencoder model achieves competitive performance compared with six recent state-of-the-art methods. Furthermore, we apply our algorithm to phytoplankton classification. We manually annotated phytoplankton attributes to develop a practical dataset for this real and special domain application, i.e., Zero-shot learning dataset for PHYtoplankton (ZeroPHY). Experiment results show that our method achieves the best performance on this real-world application.

关键词： Zero shot learning autoencoder Phytoplankton Classification

来源：评论

学校读者我要写书评

暂无评论

autoencoder-Based Features Extraction for the Health Monitoring in the Space domain 66

Autoencoder-Based Features Extraction for the Health Monitor...

引用

2023 IEEE 66th International Midwest Symposium on Circuits and Systems, MWSCAS 2023

作者： Onofri, Silvia Enttsel, Andriy Manovi, Livia Marchioni, Alex Cognetta, Salvatore Corallo, Francesco Ciancarelli, Carlo Mangia, Mauro Rovatti, Riccardo Setti, Gianluca Dei Univ. of Bologna Arces Italy Thales Alenia Space Italia S.p.A. Italy Cemse Kaust Saudi Arabia

ISBN: (纸本)9798350302103

In the satellite operation domain, the accurate pre-diction of the Remaining Useful Life (RUL) of satellite subsystems and components is fundamental for an effective management of the mission. The accuracy of the RUL estimation depends not only on the predictive model but also on the quality and quantity of degradation features to monitor and predict. This paper proposes the use of an autoencoder to extract time-domain features of a complex multi-sensor satellite sub-system. The autoencoder is tested on a real-world satellite dataset for condition monitoring. The data is injected with increasing drifts to emulate degradation phenomena. The obtained features are compared with traditional time-domain features such as mean and standard deviation. © 2023 IEEE.

关键词： autoencoder Deep Learning Feature extraction Prognostics and health management (PHM) Remaining Useful Life (RUL) Telemetry data

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：