检索结果-内蒙古大学图书馆

VAE-CoGAN: Unpaired image-to-image translation for low-level vision

SIGNAL IMAGE AND VIDEO PROCESSING 2023年第4期17卷 1019-1026页

作者： Zhang, Juan Lang, Xiaoqi Huang, Bo Jiang, Xiaoyan Shanghai Univ Engn Sci Shanghai 201620 Peoples R China

Low-level vision problems, such as single image haze removal and single image rain removal, usually restore a clear image from an input image using a paired dataset. However, for many problems, the paired training dataset will not be available. In this paper, we propose an unpaired image-to-image translation method based on coupled generative adversarial networks (CoGAN) called VAE-CoGAN to solve this problem. Different from the basic CoGAN, we propose a shared-latent space and variational autoencoder (VAE) in framework. We use synthetic datasets and the real-world images to evaluate our method. The extensive evaluation and comparison results show that the proposed method can be effectively applied to numerous low-level vision tasks with favorable performance against the state-of-the-art methods.

关键词： Dehaze Derain Generative adversarial networks variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Inference over radiative transfer models using variational and expectation maximization methods

引用

MACHINE LEARNING 2023年第3期112卷 921-937页

作者： Svendsen, Daniel Heestermans Hernandez-Lobato, Daniel Martino, Luca Laparra, Valero Moreno-Martinez, Alvaro Camps-Valls, Gustau Univ Valencia Image Proc Lab IPL Valencia Spain Univ Autonoma Madrid Dept Comp Sci Madrid Spain Univ Rey Juan Carlos Madrid Dept Signal Theory & Telecommun Madrid Spain

Earth observation from satellites offers the possibility to monitor our planet with unprecedented accuracy. Radiative transfer models (RTMs) encode the energy transfer through the atmosphere, and are used to model and understand the Earth system, as well as to estimate the parameters that describe the status of the Earth from satellite observations by inverse modeling. However, performing inference over such simulators is a challenging problem. RTMs are nonlinear, non-differentiable and computationally costly codes, which adds a high level of difficulty in inference. In this paper, we introduce two computational techniques to infer not only point estimates of biophysical parameters but also their joint distribution. One of them is based on a variational autoencoder approach and the second one is based on a Monte Carlo Expectation Maximization (MCEM) scheme. We compare and discuss benefits and drawbacks of each approach. We also provide numerical comparisons in synthetic simulations and the real PROSAIL model, a popular RTM that combines land vegetation leaf and canopy modeling. We analyze the performance of the two approaches for modeling and inferring the distribution of three key biophysical parameters for quantifying the terrestrial biosphere.

关键词： variational autoencoder Expectation maximization Radiative transfer model Inverse modeling Density estimation

来源：评论

学校读者我要写书评

暂无评论

Deep generative model with time series-image encoding for manufacturing fault detection in die casting process

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2023年第7期34卷 3001-3014页

作者： Song, Jiyoung Lee, Young Chul Lee, Jeongsu Korea Inst Ind Technol Smart Liquid Proc R&D Dept 113-58 Seohaean Ro Siheung Si Gyeonggi Do South Korea Gachon Univ Dept Mech Smart & Ind Engn 1342 Seongnamdaero Seongnam Si Gyeonggi Do South Korea

The increasing demand for advanced fault detection in manufacturing processes has encouraged the application of industrial intelligence based on deep learning. However, implementing deep learning technology at actual manufacturing sites remains challenging because the data acquired during the manufacturing process are not only unlabeled but also imbalanced time series data. In this study, we constructed semi-supervised manufacturing fault detection methods to deal with the imbalanced time series data obtained from manufacturing applications, based on recently proposed deep generative models: variational autoencoder-reconstruction along projection pathway (VAE-RaPP) and Fence generative adversarial network (Fence GAN). To apply a semi-supervised learning algorithm, 1000 labeled samples of good product were prepared. The deep generative models learned the features of good product from these labeled samples during training. Consequently, the model was sufficiently trained to distinguish good and defective product in unlabeled samples. Additionally, we converted the time series data acquired during the manufacturing process into images to improve the feature extraction capability of deep neural networks based on three encoding methods: Gramian angular difference field (GADF), Markov transition field (MTF), and recurrence plot (RP). The performance of these methods was then compared using four evaluation indicators: area under the receiver operating characteristic (AUROC), average precision (AP) score, precision-recall (PR) curve, and accuracy. The VAE-RaPP exhibited outstanding performance in all types of encoding methods when compared with the Fence GAN. This research provides a novel approach that combines the encoding of time series into images and deep generative models for manufacturing fault detection.

关键词： Fault detection Generative adversarial network variational autoencoder Time series data Image encoding Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

CNN-VAE: An intelligent text representation algorithm

引用

JOURNAL OF SUPERCOMPUTING 2023年第11期79卷 12266-12291页

作者： Xu, Saijuan Guo, Canyang Zhu, Yuhan Liu, Genggeng Xiong, Neal Fujian Business Univ Coll Informat Engn Lianpan Rd 2 Fuzhou 350506 Fujian Peoples R China Fuzhou Univ Coll Comp & Data Sci Xueyuan Rd 2 Fuzhou 350116 Fujian Peoples R China Sul Ross State Univ Dept Comp Math & Phys Sci 1404 East Highway 90 Alpine TX 79830 USA

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively.

关键词： Convolutional neural network Feature extraction Text representation Topical word embedding variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Relaying Topology: Optimization of IoT Networks With Energy Harvesting

引用

IEEE ACCESS 2023年 11卷 41827-41839页

作者： Chung, Kiseop Lim, Jin-Taek Agcy Def Dev Daejeon 34186 South Korea

In this paper, we examine Internet of Things (IoT) systems related to smart cities, smart factories, connected cars, etc. To support such systems in a wide area with low power consumption, energy harvesting technology utilizing wireless charging infrastructure is necessary for the longevity of networks. Considering that the position and amount of energy charged for each device could be unbalanced according to the distribution of nodes and energy sources, maximizing the minimum throughput among all nodes has become an NP-hard challenging issue. To overcome this challenge, we propose a machine learning based relaying topology algorithm with a novel backward-pass rate assessment method to present proper learning direction and an iterative balancing time slot allocation algorithm which can utilize a node with sufficient energy as the relay. To validate our proposed scheme, we conducted simulations on our established system model;thus, we confirm that the proposed scheme is stable and superior to conventional schemes.

关键词： Topology Internet of Things Optimization Network topology Unsupervised learning Resource management Energy harvesting variational autoencoder IoT network TDMA system energy harvesting relay

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Transformer Balanced Hashing for Multispectral Remote Sensing Image Retrieval

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2023年 16卷 7089-7099页

作者： Chen, Yaxiong Wang, Fan Lu, Lin Xiong, Shengwu Wuhan Univ Technol Sch Comp Sci & Artificial Intelligence Wuhan 430070 Peoples R China Wuhan Univ Technol Shanghai Artificial Intelligence Lab Shanghai 200232 Peoples R China Wuhan Univ Technol Sanya Sci & Educ Innovat Park Sanya 572000 Peoples R China Wuhan Univ Technol Chongqing Res Inst Chongqing 401122 Peoples R China

For remote sensing (RS) image retrieval task, hashing technology have been extensively researched in recent works. Unsupervised hashing approaches have attracted much attention in the RS data processing field because label collection takes a lot of time. Most of which fail to consider the interactions among the multichannel information of multispectral RS images and the disparity between the hash-like codes space and the Hamming space, which lead to the poor performance of multispectral RS image retrieval. In this article, we tackle these dilemmas with a novel unsupervised hashing approach, namely Unsupervised Transformer Balanced Hashing (UTBH), to utilize a convolutional variational autoencoder architecture with a novel RS transformer to perform effective hash codes learning. We first integrate a convolutional variational autoencoder architecture with a novel RS transformer, which can guide the interactions among the multichannel information of multispectral RS images. Meanwhile, a new objective function is proposed to preserve discrimination of hash codes in the hashing learning process and reduce the disparity between the hash-like codes space and the Hamming space effectively. Finally, experimental results on two multispectral RS image datasets indicate that UTBH approach achieves superior performance over other unsupervised image retrieval approaches.

关键词： Hash codes multichannel information transformer variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Evaluation of Interval Equalization of Power Quality in Active Distribution Network Based on CVAE-TS

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2023年第1期19卷 83-95页

作者： Sun, Xianshan Sheng, Yuefeng Wu, Cheng Cai, Qingnan Lai, Xunyang Deqing Cty Power Supply Co State Grid Zhejiang Ele Deqing 313200 Zhejiang Peoples R China

When distributed generation is connected to the distribution network, there are many uncertainties and various loads, and the power quality is difficult to judge. Therefore, a comprehensive evaluation method for power quality interval balance of active distribution network based on CVAE-TS (coordination Vocational Academic Education-Takagi-Sugeno) is proposed. The method of change vector analysis (CVA) is adopted to generate power data samples of active distribution network. The category labels of each data are added to the original power data as training sets for CVAE, and the number of samples generated within the interval is increased. TS modeling is adopted, fuzzy set theory is combined with least square method, incomplete electric energy data in data sample is converted into complete electric energy data by filling method, and the applicability of data is enhanced. An interval evaluation model of power quality in active power network is established by using analytic hierarchy process. The experimental results show that this method can effectively realize the sampling and filling of power data in active distribution network, the evaluation results are accurate and reliable, and the horizontal distribution of power quality can be intuitively known.

关键词： variational autoencoder TS modeling Active distribution network Power quality Interval equalization Comprehensive evaluation

来源：评论

学校读者我要写书评

暂无评论

Sparse representation learning with modified q-VAE towards minimal realization of world model

引用

ADVANCED ROBOTICS 2023年第13期37卷 807-827页

作者： Kobayashi, Taisuke Watanuki, Ryoma Natl Inst Informat Principles Informat Res Div Tokyo Japan Grad Univ Adv Studies SOKENDAI Sch Multidisciplinary Sci Dept Informat Hayama Kanagawa Japan Nara Inst Sci & Technol Div Informat Sci Nara Japan

Extraction of low-dimensional latent space from high-dimensional observation data is essential to construct a real-time robot controller with a world model on the extracted latent space. However, there is no established method for tuning the dimension size of the latent space automatically, suffering from finding the necessary and sufficient dimension size, i.e. the minimal realization of the world model. In this study, we analyze and improve Tsallis-based variational autoencoder (q-VAE), and reveal that, under an appropriate configuration, it always facilitates making the latent space sparse. Even if the dimension size of the pre-specified latent space is redundant compared to the minimal realization, this sparsification collapses unnecessary dimensions, allowing for easy removal of them. We experimentally verified the benefits of the sparsification by the proposed method that it can easily find the necessary and sufficient six dimensions for a reaching task with a mobile manipulator that requires a six-dimensional state space. Moreover, by planning with such a minimal-realization world model learned in the extracted dimensions, the proposed method was able to exert a more optimal action sequence in real-time, reducing the reaching accomplishment time by around 20%.

关键词： variational autoencoder World model Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection in Internet of Blended Environment Using Ensemble of Heterogeneous autoencoders(E-HAE)

引用

Computer Systems Science & Engineering 2023年第9期46卷 3261-3284页

作者： Lelisa Adeba Jilcha Deuk-Hun Kim Julian Jang-Jaccard Jin Kwak ISAA Lab. Department of AI Convergence NetworkAjou UniversitySuwon16499Korea ISAA Lab. Institute for Information and CommunicationAjou UniversitySuwon16499Korea Department of Computer Science and Information Technology Massey UniversityAuckland0745New Zealand Department of Cyber Security Ajou UniversitySuwon16499Korea

Contemporary attackers,mainly motivated by financial gain,consistently devise sophisticated penetration techniques to access important information or *** growing use of Internet of Things(IoT)technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation,as it facilitates multiple new attack vectors to emerge *** such,existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection *** address this problem,we designed a blended threat detection approach,considering the possible impact and dimensionality of new attack surfaces due to the aforementioned *** collectively refer to the convergence of different technology sectors as the internet of blended *** proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational *** extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02%detection ***,performance of the proposed approach was compared with various single model(autoencoder)-based network intrusion detection approaches:autoencoder,variational autoencoder,convolutional variational autoencoder,and long short-term memory variational *** proposed model outperformed all compared models,demonstrating F1-score improvements of 4.99%,2.25%,1.92%,and 3.69%,respectively.

关键词： Network intrusion detection anomaly detection TON_IoT dataset smart grid smart city smart factory digital healthcare autoencoder variational autoencoder LSTM convolutional variational autoencoder ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Generative AI for 3-D Point Clouds

引用

IEEE MULTIMEDIA 2024年第2期31卷 5-6页

作者： Kamal, Minhas Prabhakaran, Balakrishnan Univ Texas Dallas Dallas TX 75080 USA

Generative AI refers to algorithms and techniques designed to generate text, images, videos, or other data, typically in response to prompts. These algorithms leverage large generative models that learn the patterns and structures of the media data (text, images, or videos) provided during training and then generate new media data that have analogous characteristics. Much of the recent research has gone into applying generative AI for text and 2-D image data. However, generative AI for 3-D models, especially 3-D point cloud data (PCD), has compelling applications in virtual reality content generation, gaming, and product design and manufacturing, but it introduces a multitude of research challenges.

关键词： Point Cloud Transformer News Media Diffusion Process Random Noise Autoregressive Model 3 D Space Generative Adversarial Networks Diffusion Model Product Design Manufacture Of Products Encoder Decoder variational autoencoder Point Cloud Data Data Augmentation Techniques Lot Of Noise Voxel Grid Virtual Reality Games Domain Approach Virtual Design

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：