检索结果-内蒙古大学图书馆

Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction

SENSORS 2023年第18期23卷 7802页

作者： Tseng, Yu-Hsuan Wen, Chih-Yu Natl Chung Hsing Univ Dept Comp Sci & Engn Taichung 40227 Taiwan Natl Chung Hsing Univ Dept Elect Engn Taichung 40227 Taiwan Natl Chung Hsing Univ Smart Sustainable New Agr Res Ctr SMARTer Taichung 40227 Taiwan Natl Chung Hsing Univ Innovat & Dev Ctr Sustainable Agr IDCSA Taichung 40227 Taiwan

This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional variational autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.

关键词： human activity recognition variational autoencoder generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

CFNet: An infrared and visible image compression fusion network

引用

PATTERN RECOGNITION 2024年 156卷

作者： Xing, Mengliang Liu, Gang Tang, Haojie Qian, Yao Zhang, Jun Shanghai Univ Elect Power Sch Automat Engn Shanghai 200090 Peoples R China Shanghai JA SOLAR Technol Co Ltd Shanghai 200436 Peoples R China

Image fusion aims to acquire a more complete image representation within a limited physical space to more effectively support practical vision applications. Although the currently popular infrared and visible image fusion algorithms take practical applications into consideration. However, they did not fully consider the redundancy and transmission efficiency of image data. To address this limitation, this paper proposes a compression fusion network for infrared and visible images based on joint CNN and Transformer, termed CFNet. First of all, the idea of variational autoencoder image compression is introduced into the image fusion framework, achieving data compression while maintaining image fusion quality and reducing redundancy. Moreover, a joint CNN and Transformer network structure is proposed, which comprehensively considers the local information extracted by CNN and the global long-distance dependencies emphasized by Transformer. Finally, multi-channel loss based on region of interest is used to guide network training. Not only can color visible and infrared images be fused directly but more bits can be allocated to the foreground region of interest, resulting in a superior compression ratio. Extensive qualitative and quantitative analyses affirm that the proposed compression fusion algorithm achieves state-of-the-art performance. In particular, rate-distortion performance experiments demonstrate the great advantages of the proposed algorithm for data storage and transmission. The source code is available at https://***/Xiaoxing0503/CFNet.

关键词： Image fusion Image compression variational autoencoder Transformer Region of interest

来源：评论

学校读者我要写书评

暂无评论

A generative design framework for passive thermal control with macroscopic metamaterials

引用

THERMAL SCIENCE AND ENGINEERING PROGRESS 2024年 51卷

作者： Ignuta-Ciuncanu, Matei C. Tabor, Philip Martinez-Botas, Ricardo F. Imperial Coll London Dept Mech Engn Sustainable Energy Technol & Turbomachinery Lab London SW7 2AZ England

Efficient thermal management holds pivotal significance in the rapidly evolving realm of energy -dense applications, notably in high-performance computing, where the push toward miniaturization encounters limitations in controlling heat flux within confined spaces. The advent of metamaterials presents an energyfree opportunity to transform thermal control, essential to boosting system efficiency. This work marks a step toward integrating AI in the design and optimization of compact systems, such as printed circuit boards, solar collectors, and power electronics. We present an automated generative design exploration framework for thermal metamaterials capable of effectively controlling heat transfer to achieve multiple objectives: unperturbed temperature distribution (cloaking) and targeted heat flux insulation and concentration. The architected structures developed leverage the optimization of unit cell arrangements with contrasting thermal properties to exhibit characteristics not commonly occurring in nature. This framework employs a variational autoencoder (VAE), trained on bio-inspired leaf and mushroom microstructures, to assemble bi-material unit cells on a flexible lattice for arbitrary domains. By operating a genetic optimizer within the reduced design space of the VAE, we develop these assemblies to address adversarial temperature and heat flux objectives using a finite element solver. We demonstrate the modularity and scalability of the framework, outputting multi -objective metamaterial solutions for user -specified thermal requirements within a total run-time of 5 min only.

关键词： variational autoencoder Genetic algorithm Multi-objective optimization Heat conduction Thermal cloaking Passive thermal management

来源：评论

学校读者我要写书评

暂无评论

Reconstruction and generation of 3D realistic soil particles with metaball descriptor

引用

COMPUTERS AND GEOTECHNICS 2023年第1期161卷

作者： Zhao, Yifeng Gao, Xiangbo Zhang, Pei Lei, Liang Li, Stan Z. Galindo-Torres, S. A. Zhejiang Univ Coll Environm & Resources Sci 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China Westlake Univ Sch Engn Key Lab Coastal Environm & Resources Zhejiang Prov 18 Shilongshan Rd Hangzhou 310024 Zhejiang Peoples R China Westlake Univ Sch Engn 18 Shilongshan Rd Hangzhou 310024 Zhejiang Peoples R China

The morphology of soil particles is crucial in determining its granular characteristics and assembly responses. However, how to introduce accurate and various morphologies of realistic particles in modeling can be challenging, as it often requires time-consuming and costly X-ray Computed Tomography (XRCT). This has led to two prevalent problems in modeling: morphological reconstruction and generation. For reconstruction, we develop a geometric-based Metaball-Imaging algorithm. This algorithm is capable of accurately reconstructing the complex morphologies of realistic particles, including those with concave voids, which cannot be easily represented using other shape descriptors such as the spherical harmonic function. It employs a two-step approach, capturing the main contour of the particles using a series of non-overlapping spheres and then refining surface-texture details through gradient search. Four types of soil particles, hundreds of samples, are applied for evaluations. The result shows good matches on key morphological indicators (i.e., volume, surface area, sphericity, circularity, corey-shape factor, nominal diameter and surface-equivalent-sphere diameter), confirming its reconstruction precision. For generation, we propose the Metaball variational autoencoder. Assisted by deep neural networks, this method can generate new 3D particles in Metaball form, while retaining coessential morphological features with parental particles. Additionally, this method allows for control over the generated shapes through an arithmetic pattern, enabling the generation of particles with specific shapes. Two sets of XRCT images different in sample number and geometric features are chosen as parental data. On each training set, one thousand particles are generated for validations. The generation fidelity is demonstrated through comparisons of morphologies and shape-feature distributions between generated and parental particles. Examples are also provided to demonstrate contr

关键词： The metaball function Particle morphology Particle reconstruction Optimization method Particle generation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

SDM-NET: Deep Generative Network for Structured Deformable Mesh

引用

ACM TRANSACTIONS ON GRAPHICS 2019年第6期38卷 243-243页

作者： Gao, Lin Yang, Jie Wu, Tong Yuan, Yu-Jie Fu, Hongbo Lai, Yu-Kun Zhang, Hao Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China City Univ Hong Kong Sch Creat Media Hong Kong Peoples R China Cardiff Univ Sch Comp Sci & Informat Cardiff S Glam Wales Simon Fraser Univ Sch Comp Sci Burnaby BC Canada Chinese Acad Sci Inst Comp Technol Beijing Key Lab Mobile Comp & Pervas Device Beijing Peoples R China

We introduce SDM-NET, a deep generative neural network which produces structured deformable meshes. Specifically, the network is trained to generate a spatial arrangement of closed, deformable mesh parts, which respects the global part structure of a shape collection, e.g., chairs, airplanes, etc. Our key observation is that while the overall structure of a 3D shape can be complex, the shape can usually be decomposed into a set of parts, each homeomorphic to a box, and the finer-scale geometry of the part can be recovered by deforming the box. The architecture of SDM-NET is that of a two-level variational autoencoder (VAE). At the part level, a PartVAE learns a deformable model of part geometries. At the structural level, we train a Structured Parts VAE (SP-VAE), which jointly learns the part structure of a shape collection and the part geometries, ensuring the coherence between global shape structure and surface details. Through extensive experiments and comparisons with the state-of-the-art deep generative models of shapes, we demonstrate the superiority of SDM-NET in generating meshes with visual quality, flexible topology, and meaningful structures, benefiting shape interpolation and other subsequent modeling tasks.

关键词： Shape representation variational autoencoder structure geometric details generation

来源：评论

学校读者我要写书评

暂无评论

variational Generative Adversarial Network with Crossed Spatial and Spectral Interactions for Hyperspectral Image Classification

引用

REMOTE SENSING 2021年第16期13卷 3131-3131页

作者： Li, Zhongwei Zhu, Xue Xin, Ziqi Guo, Fangming Cui, Xingshuai Wang, Leiquan China Univ Petr East China Coll Oceanog & Space Informat Qingdao 266580 Peoples R China China Univ Petr East China Coll Comp Sci & Technol Qingdao 266580 Peoples R China

variational autoencoders (VAEs) and Generative Adversarial Networks (GANs) have been widely used in hyperspectral image classification (HSIC) tasks. However, the generated HSI virtual samples by VAEs are often ambiguous, and GANs are prone to the mode collapse, which lead the poor generalization abilities ultimately. Moreover, most of these models only consider the extraction of spectral or spatial features. They fail to combine the two branches interactively and ignore the correlation between them. Consequently, the variational generative adversarial network with crossed spatial and spectral interactions (CSSVGAN) was proposed in this paper, which includes a dual-branch variational Encoder to map spectral and spatial information to different latent spaces, a crossed interactive Generator to improve the quality of generated virtual samples, and a Discriminator stuck with a classifier to enhance the classification performance. Combining these three subnetworks, the proposed CSSVGAN achieves excellent classification by ensuring the diversity and interacting spectral and spatial features in a crossed manner. The superior experimental results on three datasets verify the effectiveness of this method.

关键词： hyperspectral image classification variational autoencoder generative adversarial network crossed spatial and spectral interactions

来源：评论

学校读者我要写书评

暂无评论

Nonlinear blind source separation exploiting spatial nonstationarity

引用

INFORMATION SCIENCES 2024年 665卷

作者： Sipila, Mika Nordhausen, Klaus Taskinen, Sara Univ Jyvaskyla Dept Math & Stat Jyvaskyla Finland

In spatial blind source separation the observed multivariate random fields are assumed to be mixtures of latent spatially dependent random fields. The objective is to recover latent random fields by estimating the unmixing transformation. Currently, the algorithms for spatial blind source separation can only estimate linear unmixing transformations. Nonlinear blind source separation methods for spatial data are scarce. In this paper, we extend an identifiable variational autoencoder that can estimate nonlinear unmixing transformations to spatially dependent data, and demonstrate its performance for both stationary and nonstationary spatial data using simulations. In addition, we introduce scaled mean absolute Shapley additive explanations for interpreting the latent components through nonlinear mixing transformation. The spatial identifiable variational autoencoder is applied to a geochemical dataset to find the latent random fields, which are then interpreted by using the scaled mean absolute Shapley additive explanations. Finally, we illustrate how the proposed method can be used as a pre-processing method when making multivariate predictions.

关键词： Independent component analysis Multivariate spatial data Shapley values variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Labyrinth morphological modeling and its application on unreferenced segmentation assessment

引用

BIOMEDICAL SIGNAL PROCESSING AND CONTROL 2023年第1期85卷

作者： Li, Xiaoguang Zhu, Ziyao Yin, Hongxia Zhao, Pengfei Lv, Han Tang, Ruowei Qin, Yating Zhuo, Li Wang, Zhenchang Beijing Univ Technol Beijing Key Lab Computat Intelligence & Intelligen Beijing 100124 Peoples R China Capital Med Univ Beijing Friendship Hosp Dept Radiol Beijing 100050 Peoples R China

The labyrinth of the inner ear is an important auditory and balanced sensory organ and is closely related to tinnitus, hearing loss, vertigo, and Meniere diseases. Quantitative description and measurement of the labyrinth is a challenging task in both clinical practice and medical research. A data-driven-based labyrinth morphological modeling method is proposed for extracting simple and low-dimensional representations or feature vectors to quantify the normal and abnormal labyrinths in morphology. Firstly, a two-stage pose alignment strategy is introduced to align the segmented inner ear labyrinths. Then, an energy-adaptive spatial and inter-slice dimensionality reduction strategy is adopted to extract compact morphological features via a variational autoencoder (VAE). Finally, a statistical model of the compact feature in the latent space is established to represent the morphology distribution of the labyrinths. As one of an application of our model, a reference-free quality evaluation for the segmentation of the labyrinth is explored. The experimental results show that the consistency between the proposed method and the Dice similarity coefficient (DSC) reaches 0.78. Further analysis showed that the model also has a high potential to apply to morphological analysis, such as anomaly detection, of the labyrinths.

关键词： Inner ear labyrinth modeling variational autoencoder Medical image analysis Temporal bone CT image

来源：评论

学校读者我要写书评

暂无评论

Multi-rate modulation encoding via unsupervised learning for audio event detection

引用

EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING 2024年第1期2024卷 19页

作者： Kothinti, Sandeep Reddy Elhilali, Mounya Johns Hopkins Univ Lab Computat Auditory Percept Baltimore MD 21218 USA

Technologies in healthcare, smart homes, security, ecology, and entertainment all deploy audio event detection (AED) in order to detect sound events in an audio recording. Effective AED techniques rely heavily on supervised or semi-supervised models to capture the wide range of dynamics spanned by sound events in order to achieve temporally precise boundaries and accurate event classification. These methods require extensive collections of labeled or weakly labeled in-domain data, which is costly and labor-intensive. Importantly, these approaches do not fully leverage the inherent variability and range of dynamics across sound events, aspects that can be effectively identified through unsupervised methods. The present work proposes an approach based on multi-rate autoencoders that are pretrained in an unsupervised way to leverage unlabeled audio data and ultimately learn the rich temporal dynamics inherent in natural sound events. This approach utilizes parallel autoencoders that achieve decompositions of the modulation spectrum along different bands. In addition, we introduce a rate-selective temporal contrastive loss to align the training objective with event detection metrics. Optimizing the configuration of multi-rate encoders and the temporal contrastive loss leads to notable improvements in domestic sound event detection in the context of the DCASE challenge.

关键词： Audio event detection Multi-rate processing Temporal contrastive loss Unsupervised learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Wasserstein Adversarially Regularized Graph autoencoder

引用

NEUROCOMPUTING 2023年第1期541卷

作者： Liang, Huidong Gao, Junbin Univ Sydney Univ Sydney Business Sch Sydney NSW 2006 Australia

This paper introduces Wasserstein Adversarially Regularized Graph autoencoder (WARGA), an implicit generative algorithm that directly regularizes the latent distribution of node embedding to a target distribution via the Wasserstein metric. To ensure the Lipschitz continuity, we propose two approaches: WARGA-WC that uses weight clipping method and WARGA-GP that uses gradient penalty method. The proposed models have been validated by link prediction and node clustering on real-world graphs with visualizations of node embeddings, in which WARGA generally outperforms other state-of-the-art models based on Kullback-Leibler (KL) divergence and typical adversarial framework. (c) 2023 Elsevier B.V. All rights reserved.

关键词： Wasserstein distance Graph neural networks variational autoencoder Adversarial training

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：