检索结果-内蒙古大学图书馆

VSCA: A Sentence Matching Model Incorporating Visual Perception

COGNITIVE COMPUTATION 2023年第1期15卷 323-336页

作者： Zhang, Zhe Xiao, Guangli Qian, Yurong Ma, Mengnan Leng, Hongyong Zhang, Tao XinJiang Univ Sch Software Urumqi 830000 Peoples R China XinJiang Univ Xinjiang Uygur Autonomous Reg Key Lab Signal Detec Urumqi 830046 Peoples R China Beijing Inst Technol IT Acad Beijing 100081 Peoples R China

Stacking multiple layers of attention networks can significantly improve a model's performance. However, this also increases the model's time and space complexity, making it difficult for the model to capture detailed information on the underlying features. We propose a novel sentence matching model (VSCA) that uses a new attention mechanism based on variational autoencoders (VAE), which exploits the contextual information in sentences to construct a basic attention feature map and combines it with VAE to generate multiple sets of related attention feature maps for fusion. Furthermore, VSCA introduces a spatial attention mechanism that combines visual perception to capture multilevel semantic information. The experimental results show that our proposed model outperforms pretrained models such as BERT on the LCQMC dataset and performs well on the PAWS-X data. Our work consists of two parts. The first part compares the proposed sentence matching model with state-of-the-art pretrained models such as BERT. The second part conducts innovative research on applying VAE and spatial attention mechanisms in NLP. The experimental results on the related datasets show that the proposed method has satisfactory performance, and VSCA can capture rich attentional information and detailed information with less time and space complexity. This work provides insights into the application of VAE and spatial attention mechanisms in NLP.

关键词： Natural language processing Sentence matching variational autoencoder Spatial attention

来源：评论

学校读者我要写书评

暂无评论

CVML-Pose: Convolutional VAE Based Multi-Level Network for Object 3D Pose Estimation

引用

IEEE ACCESS 2023年 11卷 13830-13845页

作者： Zhao, Jianyu Sanderson, Edward Matuszewski, Bogdan J. J. Univ Cent Lancashire Comp Vis & Machine Learning CVML Grp Preston PR1 2HE England

Most vision-based 3D pose estimation approaches typically rely on knowledge of object's 3D model, depth measurements, and often require time-consuming iterative refinement to improve accuracy. However, these can be seen as limiting factors for broader real-life applications. The main motivation for this paper is to address these limitations. To solve this, a novel Convolutional variational Auto-Encoder based Multi-Level Network for object 3D pose estimation (CVML-Pose) method is proposed. Unlike most other methods, the proposed CVML-Pose implicitly learns an object's 3D pose from only RGB images encoded in its latent space without knowing the object's 3D model, depth information, or performing a post-refinement. CVML-Pose consists of two main modules: (i) CVML-AE representing convolutional variational autoencoder, whose role is to extract features from RGB images, (ii) Multi-Layer Perceptron and K-Nearest Neighbor regressors mapping the latent variables to object 3D pose including, respectively, rotation and translation. The proposed CVML-Pose has been evaluated on the LineMod and LineMod-Occlusion benchmark datasets. It has been shown to outperform other methods based on latent representations and achieves comparable results to the state-of-the-art, but without use of a 3D model or depth measurements. Utilizing the t-Distributed Stochastic Neighbor Embedding algorithm, the CVML-Pose latent space is shown to successfully represent objects' category and topology. This opens up a prospect of integrated estimation of pose and other attributes (possibly also including surface finish or shape variations), which, with real-time processing due to the absence of iterative refinement, can facilitate various robotic applications. Code available: https://***/JZhao12/CVML-Pose.

关键词： 3D pose estimation deep learning variational autoencoder synthetic data

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection on household appliances based on variational autoencoders

引用

SUSTAINABLE ENERGY GRIDS & NETWORKS 2022年 32卷

作者： Castangia, Marco Sappa, Riccardo Girmay, Awet Abraha Camarda, Christian Macii, Enrico Patti, Edoardo Politecn Torino Dept Control & Comp Engn I-10129 Turin Italy Politecn Torino Interuniv Dept Reg & Urban Studies & Planning I-10129 Turin Italy

Electrical anomalies in residential buildings represent a serious problem that can unpredictably change the power profiles of end-users, causing a sub-optimal energy distribution. In addition, electrical faults can cause unnoticed energy wastages and higher energy bills, or even severe damages for properties and people in the most critical cases. In this paper, we introduce a novel anomaly detection method for detecting electrical faults in household appliances based on the analysis of their power signatures with unsupervised deep learning techniques. For this purpose, we trained a variational autoencoder to reconstruct the power signatures of three commonly used devices: the dishwasher, the washing machine and the dryer. For each use case, we injected several randomly generated anomalies that simulate to our best realistic electrical faults in these devices. To demonstrate the effectiveness of our method, we compared the accuracy of the variational autoencoder with the classification performance of a one-class support vector machine (OC-SVM) trained with two manual features: the energy consumption and the duration of the appliance's operations. The variational autoencoder showed higher classification accuracy with respect to the OC-SVM, reporting an F1-score greater than 90% in all the use cases. Most importantly, the results demonstrate that deep anomaly detection methods outperform traditional algorithms based on handcrafted features, allowing to better characterize the set of normal cycles and produce more precise alerts for the monitored devices. (C) 2022 Elsevier Ltd. All rights reserved.

关键词： Smart grids Household appliance Anomaly detection Unsupervised learning variational autoencoder Deep learning

来源：评论

学校读者我要写书评

暂无评论

PredLife: Predicting Fine-Grained Future Activity Patterns

引用

IEEE TRANSACTIONS ON BIG DATA 2023年第6期9卷 1658-1669页

作者： Li, Wenjing Shi, Xiaodan Huang, Dou Shen, Xudong Chen, Jinyu Kobayashi, Hill Hiroki Zhang, Haoran Song, Xuan Shibasaki, Ryosuke Univ Tokyo Ctr Spatial Informat Sci Kashiwa Chiba 2770882 Japan Univ Tokyo Informat Technol Ctr Kashiwa Chiba 2770882 Japan Locat Mind Inc Tokyo 1010048 Japan Peking Univ Sch Urban Planning & Design Shenzhen 518055 Guangdong Peoples R China Southern Univ Sci & Technol Southern Univ Sci & Technol Univ Tokyo Joint Res Dept Comp & Engn Shenzhen 518055 Guangdong Peoples R China Malardalens Univ Sch Business Soc & Technol S-72220 Vasteras Sweden Univ Tokyo Interfac Initiat Informat Studies Tokyo 1138654 Japan Reitaku Univ Kashiwa Chiba 2770065 Japan

Activity pattern prediction is a critical part of urban computing, urban planning, intelligent transportation, and so on. Based on a dataset with more than 10 million GPS trajectory records collected by mobile sensors, this research proposed a CNN-BiLSTM-VAE-ATT-based encoder-decoder model for fine-grained individual activity sequence prediction. The model combines the long-term and short-term dependencies crosswise and also considers randomness, diversity, and uncertainty of individual activity patterns. The proposed results show higher accuracy compared to the ten baselines. The model can generate high diversity results while approximating the original activity patterns distribution. Moreover, the model also has interpretability in revealing the time dependency importance of the activity pattern prediction.

关键词： Activity pattern prediction Human mobility Big GPS data variational autoencoder LSTM

来源：评论

学校读者我要写书评

暂无评论

Searching for protein variants with desired properties using deep generative models

引用

BMC BIOINFORMATICS 2023年第1期24卷 1-19页

作者： Li, Yan Yao, Yinying Xia, Yu Tang, Mingjing Yunnan Normal Univ Sch Informat Kunming Peoples R China Huazhong Agr Univ Natl Key Lab Crop Genet Improvement Wuhan Peoples R China Huazhong Agr Univ Natl Ctr Plant Gene Res Wuhan Peoples R China Chinese Acad Agr Sci Agr Genom Inst Shenzhen Shenzhen Branch Guangdong Lab Lingnan Modern AgrGenome Anal Lab Shenzhen Peoples R China Yunnan Normal Univ Engn Res Ctr Sustainable Dev & Utilizat Biomass E Minist Educ Kunming Peoples R China Yunnan Normal Univ Sch Life Sci Kunming Peoples R China

BackgroundProtein engineering aims to improve the functional properties of existing proteins to meet people's needs. Current deep learning-based models have captured evolutionary, functional, and biochemical features contained in amino acid sequences. However, the existing generative models need to be improved when capturing the relationship between amino acid sites on longer sequences. At the same time, the distribution of protein sequences in the homologous family has a specific positional relationship in the latent space. We want to use this relationship to search for new variants directly from the vicinity of better-performing *** improve the representation learning ability of the model for longer sequences and the similarity between the generated sequences and the original sequences, we propose a temporal variational autoencoder (T-VAE) model. T-VAE consists of an encoder and a decoder. The encoder expands the receptive field of neurons in the network structure by dilated causal convolution, thereby improving the encoding representation ability of longer sequences. The decoder decodes the sampled data into variants closely resembling the original *** to other models, the person correlation coefficient between the predicted values of protein fitness obtained by T-VAE and the truth values was higher, and the mean absolute deviation was lower. In addition, the T-VAE model has a better representation learning ability for longer sequences when comparing the encoding of protein sequences of different lengths. These results show that our model has more advantages in representation learning for longer sequences. To verify the model's generative effect, we also calculate the sequence identity between the generated data and the input data. The sequence identity obtained by T-VAE improved by 12.9% compared to the baseline model.

关键词： Protein engineering Temporal convolutional network Deep generative model variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A deep learning factor analysis model based on importance-weighted variational inference and normalizing flow priors: Evaluation within a set of multidimensional performance assessments in youth elite soccer players

引用

STATISTICAL ANALYSIS AND DATA MINING-AN ASA DATA SCIENCE JOURNAL 2023年第5期16卷 474-487页

作者： Kilian, Pascal Leyhr, Daniel Urban, Christopher J. Hoener, Oliver Kelava, Augustin Univ Tubingen Methods Ctr Tubingen Germany Univ Tubingen Inst Sports Sci Methods Ctr Tubingen Germany Univ North Carolina Chapel Hill Dept Psychol & Neurosci Chapel Hill NC USA Univ Tubingen Inst Sports Sci Tubingen Germany

Exploratory factor analysis is a widely used framework in the social and behavioral sciences. Since measurement errors are always present in human behavior data, latent factors, generating the observed data, are important to identify. While most factor analysis methods rely on linear relationships in the data-generating process, deep learning models can provide more flexible modeling approaches. However, two problems need to be addressed. First, for interpretation, scaling assumptions are required, which can be (at least) cumbersome for deep generative models. Second, deep generative models are typically not identifiable, which is required in order to identify the underlying latent constructs. We developed a model that uses a variational autoencoder as an estimator for a complex factor analysis model based on importance-weighted variational inference. In order to receive interpretable results and an identified model, we use a linear factor model with identification constraints in the measurement model. To maintain the flexibility of the model, we use normalizing flow latent priors. Within the evaluation of performance measures in a talent development program in soccer, we found more clarity in the separation of the identified underlying latent dimensions with our models compared to traditional PCA analyses.

关键词： complex factor analysis deep latent variable models latent variable identification soccer talent research variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Inverse design optimization framework via a two-step deep learning approach: application to a wind turbine airfoil

引用

ENGINEERING WITH COMPUTERS 2023年第3期39卷 2239-2255页

作者： Yang, Sunwoong Lee, Sanga Yee, Kwanjung Seoul Natl Univ Dept Aerosp Engn Seoul 08826 South Korea Korea Inst Ind Technol Incheon 21999 South Korea

The inverse approach is computationally efficient in aerodynamic design as the desired target performance distribution is prespecified. However, it has some significant limitations that prevent it from achieving full efficiency. First, the iterative procedure should be repeated whenever the specified target distribution changes. Target distribution optimization can be performed to clarify the ambiguity in specifying this distribution, but several additional problems arise in this process such as loss of the representation capacity due to parameterization of the distribution, excessive constraints for a realistic distribution, inaccuracy of quantities of interest due to theoretical/empirical predictions, and the impossibility of explicitly imposing geometric constraints. To deal with these issues, a novel inverse design optimization framework with a two-step deep learning approach is proposed. A variational autoencoder and multi-layer perceptron are used to generate a realistic target distribution and predict the quantities of interest and shape parameters from the generated distribution, respectively. Then, target distribution optimization is performed as the inverse design optimization. The proposed framework applies active learning and transfer learning techniques to improve accuracy and efficiency. Finally, the framework is validated through aerodynamic shape optimizations of the wind turbine airfoil. Their results show that this framework is accurate, efficient, and flexible to be applied to other inverse design engineering applications.

关键词： Inverse design optimization Multi-layer perceptron variational autoencoder Wind turbine airfoil

来源：评论

学校读者我要写书评

暂无评论

Masked autoencoder Transformer for Missing Data Imputation of PISA 25th

Masked Autoencoder Transformer for Missing Data Imputation o...

引用

25th International Conference on Artificial Intelligence in Education (AIED)

作者： Freire, Guilherme Mendonca Curi, Mariana Univ Sao Paulo Inst Ciencias Matemat & Comp Ave Trab Sao Carlense 400 BR-13566590 Sao Carlos SP Brazil

ISBN: (纸本)9783031643149;9783031643156

This study introduces a scale-down transformer model to address the challenge of missing responses in educational assessments for psychometric evaluation. Traditional estimation methods for Item Response Theory (IRT) models are frequently computationally inefficient in generating estimates for a higher number of dimensions. The challenge becomes more pronounced when dealing with missing responses. We propose a Masked autoencoder Transformer model for discrete input (DiTMAE) to impute missing answers for OECD-PISA response data. The model learns context information from the unmasked parts and reconstructs it using a decoder. For evaluation purposes, we estimate item and person parameters from two different approaches, (i) an adapted variational autoencoder that incorporates the Item Response Theory (IRT) method;(ii) the traditional statistical tool, Joint Maximum Likelihood (JML), that can produce estimates in occurrence of missing values.

关键词： Item Response Theory Missing Data Neural Networks Transformer Model variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Sound-based sleep assessment with controllable subject-dependent embedding using variational Domain Adversarial Neural Network

引用

INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2023年 1-11页

作者： Fukui, Ken-ichi Ishimaru, Shunya Kato, Takafumi Numao, Masayuki Osaka Univ Inst Sci & Ind Res SANKEN 8-1 Mihogaoka Osaka Ibaraki 5670047 Japan Osaka Univ Grad Sch Informat Sci & Technol 1-5 Yamadaoka Suita Osaka 5650871 Japan Osaka Univ Grad Sch Dent 1-8 Yamadaoka Suita Osaka 5650871 Japan

Sleep quality assessment as an indicator of daily health care plays an important role in our physiological and mental activity. Sound during sleep contains rich information on biological activities, such as body movement, snoring, and sleep bruxism. However, sound features differ depending on individual and environmental differences. In order to develop a wide-rage applicable daily sleep assessment, this paper utilizes deep learning to ease individual and environmental differences of sound features. Firstly, by variational Domain Adversarial Neural Network (VDANN) encodes sound events into latent representation, simultaneously eliminates subject-dependent features. Then, sleep pattern in the obtained latent space is trained by Long Short-Term Memory (LSTM) with associated sleep assessment of one night. We performed age group estimation from normal sleep as an objective indicator of sleep comparing to their age group. The experiment with more than 100 subjects showed that VDANN is able to extract subject independent features, and the proposed method outperforms the conventional method for age group estimation from sleep sound even for new subjects. In addition, our model is able to personalize by controlling subject-dependent embedding when after data accumulation of the subject.

关键词： Sleep quality Sound variational autoencoder Domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Using deep learning to generate design spaces for architecture

引用

INTERNATIONAL JOURNAL OF ARCHITECTURAL COMPUTING 2023年第2期21卷 337-357页

作者： Sebestyen, Adam Hirschberg, Urs Rasoulzadeh, Shervin Graz Univ Technol Inst Architecture & Media Graz Austria Vienna Univ Technol Inst Bldg & Ind Construct Vienna Austria Graz Univ Technol Inst Architecture & Media Kronesgasse 5-3 A-8010 Graz Austria

We present an early prototype of a design system that uses Deep Learning methodology-Conditional variational autoencoders (CVAE)-to arrive at custom design spaces that can be interactively explored using semantic labels. Our work is closely tied to principles of parametric design. We use parametric models to create the dataset needed to train the neural network, thus tackling the problem of lacking 3D datasets needed for deep learning. We propose that the CVAE functions as a parametric tool in itself: The solution space is larger and more diverse than the combined solution spaces of all parametric models used for training. We showcase multiple methods on how this solution space can be navigated and explored, supporting explorations such as object morphing, object addition, and rudimentary 3D style transfer. As a test case, we implemented some examples of the geometric taxonomy of "Operative Design" by Di Mari and Yoo.

关键词： deep learning generative methods parametric design design space 3D object generation variational autoencoder operative design artificial intelligence machine learning voxels

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：