检索结果-内蒙古大学图书馆

3D Generative Model Latent Disentanglement via Local Eigenprojection

COMPUTER GRAPHICS FORUM 2023年第6期42卷 e14793-e14793页

作者： Foti, Simone Koo, Bongjin Stoyanov, Danail Clarkson, Matthew J. UCL London England Univ Calif Santa Barbara Santa Barbara CA USA

Designing realistic digital humans is extremely complex. Most data-driven generative models used to simplify the creation of their underlying geometric shape do not offer control over the generation of local shape attributes. In this paper, we overcome this limitation by introducing a novel loss function grounded in spectral geometry and applicable to different neural-network-based generative models of 3D head and body meshes. Encouraging the latent variables of mesh variational autoencoders (VAEs) or generative adversarial networks (GANs) to follow the local eigenprojections of identity attributes, we improve latent disentanglement and properly decouple the attribute creation. Experimental results show that our local eigenprojection disentangled (LED) models not only offer improved disentanglement with respect to the state-of-the-art, but also maintain good generation capabilities with training times comparable to the vanilla implementations of the models. Our code and pre-trained models are available at .

关键词： disentanglement generative adversarial networks geometric deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Human Laughter Generation using Hybrid Generative Models

引用

KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS 2021年第5期15卷 1590-1609页

作者： Mansouri, Nadia Lachiri, Zied El Manar Univ Natl Engn Sch Tunisia Tunis 1002 Tunisia

Laughter is one of the most important nonverbal sound that human generates. It is a means for expressing his emotions. The acoustic and contextual features of this specific sound are different from those of speech and many difficulties arise during their modeling process. During this work, we propose an audio laughter generation system based on unsupervised generative models: the autoencoder (AE) and its variants. This procedure is the association of three main sub-process, (1) the analysis which consist of extracting the log magnitude spectrogram from the laughter database, (2) the generative models training, (3) the synthesis stage which incorporate the involvement of an intermediate mechanism: the vocoder. To improve the synthesis quality, we suggest two hybrid models (LSTM-VAE, GRU-VAE and CNN-VAE) that combine the representation learning capacity of variational autoencoder (VAE) with the temporal modelling ability of a long short-term memory RNN (LSTM) and the CNN ability to learn invariant features. To figure out the performance of our proposed audio laughter generation process, objective evaluation (RMSE) and a perceptual audio quality test (listening test) were conducted. According to these evaluation metrics, we can show that the GRU-VAE outperforms the other VAE models.

关键词： Laughter Synthesis variational autoencoder autoencoder Objective and Subjective Evaluation

来源：评论

学校读者我要写书评

暂无评论

Multicategory choice modeling with sparse and high dimensional data: A Bayesian deep learning approach

引用

DECISION SUPPORT SYSTEMS 2022年 157卷 113766-113766页

作者： Xia, Feihong Chatterjee, Rabikar Univ Rhode Isl Coll Business 233 Ballentine Hall7 Lippitt Rd Kingston RI 02881 USA Univ Pittsburgh Joseph M Katz Grad Sch Business 276C Mervis Hall Pittsburgh PA 15260 USA

The availability of sparse and high dimensional consumer shopping data poses a challenge for researchers for accurate and efficient analysis. While deep learning models can handle such data, most of the results from these models are uninterpretable. This greatly limits their value in applications aimed at better understanding multicategory shopping behavior and assisting managerial decision-making. Thus, a new approach is needed to analyze high dimensional consumer shopping data in an efficient and interpretable manner, with the potential to greatly strengthen decision support systems for managers especially at large consumer packaged goods firms and giant retailers. We propose a Bayesian deep learning approach based on variational autoencoder (VAE) designed to efficiently capture often complex and multifaceted interrelationships across items in the shopping baskets, in the form of substitute and complementary cross effects (which are observable and controllable) and coincidences (which are not). The benefits of the proposed approach are empirically demonstrated by applying our model to a high dimensional supermarket shopping dataset covering very large numbers of products at the stock-keeping unit (SKU) level, households, and shopping trips. We discuss implications for managerial decision-making and identify promising research directions.

关键词： Consumer shopping basket Consumer multicategory choice modeling Sparsity High dimensional data variational autoencoder Bayesian deep learning

来源：评论

学校读者我要写书评

暂无评论

Class-Incremental Learning With Deep Generative Feature Replay for DNA Methylation-Based Cancer Classification

引用

IEEE ACCESS 2020年 8卷 210800-210815页

作者： Batbaatar, Erdenebileg Park, Kwang Ho Amarbayasgalan, Tsatsral Davagdorj, Khishigsuren Munkhdalai, Lkhagvadorj Pham, Van-Huy Ryu, Keun Ho Chungbuk Natl Univ Sch Elect & Comp Engn Database Bioinformat Lab Cheongju 28644 South Korea Ton Duc Thang Univ Fac Informat Technol Ho Chi Minh City 700000 Vietnam

Developing lifelong learning algorithms are mandatory for computational systems biology. Recently, many studies have shown how to extract biologically relevant information from high-dimensional data to understand the complexity of cancer by taking the benefit of deep learning (DL). Unfortunately, new cancer growing up into the hundred types that make systems difficult to classify them efficiently. In contrast, the current state-of-the-art continual learning (CL) methods are not designed for the dynamic characteristics of high-dimensional data. And data security and privacy are some of the main issues in the biomedical field. This article addresses three practical challenges for class-incremental learning (Class-IL) such as data privacy, high-dimensionality, and incremental learning problems. To solve this, we propose a novel continual learning approach, called Deep Generative Feature Replay (DGFR), for cancer classification tasks. DGFR consists of an incremental feature selection (IFS) and a scholar network (SN). IFS is used for selecting the most significant CpG sites from high-dimensional data. We investigate different dimensions to find an optimal number of selected CpG sites. SN employs a deep generative model for generating pseudo data without accessing past samples and a neural network classifier for predicting cancer types. We use a variational autoencoder (VAE), which has been successfully applied to this research field in previous works. All networks are sequentially trained on multiple tasks in the Class-IL setting. We evaluated the proposed method on the publicly available DNA methylation data. The experimental results show that the proposed DGFR achieves a significantly superior quality of cancer classification tasks with various state-of-the-art methods in terms of accuracy.

关键词： Cancer DNA Task analysis Data models Computational modeling Feature extraction Biological system modeling Computational biology deep learning class-incremental learning continual learning deep generative model variational autoencoder DNA methylation cancer classification

来源：评论

学校读者我要写书评

暂无评论

ELVISort: encoding latent variables for instant sorting, an artificial intelligence-based end-to-end solution

引用

JOURNAL OF NEURAL ENGINEERING 2021年第4期18卷

作者： Rokai, Janos Racz, Melinda Fiath, Richard Ulbert, Istvan Marton, Gergely Res Ctr Nat Sci Inst Cognit Neurosci & Psychol Magyar Tudosok Korutja 2 H-1117 Budapest Hungary Semmelweis Univ Sch PhD Studies Ulloi Ut 26 H-1085 Budapest Hungary Pazmany Peter Catholic Univ Fac Informat Technol & Bion Prater Utca 50-A H-1083 Budapest Hungary

Objective. The growing number of recording sites of silicon-based probes means that an increasing amount of neural cell activities can be recorded simultaneously, facilitating the investigation of underlying complex neural dynamics. In order to overcome the challenges generated by the increasing number of channels, highly automated signal processing tools are needed. Our goal was to build a spike sorting model that can perform as well as offline solutions while maintaining high efficiency, enabling high-performance online sorting. Approach. In this paper we present ELVISort, a deep learning method that combines the detection and clustering of different action potentials in an end-to-end fashion. Main results. The performance of ELVISort is comparable with other spike sorting methods that use manual or semi-manual techniques, while exceeding the methods which use an automatic approach: ELVISort has been tested on three independent datasets and yielded average F-1 scores of 0.96, 0.82 and 0.81, which comparable with the results of state-of-the-art algorithms on the same data. We show that despite the good performance, ELVISort is capable to process data in real-time: the time it needs to execute the necessary computations for a sample of given length is only 1/15.71 of its actual duration (i.e. the sampling time multiplied by the number of the sampling points). Significance. ELVISort, because of its end-to-end nature, can exploit the massively parallel processing capabilities of GPUs via deep learning frameworks by processing multiple batches in parallel, with the potential to be used on other cutting-edge AI-specific hardware such as TPUs, enabling the development of integrated, portable and real-time spike sorting systems with similar performance to offline sorters.

关键词： spike sorting deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multi source deep learning method for drug-protein interaction prediction using k-mers and chaos game representation

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2024年 246卷

作者： Mesrabadi, Hengame Abbasi Faez, Karim Pirgazi, Jamshid Islamic Azad Univ Fac Comp & Informat Technol Engn Qazvin Branch Qazvin Iran Amirkabir Univ Technol Tehran Polytech Dept Elect Engn Tehran Iran Univ Sci & Technol Mazandaran Dept Comp Engn Behshahr Iran

Identification of drug -protein interactions plays an important role in drug discovery. Development of new calculation methods, which have high accuracy solve the problems related to the previous methods, which were expensive and time-consuming. In this article, a new model for drug -protein interactions, and a new mapping approach to represent drug -protein sequences are proposed. The proposed model consists of four parts: drug and protein descriptor section, Drug CNN and Protein CNN sections, Encoder section and classification section. In this method, first the data is prepared. At this stage, the totals are equal to each other. Then in the next step using the k-mers method and Chaos Game, the sequence of drug and protein becomes an image. In the next step, the image is used to train CNN models. These images serve as the input of independent networks for the drug and are considered as a protein. These networks are used to extract feature from drug and protein. In the last layer of these networks, features extracted from drug and protein sequences combine with each other. After concatenating, the number of features will raise. To reduce the number of features and to extract more efficient features, a variational autoencoder is used. In the last step, this combined feature vector is used to train machine learning models. The proposed method has been tested and evaluated on 6 standard data sets. The results of the experiments show that the proposed method has an acceptable performance compared to other methods in this data set.

关键词： Drug target interaction Multi source K-mers Chaos game Deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Unsupervised seizure identification on EEG

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022年 215卷 106604-106604页

作者： Yildiz, Ilkay Garner, Rachael Lai, Matthew Duncan, Dominique Univ Southern Calif Keck Sch Med Stevens Neuroimaging & Informat Inst Lab Neuro Imaging 2025 Zonal Ave Los Angeles CA 90033 USA

Background and Objective: Epilepsy is one of the most common neurological disorders, whose development is typically detected via early seizures. Electroencephalogram (EEG) is prevalently employed for seizure identification due to its routine and low expense collection. The stochastic nature of EEG makes manual seizure inspections laborsome, motivating automated seizure identification. The relevant literature focuses mostly on supervised machine learning. Despite their success, supervised methods require expert labels indicating seizure segments, which are difficult to obtain on clinically-acquired EEG. Thus, we aim to devise an unsupervised method for seizure identification on EEG. Methods: We propose the first fully-unsupervised deep learning method for seizure identification on raw EEG, using a variational autoencoder (VAE). In doing so, we train the VAE on recordings without seizures. As training captures non-seizure activity, we identify seizures with respect to the reconstruction errors at inference time. Moreover, we extend the traditional VAE training loss to suppress EEG artifacts. Our method does not require ground-truth expert labels indicating seizure segments or manual feature extraction. Results: We implement our method using the PyTorch library and execute experiments on an NVIDIA V100 GPU. We evaluate our method on three benchmark EEG datasets: (i) intracranial recordings from the University of Pennsylvania and the Mayo Clinic, (ii) scalp recordings from the Temple University Hospital of Philadelphia, and (iii) scalp recordings from the Massachusetts Institute of Technology and the Boston Children's Hospital. To assess performance, we report accuracy, precision, recall, Area under the Receiver Operating Characteristics Curve (AUC), and p-value under the Welch t-test for distinguishing seizure vs. non-seizure EEG windows. Our approach can successfully distinguish seizures from nonseizure activity, with up to 0.83 AUC on intracranial recordings. Moreove

关键词： Epilepsy Seizure EEG variational autoencoder Unsupervised learning Sparsity

来源：评论

学校读者我要写书评

暂无评论

A Novel Deep Neural Network Method for HAR-Based Team Training Using Body-Worn Inertial Sensors

引用

SENSORS 2022年第21期22卷 8507页

作者： Fan, Yun-Chieh Tseng, Yu-Hsuan Wen, Chih-Yu Natl Chung Shan Inst Sci & Technol Aeronaut Syst Res Div Simulator Syst Sect Taichung 407 Taiwan Natl Chung Hsing Univ Dept Elect Engn Taichung 402 Taiwan Natl Chung Hsing Univ Dept Comp Sci & Engn Taichung 402 Taiwan Natl Chung Hsing Univ Innovat & Dev Ctr Sustainable Agr IDCSA Taichung 402 Taiwan

Human activity recognition (HAR) became a challenging issue in recent years. In this paper, we propose a novel approach to tackle indistinguishable activity recognition based on human wearable sensors. Generally speaking, vision-based solutions struggle with low illumination environments and partial occlusion problems. In contrast, wearable inertial sensors can tackle this problem and avoid revealing personal privacy. We address the issue by building a multistage deep neural network framework that interprets accelerometer, gyroscope, and magnetometer data that provide useful information of human activities. Initially, the stage of variational autoencoders (VAE) can extract the crucial information from raw data of inertial measurement units (IMUs). Furthermore, the stage of generative adversarial networks (GANs) can generate more realistic human activities. Finally, the transfer learning method is applied to enhance the performance of the target domain, which builds a robust and effective model to recognize human activities.

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

Multimodal Remote Sensing Data Classification Based on Gaussian Mixture variational Dynamic Fusion Network

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Wang, Haoyu Liu, Xiaomin Qiao, Zhenzhuang Wang, Guoqing Chen, Haotian China Univ Min & Technol Engn Res Ctr Intelligent Control Underground Space Minist Educ Xuzhou 221116 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China

With the development of sensor technology, the rational use of multimodal data has become a research hotspot in the field of remote sensing. The multimodal fusion method can effectively improve the accuracy of remote sensing data classification by using the complementary information of different modalities. However, the existing multimodal fusion methods face many challenges, including difficulties in suppressing spectral noise, fully mining contextual information, and learning the strong adaptive fusion pattern. To address the above challenges, a Gaussian mixture variational dynamic fusion network (GM-VDFN) is proposed. First, a multimodal multiscale spatial graph is constructed, and the graph convolution is used to learn the multiscale features. In this process, a spatial topology constraint based on GM (STC-GM) is proposed, which suppresses spectral noise by constraining the topological consistency of the two modalities. Second, a multiscale dynamic graph aggregation module (MDGAM) is constructed, which can capture the shareable class identification information from multiscale features and mine personalized fusion patterns suitable for each sample. Finally, the evidence lower bound for the multimodal joint distribution is derived, and a multimodal variational autoencoder (M-VAE) is designed. Optimizing the evidence lower bound to model multimodal joint distributions, thereby learning the strong adaptive fusion pattern between modalities. Experimental results on four fusion datasets (Houston 2013, Trento, MUUFL, and Houston 2018) show that GM-VDFN achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

关键词： Laser radar Noise Remote sensing Topology Data mining Data integration Interference Classification feature fusion hyperspectral image (HSI) light detection and ranging (LiDAR) variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Learning and Reusing Quadruped Robot Movement Skills from Biological Dogs for Higher-Level Tasks

引用

SENSORS 2024年第1期24卷 28页

作者： Wan, Qifeng Luo, Aocheng Meng, Yan Zhang, Chong Chi, Wanchao Zhang, Shenghao Liu, Yuzhen Zhu, Qiuguo Kong, Shihan Yu, Junzhi Peking Univ Coll Engn Dept Adv Mfg & Robot State Key Lab Turbulence & Complex Syst Beijing 100871 Peoples R China Tencent Robot X Shenzhen 518057 Peoples R China Zhejiang Univ Inst Cyber Syst & Control Coll Control Sci & Engn Hangzhou 310027 Peoples R China Chinese Acad Sci Inst Software Sci & Technol Integrated Informat Syst Lab Beijing 100190 Peoples R China

In the field of quadruped robots, the most classic motion control algorithm is based on model prediction control (MPC). However, this method poses challenges as it necessitates the precise construction of the robot's dynamics model, making it difficult to achieve agile movements similar to those of a biological dog. Due to these limitations, researchers are increasingly turning to model-free learning methods, which significantly reduce the difficulty of modeling and engineering debugging and simultaneously reduce real-time optimization computational burden. Inspired by the growth process of humans and animals, from learning to walk to fluent movements, this article proposes a hierarchical reinforcement learning framework for the motion controller to learn some higher-level tasks. First, some basic motion skills can be learned from motion data captured from a biological dog. Then, with these learned basic motion skills as a foundation, the quadruped robot can focus on learning higher-level tasks without starting from low-level kinematics, which saves redundant training time. By utilizing domain randomization techniques during the training process, the trained policy function can be directly transferred to a physical robot without modification, and the resulting controller can perform more biomimetic movements. By implementing the method proposed in this article, the agility and adaptability of the quadruped robot can be maximally utilized to achieve efficient operations in complex terrains.

关键词： quadrupedal robots reinforcement learning motion imitation variational autoencoder

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：