检索结果-内蒙古大学图书馆

CELL GENOMICS 2023年第9期3卷 100388-100388页

作者： Zhang, Yichen Khalilitousi, Mohammadali (Sam) Park, Yongjin P. Univ British Columbia Dept Stat Vancouver BC Canada Univ British Columbia Dept Biomed Engn Vancouver BC Canada Univ British Columbia Dept Pathol & Lab Med Vancouver BC Canada Part Prov Hlth Care Author BC Canc Res Dept Mol Oncol Vancouver BC Canada

Building a comprehensive topic model has become an important research tool in single-cell genomics. With a topic model, we can decompose and ascertain distinctive cell topics shared across multiple cells, and the gene programs implicated by each topic can later serve as a predictive model in translational studies. Here, we present a Bayesian topic model that can uncover short-term RNA velocity patterns from a plethora of spliced and unspliced single-cell RNA-sequencing (RNA-seq) counts. We showed that modeling both types of RNA counts can improve robustness in statistical estimation and can reveal new aspects of dynamic changes that can be missed in static analysis. We showcase that our modeling framework can be used to identify statistically significant dynamic gene programs in pancreatic cancer data. Our results discovered that seven dynamic gene programs (topics) are highly correlated with cancer prognosis and generally enrich immune cell types and pathways.

关键词： single-cell RNA-seq topic model RNA velocity machine learning variational autoencoder pancreatic cancer pancreatic ductal adenocarcinoma

来源：评论

学校读者我要写书评

暂无评论

Deep learning–powered generation of artificial endoscopic images of GI tract ulcers

iGIE

引用

iGIE 2023年第4期2卷 452-463.e2页

作者： Bajhaiya, Deepak Unni, Sujatha Narayanan Koushik, A.K. Biophotonics Laboratory Department of Applied Mechanics and Biomedical Engineering IIT Madras Chennai India Department of Gastroenterology Sri Ramachandra Medical Centre and Research Institute Chennai India

Background and Aims: Annually, 4 million people are affected by ulcers in the GI tract, and poorly managed ulcers can lead to adverse events that may increase the risk of developing fatal diseases such as gastric cancer, GI bleeding, ulcerative colitis, and other conditions. Deep learning–based computer-aided diagnostics is essential for automating the diagnosis of such illnesses. It aids clinicians in diagnosis by reducing the time of diagnosis and lowering diagnostic errors. Data shortage is anticipated in endoscopy settings, and small data sets prevent the performance of the deep learning model from being generalized. The current study addresses data scarcity by expanding the available data through the artificial generation of new data. Methods: This study exploits the combination of the generative adversarial network (GAN) and variational autoencoders (VAE) and develops a VAE-GAN architecture to generate artificial endoscopic images. VAE-GAN offers resilience toward mode collapse, vanishing gradient, instability, and non-convergence. The generated images were tested against the trained DenseNet121 model with a higher classification threshold for ulcer identification and estimated precision and recall scores that capture the quality and diversity of the generated images, respectively. Furthermore, the generated images were also presented and compared with the clinical interpretation by an expert. The effectiveness of data augmentation by VAE-GAN was also evaluated with the developed 5-layer convolutional neural network (CNN) model for ulcer classification. Results: The proposed VAE-GAN architecture synthesized artificial realistic endoscopic images. With the trained DenseNet121 model under a higher threshold for ulcer detection, the generated images of ulcers achieved 99% precision and 92% recall. The expert achieved 57.1% classification accuracy for artificial versus real ulcer examination. The 5-layer CNN model achieved 94% classification accuracy on the test d

关键词： AI artificial intelligence CNN convolutional neural network DCGAN deep convolutional generative adversarial network GAN generative adversarial network IS inception score PCA principal component analysis VAE variational autoencoder VAE-GAN variational autoencoder–generative adversarial network WCE wireless-capsule endoscopy

来源：评论

学校读者我要写书评

暂无评论

A Generative Method for a Laryngeal Biosignal

引用

Journal of Voice 2024年

作者： Darvish, Mahdi Kist, Andreas M. Department Artificial Intelligence in Biomedical Engineering Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

The Glottal Area Waveform (GAW) is an important component in quantitative clinical voice assessment, providing valuable insights into vocal fold function. In this study, we introduce a novel method employing variational autoencoders (VAEs) to generate synthetic GAWs. Our approach enables the creation of synthetic GAWs that closely replicate real-world data, offering a versatile tool for researchers and clinicians. We elucidate the process of manipulating the VAE latent space using the Glottal Opening Vector (GlOVe). The GlOVe allows precise control over the synthetic closure and opening of the vocal folds. By utilizing the GlOVe, we generate synthetic laryngeal biosignals. These biosignals accurately reflect vocal fold behavior, allowing for the emulation of realistic glottal opening changes. This manipulation extends to the introduction of arbitrary oscillations in the vocal folds, closely resembling real vocal fold oscillations. The range of factor coefficient values enables the generation of diverse biosignals with varying frequencies and amplitudes. Our results demonstrate that this approach yields highly accurate laryngeal biosignals, with the Normalized Mean Absolute Error values for various frequencies ranging from 9.6 ⋅ 10⁻³ to 1.20 ⋅ 10⁻² for different experimented frequencies, alongside a remarkable training effectiveness, reflected in reductions of up to approximately 89.52% in key loss components. This proposed method may have implications for downstream speech synthesis and phonetics research, offering the potential for advanced and natural-sounding speech technologies. © 2024 The Authors

关键词： Biosignal Glottal area waveform Modeling Synthetic data variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

CVAD - An unsupervised image anomaly detector

引用

SOFTWARE IMPACTS 2022年 11卷

作者： Guo, Xiaoyuan Gichoya, Judy Wawira Purkayastha, Saptarshi Banerjee, Imon Emory Univ Dept Comp Sci Atlanta GA 30322 USA Emory Univ Dept Radiol & Imaging Sci Atlanta GA 30322 USA Indiana Univ Purdue Univ Sch Informat & Comp Indianapolis IN 46202 USA Arizona State Univ Sch Comp Informat & Decis Syst Engn Tempe AZ 85287 USA

Detecting out-of-distribution samples for image applications plays an important role in safeguarding the reliability of machine learning model deployment. In this article, we developed a software tool to support our OOD detector CVAD -a self-supervised Cascade variational autoencoder-based Anomaly Detector , which can be easily applied to various image applications without any assumptions. The corresponding open-source software is published for better public research and tool usage.

关键词： Anomaly detection OOD detection variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence

引用

ENVIRONMENTAL DATA SCIENCE 2023年 2卷 e1-e1页

作者： Chattopadhyay, Ashesh Pathak, Jaideep Nabizadeh, Ebrahim Bhimji, Wahid Hassanzadeh, Pedram Rice Univ Dept Mech Engn Houston TX 77005 USA NVIDIA Santa Clara CA USA Lawrence Berkeley Natl Lab Berkeley CA USA

Recent years have seen a surge in interest in building deep learning-based fully data-driven models for weather prediction. Such deep learning models, if trained on observations can mitigate certain biases in current state-of-the-art weather models, some of which stem from inaccurate representation of subgrid-scale processes. However, these data-driven models, being over-parameterized, require a lot of training data which may not be available from reanalysis (observational data) products. Moreover, an accurate, noise-free, initial condition to start forecasting with a data-driven weather model is not available in realistic scenarios. Finally, deterministic data-driven forecasting models suffer from issues with long-term stability and unphysical climate drift, which makes these data-driven models unsuitable for computing climate statistics. Given these challenges, previous studies have tried to pre-train deep learning-based weather forecasting models on a large amount of imperfect long-term climate model simulations and then re-train them on available observational data. In this article, we propose a convolutional variational autoencoder (VAE)-based stochastic data-driven model that is pre-trained on an imperfect climate model simulation from a two-layer quasi-geostrophic flow and re-trained, using transfer learning, on a small number of noisy observations from a perfect simulation. This re-trained model then performs stochastic forecasting with a noisy initial condition sampled from the perfect simulation. We show that our ensemble-based stochastic data-driven model outperforms a baseline deterministic encoder-decoder-based convolutional model in terms of short-term skills, while remaining stable for long-term climate simulations yielding accurate climatology. Impact Statement A stochastic VAE-based data-driven model pre-trained on imperfect climate simulations and re-trained with transfer learning, on a limited number of observations, leads to accurate short-term w

关键词： Data-driven climate model long-term stability transfer learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Distributed unsupervised meta-learning algorithm over multi-agent systems

引用

Digital Communications and Networks 2024年

作者： Zhenzhen Wang Bing He Zixin Jiang Xianyang Zhang Haidi Dong Di Ye Department of Electronic Engineering PLA Rocket Force University of Engineering Xi'an 710025 China College of Weaponry Engineering PLA Naval University of Engineering Wuhan 430033 China

Multi-Agent Systems (MAS), which consist of multiple interacting agents, are crucial in Cyber-Physical Systems (CPS), because they improve system adaptability, efficiency, and robustness through parallel processing and collaboration. However, most existing unsupervised meta-learning methods are centralized and not suitable for multi-agent systems where data are distributed stored and inaccessible to all agents. Meta-GMVAE, based on variational autoencoder (VAE) and set-level variational inference, represents a sophisticated unsupervised meta-learning model that improves generative performance by efficiently learning data representations across various tasks, increasing adaptability and reducing sample requirements. Inspired by these advancements, we propose a novel Distributed Unsupervised Meta-Learning (DUML) framework based on Meta-GMVAE and a fusion strategy. Furthermore, we present a DUML algorithm based on Gaussian Mixture Model (DUMLGMM), where the parameters of the Gaussian-mixture is solved by an Expectation-Maximization algorithm. Simulations on Omniglot and MiniImageNet datasets show that DUMLGMM can achieve the performance of the corresponding centralized algorithm and outperform non-cooperative algorithm.

关键词： Unsupervised meta-learning Multi-agent systems variational autoencoder Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Conf-GEM: A geometric information-assisted direct conformation generation model

Artificial Intelligence Chemistry

引用

Artificial Intelligence Chemistry 2024年第2期2卷

作者： Zhijiang Yang Youjun Xu Li Pan Tengxin Huang Yunfan Wang Junjie Ding Liangliang Wang Junhua Xiao State Key Laboratory of NBC Protection for Civilian China Infinite Intelligence Pharma Beijing 100020 China

Molecular conformations generation (MCG) aims to efficiently obtain reasonable and stable three-dimensional (3D) atomic coordinates of the atoms in the molecule from scratch, providing a structural foundation for molecular representation learning models and advanced downstream molecular design tasks such as molecular property prediction, molecular generation, and molecular docking. Existing MCG methods mostly rely on indirect distance-based strategies, which which can result in geometrically unrealistic conformations, or direct coordinate-based methods, which have larger search spaces and are prone to overfitting. Therefore, this study introduces Conf-GEM, a novel geometric information-assisted direct conformation generation model based on E-GeoGNN, a geometrically augmented 3D graph neural network with multiple scales. Pre-training and divide-and-conquer strategies, are integrated into the proposed model. Conf-GEM outperforms RDKit and nine deep-learning-based MCG models on the GEOM-QM9 and GEOM-Drugs datasets, achieving conformational coverage of 96.69% and 96.07%, respectively, without force field optimization. It also excels on the X-ray diffraction crystal structure dataset with up to 97.04% conformational coverage. In conclusion, Conf-GEM provides a novel solution for stabilizing 3D conformations generation. We provide an online prediction service ( https://*** ) with a user-friendly interface for researchers.

关键词： Molecular conformations generation variational autoencoder Divide-and-conquer method Pre-training Geometric enhanced graph neural network

来源：评论

学校读者我要写书评

暂无评论

Enhanced medical image generation through advanced latent space diffusion

Materials and Emerging Technologies for Sustainability

引用

Materials and Emerging Technologies for Sustainability 1000年

作者： Khoi M. Nguyen Hung C. Nguyen H. Huy Nguyen The-Bang Nguyen Phuoc-Thinh Nguyen Vu Tran Phu Pham Quang-Thinh Bui University of Information Technology Vietnam National University Ho Chi Minh City Ho Chi Minh City Vietnam Faculty of Information Technology HUTECH University Ho Chi Minh City Vietnam Ho Chi Minh City University of Technology (HCMUT) Vietnam National University Ho Chi Minh City Ho Chi Minh City Vietnam School of Business Information Technology University of Economics Ho Chi Minh City Ho Chi Minh City Vietnam Office of Scientific Research Technology Management and International Cooperation Tien Giang University Tien Giang Vietnam

Collecting high-quality medical image data for machine learning applications remains a significant challenge due to data scarcity, privacy concerns, and high annotation costs. To address these issues, vision generative models, particularly Latent Diffusion Models (LDMs), have emerged as state-of-the-art solutions that reduce computational demands while maintaining superior performance in data generation tasks. In this study, we propose an enhanced LDM-based approach that integrates separable self-attention mechanisms within the diffusion process, positioned after residual blocks, to improve the capture of detailed features and maintain spatial consistency. This modification reduces memory usage by 82.94% and decreases the Fréchet Inception Distance (FID) by 25.01% compared to traditional self-attention models, all while preserving image quality. Our method addresses critical challenges such as data scarcity and computational efficiency in medical imaging by combining variational autoencoders (VAEs) for latent space mapping with U-Net for noise prediction. Evaluations on five datasets — PneumoniaMNIST, BloodMNIST, ChestMNIST, Dental4k, and HandMNIST — demonstrate significant improvements in computational efficiency, memory usage, and the quality of generated images, showcasing the potential of our approach for scalable and effective medical image synthesis.

关键词： Diffusion models latent space latent diffusion models variational autoencoder medical image generation

来源：评论

学校读者我要写书评

暂无评论

Direct feature extraction from two-dimensional X-ray diffraction images of semiconductor thin films for fabrication analysis

引用

SCIENCE AND TECHNOLOGY OF ADVANCED MATERIALS-METHODS 2022年第1期2卷 23-37页

作者： Yamashita, Akihiro Nagata, Takahiro Yagyu, Shinjiro Asahi, Toru Chikyow, Toyohiro Waseda Univ Dept Adv Sci & Engn Tokyo Japan Natl Inst Mat Sci Res & Serv Div Mat Data & Integrated Syst Tsukuba Japan Natl Inst Mat Sci Res Ctr Funct Mat 1-1 Namiki Tsukuba 3050044 Japan

We built a workflow for the fabrication analysis of thin films by applying machine-learning (ML) techniques directly to the measurement data. This will lower the problem in cost of synthesizing and analyzing samples to improve the fabrication conditions. The workflow combines two ML techniques: non-negative matrix factorization (NMF) and variational autoencoder (VAE). The measurement data were two-dimensional X-ray diffraction of indium-gallium oxide system thin films. The thin films were fabricated by physical vapor techniques under multiple conditions. First, the workflow was applied to the data of the thin films fabricated through pulsed laser deposition as a proof of concept. We found that our workflow extracted features that represented crystallinity differences in addition to substrate differences. Second, VAE was analyzed to determine whether it could generate new data from its latent space. The latent space of the VAE, which learned the extracted features, represented the relationship between the fabrication conditions such as laser intensities and crystallinity. Third, the inference ability of the new data fabricated through sputtering was evaluated. The capability of the workflow we confirmed will support researchers in improving fabrication conditions by visually comparing various fabricated samples.

关键词： Two-dimensional x-ray diffraction thin films machine learning feature extraction dimensionality reduction non-negative matrix factorization variational autoencoder Materials data analysis and utilization

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Models for Improving Movie Rating Predictions: A Benchmarking Study

引用

BenchCouncil Transactions on Benchmarks, Standards and Evaluations 2024年第4期4卷

作者： Valera, Manisha Mehta, Dr. Rahul Research Scholar Gujarat Technological University Ahmedabad India Department of Electronics & Communication Engineering GEC Gujarat Rajkot India

Predicting movie ratings very precisely has become a vital aspect of personalized recommendation systems, which requires robust and high-performing models. for evaluating the effectiveness in predicting movie ratings, this study conducts a comprehensive performance analysis of various deep learning architectures, which includes BiLSTM, CNN + LSTM, CNN + GRU, CNN + Attention, CNN, VAE, Simple RNN, GRU + Attention, Transformer Encoder, FNN and ResNet. Here each model's performance is evaluated on movie reviews’ dataset, enhanced with sentiment scores and user ratings, by using a range of evaluation metrics: Mean Absolute Error (MAE), R² score, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Explained Variance. Here the results highlight distinct strengths and weaknesses among the models, in which VAE model consistently delivering superior accuracy, whereas attention-based models prove prominent improvements in interpretability and generalization. This analysis offers important insights into choosing models for movie recommendation systems, which also highlights the balance between prediction accuracy and computational efficiency. The discoveries from this study serve as a benchmark for future developments in movie rating prediction, supporting the researchers and practitioners in augmenting recommendation system performance. © 2025

关键词： Convolutional neural networks (CNN) Distilbert gated recurrent unit (GRU) Long short-term memory (LSTM) Recurrent neural networks (RNN) 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：