检索结果-内蒙古大学图书馆

IEEE Workshop on Machine Learning for Signal Processing

作者： Kincaid MacDonald Dhananjay Bhaskar Guy Thampakkul Nhi Nguyen Joia Zhang Michael Perlmutter Ian Adelstein Smita Krishnaswamy Department of Mathematics Yale University Department of Genetics Yale School of Medicine Department of Computer Science Yale University Department of Mathematics Pomona College Applied Mathematics Program Yale University Department of Statistics University of Washington Department of Mathematics Boise State University Computational Biology and Bioinformatics Program Yale University

We consider the problem of embedding point cloud data sampled from an underlying manifold with an associated flow or velocity. Such data arises in many contexts where static snapshots of dynamic entities are measured, including in high-throughput biology such as single-cell transcriptomics. Existing embedding techniques either do not utilize velocity information or embed the coordinates and velocities independently, i.e., they either impose velocities on top of an existing point embedding or embed points within a prescribed vector field. Here we present FlowArtist, a neural network that embeds points while jointly learning a vector field around the points. The combination allows FlowArtist to better separate and visualize velocity-informed structures. Our results, on toy datasets and single-cell RNA velocity data, illustrate the value of utilizing coordinate and velocity information in tandem for embedding and visualizing high-dimensional data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BRAINLM: A FOUNDATION MODEL FOR BRAIN ACTIVITY RECORDINGS 12

BRAINLM: A FOUNDATION MODEL FOR BRAIN ACTIVITY RECORDINGS

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Caro, Josue Ortega de Fonseca, Antonio H. Rizvi, Syed A. Rosati, Matteo Averill, Christopher Cross, James L. Mittal, Prateek Zappala, Emanuele Dhodapkar, Rahul M. Abdallah, Chadi G. van Dijk, David Wu Tsai Institute United States Interdepartmental Neuroscience Program Yale University United States Baylor College of Medicine United States Department of Computer Science United States Yale School of Medicine United States University of Southern California United States Interdepartmental Program in Computational Biology & Bioinformatics United States Internal Medicine United States Cardiovascular Research Center Yale University United States Department of Mathematics and Statistics Idaho State University United States

We introduce the Brain Language Model (BrainLM), a foundation model for brain activity dynamics trained on 6,700 hours of fMRI recordings. Utilizing self-supervised masked-prediction training, BrainLM demonstrates proficiency in both fine-tuning and zero-shot inference tasks. Fine-tuning allows for the accurate prediction of clinical variables like age, anxiety, and PTSD as well as forecasting of future brain states. Critically, the model generalizes well to entirely new external cohorts not seen during training. In zero-shot inference mode, BrainLM can identify intrinsic functional networks directly from raw fMRI data without any network-based supervision during training. The model also generates interpretable latent representations that reveal relationships between brain activity patterns and cognitive states. Overall, BrainLM offers a versatile and interpretable framework for elucidating the complex spatiotemporal dynamics of human brain activity. It serves as a powerful "lens" through which massive repositories of fMRI data can be analyzed in new ways, enabling more effective interpretation and utilization at scale. The work demonstrates the potential of foundation models to advance computational neuroscience research. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Directed Scattering for Knowledge Graph-Based Cellular Signaling Analysis

Directed Scattering for Knowledge Graph-Based Cellular Signa...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Aarthi Venkat Joyce Chew Ferran Cardoso Rodriguez Christopher J. Tape Michael Perlmutter Smita Krishnaswamy Program for Computational Biology and Bioinformatics Yale University Department of Mathematics University of California Los Angeles Department of Oncology University College London Cancer Institute Department of Mathematics Boise State University Departments of Genetics and Computer Science Yale University

Directed graphs are a natural model for many phenomena, in particular scientific knowledge graphs such as molecular interaction or chemical reaction networks that define cellular signaling relationships. In these situations, source nodes typically have distinct biophysical properties from sinks. Due to their ordered and unidirectional relationships, many such networks also have hierarchical and multiscale structure. However, the majority of methods performing node- and edge-level tasks in machine learning do not take these properties into account, and thus have not been leveraged effectively for scientific tasks such as cellular signaling network inference. We propose a new framework called Directed Scattering Autoencoder (DSAE) which uses a directed version of a geometric scattering transform, combined with the non-linear dimensionality reduction properties of an autoencoder and the geometric properties of the hyperbolic space to learn latent hierarchies. We show this method outperforms numerous others on tasks such as embedding directed graphs and learning cellular signaling networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory-based Models for Sleep Quality Prediction from Wearable Device Time Series Data 8

Long Short-Term Memory-based Models for Sleep Quality Predic...

引用

8th International Conference on Computer Science and Computational Intelligence, ICCSCI 2023

作者： Hidayat, Alam Ahmad Budiarto, Arif Pardamean, Bens Mathematics Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

Several studies suggest that sleep quality is associated with physical activities. Moreover, deep sleep time can be used to determine the sleep quality of an individual. In this work, we aim to find the association between physical activities and deep sleep time by modeling the time series data such as heart rate and a number of steps captured from a commercial wearable device. Our previous study demonstrates that deep learning-based time series modeling is well suited for our problem since the temporal patterns in the two physical parameters need to be captured to obtain more accurate results. We first preprocess our series data to have a time-step size of 10 minutes. To improve our previous effort in this modeling, we compare four different variants of Long Short-Term Memory (LSTM)-based models, ranging from single input to dual input models. Our result shows that the simple stacked LSTM model performs better for our data because the remaining models suffer from overfitting due to a larger number of the trained parameters. © 2023 The Authors. Published by Elsevier B.V.

关键词： deep learning forecasting sleep quality time series wearable devices

来源：评论

学校读者我要写书评

暂无评论

SRECG: ECG Signal Super-Resolution Framework for Portable/Wearable Devices in Cardiac Arrhythmias Classification

引用

IEEE Transactions on Consumer Electronics 2023年第3期69卷 250-260页

作者： Chen, Tsai-Min Tsai, Yuan-Hong Tseng, Huan-Hsin Liu, Kai-Chun Chen, Jhih-Yu Huang, Chih-Han Li, Guo-Yuan Shen, Chun-Yen Tsao, Yu National Taiwan University and Academia Sinica Graduate Program of Data Science Taipei106319 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei115 Taiwan Taiwan Artificial Intelligence Academy Foundation Program of Taiwan AI Academy New Taipei22065 Taiwan Artificial Intelligence Foundation Technology Development Center New Taipei24158 Taiwan Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei10617 Taiwan Institute of Biomedical Sciences Academia Sinica Taipei115 Taiwan National Taiwan University Department of Mathematics Taipei10617 Taiwan

A combination of cloud-based deep learning (DL) algorithms with portable/wearable (P/W) devices has been developed as a smart heath care system to support automatic cardiac arrhythmias (CAs) classification using electrocardiography (ECG). However, long-term and continuous ECG monitoring is challenging because of limitations of batteries and transmission bandwidth of P/W devices while incorporated with consumer electronics (CE). A feasible approach to address this challenge is to decrease sampling rates. However, low sampling rates lead to low-resolution signals that hinder the CAs classification performance. In this study, we propose a DL-based ECG signal super-resolution framework (called SRECG) to enhance low-resolution ECG signals by jointly considering the accuracies when applied to the DL-based high-resolution multiclass classifier (HMC) of CAs. In our experiments, we downsampled the ECG signals from the CPSC2018 dataset and evaluated their HMC accuracies with and without the SRECG. Experimental results show that SRECG can well improve the HMC accuracies as compared to traditional interpolation methods. Moreover, approximately half of the CAs classification accuracies of HMC were maintained within the enhanced ECG signals by SRECG. The promising results confirm that SRECG can be suitably used to enhance low-resolution ECG signals from P/W devices with CE to improve their cloud-based HMC performances. © 1975-2011 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

ProtSCAPE: Mapping the landscape of protein conformations in molecular dynamics

arXiv

引用

arXiv 2024年

作者： Viswanath, Siddharth Bhaskar, Dhananjay Johnson, David R. Rocha, João Felipe Castro, Egbert Grady, Jackson D. Grigas, Alex T. Perlmutter, Michael A. O’Hern, Corey S. Krishnaswamy, Smita Department of Computer Science Yale University United States Department of Genetics Yale University United States Program in Computing Boise State University United States Computational Biology and Bioinformatics Program Yale University United States Department of Mathematics Boise State University United States

Understanding the dynamic nature of protein structures is essential for comprehending their biological functions. While significant progress has been made in predicting static folded structures, modeling protein motions on microsecond to millisecond scales remains challenging. To address these challenges, we introduce a novel deep learning architecture, Protein Transformer with Scattering, Attention, and Positional Embedding (ProtSCAPE), which leverages the geometric scattering transform alongside transformer-based attention mechanisms to capture protein dynamics from molecular dynamics (MD) simulations. ProtSCAPE utilizes the multi-scale nature of the geometric scattering transform to extract features from protein structures conceptualized as graphs and integrates these features with dual attention structures that focus on residues and amino acid signals, generating latent representations of protein trajectories. Furthermore, ProtSCAPE incorporates a regression head to enforce temporally coherent latent representations. Importantly, we demonstrate that ProtSCAPE generalizes effectively from short to long trajectories and from wild-type to mutant proteins, surpassing traditional approaches by delivering more precise and interpretable upsampling of dynamics. © 2024, CC BY.

关键词： Molecular docking

来源：评论

学校读者我要写书评

暂无评论

Count-Data Mixed Models of Topical Tweets: A Case of Indonesia Flood Events

引用

Procedia Computer Science 2023年 227卷 805-812页

作者： Alam Ahmad Hidayat Bens Pardamean Mathematics Department School of Computer Science Bina Nusantara University Jakarta Indonesia 11480 Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia 11480 Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta Indonesia 11480

Examining topic-level variability in modeling Twitter data can potentially yield more comprehensive insights into public perception during critical periods, thereby enhancing natural disaster mitigation and surveillance efforts. In this study, we utilized generalized linear mixed models (GLMMs) to illustrate the variability in tweet counts related to specific topics in Indonesia during the flood events that occurred in February 2021. The glmmTMB library in R was employed for this purpose. The data were assumed to follow two distinct exponential distributions: Poisson and Negative Binomial. To incorporate random effects, random intercepts and random slopes were introduced, allowing them to vary randomly across topics in the initial two models. Additionally, the final model addressed issues related to dispersion and zero-inflation. By evaluating the Akaike Information Criteria scores, we determined that a model based on the Negative Binomial distribution with random zero-inflation intercepts best fit the data. The chosen model formulation and the estimated parameters have the potential to forecast topic-specific trends in Indonesian flood-related Twitter data.

关键词： count data disaster surveillance floods mixed models Twitter

来源：评论

学校读者我要写书评

暂无评论

Indonesian Agricultural-crops Classification Using Transfer Learning Model

引用

Procedia Computer Science 2023年 227卷 128-136页

作者： Mahmud Isnan Alam Ahmad Hidayat Bens Pardamean Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Department of Mathematics School of Computer Science Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Classification of Indonesian crops is a critical task in developing farming and getting more understanding of agriculture. However, there is no clear task in classifying types of crops in Indonesia. Transfer learning has been used successfully in a variety of image classification applications. Thus, in this paper, we collected images of Indonesian crops from the internet randomly and proposed a classification by using transfer learning of deep learning with four pre-trained models: EffficientNet- B0, ResNet18, VGG19, and AlexNet. In the experiment, augmentation techniques such as random horizontal flip, random vertical flip, and random affine were utilized to prevent the network from overfitting. The result found that EfficientNet-B0 outperformed other models with an accuracy of 82.55. Then, the model struggled to distinguish between crops in the same family. According to the results, although transfer learning can work well to classify images of Indonesian agricultural crops, some improvements are still required to address existing issues.

关键词： Agriculture Classification Crop Deep Learning Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion curvature for estimating local curvature in high dimensional data 22

Diffusion curvature for estimating local curvature in high d...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Dhananjay Bhaskar Kincaid MacDonald Oluwadamilola Fasina Dawson Thomas Bastian Rieck Ian Adelstein Smita Krishnaswamy Department of Genetics Yale University Department of Mathematics Yale University Applied Mathematics Program Yale University Department of Mathematics Department of Physics Yale University Institute of AI for Health Helmholtz Pioneer Campus Helmholtz Munich Department of Computer Science Department of Genetics Applied Mathematics Program Program for Computational Biology and Bioinformatics Yale University

ISBN: (纸本)9781713871088

We introduce a new intrinsic measure of local curvature on point-cloud data called diffusion curvature. Our measure uses the framework of diffusion maps, including the data diffusion operator, to structure point cloud data and define local curvature based on the laziness of a random walk starting at a point or region of the data. We show that this laziness directly relates to volume comparison results from Riemannian geometry. We then extend this scalar curvature notion to an entire quadratic form using neural network estimations based on the diffusion map of point-cloud data. We show applications of both estimations on toy data, single-cell data and on estimating local Hessian matrices of neural network loss landscapes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Entropic Optimal Transport Eigenmaps for Nonlinear Alignment and Joint Embedding of High-Dimensional Datasets

arXiv

引用

arXiv 2024年

作者： Landa, Boris Kluger, Yuval Ma, Rong Department of Electrical Engineering Yale University United States Program in Applied Mathematics Yale University United States Department of Biostatistics Harvard University United States Interdepartmental Program in Computational Biology and Bioinformatics Yale University United States Department of Pathology Yale University School of Medicine United States

Embedding high-dimensional data into a low-dimensional space is an indispensable component of data analysis. In numerous applications, it is necessary to align and jointly embed multiple datasets from different studies or experimental conditions. Such datasets may share underlying structures of interest but exhibit individual distortions, resulting in misaligned embeddings using traditional techniques. In this work, we propose Entropic Optimal Transport (EOT) eigenmaps, a principled approach for aligning and jointly embedding a pair of datasets with theoretical guarantees. Our approach leverages the leading singular vectors of the EOT plan matrix between two datasets to extract their shared underlying structure and align the datasets accordingly in a common embedding space. We interpret our approach as an inter-data variant of the classical Laplacian eigenmaps and diffusion maps embeddings, showing that it enjoys many favorable analogous properties. We then analyze a data-generative model where two observed high-dimensional datasets share latent variables on a common low-dimensional manifold, but each dataset is subject to data-specific translation, scaling, nuisance structures, and noise. We show that in a high-dimensional asymptotic regime, the EOT plan recovers the shared manifold structure by approximating a kernel function evaluated at the locations of the latent variables. Subsequently, we provide a geometric interpretation of our embedding by relating it to the eigenfunctions of population-level operators encoding the density and geometry of the shared manifold. Finally, we showcase the performance of our approach for data integration and embedding through simulations and analyses of real-world biological data, demonstrating its advantages over alternative methods in challenging scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Embeddings

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：