检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Chen, Yenho Mudrik, Noga Johnsen, Kyle A. Alagapan, Sankaraleengam Charles, Adam S. Rozell, Christopher J. Machine Learning Center Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Coulter Dept. of Biomedical Engineering Emory University Georgia Institute of Technology United States Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University United States

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model’s ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. © 2024, CC BY-SA.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Improving Hospital Preparedness for Future Pandemics with Machine Learning and Queue Management Solutions

Improving Hospital Preparedness for Future Pandemics with Ma...

引用

International Conference on Intelligent Computing in Data sciences (ICDS)

作者： Khalil Bouramtane Said Kharraja Jamal Riffi Omar EL Beqqali Saïd Boujraf University of Jean Monnet Saint-Etienne IUT of Roanne LASPI RU ROANNE FRANCE Faculty of science Dhar El Mahraz Laboratory of Computer Science Signals Automation and Cognitivism (LISAC) University Sidi Mohamed Ben Abdellah Fez Morocco Dept. Biophysics & Clinical MRI Methods Faculty of Medicine Clinical Neuroscience Laboratory University of Sidi Mohamed Ben Abdellah Fez Morocco

ISBN: (数字)9798350351200

ISBN: (纸本)9798350351217

The COVID-19 pandemic has underscored the critical need for resilient and efficient hospital workflows capable of managing sudden increases in patient volume. This study presents a comprehensive approach that integrates advanced machine learning algorithms with queue management techniques to enhance hospital preparedness and response during pandemics. By Employing predictive analytics and classification systems, our methodology improves patient triage, optimizes resource allocation, and reduces wait times, thereby enhancing overall patient care. The study includes a detailed analysis of machine learning models used for patient prioritization and an exploration of queue management strategies to streamline patient flow. Our findings indicate substantial improvements in hospital efficiency and the ability to handle peak demands during health crises. This research provides actionable insights and a robust framework for healthcare administrators aiming to fortify their facilities against future pandemic scenarios, ultimately contributing to better healthcare outcomes.

关键词： Machine learning algorithms Pandemics Hospitals Heuristic algorithms Machine learning Data models Resource management Servers Predictive analytics Queueing analysis

来源：评论

学校读者我要写书评

暂无评论

Improved Prediction Of Ligand-Protein Binding Affinities By Meta-Modeling

arXiv

引用

arXiv 2023年

作者： Lee, Ho-Joon Emani, Prashant S. Gerstein, Mark B. Dept. of Genetics and Yale University New HavenCT06510 United States Yale Center for Genome Analysis Yale University New HavenCT06510 United States Dept. of Molecular Biophysics & Biochemistry Yale University New HavenCT06520 United States Program in Computational Biology & Bioinformatics Yale University New HavenCT06520 United States Dept. of Computer Science Yale University New HavenCT06520 United States Dept. of Statistics & Data Science Yale University New HavenCT06520 United States Dept. of Biomedical Informatics & Data Science Yale University New HavenCT06520 United States

The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity between ligands and proteins. Many computational models for binding affinity prediction have been developed, but with varying results across targets. Given that ensembling or meta-modeling approaches have shown great promise in reducing model-specific biases, we develop a framework to integrate published force-field-based empirical docking and sequence-based deep learning models. In building this framework, we evaluate many combinations of individual base models, training databases, and several meta-modeling approaches. We show that many of our meta-models significantly improve affinity predictions over base models. Our best meta-models achieve comparable performance to state-of-the-art deep learning tools exclusively based on 3D structures, while allowing for improved database scalability and flexibility through the explicit inclusion of features such as physicochemical properties or molecular descriptors. We further demonstrate improved generalization capability by our models using a large-scale benchmark of affinity prediction as well as a virtual screening application benchmark. Overall, we demonstrate that diverse modeling approaches can be ensembled together to gain meaningful improvement in binding affinity prediction. © 2023, CC BY-NC-SA.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time

arXiv

引用

arXiv 2021年

作者： Zhu, Feng Sedler, Andrew R. Grier, Harrison A. Ahad, Nauman Davenport, Mark A. Kaufman, Matthew T. Giovannucci, Andrea Pandarinath, Chethan Neuroscience Graduate Program Emory University Center for Machine Learning Georgia Tech Computational Neuroscience Graduate Program The University of Chicago School of Electrical and Computer Engineering Georgia Tech Dept. of Organismal Biology and Anatomy The University of Chicago Neuroscience Institute The University of Chicago Joint Dept. of Biomedical Engineering UNC Chapel Hill NC State University UNC Chapel Hill Neuroscience Center Coulter Dept. of Biomedical Engineering Emory University Georgia Tech Dept. of Neurosurgery Emory University

Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data. © 2021, CC BY-NC-SA.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Sonic Waves Travel-time Prediction: When Machine Learning Meets Geophysics

Sonic Waves Travel-time Prediction: When Machine Learning Me...

引用

Green Energy, Computing and Sustainable Technology (GECOST), International Conference on

作者： W. K. Wong Yohanes Nuwara Filbert H. Juwono Foad Motalebi Dept. of Electrical and Computer Eng Curtin University Malaysia Miri Malaysia Corporate Information Technology Div. Asia Pulp and Paper Sinarmas Jakarta Indonesia Computer Science Program University of Southampton Malaysia Johor Malaysia

ISBN: (纸本)9781665486644

Sonic wave travel-time prediction is an important task in oil and gas exploration as it provides important information on the content and lithography of the rocks. Travel-time data, however, are not always accessible due to practical considerations. Currently, machine learning methods have been used to infer these values. In this paper, we look at the application of machine learning in predicting sonic wave travel-time, specifically in terms of challenges, benchmarks, and datasets. In addition, we present some preliminary results of sonic wave travel-time prediction using existing machine learning regression methods, namely curve fitting artificial neural network and multiple linear regression. Finally, this paper is aimed to act as a ”bridge” between machine learning practitioners and domain-specific oil and gas engineers.

关键词： Drilling Machine learning algorithms Oils Lithography Machine learning Artificial neural networks Geophysics

来源：评论

学校读者我要写书评

暂无评论

Low-Energy and Reduced-Area Hardware Architecture for the Versatile Video Coding FME

Low-Energy and Reduced-Area Hardware Architecture for the Ve...

引用

Symposium on Integrated Circuits and Systems Design (SBCCI)

作者： Vanio Rodrigues Filho Ismael Seidel Nicole Citadin Marcio Monteiro Mateus Grellert José Luis Güntzel Dept. of Informatics and Statistics (INE) Embedded Computing Lab. (ECL) Computer Science Graduate Program (PPGCC) Federal University of Santa Catarina (UFSC) Florianópolis Brazil Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

The Versatile Video Coding (VVC) standard incorporates a number of new tools to significantly improve the coding efficiency over its predecessor, the High Efficiency Video Coding (HEVC), at the cost of increased complexity. Hence, to meet real-time and energy efficiency requirements, portable devices must adopt techniques to effectively reduce the VVC complexity, including customized hardware accelerators. This work presents a low-energy hardware architecture design for the Fractional Motion Estimation (FME), which is amongst the most critical VVC and HEVC encoder steps. The proposed architecture reduces the FME complexity by operating over a subset of candidates selected to reduce the energy and area demands without compromising too much the coding efficiency. At the average BD-Rate of only 0.34% and 0.28% for the Low Delay with P slices only (LD-P) and Random Access (RA) configurations, respectively, the proposed architecture achieves a 75.5% energy consumption reduction when compared to a baseline FME architecture while occupying only 36.6 % of the area.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding features on evolutionary policy optimizations: Feature learning difference between gradient-based and evolutionary policy optimizations 20

Understanding features on evolutionary policy optimizations:...

引用

35th Annual ACM Symposium on Applied Computing, SAC 2020

作者： Lee, Sangyeop Ha, Myoung Hoon Moon, Byoungro Dept. of Computer Science and Engineering Seoul National University Seoul Korea Republic of Center for Neuroscience-inspired Artificial Intelligence KAIST Daejeon Korea Republic of

ISBN: (纸本)9781450368667

We analyze two deep reinforcement learning algorithms, gradient-based policy optimization and evolutionary one, by a number of visualization techniques and supplement experiments. As such techniques, filter visualization and saliency map are used to examine whether meaningful features properly extracted in the two algorithms. In addition to visual analysis, some experiments are devised to enhance the validity of the analysis. We observed that an evolutionary policy optimization tends to make use of the prior knowledge and learn the prior action distribution of the policy by a powerful exploration ability, which a gradient-based algorithm cannot do easily. © 2020 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Age from White Matter Diffusivity with Residual Learning

arXiv

引用

arXiv 2023年

作者： Gao, Chenyu Kim, Michael E. Lee, Ho Hin Yang, Qi Khairi, Nazirah Mohd Kanakaraj, Praitayini Newlin, Nancy R. Archer, Derek B. Jefferson, Angela L. Taylor, Warren D. Boyd, Brian D. Beason-Held, Lori L. Resnick, Susan M. Huo, Yuankai Van Schaik, Katherine D. Schilling, Kurt G. Moyer, Daniel Išgum, Ivana Landman, Bennett A. Dept. of Electrical and Computer Engineering Vanderbilt University Nashville United States Dept. of Computer Science Vanderbilt University Nashville United States Vanderbilt Memory and Alzheimer’s Center Vanderbilt University Medical Center Nashville United States Dept. of Neurology Vanderbilt University Medical Center Nashville United States Dept. of Medicine Vanderbilt University Medical Center Nashville United States Dept. of Psychiatry and Behavioral Sciences Vanderbilt University Medical Center Nashville United States Vanderbilt Center for Cognitive Medicine Vanderbilt University Medical Center Nashville United States Laboratory of Behavioral Neuroscience National Institute on Aging National Institutes of Health Baltimore United States Dept. of Radiology and Radiological Sciences Vanderbilt University Medical Center Nashville United States Dept. of Biomedical Engineering and Physics Dept. of Radiology and Nuclear Medicine Amsterdam University Medical Center University of Amsterdam Amsterdam Netherlands

Imaging findings inconsistent with those expected at specific chronological age ranges may serve as early indicators of neurological disorders and increased mortality risk. Estimation of chronological age, and deviations from expected results, from structural magnetic resonance imaging (MRI) data has become an important proxy task for developing biomarkers that are sensitive to such deviations. Complementary to structural analysis, diffusion tensor imaging (DTI) has proven effective in identifying age-related microstructural changes within the brain white matter, thereby presenting itself as a promising additional modality for brain age prediction. Although early studies have sought to harness DTI’s advantages for age estimation, there is no evidence that the success of this prediction is owed to the unique microstructural and diffusivity features that DTI provides, rather than the macrostructural features that are also available in DTI data. Therefore, we seek to develop white-matter-specific age estimation to capture deviations from normal white matter aging. Specifically, we deliberately disregard the macrostructural information when predicting age from DTI scalar images, using two distinct methods. The first method relies on extracting only microstructural features from regions of interest (ROIs). The second applies 3D residual neural networks (ResNets) to learn features directly from the images, which are non-linearly registered and warped to a template to minimize macrostructural variations. When tested on unseen data, the first method yields mean absolute error (MAE) of 6.11 ± 0.19 years for cognitively normal participants and MAE of 6.62 ± 0.30 years for cognitively impaired participants, while the second method achieves MAE of 4.69 ± 0.23 years for cognitively normal participants and MAE of 4.96 ± 0.28 years for cognitively impaired participants. We find that the ResNet model captures subtler, non-macrostructural features for brain age prediction. © 2023, C

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Edge-Based Infrared-Ultrasonic Anti-Collision Radar System for Robotic Navigation: *Applications of Cost-effective Bisensory System for Obstacle Detection, Tracking, and Avoidance

Edge-Based Infrared-Ultrasonic Anti-Collision Radar System f...

引用

IEEE Conference on Technologies for Homeland Security

作者： Kosisochukwu Pal Nnoli Mbadiwe Samuel Benyeogor Jones Ifeanyi Bolu Oladayo Olufemi Olakanmi Dept. of Computer Science and Electrical Engineering Jacobs University Bremen Germany Dept. of Physics Westfälische Wilhelms-Universität Münster Münster Germany Junior Information Technology Analyst Program NPower Canada Toronto Canada Dept. of Electrical and Electronics Engineering University of Ibadan Ibadan Nigeria

ISBN: (纸本)9781665494052

Significant progress has been made in the development of an edge computing system for the fusion, representation, and visualization of dual-sensor data for obstacle avoidance control of mobile robots. This involves the use of an error-filtering covariance and averaging algorithm to logically fuse distance measurements from a pair of infrared and ultrasonic sensors, which was instrumented into a robot and used to generate radar visuals to track the proximity of ambient obstacles within 180 degrees spanning ahead of the robot. Hands-on experiments were performed to evaluate the performance and applicability of the system in real-time. The results show that the developed system is viable and robust. In line with the emerging field of edge computing, this work is an efficient, portable, and cost-effective approach to developing mobile robotic systems.

关键词： Visualization Navigation Fuses Sensor fusion Robot sensing systems Radar tracking Acoustics

来源：评论

学校读者我要写书评

暂无评论

Disclosure Privacy Information Social Media on TikTok

Disclosure Privacy Information Social Media on TikTok

引用

International Conference on Information Management and Technology (ICIMTech)

作者： Dedy Syamsuar Fazri Fahrezi Ahnaf Favian Edy Irwansyah Achmad Fakhri Irawan Professional Engineer Program Dept. Information System Department Faculty of Engineering School of Information System Bina Nusantara University Jakarta Indonesia Information System Department School of Information System Bina Nusantara University Jakarta Indonesia Computer Science Department School of Information System Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350390025

ISBN: (纸本)9798350390032

With the rapid development of technology, the use of social media by the public, especially among young people, is increasing. One of the social media platforms currently used by young people is the TikTok application. It is a video-based TikTok feature accompanied by music, writing, and pictures that are considered attractive, so teenagers like it to show their existence and self-disclosure. Therefore, this study aims to examine the intention of users to disclose their privacy. As the basis of the theory, this study deployed the privacy calculus theory, where the perceived benefits and perceived risks play crucial roles in the intention to disclose their privacy. The study successfully collected 369 responses. The empirical findings indicated that only the relationship between Perceived Personalization (PP) and Perceived Risk (PR) was not supported. However, all the remaining hypotheses were supported. These findings emphasize how several complicated variables influence social media users' intentions to disclose their privacy. When people feel in control of their privacy settings and see significant benefits, they are more likely to divulge personal information; nevertheless, perceived risks can greatly discourage users.

关键词： Privacy Video on demand Social networking (online) Writing Control systems Calculus Information management Web sites

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：