检索结果-内蒙古大学图书馆

Explainable machine learning for movement disorders - Classification of tremor and myoclonus

computers in Biology and Medicine 2025年第Pt B期192卷 110180-110180页

作者： van den Brandhof, Elina L. Tuitert, Inge Madelein van der Stouwe, A.M. Elting, Jan W.J. Dalenberg, Jelle R. Svorenova, Tatiana Klamer, Marrit R. Marapin, Ramesh S. Biehl, Michael Tijssen, Marina A.J. Expertise Center Movement Disorders Groningen University Medical Center Groningen Groningen Netherlands Department of Neurology University Medical Center Groningen University of Groningen Groningen Netherlands Bernoulli Institute for Mathematics Computer Science and Artificial Intelligence University of Groningen Groningen Netherlands NHL Stenden University of Applied Sciences Leeuwarden Netherlands Department of Neurology P.J. Safarik University Kosice Slovakia Department of Neurology University Hospital of L. Pasteur Kosice Slovakia SMQB Institute of Metabolism and Systems Research College of Medical and Dental Sciences University of Birmingham Birmingham United Kingdom

Background: Treatment for essential tremor (ET) and cortical myoclonus (CM) differs. As their clinical distinction can be difficult, with large inter- and intra-observer variability, there is a need for additional diagnostic tools. Objectives: We aim to develop a machine learning based approach using accelerometry data to support clinicians in their diagnosis of ET versus CM. Methods: We recorded the upper body movements of 19 ET and 19 CM patients performing 21 tasks using eight accelerometry sensors. The phenotype was classified by applying an explainable machine learning method called generalized matrix learning vector quantization (GMLVQ) to the power spectrum derived from the accelerometry recordings. In addition to the general classification performance, GMLVQ provides context for the decisions made. This includes the relevance of frequencies and thus the identification of distinct patterns in the phenotypes. Results: For all postures and dynamic tasks, excellent classification results were reached with AUROC approaching 1,0. For the classification, GMLVQ considers the overall shape of the power spectrum, whereby the frequencies 5–7 Hz as well as 3–4 and 9–10 Hz are of particular importance. These frequencies correspond to the tremor peak and local minima that are also observed as characteristics in the literature. Conclusion: The excellent classification results provide a proof of concept for the discrimination of ET and CM by applying a GMLVQ machine learning analysis to power spectra derived from accelerometry recordings. Such a system could support clinicians to improve the diagnostic accuracy. © 2025 The Authors

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Predicting isocitrate dehydrogenase mutation status in glioma using structural brain networks and graph neural networks

arXiv

引用

arXiv 2021年

作者： Wei, Yiran Li, Yonghao Chen, Xi Schönlieb, Carola-Bibiane Li, Chao Price, Stephen J. Department of Clinical Neuroscience University of Cambridge School of Biological Sciences Nanyang Technological University Department of Computer Science University of Bath Department of Applied Mathematics and Theoretical Physics University of Cambridge

Glioma is a common malignant brain tumor with distinct survival among patients. The isocitrate dehydrogenase (IDH) gene mutation provides critical diagnostic and prognostic value for glioma. It is of crucial significance to non-invasively predict IDH mutation based on pre-treatment MRI. Machine learning/deep learning models show reasonable performance in predicting IDH mutation using MRI. However, most models neglect the systematic brain alterations caused by tumor invasion, where widespread infiltration along white matter tracts is a hallmark of glioma. Structural brain network provides an effective tool to characterize brain organisation, which could be captured by the graph neural networks (GNN) to more accurately predict IDH mutation. Here we propose a method to predict IDH mutation using GNN, based on the structural brain network of patients. Specifically, we firstly construct a network template of healthy subjects, consisting of atlases of edges (white matter tracts) and nodes (cortical/subcortical brain regions) to provide regions of interest (ROIs). Next, we employ autoencoders to extract the latent multi-modal MRI features from the ROIs of edges and nodes in patients, to train a GNN architecture for predicting IDH mutation. The results show that the proposed method outperforms the baseline models using the 3D-CNN and 3D-DenseNet. In addition, model interpretation suggests its ability to identify the tracts infiltrated by tumor, corresponding to clinical prior knowledge. In conclusion, integrating brain networks with GNN offers a new avenue to study brain lesions using computational neuroscience and computer vision approaches. © 2021, CC BY-NC-ND.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Uncertainty quantification for molecular property predictions with graph neural architecture search†

arXiv

引用

arXiv 2023年

作者： Jiang, Shengli Qin, Shiyi Van Lehn, Reid C. Balaprakash, Prasanna Zavala, Victor M. Department of Chemical and Biological Engineering University of Wisconsin–Madison 1415 Engineering Dr MadisonWI53706 United States Computing and Computational Sciences Directorate Oak Ridge National Laboratory P.O. Box 2008 Oak RidgeTN37831 United States Mathematics and Computer Science Division Argonne National Laboratory LemontIL60439 United States

Graph Neural Networks (GNNs) have emerged as a prominent class of data-driven methods for molecular property prediction. However, a key limitation of typical GNN models is their inability to quantify uncertainties in the predictions. This capability is crucial for ensuring the trustworthy use and deployment of models in downstream tasks. To that end, we introduce AutoGNNUQ, an automated uncertainty quantification (UQ) approach for molecular property prediction. AutoGNNUQ leverages architecture search to generate an ensemble of high-performing GNNs, enabling the estimation of predictive uncertainties. Our approach employs variance decomposition to separate data (aleatoric) and model (epistemic) uncertainties, providing valuable insights for reducing them. In our computational experiments, we demonstrate that AutoGNNUQ outperforms existing UQ methods in terms of both prediction accuracy and UQ performance on multiple benchmark datasets, and generalizes well to out-of-distribution datasets. Additionally, we utilize t-SNE visualization to explore correlations between molecular features and uncertainty, offering insight for dataset improvement. AutoGNNUQ has broad applicability in domains such as drug discovery and materials science, where accurate uncertainty quantification is crucial for decision-making. © 2023, CC BY-NC-ND.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Brownian motion in a magneto Thermo-diffusion fluid flow over a semi-circular stretching surface

引用

Partial Differential Equations in applied mathematics 2024年 12卷

作者： Munjam, Shankar Rao Gopal, D. Kishan, N. Formanova, Shoira Karthik, K. Ahmad, Furqan Waqas, M. Gupta, Manish Khan, M. Ijaz School of Technology Woxsen University Telangana Hyderabad 502345 India Junior Lecturer in Mathematics Telangana Tribal Welfare Upgraded Residential Junior College for Boys Cheemanpally Telangana Nizamabad District 503165 India Department of Mathematics UCS Osmania University Telangana Hyderabad 500007 India Department of Chemistry and Its Teaching Methods Tashkent State Pedagogical University Tashkent Uzbekistan Department of Studies in Mathematics Davangere University Karnataka Davangere India Western Caspian University Baku Azerbaijan NUTECH School of Applied Sciences and Humanities National University of Technology Islamabad 44000 Pakistan Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Division of Research and Development Lovely Professional University Phagwara India Department of Mechanical Engineering College of Engineering Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia

The current study explores the mass and heat transport analysis of a Casson liquid stream past a curved surface. The current model considers the effect of magnetic strength brought on by the strength of the applied uniform magnetic field. The significance of thermophoresis and Brownian motion are also taken into account using the Buongiorno nano-liquid model. The study of liquid flow over stretching sheets frequently addresses practical issues that have garnered significant attention from researchers due to their importance in various domains, including microfluidics, fibreglass production, manufacturing, transportation, metal extrusion, thermal insulation, glass production, paper manufacturing, and acoustic blasting. The governing partial differential equations (PDEs) are converted into ordinary differential equations (ODEs) using the similarity variables. These equations are numerically solved using the finite difference method (FDM). The concentration, temperature, and velocity graphs were produced by varying the different physical parameters. The upsurge in the magnetic parameter reduces the velocity profile. As the magnetic parameter increases, thermal and concentration profiles upsurge. The decrease in velocity profile can be seen as the Casson parameter rises. The intensification in values of thermophoretic parameter enhances the thermal and concentration profiles. The concentration and thermal profiles reduce as the curvature parameter upsurges. © 2024 The Author(s)

关键词： Casson fluid Curved stretching sheet Nanofluid Thermophoresis and Brownian motion

来源：评论

学校读者我要写书评

暂无评论

The quadric ansatz for the mn-dispersionless KP equation, and supersymmetric Einstein-weyl spaces

arXiv

引用

arXiv 2021年

作者： Dunajski, Maciej Plansangkate, Prim Department of Applied Mathematics and Theoretical Physics University of Cambridge Wilberforce Road CambridgeCB3 0WA United Kingdom Applied Analysis Research Unit Division of Computational Science Faculty of Science Prince of Songkla University Songkhla90110 Thailand

We consider two multi–dimensional generalisations of the dispersionless Kadomtsev-Petviashvili (dKP) equation, both allowing for arbitrary dimensionality, and non–linearity. For one of these generalisations, we characterise all solutions which are constant on a central quadric. The quadric ansatz leads to a second order ODE which is equivalent to Painleve I or II for the dKP equation, but fails to pass the Painlevé test in higher dimensions. The second generalisation of the dKP equation leads to a class of Einstein–Weyl structures in an arbitrary dimension, which is characterised by the existence of a weighted parallel vector field, together with further holonomy reduction. We construct and characterise an explicit new family of Einstein–Weyl spaces belonging to this class, and depending on one arbitrary function of one variable. Copyright © 2021, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A computational framework for Carreau nanomaterial induced by stretchy regime considering Brownian diffusion, viscous dissipation, ferromagnetism and thermophoresis

引用

Partial Differential Equations in applied mathematics 2025年 13卷

作者： Hussain, Iftikhar Khan, Waqar Azeem Tabrez, Muhammad Waqas, M. Ibrahim, Talib K. Saidani, Taoufik Kausar, M.S. Zamri, Nurnadiah Abdullaeva, Barno Garalleh, Hakim AL Department of Mathematics Mohi-ud-Din Islamic University Nerian Sharif Jammu and Kashmir Azad 12010 Pakistan School of Mathematics and Statistics Beijing Institute of Technology Beijing 100081 China NUTECH School of Applied Sciences and Humanities National University of Technology Islamabad 44000 Pakistan Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Besut Campus Terengganu Besut 22200 Malaysia Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Petroleum Engineering College of Engineering Knowledge University Erbil 44001 Iraq Department of Petroleum Engineering Al-Kitab University Altun Kupri Iraq Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Faculty of Informatics and Computing Universiti Sultan Zainal Abidin (Kampus Gong Badak) Terengganu Kuala Terengganu 21300 Malaysia Department of Mathematics and Information Technologies Vice-Rector for Scientific Affairs Tashkent State Pedagogical University Tashkent Uzbekistan Department of Mathematical Science College of Engineering University of Business and Technology Jeddah 21361 Saudi Arabia

In recent decade, the research in nanotechnology brought the idea of nanofluids which are highly conducting materials. Some important applications of nanofluids are justified in pharmaceutical industry, coolants in vehicles engine, preparation process of various medicines for treatment of fatal diseases like cancer, aircraft industry, latest heat exchangers etc. The ferro particles are special class of nanomaterial which attract variety of interest from the researchers. The objective of current research is to perform the investigation for heat and mass transfer subject to Carreau nanofluid to observe the enhancement of heat transmission phenomena. The induction of magnetic dipole has been observed for thermal transport phenomenon. The flow is causing by stretched surface. A simplified system is obtained by utilizing the dimensionless variables. Physical interpretation of results have been presented. Result showed that temperature profile in presence of ferrofluid fluid boosts up with escalation in thermophoresis parameter, while opposite behavior is noted for power law index. The concentration of ferrofluid showing declining behavior for Schmidt numbers and rises for thermophoresis parameter. © 2024

关键词： Carreau ferrofluid Heat and mass transfer Magnetic dipole Numerical solution

来源：评论

学校读者我要写书评

暂无评论

Developing a Robotic Solar-Powered Fire Detection and Avoidance System With Machine Learning-Based Sensing

Developing a Robotic Solar-Powered Fire Detection and Avoida...

引用

Communication, Security and Artificial Intelligence (ICCSAI), International Conference on

作者： Preeti Verma Arun Gangwar Bharat Singh Shubhendra Pratap Singh Pooja Vats Reddy Ganesh School of Electronic and Electrical Engineering Dev Bhoomi Uttarakhand University Uttarakhand Department of Electrical Engineering Invertis University Bareilly Uttar Pradesh School of COMPUTER SCIENCE AND APPLICATIONS IIMT University Meerut Department of EE TMU Moradabad India Department of Mathematics School of Basic & Applied Sciences K. R. Mangalam University Gurugram Haryana India Engineering Department UTAS-IBRI Sultanate of Oman

This research addresses the challenge of ensuring a consistent energy supply for forest fire surveillance systems, which is critical in the field of computer science, AI, ML, Data Mining, NLP, computer Vision, and Robotics. Traditional solar-powered solutions rely on fixed-mounted rooftop panels, which are often inadequate due to their limited electricity production capacity, especially under variable weather conditions. This study introduces an innovative, all-weather, autonomous solar tracking system that adapts to the changing position of the sun throughout the seasons, ensuring optimal energy collection for the surveillance equipment. To properly navigate the sun motion, the cautioned gadget merges sun's trajectory monitoring modalities with pv sensing. It begins via determining the season with a sensor that measures the volume of sunshine. The sun function detector & a customized PV itinerary algorithms then estimate the solar's course. The gadget makes use of specific tracking algorithms for sunny, gloomy, and moist instances, using artificial intelligence algorithms to forecast versions in the weather & adjust the panels as it should be. The approach has been proved in simulated experiments to be able to mitigating the influence of versions in the climate at the same time as keeping a steady and specific alignment facing the sun in all climates. The technique will increase the ability of photovoltaic cells utilized for wooded area fire tracking to produce electricity, improving the dependability and effectiveness of such vital device. This precise use of AI and gadget getting to know in environmental surveillance represents a step towards stronger and longer-lasting fire caution systems, which might be important for woodland preservation and management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uniqueness of weak solutions to the primitive equations in some anisotropic spaces

引用

Journal of Differential Equations 2025年 444卷

作者： Tim Binz Yoshiki Iida Program in Applied and Computational Mathematics Princeton University Fine Hall Washington Road Princeton 08544 NJ the United States of America Department of Pure and Applied Mathematics Graduate School of Fundamental Science and Engineering Waseda University Okubo 3-4-1 Shinjuku-ku Tokyo 169-8555 Japan

We consider the both 3D and 2D viscous primitive equations for ocean in the isothermal setting. While strong global well-posedness of the viscous primitive equations for large data in H 1 has already proved, the uniqueness of the weak solutions of Leray–Hope type for given initial data in L 2 remains an outstanding open problem. In this paper, we establish a new conditional uniqueness result for weak solutions to the primitive equations, that is, if a weak solution belongs some scaling invariant function spaces, and satisfies some additional assumptions, then the weak solution is unique. In particular, our result can be obtained as different one from z -weak solutions framework by adopting some anisotropic approaches with the homogeneous toroidal Besov spaces. As an application of the proof, we establish the energy equality for weak solutions in the uniqueness class given in the main theorem.

关键词： 35Q86 35K59 86A05 86A10 35Q35 Primitive equations Conditional uniqueness Anisotropic spaces Besov spaces Scaling invariance

来源：评论

学校读者我要写书评

暂无评论

Mathematical modelling and projection of Buruli ulcer transmission dynamics using classical and fractional derivatives: A case study of Cameroon

引用

Partial Differential Equations in applied mathematics 2023年 8卷

作者： Fandio, Rubin Abboubakar, Hamadjam Fouda, Henri Paul Ekobena Kumar, Anoop Nisar, Kottakkaran Sooppy The University of Yaoundé I Laboratory of Biophysics P.O. Box 812 Cameroon The University of Ngaoundéré University Institute of Technology Department of Computer Engineering P.O. Box 455 Ngaoundéré Cameroon The University of Yaoundé I Faculty of Science Department of Physics P.O. Box 812 Cameroon Central University of Punjab School of Basic and Applied Sciences Department of Mathematics and Statistics Bathinda Punjab 151001 India Department of Mathematics College of Science and Humanities in Alkharj Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia

The goal of this work is to derive and study a new model which traduces the transmission dynamics of the Buruli ulcer (BU), in which we replace mass action incidences with standard incidences, consider latent period, and by using both integer and fractional derivatives. We first present reported data of Buruli in Cameroon between 01/01/2001 and 31/12/2014, and the statistical model that approximates real data as closely as possible, and thus make a forecasting in the next sixteen years. After that, we formulate a Susceptible humans-Exposed humans-Infectious humans-Recovered humans-Susceptible humans;Susceptible vectors-Infectious vectors (SEIRS-SI) type compartmental model of Buruli Ulcer using integer derivative. We compute the basic reproduction number denoted by R₀ and prove the asymptotic stability of the Buruli-free equilibrium whenever R₀<1. Then, for R₀>1, we prove the existence of an unique endemic equilibrium point and its global stability using the general theory of Lyapunov. We perform parameter estimation to calibrate our model using real data from Cameroon, while sensitivity analysis is conducted to determine important parameters in the BU dynamics. From this model calibration, we obtain R₀=2.0843 which is greater than one and implies that BU ulcer is endemic in the country. To determine whether if or not the BU admits one or multiple waves, we compute the strength number denoted by A₀. We find that A₀≈17>0 which means that Bu admits multiple epidemic waves. We then replace integer derivative with the Caputo fractional derivative. Asymptotic stability of equilibrium points are also performed for the fractional model. This follows by the proof of existence and the uniqueness of solutions of the fractional model. We then construct a numerical scheme based on the Adams–Bashforth–Moulton (ABM) Method. Theoretical results are validated from numerical simulations. These last also permits to eva

关键词： Asymptotic stability Buruli ulcer Caputo derivative Parameter estimation Strength number

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approach for Complex Activity Recognition using Heterogeneous Sensors from Wearable Device

Deep Learning Approach for Complex Activity Recognition usin...

引用

2021 Research, Invention, and Innovation Congress: Innovation Electricals and Electronics, RI2C 2021

作者： Hnoohom, Narit Jitpattanakul, Anuchit You, Ilsun Mekruksavanich, Sakorn Mahidol University Image Information and Intelligence Laboratory Department of Computer Engineering Faculty of Engineering Nakhon Pathom Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand Soonchunhyang University Department of Information Security Engineering Asan31538 Korea Republic of University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand

ISBN: (纸本)9781665403009

The classification of simple and complex sequences of operations is made easier according to the use of heterogeneous sensors from a wearable device. Sensor-based human activity recognition (HAR) is being used in smartphone platforms for elderly healthcare monitoring, fall detection, and inappropriate behavior prevention, such as smoking habit, unhealthy eating, and lack of exercise. Common machine learning and deep learning techniques have recently been presented to tackle the HAR issue, with a focus on everyday activities, particularly general human activities including moving, sitting, and standing. However, there is an intriguing and challenging HAR research subjects involving more complicated psychological activities in various environments, including smoking, eating, and drinking. The use of heterogeneous sensor data to enhance recognition performance over sensor-based deep learning networks is considered in this work. We demonstrate that using a combination of two inertial measurement units outperforms employing either an accelerometer or a gyroscope by utilizing four deep learning classifiers to recognize complex human activity (CHA). Furthermore, we describe the impact of five window sizes (5s - 40s) on a publicly accessible benchmark dataset and how increasing window size effects to the classification performance of CHA deep learning networks. © 2021 IEEE.

关键词： Deep learning

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：