检索结果-内蒙古大学图书馆

Quantifying performance of machine learning methods for neuroimaging data

NEUROIMAGE 2019年 199卷 351-365页

作者： Jollans, Lee Boyle, Rory Artiges, Eric Banaschewski, Tobias Desrivieres, Sylvane Grigis, Antoine Martinot, Jean-Luc Paus, Tomas Smolka, Michael N. Walter, Henrik Schumann, Gunter Garavan, Hugh Whelan, Robert Trinity Coll Dublin Sch Psychol Dublin Ireland Max Planck Inst Psychiat Dept Translat Res Psychiat Munich Germany Univ Paris 05 Univ Paris Sud Sorbonne Paris Cite INSERM Unit Neuroimaging & Psychiat 1000Inst Nat Paris France Orsay Hosp Psychiat Dept 91G16 Orsay France Heidelberg Univ Med Fac Mannheim Cent Inst Mental Hlth Dept Child & Adolescent Psychiat & Psychotherapy Sq J5 D-68159 Mannheim Germany Kings Coll London Inst Psychiat Psychol & Neurosci Social Genet & Dev Psychiat Ctr MRC London England Univ Paris Saclay CEA NeuroSpin F-91191 Gif Sur Yvette France Maison de Solenn Paris France Univ Toronto Holland Bloorview Kids Rehabil Hosp Bloorview Res Inst Toronto ON M6A 2E1 Canada Univ Toronto Dept Psychol Toronto ON M6A 2E1 Canada Univ Toronto Dept Psychiat Toronto ON M6A 2E1 Canada Tech Univ Dresden Dept Psychiat Dresden Germany Tech Univ Dresden Neuroimaging Ctr Dresden Germany Charite Univ Med Berlin Charitepl 1 Berlin Germany Free Univ Berlin Charitepl 1 Berlin Germany Humboldt Univ Charitepl 1 Berlin Germany Berlin Inst Hlth Charitepl 1 Berlin Germany Dept Psychiat & Psychotherapy Charitepl 1 Berlin Germany Campus Charite Mitte Charitepl 1 Berlin Germany Univ Vermont Dept Psychiat Burlington VT USA Trinity Coll Dublin Global Brain Hlth Inst Dublin Ireland

Machine learning is increasingly being applied to neuroimaging data. However, most machine learning algorithms have not been designed to accommodate neuroimaging data, which typically has many more data points than subjects, in addition to multicollinearity and low signal-to-noise. Consequently, the relative efficacy of different machine learning regression algorithms for different types of neuroimaging data are not known. Here, we sought to quantify the performance of a variety of machine learning algorithms for use with neuroimaging data with various sample sizes, feature set sizes, and predictor effect sizes. The contribution of additional machine learning techniques - embedded feature selection and bootstrap aggregation (bagging) - to model performance was also quantified. Five machine learning regression methods - Gaussian Process regression, Multiple Kernel Learning, Kernel Ridge regression, the Elastic Net and Random Forest, were examined with both real and simulated MRI data, and in comparison to standard multiple regression. The different machine learning regression algorithms produced varying results, which depended on sample size, feature set size, and predictor effect size. When the effect size was large, the Elastic Net, Kernel Ridge regression and Gaussian Process regression performed well at most sample sizes and feature set sizes. However, when the effect size was small, only the Elastic Net made accurate predictions, but this was limited to analyses with sample sizes greater than 400. Random Forest also produced a moderate performance for small effect sizes, but could do so across all sample sizes. Machine learning techniques also improved prediction accuracy for multiple regression. These data provide empirical evidence for the differential performance of various machines on neuroimaging data, which are dependent on number of sample size, features and effect size.

关键词： Machine learning Neuroimaging regression algorithms Reproducibility

来源：评论

学校读者我要写书评

暂无评论

Estimation of unknown speaker's height from speech

引用

INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY 2009年第4期12卷 149-160页

作者： Mporas, Iosif Ganchev, Todor Univ Patras Dept Elect & Comp Engn Wire Commun Lab Rion 26500 Greece

In the present study, we propose a regression-based scheme for the direct estimation of the height of unknown speakers from their speech. In this scheme every speech input is decomposed via the openSMILE audio parameterization to a single feature vector that is fed to a regression model, which provides a direct estimation of the persons' height. The focus in this study is on the evaluation of the appropriateness of several linear and non-linear regression algorithms on the task of automatic height estimation from speech. The performance of the proposed scheme is evaluated on the TIMIT database, and the experimental results show an accuracy of 0.053 meters, in terms of mean absolute error, for the best performing Bagging regression algorithm. This accuracy corresponds to an averaged relative error of approximately 3%. We deem that the direct estimation of the height of unknown people from speech provides an important additional feature for improving the performance of various surveillance, profiling and access authorization applications.

关键词： Human height estimation from speech Speech processing regression algorithms

来源：评论

学校读者我要写书评

暂无评论

Brain-Machine Interfaces Lessons for Prosthetic Hand Control

引用

HAND CLINICS 2021年第3期37卷 391-399页

作者： Vaskov, Alex K. Chestek, Cynthia A. Univ Michigan Robot Inst 2505 Hayward St Ann Arbor MI 48109 USA Univ Michigan Dept Biomed Engn 2200 Bonisteel Blvd Ann Arbor MI 48109 USA Univ Michigan Dept Elect Engn & Comp Sci 1301 Beal Ave Ann Arbor MI 48109 USA Univ Michigan Neurosci Grad Program 204 Washtenaw Ave Ann Arbor MI 48109 USA

Brain-machine interfaces (BMI) are being developed to restore upper limb function for persons with spinal cord injury or other motor degenerative conditions. BMI and implantable sensors for myoelectric prostheses directly extract information from the central or peripheral nervous system to provide users with high fidelity control of their prosthetic device. Control algorithms have been highly transferable between the 2 technologies but also face common issues. In this review of the current state of the art in each field, the authors point out similarities and differences between the 2 technologies that may guide the implementation of common solutions to these challenges.

关键词： Brain-machine interfaces Fine motor control regression algorithms Pattern recognition Calibration methods

来源：评论

学校读者我要写书评

暂无评论

Comprehensive evaluation of empirical algorithms for estimating land surface evapotranspiration

引用

AGRICULTURAL AND FOREST METEOROLOGY 2018年 256卷 334-345页

作者： Carter, Corinne Liang, Shunlin Univ Maryland Dept Geog College Pk MD 20742 USA

Many empirical algorithms for obtaining evapotranspiration (ET) from vegetation indices (VIs) have been developed, but there has been little work comparing these algorithms to each other or deriving coefficients for them using large data sets for training and validation. Twelve different vegetation index-based regression algorithms for retrieval of ET on a daily basis are reviewed and evaluated here. New coefficients have been derived for four of these algorithms using data from 181 Ameriflux and Fluxnet2015 sites and 1 km MODIS subsets centered at each site location. Algorithm validation with previously published and new coefficients was performed using one year of data from each Ameriflux and Fluxnet2015 site. There was a wide range of performance of these algorithms, with the median R-2 by site in the 0.6 to 0.7 range, median root mean square error (RMSE) about 25 W/m(2) and median bias within 10 W/m(2). When algorithm coefficients were re-derived, the RMSE and bias of the worst-performing algorithms were largely reduced, but R-2 was little changed. Agricultural and wetland sites had a low bias across most of the algorithms, and wetland sites had a higher RMSE. When several of the algorithms were re-tuned to obtain coefficients specific to each surface type, the biases of the agricultural and wetland sites were reduced to those more typical of other site types, and RMSE for agricultural and wetland sites was also reduced. The effects of linear interpolation of VIs to obtain daily LE and interpolation over periods of rapid VI change at agricultural sites were examined. No significant algorithm performance degradation was found in either case. It is recommended to use more detailed algorithms when possible, with inclusion of net radiation as a parameter along with VI at a minimum.

关键词： Evapotranspiration Remote sensing Vegetation index regression algorithms MODIS Fluxnet

来源：评论

学校读者我要写书评

暂无评论

A Comparison of machine learning regression models for critical bus voltage and load mapping with regards to max reactive power in PV buses

引用

ELECTRIC POWER SYSTEMS RESEARCH 2021年 191卷 106883-106883页

作者： Fachini, F. Fuly, B. I. L. Fed Unviers Itajuba Inst Elect & Energy Syst Itajuba Brazil

The aim of this paper is to compare voltage and system loading mapping capabilities of a variety of regression algorithms, such as Adaptive Network based Fuzzy Inference System (ANFIS), Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), Support Vector regression (SVR), and Decision Tree (DT). A voltage sensitivity matrix is generated from the power flow Jacobian matrix for a loading scenario near the unstable point. Principal Component Analysis (PCA) is used to separate the system, close to the critical point, in order to group the buses into coherent voltage controlling areas. For different reactive power injection scenarios, we have different bus voltages that can be mapped by the aforementioned regression algorithms. The algorithms are trained with limited amounts of data, in order to establish a fair comparison between them. The present work shows that ANFIS and KNN have a better performance in critical voltage and load prediction when compared to the rest. The academic IEEE 14 and 118 bus systems are employed with all its limits considered, so the results may be reproduced.

关键词： regression algorithms ANFIS KNN PCA Voltage controlling areas

来源：评论

学校读者我要写书评

暂无评论

Movement-Based Control for Upper-Limb Prosthetics: Is the regression Technique the Key to a Robust and Accurate Control?

引用

FRONTIERS IN NEUROROBOTICS 2018年 12卷 41页

作者： Legrand, Mathilde Merad, Manelle de Montalivet, Etienne Roby-Brami, Agnes Jarrasse, Nathanael Sorbonne Univ CNRS INSERM ISIRInst Syst Intelligents & Robot Paris France

Due to the limitations of myoelectric control (such as dependence on muscular fatigue and on electrodes shift, difficulty in decoding complex patterns or in dealing with simultaneous movements), there is a renewal of interest in the movement-based control approaches for prosthetics. The latter use residual limb movements rather than muscular activity as command inputs, in order to develop more natural and intuitive control techniques. Among those, several research works rely on the interjoint coordinations that naturally exist in human upper limb movements. These relationships are modeled to control the distal joints (e.g., elbow) based on the motions of proximal ones (e.g., shoulder). The regression techniques, used to model the coordinations, are various [Artificial Neural Networks, Principal Components Analysis (PCA), etc.] and yet, analysis of their performance and impact on the prosthesis control is missing in the literature. Is there one technique really more efficient than the others to model interjoint coordinations? To answer this question, we conducted an experimental campaign to compare the performance of three common regression techniques in the control of the elbow joint on a transhumeral prosthesis. Ten non-disabled subjects performed a reaching task, while wearing an elbow prosthesis which was driven by several interjoint coordination models obtained through different regression techniques. The models of the shoulder-elbow kinematic relationship were built from the recordings of fifteen different non-disabled subjects that performed a similar reaching task with their healthy arm. Among Radial Basis Function Networks (RBFN), Locally Weighted regression (LWR), and PCA, RBFN was found to be the most robust, based on the analysis of several criteria including the quality of generated movements but also the compensatory strategies exhibited by users. Yet, RBFN does not significantly outperform LWR and PCA. The regression technique seems not to be the most

关键词： upper-limb prosthetics movement-based control shoulder-elbow coordinations regression algorithms motor strategy

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis Using Multiple regression Models for Forecasting Photovoltaic Power Generation

引用

ENERGIES 2024年第7期17卷 1564页

作者： Abdullah, Burhan U. Din Khanday, Shahbaz Ahmad Islam, Nair Ul Lata, Suman Fatima, Hoor Nengroo, Sarvar Hussain Sharda Univ Sch Engn & Technol Knowledge Pk 3 Greater Noida 201306 Uttar Pradesh India Korea Adv Inst Sci & Technol Cho Chun Shik Grad Sch Mobil Daejeon 34051 South Korea Tech Univ Denmark DTU Dept Engn & Technol DK-2800 Ballerup Denmark

Effective machine learning regression models are useful toolsets for managing and planning energy in PV grid-connected systems. Machine learning regression models, however, have been crucial in the analysis, forecasting, and prediction of numerous parameters that support the efficient management of the production and distribution of green energy. This article proposes multiple regression models for power prediction using the Sharda University PV dataset (2022 Edition). The proposed regression model is inspired by a unique data pre-processing technique for forecasting PV power generation. Performance metrics, namely mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R2-score, and predicted vs. actual value plots, have been used to compare the performance of the different regression. Simulation results show that the multilayer perceptron regressor outperforms the other algorithms, with an RMSE of 17.870 and an R2 score of 0.9377. Feature importance analysis has been performed to determine the most significant features that influence PV power generation.

关键词： photovoltaic regression algorithms mean absolute error mean squared error root mean squared error grid forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparative evaluation of Machine Learning algorithms and Physical based models for the prediction of Vessel Speed in real life applications. 25

Comparative evaluation of Machine Learning algorithms and Ph...

引用

25th Pan-Hellenic Conference on Informatics with International Participation (PCI)

作者： Alexiou, Kiriakos Pariotis, Efthimios G. Zannis, Theodoros C. Polyzos, Stylianos Leligou, Helen C. Univ West Attica Dept Ind Design & Prod Engn Athens 12243 Greece Hellen Naval Acad Naval Architecture & Marine Engn Sect Piraeus 18539 Greece

ISBN: (纸本)9781450395557

The fourth quarter of the year 2021 might be the start of new global energy crisis. A natural gas shortage in Europe has driven prices to record highs and consequently increased the price of Diesel. The prementioned increase of the fuel prices constitutes the most important reason for an equal increase of operating costs in shipping companies. On the other hand, the huge fires that broke out in many parts of southern Europe in the summer of 2021, have made it clear to governments that stricter environmental protection measures need to be taken. The existing European Union (EU) regulation specifies a maximum Sulphur content of marine fuels from of 0.50%. Stricter environmental protection rules are expected to further reduce the profit margin in shipping. To compensate the above two adverse effects, the shipping companies have to either renew their fleet with new and more environmentally friendly ships, or try to optimize the performance of their existing fleet. The prediction of a key aspect of the performance of a ship, such us the speed that achieves with a given engine torque is a crucial tool in both designing of new vessel and optimize the performance in existing ones. In this paper, author compares the performance of a well-known physically based system simulation software (Simcenter Amesim) against Machine Learning (ML) algorithms in the prediction of an ocean-going vessel speed at various operating conditions according to a real-life sea route over a period of six days. Two different predictive ML algorithms are evaluated: Artificial Neural Network (ANN) and Vector Linear regression (VLR), since based on the literature, they are suggested as the most suitable for this type of problems. Actual data from the onboard Automated Data Logging & Monitoring (ADLM) system have been used. The study shows that both pathways (either using system simulation or ML), are adequate for vessel speed prediction with reasonable accuracy. Specifically, the simulation tool is able

关键词： Artificial Intelligence (AI) Machine Learning (ML) Simcenter Amesim Simulation Prediction regression algorithms Data Mining Artificial Neural Network (ANN)

来源：评论

学校读者我要写书评

暂无评论

Smart Stores: A scalable foot traffic collection and prediction system 1

引用

17th Industrial Conference on Data Mining (ICDM)

作者： Abrishami, Soheila Kumar, Piyush Nienaber, Wickus Florida State Univ Tallahassee FL 32306 USA Bloom Intelligence Tallahassee FL 32303 USA

ISBN: (数字)9783319627014

ISBN: (纸本)9783319627014;9783319627007

An accurate foot traffic prediction system can help retail businesses, physical stores, and restaurants optimize their labor schedule and costs, and reduce food wastage. In this paper, we design a large scale data collection and prediction system for store foot traffic. Our data has been collected from wireless access points deployed at over 100 businesses across the United States for a period of more than one year. This data is centrally processed and analyzed to predict the foot traffic for the next 168 hours (a week). Our current predictor is based on Support Vector regression (SVR). There are a few other predictors that we have found that are similar in accuracy to SVR. For our collected data the average foot traffic per hour is 35 per store. Our prediction result is on average within 22% of the actual result for a 168 hour (a week) period.

关键词： Time series forecasting regression algorithms Foot traffic Wireless access point Bloom Intelligence

来源：评论

学校读者我要写书评

暂无评论

Improved method for measuring frequency ratios in GSM mobile phones

Improved method for measuring frequency ratios in GSM mobile...

引用

IEEE Custom Integrated Circuits Conference

作者： Bode, P Lampe, A Helfenstein, M Gollnick, M Philips Semicond Nurnberg Germany

ISBN: (纸本)0780384954

The principle of operation of the ubiquitous low-cost digital circuits for frequency measurement appears to be unchanged since decades. In applications with very high accuracy requirements such as in GSM mobile phones, these conventional solutions can lead to excessive measurement periods with detrimental effect on the stand-by time. In this paper, we present a novel frequency measurement technique which is based on regression algorithms. Experiments with a HW implementation prove that the crucial product of measurement error and measurement period can be reduced by orders of magnitude compared to conventional solutions while the slight extension of the digital circuitry is virtually for free.

关键词： cellular radio mobile handsets frequency measurement regression analysis measurement errors frequency ratio measurement GSM mobile phones low-cost digital frequency measurement circuits high accuracy measurement regression algorithms measurement error measurement period Error measure Mobile phones frequency measurement cellular radio regression analysis accuracy of measurement frequency ratio

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：