检索结果-南通市图书馆

Using BlazePose on Spatial Temporal Graph Convolutional Networks for Action Recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第1期74卷 19-36页

作者： Motasem S.Alsawadi El-Sayed M.El-kenawy miguel rio Electronic and Electrical Engineering Department University College LondonLondonWC1E 7JEEngland Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt

The ever-growing available visual data(i.e.,uploaded videos and pictures by internet users)has attracted the research community’s attention in the computer vision ***,finding efficient solutions to extract knowledge from these sources is ***,the BlazePose system has been released for skeleton extraction from images oriented to mobile *** this skeleton graph representation in place,a Spatial-Temporal Graph Convolutional Network can be implemented to predict the *** hypothesize that just by changing the skeleton input data for a different set of joints that offers more information about the action of interest,it is possible to increase the performance of the Spatial-Temporal Graph Convolutional Network for HAR ***,in this study,we present the first implementation of the BlazePose skeleton topology upon this architecture for action ***,we propose the Enhanced-BlazePose topology that can achieve better results than its ***,we propose different skeleton detection thresholds that can improve the accuracy performance even *** reached a top-1 accuracy performance of 40.1%on the Kinetics *** the NTU-RGB+D dataset,we achieved 87.59%and 92.1%accuracy for Cross-Subject and Cross-View evaluation criteria,respectively.

关键词： Action recognition BlazePose graph neural network OpenPose skeleton spatial temporal graph convolution network

Advanced Guided Whale Optimization Algorithm for Feature Selection in BlazePose Action Recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第9期37卷 2767-2782页

作者： Motasem S.Alsawadi El-Sayed M.El-kenawy miguel rio Electronic and Electrical Engineering Department University College LondonLondonWC1E7JEEngland Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt

The BlazePose,which models human body skeletons as spatiotem-poral graphs,has achieved fantastic performance in skeleton-based action *** extraction from photos for mobile devices has been made possible by the BlazePose system.A Spatial-Temporal Graph Con-volutional Network(STGCN)can then forecast the *** Spatial-Temporal Graph Convolutional Network(STGCN)can be improved by simply replacing the skeleton input data with a different set of joints that provide more information about the activity of *** the other hand,existing approaches require the user to manually set the graph’s topology and then fix it across all input layers and *** research shows how to use the Statistical Fractal Search(SFS)-Guided whale optimization algorithm(GWOA).To get the best solution for the GWOA,we adopt the SFS diffusion algorithm,which uses the random walk with a Gaussian distribution method common to growing *** values are transformed into binary to apply to the feature-selection problem in conjunction with the BlazePose skeletal topology and stochastic fractal search to construct a novel implementation of the BlazePose topology for action *** our experiments,we employed the Kinetics and the NTU-RGB+D *** achieved actiona accuracy in the X-View is 93.14%and in the X-Sub is 96.74%.In addition,the proposed model performs better in numerous statistical tests such as the Analysis of Variance(ANOVA),Wilcoxon signed-rank test,histogram,and times analysis.

关键词： BlazePose metaheuristics convolutional networks feature selection action recognition

Recent advances and applications of machine learning in solidstate materials science

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

npj Computational Materials 2019年第1期5卷 394-429页

作者： Jonathan Schmidt Mário R.G.Marques Silvana Botti miguel A.L.Marques Institut für Physik Martin-Luther-Universität06120 Halle-WittenbergHalle(Saale)Germany Institut für Festkörpertheorie und-optik Friedrich-Schiller-Universität JenaMax-Wien-Platz 107743 JenaGermany

One of the most exciting tools that have entered the material science toolbox in recent years is machine *** collection of statistical methods has already proved to be capable of considerably speeding up both fundamental and applied *** present,we are witnessing an explosion of works that develop and apply machine learning to solid-state *** provide a comprehensive overview and analysis of the most recent research in this *** a starting point,we introduce machine learning principles,algorithms,descriptors,and databases in materials *** continue with the description of different machine learning approaches for the discovery of stable materials and the prediction of their crystal *** we discuss research in numerous quantitative structure–property relationships and various approaches for the replacement of first-principle methods by machine *** review how active learning and surrogate-based optimization can be applied to improve the rational design process and related examples of *** major questions are always the interpretability of and the physical understanding gained from machine learning *** consider therefore the different facets of interpretability and their importance in materials ***,we propose solutions and future research paths for various challenges in computational materials science.

关键词： learning gained starting

A different vision of translational research in biomarker discovery: a pilot study on circulatory mitochondrial proteins as Parkinson’s disease potential biomarkers

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Translational Neurodegeneration 2020年第2期9卷 118-131页

作者： Sandra I.Anjo Patrícia Valério dos Santos Luiza Rosado Graça Baltazar Inês Baldeiras Diana Pires Andreia Gomes Cristina Januário miguel Castelo-Branco Mário Grãos Bruno Manadas CNC-Center for Neuroscience and Cell Biology University of CoimbraCoimbraPortugal Faculty of Medicine University of CoimbraCoimbraPortugal Centro de Investigação em Ciências da Saúde(CICS-UBI) Universidade da Beira InteriorCovilhãPortugal Centro Hospitalar Cova da Beira E.P.ECovilhãPortugal Neurology Department Centro Hospitalar e Universitário de CoimbraCoimbraPortugal Coimbra Institute for Biomedical Imaging and Translational Research(CIBIT) CoimbraPortugal Biocant Biotechnology Transfer AssociationCantanhedePortugal Institute for Interdisciplinary Research University of Coimbra(IIIUC)CoimbraPortugal

Background The identification of circulating biomarkers that closely correlate with Parkinson’s Disease(PD)has failed several times in the ***,in this pilot study,a translational approach was conducted,allowing the evaluation of the plasma levels of two mitochondrial-related proteins,whose combination leads to a robust model with potential diagnostic value to discriminate the PD patients from matched *** The proposed translational approach was initiated by the analysis of secretomes from cells cultured under control or well-defined oxidative stress conditions,followed by the identification of proteins related to PD pathologic mechanisms that were altered between the two *** pipeline was further translated into the analysis of undepleted plasma samples from 28 control and 31 PD *** From the secretome analysis,several mitochondria-related proteins were found to be differentially released between control and stress conditions and to be able to distinguish the two ***,two mitochondrial-related proteins were found to be significantly changed in a PD cohort compared to matched ***,a linear discriminant model with potential diagnostic value to discriminate PD patients was obtained using the combination of these two *** proteins are associated with apoptotic mitochondrial changes,which may correspond to potential indicators of cell ***,one of these proteins,the VPS35 protein,was reported in plasma for the first time,and its quantification was only possible due to its previous identification in the secretome *** In this work,an adaptation of a translational pipeline for biomarker selection was presented and transposed to neurological diseases,in the present case Parkinson’s *** novelty and success of this pilot study may arise from the combination of:i)a translational research pipeline,where plasma samples are interrogated using knowledge previously ob

关键词： Mitochondrial-related proteins SWATH-MS Parkinson's disease Biomarker discovery Blood-biomarker Secretomes Oxidative stress

Neuropsychological features of progranulin-associated frontotemporal dementia: a nested case-control study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2021年第5期16卷 910-915页

作者： Marisa Lima miguel Tábuas-Pereira Diana Duro João Durães Daniela Vieira Inês Baldeiras Maria Rosário Almeida Isabel Santana Neurology Department Centro Hospitalar e Universitário de CoimbraCoimbraPortugal University of Coimbra Faculty of MedicineCoimbraPortugal University of Coimbra Center for Neuroscience and Cell BiologyCoimbraPortugal University of Coimbra Center for Research in Neuropsychology and Cognitive Behavioral Intervention(CINEICC)Faculty of Psychology and Educational SciencesCoimbraPortugal

The distinction between sporadic and genetic behavioural-variant frontotemporal dementia(bvFTD)regarding some neuropsychological(NP)features remains ***,progranulin(GRN)-associated bvFTD frequently presents with early episodic memory impairment and some degree of parietal dysfunction which are supporters of Alzheimer’s disease(AD)*** this context,we aimed to characterize the NP profile of GRN-bvFTD as compared to sporadic-bvFTD and AD in patients with mild dementia(Mini-Mental State Examination score≥17 and Clinical Dementia Rating Scale score≤*** identified 21 patients at Centro Hospitalar e Universitário de Coimbra,Portugal with GRN mutations belonging to fifteen different *** our focus was bvFTD variants,FTD-related aphasic forms(3 patients)were *** remaining 18 GRN-bvFTD were further matched with 18 sporadic-bvFTD and 18 AD patients according to disease staging,age and *** patients completed the Mini-Mental State Examination,Montreal Cognitive Assessment(MoCA)and a comprehensive NP assessment *** were converted into *** between groups in individual NP measures and NP domains were assessed through non-parametric tests(Kruskal-Wallis test analysis)and eta squared(ŋ2)was calculated as a measure of effect *** comparisons show that GRN patients have worse performances on verbal retrieval processes(P=0.039,ŋ2=0.110)and visuoconstructive abilities(P=0.039,ŋ2=0.190)than sporadic bvFTD *** compared to AD,GRN patients present a higher impairment in frontal(P=0.001,ŋ2=0.211)and parietal(P=0.041,ŋ2=0.129)measures and a better performance in memory tasks(P=0.020,ŋ2=0.120).Sporadic-bvFTD forms are worse than AD in frontal measures(P=0.032,ŋ2=0.200),being better in both memory(P=0.010,ŋ2=0.131)and visuospatial skills(P=0.023,ŋ2=0.231).Considering these results,we conclude that GRN-bvFTD patients present a NP profile that associates the typical patterns of FTD and AD ***

关键词： Alzheimer’s disease behavioral variant frontotemporal dementia cognitive profile frontotemporal dementia genetics memory neuropsychology progranulin visuoconstructive ability

Behavior of wood basic density according to environmental variables

在线全文

学校读者我要写书评

暂无评论

Journal of Forestry Research 2022年第2期33卷 497-505页

作者： Gabriel Marcos Vieira Oliveira JoséMárcio de Mello Carlos Rogério de Mello JoséRoberto Soares Scolforo Eder Pereira miguel Thiago Campos Monteiro Brazil Institute of Agricultural and Forestry Defense of Espírito Santo(IDAF) Av.Lourival Lugon Moulinnº300CentroJerônimo MonteiroES CEP:29.550-000Brazil Department of Forestry Sciences Universidade Federal de Lavras-UFLACaixa Postal 3037LavrasMG CEP:37.200-000Brazil Engineering Department Universidade Federal de Lavras-UFLACaixa Postal 3037LavrasMG CEP:37.200-000Brazil Forestry Engineering Department Faculdade de TecnologiaUniversity of Brasilia-UnBCampus Universitário Darcy RibeiroCaixa Postal 4357Asa Norte-BrasíliaDF CEP:70910-900Brazil Department of Forestry Engineering and Technology Universidade Federal do Paraná-UFPRAv.Pref.Lothário Meissner632Jardim BotânicoCuritibaPR CEP:80.210-170Brazil

The relationships between climate conditions and wood density in tropical forests are still poorly *** quantify spatial dependence of wood density in the state of Minas Gerais(MG,Brazil),map spatial distribution of density,and correlate density with climate variables,we extracted data from the Forest Inventory of Minas Gerais for 1988 trees scaled throughout the territory and measured wood density of discs removed from the *** variables were extracted from the database of the Ecological-Economic Zoning of Minas *** spatial analysis,tree densities were measured at 44 georeferenced sampling *** data were subjected to exploratory analysis,variography,cross-validation,model selection,and ordinary *** relationships between wood density and environmental variables were calculated using dispersion matrices,linear correlation,and *** density proved to be highly spatially dependent,reaching a correlation of 96%,and was highly continuous over a distance of 228 *** distribution of wood density followed a continuous gradient of 514-659 kg m^(−3),enabling corre-lation with environment *** was correlated with mean annual precipitation(−0.57),temperature(0.63),and evapotranspiration(0.83).Geostatistical methods proved useful in predicting wood density in native tropical forests with different climate *** results confirmed the sensitivity of wood density to climate change,which could affect future carbon stock in forests.

关键词： Biomass Climate variables Geostatistics Hardwood Forest inventory Minas Gerais

Trivial and Simple Spectrum for SL(d,R) Cocycles with Free Base and Fiber Dynamics

在线全文

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2015年第7期31卷 1113-1122页

作者： Mrio BESSA Paulo VARANDAS Departamento de Matemtica Universidade da Beira InteriorRua Marquês d'vila e Bolama6201-001 CovilhPortugal Departamento de Matemtica Universidade Federal da BahiaAv.Ademar de Barros s/n40170-110 SalvadorBrazil

Let ACD（M, SL（d,R）） denote the pairs （f, A） so that f∈ A C Diff^1（M） is a C^1-Anosov transitive diffeomorphisms and A is an SL（d,R） cocycle dominated with respect to f. We prove that open and densely in ACD（M, SL（d,R））, in appropriate topologies, the pair （f,A） has simple spectrum with respect to the unique maximal entropy measure μf. Then, we prove prevalence of trivial spectrum near the dynamical cocycle of an area-preserving map and also for generic cocycles in AUtLeb（M） × LP（M, SL（d, R））.

关键词： Linear cocycles Lyapunov exponents Anosov diffeomorphisms topological conjugacy,maximal entropy measures

Quantitative Progress Evaluation of Post-stroke Patients Using a Novel Bimanual Cable-driven Robot

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2021年第6期18卷 1331-1343页

作者： Thiago Alves Rogério Sales Gonçalves Giuseppe Carbone Laboratory of Automation and Robotics School of Mechanical EngineeringFederal University of UberlândiaUberlândia38400-902Brazil Department of Mechanical Energy and Management EngineeringUniversity of Calabria87036RendeItaly

Rehabilitation is the most effective way to reduce motor impairments in post-stroke *** process demands several hours with a specialized *** resources and personnel shortages,the literature reports a high interest in robotic assisted rehabilitation ***,cable-driven robotic architectures are attracting significant research interest for post-stroke ***,the existing cable-driven robots are mostly unilateral devices allowing the rehabilitation only of the most affected *** leaves unaddressed the rehabilitation of bimanual activities,which are predominant within the common Activities of Daily Living(ADL).Thus,this paper presents a specific novel design to achieve bimanual rehabilitation tasks that has been named as BiCAR ***,this paper provides a full insight on the BiCAR system as well as on its dedicated developed software *** particular,BiEval software has been developed as based on a serious game strategy and a virtual reality environment to track the patient exercising duration,motion ranges,speeds,and forces over time for achieving a quantitative assessment of the rehabilitation ***,the paper presents the BiCAR/BiEval capabilities by referring to a pilot Randomized Controlled Trial(RCT).The clinical trials have been used to validate the BiCAR/BiEval in terms of engineering feasibility and user acceptance to achieve an innovative cost-oriented integrated hardware/software device for the bimanual assistive rehabilitation of post-stroke patients.

关键词： Cable-driven robots Low cost Stroke rehabilitation Bimanual Progress tracking Serious games

Comparison of Classical Models for Evaluating the Heat Requirements of Olive(Olea europeae L.) in Portugal

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Integrative Plant Biology 2006年第6期48卷 664-671页

作者： Helena Ribeiro Mário Cunha Ilda Abreu Autonomous Section of Agricultural Sciences Faculty of Sciences University of Porto4485-661 VairaoPortugal Department of Botany Faculty of SciencesUniversity of Porto1191-4150 PortoPortugal Institute of Agricultural Sciences and Technology 4485-661 VairaoPortugal Department of Botany Faculty of Sciences University of Porto1191-4150 PortoPortugal Institute for Molecular and Cell Biology 823-4150 PortoPortugal

The aim of the present study was to compare the accuracy and reproducibility of six statistical models for the calculation of olive （Olea europeae L.） heat requirements to trigger the onset of flowering in three Portuguese regions： Reguengos de Monsaraz, Valenga do Douro, and Braga. Other alms were to ascertain the date on which the heat-accumulation period started and the threshold temperatures above which the development of reproductive structures starts in olives. The starting and peak dates for the regional O. europeae flowering season were estimated by monitoring airborne pollen from 1998 to 2004 using ＂Cour＂- type samplers. The threshold temperature values calculated for the three regions were very similar （9.0 ℃ for Valenca do Douro, 9.2 ℃ for Reguengos de Monsaraz, and 9.7 ℃ for Braga）. The accumulated daily mean temperature model had less interannual and inter-regional variation, showing best predictive results for 2004, with absolute differences between the observed and predicted dates of 4 d in Reguengos de Monsaraz and 2 d In Valenca do Douro and Braga for the onset of flowering date and of 2 d In Reguengos de Monsaraz, 7 d in Valenca do Douro, and 4 d in Braga for peak flowering dates. This model was the most accurate, reproducible, and operational to calculate heat requirements for olives to flower, with an average mean temperature accumulation of 1 446 ℃ In Reguengos, 1 642 ℃ in Valenga do Douro, and 1 703℃ In Braga to reach the onset of flowering. The best initial date for this accumulation was 1 January.

关键词： flowering season heat requirements olives pollen Portugal