PCAfold: Python software to generate, analyze and improve PCA-derived low-dimensional manifolds

Zdybał, Kamila; Armstrong, E. F.; Parente, Alessandro; Sutherland, James C.

doi:10.1016/j.softx.2020.100630

Cited by 19 publications

(12 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several reports have shown that the SVM classifier is a crucial tool for classification problems in sports medicine and lower limb biomechanics ( Xiang et al, 2022 ; Phinyomark et al, 2015 ; Christian et al, 2016 ). In the previous studies, an unsupervised PCA algorithm was commonly used in data preprocessing for discovering the underlying low-dimensional manifolds in high-dimensional datasets ( Zdybał et al, 2020 ) and for data extraction consideration ( Wu and Wang, 2008 ; Taylor et al, 2013 ; Clermont et al, 2017 ; Suda et al, 2020 ). Eleven low-dimensional features were extracted in our study, explaining 90% cumulative variance of the original data.…”

Section: Discussionmentioning

confidence: 99%

Automatic Classification of Barefoot and Shod Populations Based on the Foot Metrics and Plantar Pressure Patterns

Xiang

Mei

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

The human being’s locomotion under the barefoot condition enables normal foot function and lower limb biomechanical performance from a biological evolution perspective. No study has demonstrated the specific differences between habitually barefoot and shod cohorts based on foot morphology and dynamic plantar pressure during walking and running. The present study aimed to assess and classify foot metrics and dynamic plantar pressure patterns of barefoot and shod people via machine learning algorithms. One hundred and forty-six age-matched barefoot (n = 78) and shod (n = 68) participants were recruited for this study. Gaussian Naïve Bayes were selected to identify foot morphology differences between unshod and shod cohorts. The support vector machine (SVM) classifiers based on the principal component analysis (PCA) feature extraction and recursive feature elimination (RFE) feature selection methods were utilized to separate and classify the barefoot and shod populations via walking and running plantar pressure parameters. Peak pressure in the M1-M5 regions during running was significantly higher for the shod participants, increasing 34.8, 37.3, 29.2, 31.7, and 40.1%, respectively. The test accuracy of the Gaussian Naïve Bayes model achieved an accuracy of 93%. The mean 10-fold cross-validation scores were 0.98 and 0.96 for the RFE- and PCA-based SVM models, and both feature extract-based and feature select-based SVM models achieved an accuracy of 95%. The foot shape, especially the forefoot region, was shown to be a valuable classifier of shod and unshod groups. Dynamic pressure patterns during running contribute most to the identification of the two cohorts, especially the forefoot region.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Classification of Barefoot and Shod Populations Based on the Foot Metrics and Plantar Pressure Patterns

Xiang

Mei

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…1 ). The proposed algorithm is available in the PCAfold Python library [30] . The supplementary material includes an example code snippet for running the algorithm on a combustion dataset.…”

Section: Manifold-informed Subset Of State Variablesmentioning

confidence: 99%

Manifold-informed state vector subset for reduced-order modeling

Zdybał

Sutherland

Parente

2023

Proceedings of the Combustion Institute

Self Cite

View full text Add to dashboard Cite

“…In order to determine the best scaling for the input parameters, we use a recently proposed cost function, , that can help assess the quality of data parameterization for regression tasks [45,53]. By minimizing the cost value, we determine which scaling factor shall be applied on the design variables (independent variables) to yield good regressibility of each objective function (dependent variables).…”

Section: Regression Model Performancementioning

confidence: 99%

“…The closer 𝑅 2 is to unity, the better the regression model predictions. Since the overall 𝑅 2 computed for all points in the dataset can be misleading, the data matrix is divided into a number of bins (15)(16)(17)(18)(19)(20), according to the objective function under investigation, and 𝑅 2 is computed in each bin to investigate the prediction performance thoroughly [45]. With this approach, we make sure that the trained model does not focus on any specific region but represents the entire dataset well.…”

Section: Regression Model Performancementioning

confidence: 99%

Reduced-order modeling of supersonic fuel–air mixing in a multi-strut injection scramjet engine using machine learning techniques

et al. 2023

Self Cite

View full text Add to dashboard Cite

PCAfold: Python software to generate, analyze and improve PCA-derived low-dimensional manifolds

Cited by 19 publications

References 20 publications

Automatic Classification of Barefoot and Shod Populations Based on the Foot Metrics and Plantar Pressure Patterns

Automatic Classification of Barefoot and Shod Populations Based on the Foot Metrics and Plantar Pressure Patterns

Manifold-informed state vector subset for reduced-order modeling

Reduced-order modeling of supersonic fuel–air mixing in a multi-strut injection scramjet engine using machine learning techniques

Contact Info

Product

Resources

About