965 53 14505 5 44771 document 14505 StepDetectionStudy-20210121T123804Z-001.zip application/zip 2c04fe652c2edd61d75862aa87f09163 MD5 716182198 2021-01-29 15:06:21 https://researchdata.bath.ac.uk/965/1/StepDetectionStudy-20210121T123804Z-001.zip 965 1 1 application/zip other Data and Google Colab (Jupyter) notebooks to replicate algorithm development and testing en public cc_gnu_lgpl

StepDetectionStudy-20210121T123804Z-001.zip

data 14933 3 46783 document 14933 README.md text/plain 078f7f862769118f7f18adc97b3b2346 MD5 4641 2021-05-03 10:22:27 https://researchdata.bath.ac.uk/965/2/README.md 965 2 2 text/plain other README file with instruction on how to use FootNet and how to navigate the associated Github repository (https://github.com/adrianrivadulla/FootNet) en public cc_gnu_lgpl

README.md

documentation 14935 4 46796 document 14935 Technical-Details.md text/plain 69c6cea1cb2d9da94e9941aef7e77cbd MD5 1266 2021-05-04 12:53:10 https://researchdata.bath.ac.uk/965/3/Technical-Details.md 965 3 3 text/plain other Instructions on how to run the notebooks en public cc_gnu_lgpl

Technical-Details.md

documentation archive 10696 disk0/00/00/09/65 2021-07-26 09:54:57 2024-07-15 11:09:56 2021-07-26 09:54:57 data_collection show Rodriguez Rivadulla Adrian A.Rodriguez.Rivadulla@bath.ac.uk 0000-0003-4046-4750 University of Bath TRUE Chen Xi xc841@bath.ac.uk 0000-0002-3577-3308 University of Bath FALSE Weir Gillian 0000-0001-5147-8213 University of Massachusetts FALSE Cazzola Dario D.Cazzola@bath.ac.uk 0000-0001-7877-6755 University of Bath FALSE Trewartha Grant G.Trewartha@tees.ac.uk 0000-0002-9021-8956 University of Bath FALSE Hamill Joseph 0000-0003-0802-9708 University of Massachusetts FALSE Preatoni Ezio E.Preatoni@bath.ac.uk 0000-0001-5383-7072 University of Bath FALSE GS0020 dept_health treadmill running, biomechanics, running gait, locomotion, gait, running, kinematics, ground reaction forces The project directory StepDetectionStudy is organised as follows: - Data > OriginalDatasets: Folder containing the entire datasets (*_dataset.npy files). - Data > DataFolds.npy: File containing the training data grouped in 5 folds. - Data > TestingSet.npy: File containing the testing set. Data are organised as Python dictionaries containing the kinematic input features ['X'], label vectors ['Y'], metadata about the trials ['meta'] and vertical GRF ['GRFv']. Each of those dictionary keys contains a list with nested lists with the structure participant > trial > stride. For instance, `dataset['X'][0][0][0]` accesses the kinematic input features characterising the first stride recorded in the first trial of the first participant in dataset. - CrossValidation > Models: Folder containing the five models developed during cross validation. - CrossValidation > Results: Folder containing the summary performance metrics for each model on its corresponding validation set and Bland-Altman plots comparing foot strike, toe off and contact times as predicted by FootNet vs gold standard method. - FinalTest > FootNet_best_candidate: Folder containing the best set of parameters resulting from cross validation. Summary performance metrics on testing set and Bland-Altman plots comparing foot strike, toe off and contact times as predicted by FootNet vs gold standard method. - FinalTest > y_and_yhat.mat: File containing testing predictions, target labels and metadata from testing stride cycles for posterior analyses in Matlab presented in the paper. - FinalModel: Folder containing the final updated model resulting from FinalTest as a SavedModel directory (Tensorflow model format) and as .h5. - Notebooks > TrainTest_Split.ipynb: Google Colab (Jupyter) notebook demonstrating how the dataset splitting was performed, including training and testing (70/30) and further folding of training dataset in 5 folds. - Notebooks > CrossValidation.ipnyb. Google Colab (Jupyter) notebook that performs 5-fold cross-validation and selects the best set of weights as best candidate for the final test. - Notebooks > FinalTest.ipnyb: Google Colab (Jupyter) notebook that updates the best candidate model resulting from cross-validation with the 5 folds as training set and performs the final test on the testing set. This dataset includes the input features and target labels needed to train and test FootNet. The input features include the distal tibia anteroposterior velocity, ankle plantar/dorsi flexion angle and foot centre of mass anteroposterior and vertical velocities. Additionally, ground reaction force data and trial names are also included. 2021-07-26 University of Bath public https://github.com/adrianrivadulla/FootNet GitHub repository including further details on the algorithm, its development and use RightsHolder University of Bath University of Bath https://doi.org/10.13039/501100000835 PhD studentship NURVV PhD studentship This dataset includes data coming from five different datasets collected in three independent laboratories (see associated publication for more details). It includes treadmill running kinematics and kinetics processed to obtain the previously mentioned variables and chopped in running gait cycles. The original datasets were fully reprocessed as described in the Methods section of the associated publication. en 1 10.15125/BATH-00965 https://doi.org/10.1371/journal.pone.0248608 pub https://doi.org/10.5281/zenodo.5532715 data open