KiMoRe Wrangling and Analysis
Matlab wrangling and reshaping
You need to place the Kimore Dataset ../Kimore in relation to this repository (of course you can change this but you need to change the code as well), see:
Standardizing the data and checking for data quality with the Matlab script matlab_to_R_batch_converter.m (found from matlab-folder)that exports the checked data as .mat and .hdf5 files, with the following hierarchical data structure:
Joint Data: Subject Code -> excercises -> Ex_idx -> joints -> Joint_Name - > 9 columns [0-8] with as many samples as recorded Column names: time_ms cameraX cameraY cameraZ confidenceState AbsQuat_1 AbsQuat_2 AbsQuat_3 AbsQuat_4
Metadata: gender (0 = female, 1 = male) / age (in years) / group and here the groupis your classification label in integers with the following LUT
- CG-E = 0 (Control, Expert)
- CG-NE = 1 (Control, Non-Expert)
- GPP-S = 2 (Stroke)
- GPP-P = 3 (Parkinson’s disease)
- GPP-B = 4 (Low Back Pain)
Upper row contains RAW values (left, position, right, orientation), and the bottom row contains the timeseries with estimated (non-tracked) joint positions and orientations dropped. https://youtu.be/HVF_G9zguJc
KiMoRe
See details about the dataset on the Wiki page
Capecci, M., Ceravolo, M. G., Ferracuti, F., Iarlori, S., Monteriù, A., Romeo, L., & Verdini, F. (2019). The KIMORE dataset: KInematic assessment of MOvement and clinical scores for remote monitoring of physical REhabilitation. IEEE Transactions on Neural Systems and Rehabilitation Engineering ( Volume: 27 , Issue: 7 , July 2019 ). https://doi.org/10.1109/TNSRE.2019.2923060