Closed rmndrs89 closed 3 months ago
Since the GSD algorithm requires at least 5 consecutive steps to detect the event as a gait sequence, the algorithm fails to identify the gait sequence for this special case. The issue should be solved in a way that 'gait_sequences' in https://github.com/neurogeriatricskiel/NGMT/blob/main/ngmt/modules/icd/_paraschiv.py should be optional.
However, still we can apply ICD to the referred data. For this purpose, we need to change the algorithm in the following way. When 'gait_sequences' are not provided, the ICD should create artificial gait sequences that cover the active parts of the data and then identify initial contacts within defined limits.
The issue is closed since it is mentioned here GSD Issues in an organized way.
Hi @masoudabedinifar,
see here one of the errors for a single participant, when trying to analyze the Timed Up and Go trials from the Keep Control project. The corresponding notebook can be found here: paper/keepcontrol_tug.ipynb
We should check this for a couple of participants in the Keep Control dataset.
Best regards, Robbin