Data-Driven Goal Recognition in Transhumeral Prostheses Using Process Mining Techniques

The evaluation results can be replicated with codebase experiments_with_10_subjects.zip. The codebase running_example.zip provide the tool to replicate the example in section IV. The 30 features (f1-f30) used in the running example are: Sfe, Saa, Scpr, Scde, Tfe, Tb, BSH_MAV, TLAH_SC, TLAH_MAV, TLH_MAV, DA_MAV, DM_MAV, DP_MAV, BLH_RMS, BSH_ZC, BLH_ZC, TLAH_ZC, TLH_ZC, DA_ZC, DM_ZC, DP_ZC, BSH_SC, BLH_SC, DA_SC, DP_SC, dSfe, dSaa, dScpr, dTfe, dTb. The meaning of each feature can be found here: https://github.com/tianshi-yu/UpperLimbReachingData_HRL_Unimelb. The instructions of running the codes can be found here: https://github.com/zihangs/target_poses_recognition_pm.