Title | ||
---|---|---|
IMU, sEMG, or their cross-correlation and temporal similarities: Which signal features detect lateral compensatory balance reactions more accurately? |
Abstract | ||
---|---|---|
•This paper investigates machine learning-based models trained on kinematic (IMU), sEMG, and a proposed “Hybrid” feature set towards detecting lateral compensatory stepping reactions (CBRs).•Using a random forest classifier with 263 features, CBR detection (i.e., CBR vs normal gait) accuracies were 90.50% and 99.33% using sEMG- and IMU-based features, respectively.•For multiclass identification (i.e., side-step vs cross-over vs normal gait), accuracies dropped to 80.00% (sEMG) and 93.33% (IMU).•The findings demonstrate that IMU-based features are favourable over sEMG and Hybrid features for the task of CBR detection, with incremental value for type identification.•Shank as the best overall location for the multiclass identification, and chest as the most accurate for CBR detection. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.cmpb.2019.105003 | Computer Methods and Programs in Biomedicine |
Keywords | Field | DocType |
Compensatory balance reactions,Wearable inertial measurement units,Machine learning,Electromyography,Fall risk assessment | Computer vision,Kinematics,Activity recognition,Gait,Computer science,Electromyography,Artificial intelligence,Inertial measurement unit,Random forest,Classifier (linguistics),Cross-validation | Journal |
Volume | ISSN | Citations |
182 | 0169-2607 | 0 |
PageRank | References | Authors |
0.34 | 0 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mina Nouredanesh | 1 | 0 | 0.34 |
James Yungjen Tung | 2 | 22 | 4.59 |