Feature Extraction Methods Using Lower-limb Electromyogram Signals for Intention Recognition of Gait Initiation
- Feature Extraction Methods Using Lower-limb Electromyogram Signals for Intention Recognition of Gait Initiation
- 정상훈; 김영훈; 김형민; 황요하; 김승종; 안진웅; 이종민
- Issue Date
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
- Intention recognition of gait initiation is important for first step control of lower-limb exoskeleton gait. Using surface electromyogram (sEMG) signals from the soleus and gluteus medius, we were able to detect gait initiation in conjunction with the side of first step. Two feature extraction methods are suggested; waveform lengths of soleus sEMG signals, and statistics of cross-correlation coefficients between sEMG signals of two muscles. Our results indicate that the performances of both methods make them suitable for first step control of exoskeleton gait with delay times less than 300 msec and detection rates above 90%.
- Appears in Collections:
- KIST Publication > Conference Paper
- Files in This Item:
There are no files associated with this item.
- RIS (EndNote)
- XLS (Excel)
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.