Classification of desired motion speed — A study based on cerebral hemoglobin information

To achieve more intelligent performance for walking-assistive devices, spontaneous motion intention of walking speed should be identified for providing a control command. In this paper, cerebral hemoglobin information was analyzed to recognize three levels of walking speed: low speed, medium speed and high speed. Eleven subjects carried out walking experiment in three speed levels with cerebral hemoglobin information being recorded. Oxygenated hemoglobin (oxyHb) was mainly analyzed. OxyHb signals were decomposed into four frequency bands ((I) 0Hz~0.03Hz, (II) 0.03Hz~0.06Hz, (III) 0.06Hz~0.09Hz, (IV) 0.09Hz~0.12Hz) by using wavelet packets. A novel method of time-frequency-space analysis was proposed to seek for significant regional features by combining the significant channels and their adjacent areas. Support vector machine (SVM) method was used for pattern recognition, and the corresponding recognition rate of three levels of speed achieved to 75%. The results indicate that the proposed method of time-frequency-space analysis is feasible for recognizing expected walking speed, and cerebral hemoglobin information could reflect humans' spontaneous motion intention. Moreover, it may provide a more intelligent control method for walking-assistive devices and promote its development in the future.