39
Correlations of Gait Phase Kinematics and Cortical EEG: Modelling Human Gait with Data…
DOI: http://dx.doi.org/10.5772/intechopen.88465
Support vector machines had 58–59% training accuracies and so did J48 algorithm. Random tree had 67% while Naïve Bayes and linear SVM showed more than
98% accuracy perhaps attributed to complex decision boundaries.
4. Discussion
Torque-based reconstructions of gait from mobile phone triaxial accelerometer
data may help identifying swing and stance phases in gait in addition to allowing
Figure 5.
Spectral changes for swing and stance phases of a gait cycle. (A) Swing phase of gait cycle showing higher delta
and theta bands in frontal regions (F8, F3 and F7) electrodes. (B) Stance phase of gait cycle showing higher
delta band parietal regions (P7 and P8). (C and D) Scalp maps for frequency ranges during swing (C) and
stance gait phases (D).
Figure 6.
Classification of gait data using machine learning algorithms. Naïve Bayes (NB), J48 decision tree, random
tree, support vector machine algorithms with polynomial, linear, radial and sigmoidal and radial basis
functions allowed classifying gait data.
Correlations of Gait Phase Kinematics and Cortical EEG: Modelling Human Gait with Data…
DOI: http://dx.doi.org/10.5772/intechopen.88465
Support vector machines had 58–59% training accuracies and so did J48 algorithm. Random tree had 67% while Naïve Bayes and linear SVM showed more than
98% accuracy perhaps attributed to complex decision boundaries.
4. Discussion
Torque-based reconstructions of gait from mobile phone triaxial accelerometer
data may help identifying swing and stance phases in gait in addition to allowing
Figure 5.
Spectral changes for swing and stance phases of a gait cycle. (A) Swing phase of gait cycle showing higher delta
and theta bands in frontal regions (F8, F3 and F7) electrodes. (B) Stance phase of gait cycle showing higher
delta band parietal regions (P7 and P8). (C and D) Scalp maps for frequency ranges during swing (C) and
stance gait phases (D).
Figure 6.
Classification of gait data using machine learning algorithms. Naïve Bayes (NB), J48 decision tree, random
tree, support vector machine algorithms with polynomial, linear, radial and sigmoidal and radial basis
functions allowed classifying gait data.