Advances in Neural Signal Processing
34
GAIT include floor based sensors (FS), wearable sensors (WS) and non-wearable
sensors (NWS) techniques [6]. In techniques involving NWS, gait has been captured using cameras with video and image processing allowing features to attribute
to gait patterns [7]. FS based techniques use force plates located on the ground to
extract the walking parameters through pressure estimates and ground reaction
forces [8]. In WS based techniques, sensors like accelerometers [9–11], gyroscopes,
goniometers, etc. attached to the different biomechanical parts of the human
body frame measure gait patterns during walking [12]. Peak detection methods in
algorithms allow gauging gait events like heel strike, swing and stance from accelerometer and gyroscope data [13–16].
Aiming towards potential applications in medicine, it has been noted that
gait and posture control in patients with neurodegenerative disorders become
irregular due to weakening of motor neurons that controls the muscles [17].
Neurodegenerative diseases including the Parkinson’s and Huntington disease result
in progressive degeneration of neurons causes changes in neuromuscular control
[18]. In clinical analysis, in order to understand the patient’s walking capability and
movement tracking usually require expensive (cost, effort and time) methodologies
and structured laboratories [19, 20]. A study by Hausdorff et al. [21] had demonstrated the differences between gait cycles and subphases duration in Parkinson’s
patients compared to normal subjects. Also, magnitude difference between gait
stride intervals of human subjects with neurodegenerative conditions have been
analysed by using (DFAT) detrended fluctuation analysis techniques [22].
Research progress in understanding the brain function during gait intent, but
the information on movement-related cortical activity, neural circuit mechanisms
and computations underlying the control of upright walking in humans are yet to
be understood completely [23, 24]. Studies have shown rhythmic foot and leg movements recruit primary motor cortex [25, 26], while fNIRS has shown involvement of
frontal, premotor and supplementary motor areas during walking [27, 28]. Recent
literature have indicated augmented beta oscillations during double support phases
of the gait cycle (event-related synchronization, ERS) and to be suppressed during the swing and single support phases (event-related desynchronization, ERD)
[29–35]. Other studies have shown enhanced gamma oscillations during early and
mid-swing phases of gait cycle and suppressed gamma rhythms towards the end of
the swing phase and during the double support [36–40].
Studies involving other techniques such as single-photon emission computed
tomography (SPECT) have reported neural characteristics during voluntary
walking; studies [41, 42] using SPECT evaluated changes in the brain activity as a
result of walking, and identified the SMA, S1, M1, cerebellum, and basal ganglia
functioning as the control mechanisms of bipedal gait. Another SPECT study [43],
investigated cortical activation during treadmill walking and found network activation in the premotor cortex, somatosensory association cortex, cingulate cortex
and brain stem apart from the structures reported [41]. In both tomography SPECT
studies, walking tasks were carried out prior to image acquisition.
Additionally, neurodegenerative diseases that relate to gait effects can be classified using machine learning tools as a decision support to clinicians for better
prediction [44] of patient conditions. Gait disorder related to amyotrophic lateral
sclerosis (ALS) have been classified by using wavelet-based scheme and features
reflect regularity and gait coherence between both limbs as seen from the approximation part of the raw gait signal [45].
Identification and classification of human gait using low cost experimental
techniques are crucial and necessary for the developing countries like India.
Current diagnosing techniques for gait related disorders are more expensive
and inaccessible to the common people. The main purpose of this study was to
34
GAIT include floor based sensors (FS), wearable sensors (WS) and non-wearable
sensors (NWS) techniques [6]. In techniques involving NWS, gait has been captured using cameras with video and image processing allowing features to attribute
to gait patterns [7]. FS based techniques use force plates located on the ground to
extract the walking parameters through pressure estimates and ground reaction
forces [8]. In WS based techniques, sensors like accelerometers [9–11], gyroscopes,
goniometers, etc. attached to the different biomechanical parts of the human
body frame measure gait patterns during walking [12]. Peak detection methods in
algorithms allow gauging gait events like heel strike, swing and stance from accelerometer and gyroscope data [13–16].
Aiming towards potential applications in medicine, it has been noted that
gait and posture control in patients with neurodegenerative disorders become
irregular due to weakening of motor neurons that controls the muscles [17].
Neurodegenerative diseases including the Parkinson’s and Huntington disease result
in progressive degeneration of neurons causes changes in neuromuscular control
[18]. In clinical analysis, in order to understand the patient’s walking capability and
movement tracking usually require expensive (cost, effort and time) methodologies
and structured laboratories [19, 20]. A study by Hausdorff et al. [21] had demonstrated the differences between gait cycles and subphases duration in Parkinson’s
patients compared to normal subjects. Also, magnitude difference between gait
stride intervals of human subjects with neurodegenerative conditions have been
analysed by using (DFAT) detrended fluctuation analysis techniques [22].
Research progress in understanding the brain function during gait intent, but
the information on movement-related cortical activity, neural circuit mechanisms
and computations underlying the control of upright walking in humans are yet to
be understood completely [23, 24]. Studies have shown rhythmic foot and leg movements recruit primary motor cortex [25, 26], while fNIRS has shown involvement of
frontal, premotor and supplementary motor areas during walking [27, 28]. Recent
literature have indicated augmented beta oscillations during double support phases
of the gait cycle (event-related synchronization, ERS) and to be suppressed during the swing and single support phases (event-related desynchronization, ERD)
[29–35]. Other studies have shown enhanced gamma oscillations during early and
mid-swing phases of gait cycle and suppressed gamma rhythms towards the end of
the swing phase and during the double support [36–40].
Studies involving other techniques such as single-photon emission computed
tomography (SPECT) have reported neural characteristics during voluntary
walking; studies [41, 42] using SPECT evaluated changes in the brain activity as a
result of walking, and identified the SMA, S1, M1, cerebellum, and basal ganglia
functioning as the control mechanisms of bipedal gait. Another SPECT study [43],
investigated cortical activation during treadmill walking and found network activation in the premotor cortex, somatosensory association cortex, cingulate cortex
and brain stem apart from the structures reported [41]. In both tomography SPECT
studies, walking tasks were carried out prior to image acquisition.
Additionally, neurodegenerative diseases that relate to gait effects can be classified using machine learning tools as a decision support to clinicians for better
prediction [44] of patient conditions. Gait disorder related to amyotrophic lateral
sclerosis (ALS) have been classified by using wavelet-based scheme and features
reflect regularity and gait coherence between both limbs as seen from the approximation part of the raw gait signal [45].
Identification and classification of human gait using low cost experimental
techniques are crucial and necessary for the developing countries like India.
Current diagnosing techniques for gait related disorders are more expensive
and inaccessible to the common people. The main purpose of this study was to