“You can tell by the way I use my walk.” Predicting the presence of cognitive load with gait measurements

Abstract

BackgroundThere is considerable evidence that a person’s gait is affected by cognitive load. Research in this field has implications for understanding the relationship between motor control and neurological conditions in aging and clinical populations. Accordingly, this pilot study evaluates the cognitive load based on gait accelerometry measurements of the walking patterns of ten healthy individuals (18–35 years old).MethodsData points were collected using six triaxial accelerometer sensors and treadmill pressure reports. Stride and window extraction methods were used to process these data points and separate into statistical features. A binary classification was created by using logistic regression, support vector machine, random forest, and learning vector quantization to classify cognitive load vs. no cognitive load.ResultsWithin and between subjects, a cognitive load was predicted with accuracy values ranged of 0.93–1 by all four models. Various feature selection methods demonstrated that only 2–20 variables could be used to achieve similar levels of accuracies.ConclusionCoupling sensors with machine learning algorithms to detect the most minute changes in gait patterns, most of which are too subtle to identify with the human eye, may have a remarkable impact on the potential to detect potential neuromotor illnesses and fall risks. In doing so, we can open a new window to human health and safety prevention.

Digital natives and dual task: Handling it but not immune against cognitive-locomotor interferences

“…In previous studies [25][26][27][28][29][30], changes in different parameters such as walking speed, cadence, step length, double support time etc. were computed while performing secondary tasks to assess cost of dual-tasking on gait.…”

Digital Natives and Dual Task: Handling It But Not Immune Against Cognitive-Locomotor Interferences

“…In previous studies [18][19][20][21][22][23], changes in different parameters such as walking speed, cadence, step length, double support time etc. were computed while performing secondary tasks to assess cost of dual-tasking on gait.…”

Acceleration Gait Measures as Proxies for Motor Skill of Walking: A Narrative Review

“…Data collection involves technical issues [149], such as sampling rates used, frequency response requirements for different tasks, placement and alignment of the accelerometer on the trunk [26], and how they are attached for long-term and short-term use. To derive AGMs, there are several pre-processing steps that can be used to prepare the signal data [86], [150], such as filtering or extracting noise from the signals [151]- [153], event detection and labeling [66], [71], [154]- [156], wavelet analysis and decomposition [68], [157], [158], Fourier or Laplace transformations [159], integration [150], [160], [161], tilt correction [86], nonlinear techniques [158], statistical calculations [67], [162]. A non-exhaustive list of signal pre-processing tasks can be found in Figure 1-C.…”

“…• The mean trends of the acceleration signal amplitudes in the ML, V, and AP directions from different gait phases and activities can be used to characterize a feature of the specific gait phase or activity [67], [174]. • Correlation and covariance of the acceleration signal amplitudes between the pairs of ML, V, and AP directions (ML-V, ML-AP, V-AP) can help elucidate differences among activities that involve translation in just one dimension [67]. For example, in Dasgupta et al and Sejdic et al, correlations and covariances were calculated as a basic statistical features [16], [67].…”

“…• Correlation and covariance of the acceleration signal amplitudes between the pairs of ML, V, and AP directions (ML-V, ML-AP, V-AP) can help elucidate differences among activities that involve translation in just one dimension [67]. For example, in Dasgupta et al and Sejdic et al, correlations and covariances were calculated as a basic statistical features [16], [67]. Additionally, the auto-covariance can also be used to estimate stride time and stride regularity [66], [71].…”