A Novel Probabilistic Network Model for Estimating Cognitive-Gait Connection Using Multimodal Interface

Research in human gait analysis has captivated several computer vision researchers to solve human identification problems. The proposed work provides a novel approach for cognitive state estimation via multimodal analysis. The advantage of the multimodal system is to provide adequate motion signatures with the ensemble of multimodal gait data to ensure data reliability for classification. The relationship between human cognitive states and gait is predicted using both temporal and nontemporal probabilistic models. We estimate prior probability tables for the nontemporal probabilistic model known as a simple Bayesian model after analyzing the data acquired from the inertial measurement unit (IMU), electroencephalography (EEG), and multiple Kinect V2.0 sensors. A novel dynamic Bayesian network (DBN) is used as a probabilistic temporal model for estimating the most probable sequence of transitions among human cognitive states. We apply Gaussian mixture modeling with expectation maximization (GMM-EM) to tune transition and emission probabilities for maximizing the probability of the observed sequence. A promising estimation accuracy of 88.6% is obtained. Also, principal component analysis (PCA) and
$k$
-nearest neighbor (kNN) algorithms are applied separately to calculate the input probabilities for DBN model. It is observed that both GMM-EM and kNN-based approaches outperform all the state-of-the-art techniques. Moreover, standard statistical tests are performed on the acquired data set to validate the experimental results.