Emotion and motion: Toward emotion recognition based on standing and walking.

Emotion recognition is key to interpersonal communication and to human-machine interaction. Body expression may contribute to emotion recognition, but most past studies focused on a few motions, limiting accurate recognition. Moreover, emotions in most previous research were acted out, resulting in non-natural motion, which is unapplicable in reality. We present an approach for emotion recognition based on body motion in naturalistic settings, examining authentic emotions, natural movement, and a broad collection of motion parameters. A lab experiment using 24 participants manipulated participants' emotions using pretested movies into five conditions: happiness, relaxation, fear, sadness, and emotionally-neutral. Emotion was manipulated within subjects, with fillers in between and a counterbalanced order. A motion capture system measured posture and motion during standing and walking; a force plate measured center of pressure location. Traditional statistics revealed nonsignificant effects of emotions on most motion parameters; only 7 of 229 parameters demonstrate significant effects. Most significant effects are in parameters representing postural control during standing, which is consistent with past studies. Yet, the few significant effects suggest that it is impossible to recognize emotions based on a single motion parameter. We therefore developed machine learning models to classify emotions using a collection of parameters, and examined six models: k-nearest neighbors, decision tree, logistic regression, and the support vector machine with radial base function and linear and polynomial functions. The decision tree using 25 parameters provided the highest average accuracy (45.8%), more than twice the random guess for five conditions, which advances past studies demonstrating comparable accuracies, due to our naturalistic setting. This research suggests that machine learning models are valuable for emotion recognition in reality and lays the foundation for further progress in emotion recognition models, informing the development of recognition devices (e.g., depth camera), to be used in home-setting human-machine interactions.

Evolving Toward Subject-Specific Gait Rehabilitation Through Single-Joint Resistive Force Interventions.

Walking is one of the most relevant tasks that a person performs in their daily routine. Despite its mechanical complexities, any change in the external conditions that applies some external perturbation, or in the human musculoskeletal system that limits an individual's movement, entails a motor response that can either be compensatory or adaptive in nature. Incidentally, with aging or due to the occurrence of a neuro-musculoskeletal disorder, a combination of such changes including reduced sensory perception, muscle weakness, spasticity, etc. has been reported, and this can significantly degrade the human walking performance. Various studies in gait rehabilitation literature have identified a need for the development of better rehabilitation paradigms and have implied that an efficient human robot interaction is critical. Understanding how humans respond to a particular gait alteration can be beneficial in designing an effective rehabilitation paradigm. In this context, the current work investigates human locomotor adaptation to resistive alteration to the hip and ankle strategies of walking. A cable-driven robotic system, which does not add mobility constraints, was used to implement resistive force interventions within the hip and ankle joints separately through two experiments with eight healthy adult participants in each. In both cases, the intervention was applied during the push-off phase of walking, i.e., from pre-swing to terminal swing. The results showed that subjects in both groups adopted a compensatory response to the applied intervention and demonstrated intralimb and interlimb adaptation. Overall, the participants demonstrated a deviant gait implying lower limb musculoskeletal adjustments as if to compensate for a hip or ankle abnormality.