The Effectiveness of Multi-Label Classification and Multi-Output Regression in Social Trait Recognition.

First impressions make up an integral part of our interactions with other humans by providing an instantaneous judgment of the trustworthiness, dominance and attractiveness of an individual prior to engaging in any other form of interaction. Unfortunately, this can lead to unintentional bias in situations that have serious consequences, whether it be in judicial proceedings, career advancement, or politics. The ability to automatically recognize social traits presents a number of highly useful applications: from minimizing bias in social interactions to providing insight into how our own facial attributes are interpreted by others. However, while first impressions are well-studied in the field of psychology, automated methods for predicting social traits are largely non-existent. In this work, we demonstrate the feasibility of two automated approaches-multi-label classification (MLC) and multi-output regression (MOR)-for first impression recognition from faces. We demonstrate that both approaches are able to predict social traits with better than chance accuracy, but there is still significant room for improvement. We evaluate ethical concerns and detail application areas for future work in this direction.

Atypical Asymmetry for Processing Human and Robot Faces in Autism Revealed by fNIRS.

Deficits in the visual processing of faces in autism spectrum disorder (ASD) individuals may be due to atypical brain organization and function. Studies assessing asymmetric brain function in ASD individuals have suggested that facial processing, which is known to be lateralized in neurotypical (NT) individuals, may be less lateralized in ASD. Here we used functional near-infrared spectroscopy (fNIRS) to first test this theory by comparing patterns of lateralized brain activity in homologous temporal-occipital facial processing regions during observation of faces in an ASD group and an NT group. As expected, the ASD participants showed reduced right hemisphere asymmetry for human faces, compared to the NT participants. Based on recent behavioral reports suggesting that robots can facilitate increased verbal interaction over human counterparts in ASD, we also measured responses to faces of robots to determine if these patterns of activation were lateralized in each group. In this exploratory test, both groups showed similar asymmetry patterns for the robot faces. Our findings confirm existing literature suggesting reduced asymmetry for human faces in ASD and provide a preliminary foundation for future testing of how the use of categorically different social stimuli in the clinical setting may be beneficial in this population.

Socially assistive robotics for post-stroke rehabilitation.

BACKGROUND: Although there is a great deal of success in rehabilitative robotics applied to patient recovery post stroke, most of the research to date has dealt with providing physical assistance. However, new rehabilitation studies support the theory that not all therapy need be hands-on. We describe a new area, called socially assistive robotics, that focuses on non-contact patient/user assistance. We demonstrate the approach with an implemented and tested post-stroke recovery robot and discuss its potential for effectiveness. RESULTS: We describe a pilot study involving an autonomous assistive mobile robot that aids stroke patient rehabilitation by providing monitoring, encouragement, and reminders. The robot navigates autonomously, monitors the patient's arm activity, and helps the patient remember to follow a rehabilitation program. We also show preliminary results from a follow-up study that focused on the role of robot physical embodiment in a rehabilitation context. CONCLUSION: We outline and discuss future experimental designs and factors toward the development of effective socially assistive post-stroke rehabilitation robots.