The ECHOS Platform to Enhance Communication for Nonverbal Children with Autism

Abstract

Current augmentative communication technology has had limited success conveying the needs of some individuals with minimally verbal autism spectrum disorder (mvASD). Primary caregivers report being able to better understand these individuals' non-traditional utterances than those less familiar with the individual such as teachers and community members. We present an eight-month multi-phase case study for a translational platform, ECHOS, that uses primary caregivers' unique knowledge to enhance communicative and affective exchanges between mvASD individuals and the broader community. Through iterative development and participatory design, we discovered that physiological sensors were impractical for long-term use, on-body audio was content rich and easily accessible, and a custom in-the-moment labeling app was transformative in obtaining accurate labels from caregivers for machine learning advancements. This paper presents the design methodology, results, and reflections from our case study and provides insights into development with and for the special needs community.

Technological Evolvement in AAC Modalities to Foster Communications of Verbally Challenged ASD Children: A Systematic Review

“…The focused group of users includes instructors, therapists, teachers, parents, autistic children, and children with language impairments. In a similar direction, a solution demonstrated by Pavel Zlatarov [17], which includes an efficient and responsive user interface, supported by a database of uniquely tailored details for individual use, a personalized vocabulary and performance statistics are stored and maintained within each child's account, allowing for the accurate and unbiased monitoring and review of their subsequent progress whereas the research by K. T. Johnson et al [63] addressed the layout and eight-month duration case study on a platform called "ECHOS (Enhancing Communication using Holistic Observations and Sensing)" for communicative interaction which consists of Phase I and II. In Phase, I the utilization of numerous physiological sensors with adhesive electrodes was inefficient for longterm usage whereas in Phase II an affordable audio recorder contributed to efficacious and communicative data while maximizing simplicity, ease of utilization, and possible scalability.…”

iBVP Dataset: RGB-Thermal rPPG Dataset with High Resolution Signal Quality Labels

“…The achieved distribution of heart rate computed from ground-truth PPG signals can be observed in Figure 2B. Furthermore, as wearable sensors are less reliable under significant motion conditions [48], we added an experimental condition that involved guided head movement. Each condition lasted for 3 min, with 1 min of rest after each condition.…”

PhysioKit: An Open-Source, Low-Cost Physiological Computing Toolkit for Single- and Multi-User Studies

“…Cognitively challenging math tasks with varying degrees of difficulty levels were chosen, as these have been reported to alter the physiological responses [80,81]. Furthermore, as wearable sensors are less reliable under significant motion conditions [82], we added an experimental condition that involved guided head movement. The PPG sensor on the ear remained relatively stable under all conditions, except during head movement, which provided us with the opportunity to investigate the impact of movement on signal quality at different sensor sites under varying motion conditions.…”