AI-Enabled Assistive Ecosystems for Inclusive Participation in Education

Ensuring equitable participation for students with invisible disabilities in educational environments remains a persistent and complex challenge. Existing approaches often rely on reactive support that does not address the dynamic, unpredictable nature of conditions such as epilepsy. There is a growing need for proactive, integrated assistive systems that support both safety and autonomy.

This paper presents a proof-of-concept study exploring an AI-enabled assistive ecosystem that integrates wearable sensing, machine learning, and trained assistance dogs to support safe and independent participation in education. A smart collar equipped with motion sensors is used to detect trained alert behaviours in assistance dogs. When triggered, the system sends a warning to a caregiver or support contact via a mobile device, indicating that an epileptic seizure may be imminent and providing the individual’s location. Together, these elements suggest a pathway toward multimodal detection systems capable of enabling early alerts and timely intervention.

This work contributes to hybrid human–animal–AI assistive ecosystems that extend beyond traditional accommodation models, establishing the technical feasibility of an intelligent assistive ecosystem and demonstrating how multimodal sensing can support proactive, autonomous participation where existing accommodation frameworks fall short.