Shelley Brady

Dr. Shelley Brady

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 October 2025 in Animals
Verified
Journal Article
Open access
PDF file
SBShelley Brady
Shelley Brady
ASAlan Smeaton
Alan Smeaton
HSHailin Song
Hailin Song
TWTomas Ward
Tomas Ward
ASAoife Smeaton
Aoife Smeaton
JDJennifer Dowler
Jennifer Dowler
Assistance dogs have shown promise in alerting to epileptic seizures in their owners, but current approaches often lack consistency, standardisation, and objective validation. This proof-of-concept study presents the development and initial validation of a wearable behaviour-alert detection collar developed for trained assistance dogs. It demonstrates the technical feasibility for automated detection of trained signalling behaviours. The collar integrates an inertial sensor and machine learning pipeline to detect a specific, trained alert behaviour of two rapid clockwise spins used by dogs to signal a seizure event. Data were collected from six trained dogs, resulting in 135 labelled spin alerts. Although the dataset size is limited compared to other machine learning applications, this reflects the real-world constraint that it is not practical for assistance dogs to perform excessive spin signalling during their training. Four supervised machine learning models (Random Forest, Logistic Regression, Naïve Bayes, and SVM) were evaluated on segmented accelerometer and gyroscope data. Random Forest achieved the highest performance (F1-score = 0.65; accuracy = 92%) under a Leave-One-DOG-Out (LODO) protocol. The system represents a novel step toward combining intentional canine behaviours with wearable technology, aligning with trends on the Internet of Medical Things. This proof-of-concept demonstrates technical feasibility and provides a foundation for future development of real-time seizure-alerting systems, representing an important first step toward scalable animal-assisted healthcare innovation.

1 June 2026 in EDULEARN Proceedings
Verified
Conference Paper
Closed access
PDF file
SBShelley Brady
Shelley Brady
HSHailin Song
Hailin Song
ASAlan Smeaton
Alan Smeaton
TWTomás Ward
Tomás Ward
ASAoife Smeaton
Aoife Smeaton
NDNorman Delanty
Norman Delanty

1 January 2026 in Analytical Methods
Verified
Journal Article
Open access
Dinakaran ThirumalaiDinakaran Thirumalai
Dinakaran Thirumalai
VBVarvara Bolikava
Varvara Bolikava
SBShelley Brady
Shelley Brady
ASAlan Smeaton
Alan Smeaton
TWTomás E. Ward
Tomás E. Ward
AMAoife Morrin
Aoife Morrin
Canine olfactory detection has supported explosives and narcotics identification for over five decades, yet our understanding of its mechanistic basis remains limited from an analytical chemistry perspective.

30 September 2026 in Ubiquity Proceedings
Verified
Journal Article
Open access
PDF file
SBShelley Brady
Shelley Brady
HSHailin Song
Hailin Song
ASAlan F. Smeaton
Alan F. Smeaton
TWTomás Ward
Tomás Ward
ASAoife Smeaton
Aoife Smeaton
SOSusan O’NEill
Susan O’NEill
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.

3 September 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
SBShelley Brady
Shelley Brady
ASAlan Smeaton
Alan Smeaton
HSHailin Song
Hailin Song
TWTomas Ward
Tomas Ward
ASAoife Smeaton
Aoife Smeaton
JDJennifer Dowler
Jennifer Dowler
Assistance dogs have shown promise in alerting to epileptic seizures in their owners, but current approaches often lack consistency, standardisation, and objective validation. This proof-of-concept study presents the development and initial validation of a wearable behaviour-alert detection collar developed for trained assistance dogs. It demonstrates the technical feasibility for automated detection of trained signalling behaviours. The collar integrates an inertial sensor and machine learning pipeline to detect a specific, trained alert behaviour, two rapid clockwise spins used by dogs to signal a seizure event. Data were collected from six trained dogs, resulting in 135 la-belled spin alerts. Although the dataset size is limited compared to other machine learning applications, this reflects the real-world constraint that it is not practical for assistance dogs to perform excessive spin signalling during their training. Four super-vised machine learning models (Random Forest, Logistic Regression, Naïve Bayes, and SVM) were evaluated on segmented accelerometer and gyroscope data. Random Forest achieved the highest performance (F1-score = 0.65; accuracy = 92%) under a Leave-One-DOG-Out (LODO) protocol. The system represents a novel step toward combining intentional canine behaviours with wearable technology, aligning with trends in the Internet of Medical Things. This proof-of-concept demonstrates technical feasibility and provides a foundation for future development of real-time seizure alerting systems, representing an important first step toward scalable animal-assisted healthcare innovation.