Internet of Things-Based Decision Support System for Toddler Health Using Mamdani Fuzzy Logic

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Purpose – This study develops and evaluates an Internet of Things-based decision support system using Mamdani fuzzy logic for the early identification of febrile seizure risk in toddlers. The system integrates continuous body-temperature and heart-rate monitoring to provide automated risk classification and real-time warning information. Design/methods/approach – The prototype combines an Arduino Uno, a GY-906 non-contact temperature sensor, a pulse sensor, an ESP8266 communication module, and a web-based monitoring platform. Body temperature and heart rate were processed through a Mamdani fuzzy inference system comprising fuzzification, nine clinical IF–THEN rules, MAX rule aggregation, and centroid defuzzification. Hardware performance was validated against standard clinical instruments using 30 toddler measurements. System classification was compared with risk assessments independently assigned by a senior pediatrician, while end-to-end latency was evaluated through 30 transmission cycles. Findings – The GY-906 sensor achieved 98.92% accuracy with a mean squared error of 0.214, while the pulse sensor achieved 96.35% accuracy with a mean squared error of 12.67. The fuzzy inference system correctly classified 29 of 30 cases, resulting in 96.67% accuracy, 100% sensitivity, and 93.33% specificity. The system also achieved an average end-to-end latency of 1.877 seconds, indicating responsive real-time monitoring under controlled laboratory network conditions. Research implications/limitations – The proposed system may support caregivers and healthcare professionals by providing consistent and timely early-warning information. However, the prototype was validated using a relatively small sample, depends on stable network connectivity, and requires broader prospective clinical validation before routine medical implementation. Originality/value – This study integrates real-time multivariable IoT monitoring with Mamdani fuzzy reasoning to transform uncertain pediatric vital-sign boundaries into interpretable febrile seizure risk classifications.