<![CDATA[This paper addresses the critical challenges of managing stress in autistic children by introducing an innovative deployable system designed to detect signs of stress through continuous monitoring of physiological and environmental indicators. The system, implemented as a convenient portable detection system, measures key parameters such as heart rate, body temperature and skin conductance. The data is accessed in real-time and displayed on the Blynk application with an IoT system and viewed remotely via an Android device, allowing caregivers to receive instant notifications upon detection of potential stress symptoms. This timely alert system enables rapid intervention, potentially reducing stress intensity and providing peace of mind to caregivers. The study further compares three powerful data analysis methods namely Support Vector Machine (SVM), K-nearest neighbors (KNN) and Random Forest (RF) in interpreting the collected sensor data. The SVM-based system achieved a fairly good detection accuracy of 90%, KNN also showed excellent results of 92% while the Random Forest-based system showed superior performance with an impressive accuracy of 95%. These findings suggest that the Random Forest method exhibits a superior level of effectiveness in accurately predicting the onset of stress conditions., providing the importance for technological advancements that can be applied in supporting better management of autism-related behavioral defenses.]]>
