A Cost-Effective Fall-Detection Framework for the Elderly Using Sensor-Based Technologies

Falls are critical events among the elderly living alone in their rooms and can have intense consequences, such as the elderly person being left to lie for a long time after the fall. Elderly falling is one of the serious healthcare issues that have been investigated by researchers for over a decade, and several techniques and methods have been proposed to detect fall events. To overcome and mitigate elderly fall issues, such as being left to lie for a long time after a fall, this project presents a low-cost, motion-based technique for detecting all events. In this study, we used IRA-E700ST0 pyroelectric infrared sensors (PIR) that are mounted on walls around or near the patient bed in a horizontal field of view to detect regular motions and patient fall events; we used PIR sensors along with Arduino Uno to detect patient falls and save the collected data in Arduino SD for classification. For data collection, 20 persons contributed as patients performing fall events. When a patient or elderly person falls, a signal of different intensity (high) is produced, which certainly differs from the signals generated due to normal motion. A set of parameters was extracted from the signals generated by the PIR sensors during falling and regular motions to build the dataset. When the system detects a fall event and turns on the green signal, an alarm is generated, and a message is sent to inform the family members or caregivers of the individual. Furthermore, we classified the elderly fall event dataset using five machine learning (ML) classifiers, namely: random forest (RF), decision tree (DT), support vector machine (SVM), naïve Bayes (NB), and AdaBoost (AB). Our result reveals that the RF and AB algorithms achieved almost 99% accuracy in elderly fall-d\detection.