WHEELCHAIR-PERSON FALL DETECTION WITH INTERNET OF THINGS
Foong Seew Hon, Raed Abdulla, Sathish Kumar Selvaperumal, Chandrasekharan Nataraj, Dhakshyani Ratnadurai · Solid State Technology · 2020
Falling down is among the major causes of medical problem that are faced by the elderly peopleand movement disability person. These people tend to injure themselves from falling down when they alone.When a falling event occurred, medical attention needs to provide immediately in order to reduce the risk offaller from getting severe injuries which may lead to death. Several technologies have been developed whichsome utilized webcams to monitor their activities. However, the cost of operation and installation isexpensive and only applicable for indoor environment. Some user also worried about their privacy issues.Current commercialized device is by wearing a wearable wireless emergency transmitter which restrictmovement of user and produce high false alarm. This research proposed a wheelchair-person fall detectionsystem with IoT which is cost effective and reliable to detect fall and alert surrounding to call for help. Forfall detection, gyroscope, GPS module, FSR pressure sensor and microcontroller are implemented into thesystem. The gyroscope is use to detect the position of the wheelchair while the FSR pressure sensor whichplaced on the sit pad of the wheelchair will be used to detect and recognized the gesture of the user. Bothworks together to detect fall event which increase the accuracy of the fall detection. GPS module used toallocate the location of the wheelchair when fall event occur. When fall event occur, all the data includes thelocation of the wheelchair will be sent to blynk mobile application. The IoT system will sent emailnotification to the registered person to alert them fall event happen and help needed. Moreover, this systemrequires less implementation cost and provides a quick response. It can install in the existing commercialwheelchair. However, the limitation of this system is it required a good WIFI connection. For futurerecommendation, a better GUI design can be implemented into the system besides that, more detectionsystem can be added on to increase the accuracy of the system