Mobile and sensor network based rescue management system
In case of disaster, search and rescue operations are performed to locate and rescue victims. However, the effectiveness and efficiency of such rescue operations is often compromised because of the lack of availability of information that could help determine the current location of the person trapped in an emergency situation and thus seeking for help. Moreover, lack of feedback from people under threat or those near them further poses problems to timely rescue of the victim. Wireless sensor networks utilize the technologies which can cause an alert for the immediate rescue operation to begin, whenever this disaster is struck. The proposed mobile and sensor network -based rescue management system (MS-RMS) would cater to this issue in both situations, one in which there is infrastructure support and the other where there is no GSM/CDMA infrastructure support. MS-RMS system thus ensures safety through fast effective response to an emergency situation regardless of the type of the accident or the conscious state of the victim (in the sense that he may be able to place a call or may not be able to do so). Key feature of this system is that it offers mobile and sensor-based solution that helps victims to seek help from the rescue team. The proposed solution can be divided into two stages: (1) The transfer of the vital health care signs of the person to the cloud server (ThingSpeak) along with the GPS location, and setting a threshold for the health care signs, beyond which, a response is required from the rescue team followed by immediate action. (2) In case of infrastructure failure, the data from the sensors attached to the body of the person is transmitted continuously, and the rescue team effectively estimates the location of the person by using the received signal strength indicator (RSSI). Taking into account the environmental factors such as temperature and humidity which affect the RSSI values, we include these as features to train our neural network model that is used to predict the distance.