Abstract: Recent developments in the communications and electronic industry have provided the stage for producing multi-purpose, cost-effective sensor nodes with low energy consumption in small dimensions and the ability to communicate in short distances. This paper is aimed at improving the efficiency of sensor networks in the body sensor networks by using the learning automata smart method and a new data aggregation technique. The data is transmitted from clusters to the base station by a data aggregation technique and a scheduling algorithm (vital signs written in C++). Now automata data is sent inside a random environment. According to the learning algorithm with a variable structure LRI in which penalty is zero and reward is given to the vital signs considering their type, the random environment returns data to automata so that automata uses it for selecting its next action. If critical signs have received the maximum reward after N repetition, it is determined as the best action of automata. Then this data is sent to the physician after being transmitted to the sink node (base station) via the internet, and the physician diagnoses the disease and returns the treatment result. To examine the performance of the proposed protocol, we studied its behavior through simulation. NS-2 simulator environment has been used for simulating protocol. The scenario has been implemented by OTCL, and we used files created by this language and the C++ programming language in NS-2 space. The results of the simulation show that the proposed protocol has had a better performance.
Amirreza saba, Xiang Michelle Liu and Mohamed Abdulnabi, 2021. An Adaptive Scheduling Algorithm for Collecting Data in Wireless Body Sensor Networks. Asian Journal of Information Technology, 20: 210-219.