Dynamic control of data measurement intervals in a networked sensing system using neurocomputing

A new algorithm for dynamic controlling of data measurement intervals in a networked sensing system (NSS) is presented in this paper. The method is developed on a wireless sensor network (WSN) for food quality supervision during the transportation process using containers. The artificial neural network (ANN) is used for data approximation due to its learning capability and high flexibility. At each instance, the measurement interval is changed dynamically depending on the stability of the environmental parameters in the container. The wireless sensor network is able to detect the possible unstable situations automatically with low energy consumption. Firstly, the performance of the dynamic control mechanism is tested in a simulation environment. Later, the developed algorithm is implemented to adjust the measurement intervals in a real transportation system. The new developed technique could be applied to decrease the power consumption in various applications of the networked sensing systems.