Abstract: The state of art development in wireless communication has led to the development of various wireless sensors. The wireless sensors are versatile and low priced and can be used for several different applications like temperature monitoring, health monitoring. However there are certain limitations to the use of such sensors. Two of the few major limitations of wireless sensor networks are its inability to store data and transmit it back when needed and unreliability i.e. the sensor, due to its limited channel, bandwidth and lack of security becomes unreliable. The objective of this paper is to address the above two problems. The unreliability of the system is tackled by using artificial neural networks for data filtering i.e. the data at the sensor gateway is transmitted to an artificial neural network which filters out redundant data and also compresses the relevant data. The data is then transferred to cloud for storage where it can be accessed when needed. This can have various applications in data monitoring, prediction of natural disasters, weather forecast etc.

Keywords: WSN, Artificial neural network, Sensor gateway.