IOSR Journal of Electrical and Electronics Engineering (IOSR-JEEE) e-ISSN: 2278-1676,p-ISSN: 2320-3331, Volume 9, Issue 4 Ver. II (Jul – Aug. 2014), PP 19-25 www.iosrjournals.org www.iosrjournals.org 19 | Page Learning In Wireless Sensor Networks for Environmental Monitoring Dr M. Dash 1 , Mrs. M. Balabantaray 2 , Mr. D. P. Moharana 3 ,Mrs. R. Mohanty 4 ( 1 Etc, Oec India) (2 etc,Oec India) (3 etc,Oec India) (4 etc,Oec India) Abstract: This paper brings two main contributions to the use of learning techniques in a sensor network. First, an approach which combines time series prediction and model selection for reducing the amount of communication called adaptive model selection, is to let the sensors determine in an automated manner a prediction model that does not only fits their measurements, but that also reduces the amount of transmitted data. The second main contribution is the design of a distributed approach for modeling sensed data, based on the principal component analysis. We first show that the sensor measurements can be transformed along a routing tree in such a way that (i) most of the variability in the measurements is retained, and (ii) the network load sustained by sensor nodes is reduced and more evenly distributed. Keywords: Learning techniques, sensor network , time series prediction , adaptive model selection. I. Introduction Wireless sensor networks form an emerging class of computing devices capable of observing the world with an unprecedented resolution, and promise to provide a revolutionary instrument for environmental monitoring. Such a network is composed of a collection of battery-operated wireless sensors, or sensor nodes, each of which is equipped with sensing, processing and wireless communication capabilities. Recent advances are in microelectronics and wireless technologies, wireless sensors are small in size, and can be deployed at low cost over different kinds of environments in order to monitor both over space and time the variations of physical quantities such as temperature, humidity, light, or sound. In environmental monitoring studies, many applications are expected to run unattended for months or years. Sensor nodes are however constrained by limited resources, particularly in terms of energy. Since communication is one order of magnitude more energy- consuming than processing, the design of data collection schemes that limit the amount of transmitted data is therefore recognized as a central issue for wireless sensor networks .An efficient way to address this challenge is to approximate, by means of mathematical models, the evolution of the measurements taken by sensors over space and/or time. Indeed, whenever a mathematical model may be used in place of the true measurements, significant gains in communications may be obtained by only transmitting the parameters of the model instead of the set of real measurements. Since in most cases there is little or no a priori information about the variations taken by sensor measurements, the models must be identified in an automated manner. This calls for the use of machine learning techniques, which allow to model the variations of future measurements on the basis of past measurements. In wireless sensor networks, communication is among the most energy-consuming task for a wireless sensor. This paper focuses on the design of learning techniques that trade data accuracy with communication by means of prediction models. Since sensor network measurements are very often correlated, the prediction models can often significantly reduce the communication while causing little loss in the accuracy of the measurements. Wireless sensor networks (WSN) form an emerging class of networks able to monitor environments with high spatiotemporal accuracy. The network is composed of tiny devices known as wireless sensors or motes, endowed with a microprocessor, a memory, a radio, a battery, and one or more sensors such as temperature, humidity, light or sound sensors [3]. The transmission of data from a WSN to an observer raises numerous issues: wireless sensors are constrained by limited resources, in terms of energy, network data throughput, and computational power. The communication module is a particularly constrained resource since the amount of data that can be routed out of the network is inherently limited by the network capacity. Also, wireless communication is an energy consuming task, identified in many situations as the primary factor of lifetime reduction [3]. The sensor network data are very often correlated both over space and time. Machine learning algorithms can be used to detect these redundancies, and to represent them by means of mathematical models. The use of mathematical models instead of the raw data can allow to substantially reduce the amount of data transmitted in the network, and thus to extend application lifetime. A typical scenario for a sensor network consists in placing a set of wireless sensors in an environment, such as a field, a forest or a town, and to use the collected measurements to monitor, detect, or track the evolution of a phenomenon over space and time. The network is usually connected to a base station by means of a routing tree, such as illustrated in Figure 1. The base station allows to centralize the data collected from the network, and acts as a gateway between the sensor