Abstract not found

Abstract — A wireless sensor network (WSN) is energy con-strained, and the extension of its lifetime is one of the most important issues in its design. Usually, a WSN collects a large amount of data from the environment. In contrast to the conventional remote sensing – based on satellites that collect large images, sound files, or specific scientific data – sensor networks tend to generate a large amount of sequential small and tuple-oriented data from several nodes, which constitutes data streams. In this work, we propose and evaluate two algorithms based on data stream, which use sampling and sketch techniques, to reduce data traffic in a WSN and, consequently, decrease the delay and energy consumption. Specifically, the sampling solution, provides a sample of only log n items to represent the original data of n elements. Despite of the reduction, the sampling solution keeps a good data quality. Simulation results reveal the efficiency of the proposed meth-ods by extending the network lifetime and reducing the delay without loosing data representativeness. Such a technique can be very useful to design energy-efficient and time-constrained sensor networks if the application is not so dependent on the data precision or the network operates in an exception situation (e.g., there are few resources remaining or there is an urgent situation). I.

Abstract not found

The processes of extracting knowledge structures for continuous, rapid records are known as the Data Stream Mining. The main issue in stream mining is handling streams of elements delivered rapidly which makes it infeasible to store everything in active storage. To overcome this problem of handling voluminous data we exposed a novel load shedding system using window based aggregate function of the data stream in which we accept those tuples in the stream that meet a criterion. Accepted tuples are conceded to another process as a stream, while further tuples are dropped. This proposed model conceivably segregates the data input stream into windows and probabilistically decides which tuple to drop based on the window function. The best window aggregate function used for dropping tuples is identified with the three prediction models used in data mining they are Decision Tree, Naïve Bayes and Logistic Regression. The result shows that the cumulative distance and density rank functions outperforms the remaining methods. Distinct to prior methods, our method preserves uniformity of windows all over a query plan, and constantly distributes subsets of the original query responds with insignificant denial in the excellence of the consequence.

Wireless Sensor Networks(WSN) are traditionally characterized as distributed ad hoc mesh networks deployed for measurement of physical parameters such as temperature, pressure and humidity etc., physiological parameters like body temperature, motion, orientation