MachineLearning

In this paper the problem of indoor positioning based on readings from its embedded sensors, utilizing machine learning methodologies is investigated. It is useful to differentiate algorithms based on computational performance rather than classification accuracy alone. As although classification accuracy between the algorithms is similar, computational performance can differ significantly and it can affect to the quality of the indoor positioning device if it takes a considerable time to display the current position [1]. So the objective of this paper is to perform a comparative analysis of 8 machine learning algorithms namely, K means, Hierarchical, Gaussian mixture , density based , Nearest neighbor, feature agglomeration , Linear Regression and Logistic Regression. A real world indoor fixed environment is considered a large dataset of 1278 data points is collected. Then the performance of the above mentioned machine learning algorithms are examined. In this paper the processing time of the different machine learning techniques are being estimated by considering the collected data set, over a fixed indoor area of 52.545 m2. The paper is organized as follows. In Section I, introduction and background analysis of the research is included and in section II, other indoor localization systems and their limitations are examined. In Section III, our application and data collection Process, the testing environment, and the Methodology of our analysis are being described briefly. Section IV comprises the results of our analysis. Finally, the paper concludes with a discussion of future directions for research by eliminating the problems existing with the current research methodology.