Volume 8 Issue 2 - March 2017

  • 1. A novel approach to reduce the noise of time series data using predictive weighted moving average

    Authors : T Rajesh, Dr. K V G Rao

    Pages : 220-230

    DOI : http://dx.doi.org/10.21172/1.82.030

    Keywords : Time SeriesPitfallsSecular TrendCyclic variationSeasonal variationsMoving AverageWeighted moving averageMLP

    Abstract :

    With the growing demand of the long term and short term planning based on predictions of time series data, this is the demand of the modern research to provide significant and promising methods for time series data analysis. Nevertheless the time series are prone to fluctuations and thus makes it difficult to analysis and perform any kind of predictive operations for making decisions. Time series clustering is an important solution to various problems in numerous fields of research, including business, medical science, and finance. However, conventional clustering algorithms are not practical for time series data because they are essentially designed for static data. This impracticality results in poor clustering accuracy in several systems. Thus smoothing of the time series is the most significant part of the research. Hence this work analyses the performance of various types of smoothing methods like moving average, weighted moving average and identifies the pitfalls of these methods. The final outcome of this work is proposing and evaluating the performance of a predictive weighted moving average method for smoothing the data. The novelty of the work includes reduction of the difference between the actual data points from the time series and calculated average time series. This contribution will help this work to contribute in an algorithm for calculating the piecewise aggregate approximation of a time series and also proposing a clustering algorithm in future.

    Citing this Journal Article :

    T Rajesh, Dr. K V G Rao, "A novel approach to reduce the noise of time series data using predictive weighted moving average", https://www.ijltet.org/journal_details.php?id=911&j_id=3679, Volume 8 Issue 2 - March 2017, 220-230, #ijltetorg