When collecting the Internet of Things data using various sensors or other devices, it may be possible to miss several kinds of values of interest. In this paper, we focus on estimating the missing values in IoT time series data using three interpolation algorithms, including (1) Radial Basis Functions, (2) Moving Least Squares (MLS), and (3) Adaptive Inverse Distance Weighted. To evaluate the performance of estimating missing values, we estimate the missing values in eight selected sets of IoT time series data, and compare with those imputed by the standard kNN estimator. Our experiments indicate that in most experiments the estimation based on the Lancaster’s MLS is the best. It is also found that the number of nearest observed values for reference and the distribution of missing values could strongly affect the accuracy of imputation.
Comparison of Estimating Missing Values in IoT Time Series Data Using Different Interpolation Algorithms / Ding, Zengyu; Mei, Gang; Cuomo, Salvatore; Li, Yixuan; Xu, Nengxiong. - In: INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING. - ISSN 0885-7458. - 48:3(2020), pp. 534-548. [10.1007/s10766-018-0595-5]
Comparison of Estimating Missing Values in IoT Time Series Data Using Different Interpolation Algorithms
Cuomo, Salvatore
;
2020
Abstract
When collecting the Internet of Things data using various sensors or other devices, it may be possible to miss several kinds of values of interest. In this paper, we focus on estimating the missing values in IoT time series data using three interpolation algorithms, including (1) Radial Basis Functions, (2) Moving Least Squares (MLS), and (3) Adaptive Inverse Distance Weighted. To evaluate the performance of estimating missing values, we estimate the missing values in eight selected sets of IoT time series data, and compare with those imputed by the standard kNN estimator. Our experiments indicate that in most experiments the estimation based on the Lancaster’s MLS is the best. It is also found that the number of nearest observed values for reference and the distribution of missing values could strongly affect the accuracy of imputation.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.