Title: Predicting missing data for data integrity based on the linear regression model
Authors: Kai Gao; Chin-Chen Chang; Yanjun Liu
Addresses: Department of Information Engineering and Computer Science, Feng Chia University, No. 100, Wenhwa Rd., Seatwen, Taichung, 407, Taiwan ' Department of Information Engineering and Computer Science, Feng Chia University, No. 100, Wenhwa Rd., Seatwen, Taichung, 407, Taiwan ' Department of Information Engineering and Computer Science, Feng Chia University, No. 100, Wenhwa Rd., Seatwen, Taichung, 407, Taiwan
Abstract: Multiple linear regression is an important data analysis technique. Based on this technique, we propose a new method for predicting missing data items and detecting possible errors in the data. The proposed method has a key feature that it can be used to predict not only just one missing item, but also two or more missing items within a certain tolerance. At the same time, we perform a few experiments to prove the feasibility of our proposed method. The results of our experiments show that our method can indeed predict one or more missing items within an acceptable range and find the error of the original data.
Keywords: multiple linear regression; missing data; data integrity; predict.
International Journal of Embedded Systems, 2021 Vol.14 No.4, pp.355 - 362
Received: 22 May 2020
Accepted: 08 Jul 2020
Published online: 05 Oct 2021 *