A Study on Imputation Methods for Vehicle Traffic Data
S. Narmadha1, V. Vijayakumar2

1S. Narmadha, Research Scholar, Sri Ramakrishna College of Arts and Science, Coimbatore (Tamil Nadu), India.
2Dr. V. Vijayakumar, Professor, Sri Ramakrishna College of Arts and Science, Coimbatore (Tamil Nadu), India.
Manuscript received on 06 February 2019 | Revised Manuscript received on 12 February 2019 | Manuscript Published on 19 February 2019 | PP: 415-420 | Volume-7 Issue-5S January 2019 | Retrieval Number: ES2174017519/19©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Quality traffic data is an essential for traffic related researches and developing transport applications. These data is collected from inductive loops, sensors, radars, cameras, mobile GPS (Global positioning system) and microwave sensors etc. Harsh environment, malfunctions of detectors, hardware, software and communication device failures leads the problem of traffic data loss. It will greatly reduce the predicting performance of the traffic volume data. It affects the important process of intelligent transportation systems. Imputation methods are used to find the missing data and produce as a complete data. Many imputation methods have been proposed in existing to estimate traffic analysis. In this paper imputation methods were discussed and analyzed.
Keywords: Imputation, Missing Data, Quality, Prediction, Deep Learning.
Scope of the Article: Heterogeneous and Streaming Data