General Information
    • ISSN: 1793-8201 (Print), 2972-4511 (Online)
    • Abbreviated Title: Int. J. Comput. Theory Eng.
    • Frequency: Quarterly
    • DOI: 10.7763/IJCTE
    • Editor-in-Chief: Prof. Mehmet Sahinoglu
    • Associate Editor-in-Chief: Assoc. Prof. Alberto Arteta, Assoc. Prof. Engin Maşazade
    • Executive Editor: Ms. Mia Hu
    • Abstracting/Indexing: Scopus (Since 2022), INSPEC (IET), CNKI,  Google Scholar, EBSCO, etc.
    • E-mail:
    • Journal Metrics:

Prof. Mehmet Sahinoglu
Computer Science Department, Troy University, USA
I'm happy to take on the position of editor in chief of IJCTE. We encourage authors to submit papers concerning any branch of computer theory and engineering.

IJCTE 2023 Vol.15(2): 68-75
DOI: 10.7763/IJCTE.2023.V15.1333

Ridge Regularized Imputed Scaled Clipping Normalization Based Pre-processing for Marine Weather Forecasting

J. Deepa Anbarasi* and V. Radha

Manuscript received September 2, 2022; revised November 11, 2022; accepted January 28, 2023.

Abstract—The prediction of marine weather is an application employed for forecasting atmospheric conditions for a given position and time. Data pre-processing is the first step in the marine weather forecasting process. Data mining method is employed for changing data. The purpose of the data pre-processing is to clean and organize the text for an accurate classification process. Also, the pre-processing of large datasets is used to remove the noisy and missing values encountered during the data collection. Many existing data pre-processing methods are studied to improve forecasting performance. However, the conventional methods of space complexity and time complexity during pre-processing were not reduced. In order to address these problems, Ridge Regularized-Imputed-Scaled Clipping Normalization-based Deep Learnt Data Pre-processing (RRISCN-DLDP) Method is introduced. The key objective of the RRISCN-DLDP method is to remove the noisy data and to fill in the missing values in the database for improving the classification performance. RRISCN Method comprises six layers, namely one input layer, four hidden layers, and one output layer for efficient pre-processing. Initially in RRISCN Method, the number of marine weather data points is collected from the database at the input layer. After that, the input marine weather data is transmitted to hidden layer 1. In that layer, Ridge Regularized data quality is assessed through mismatched data types, mixed data values, and data outliers with higher data quality. Then, the missing data values are filled in hidden layer 2 to perform a data cleaning process using Imputed nearest neighbor interpolation through approximating the feature value for a non-given point in corresponding columns with a lesser error rate. Next, the data duplication is removed in the hidden layer 3 by using pointwise animator correlation analysis to execute the data reduction process for measuring the two marine weather data points. Followed by, the data transformation is performed through the scaled clipping normalization process. In this way, efficient data pre-processing is carried out by using RRISCN Method to minimize time and space consumption. Experimental evaluation is performed using various quantitative metrics namely accuracy, space complexity as well as the time involved in pre-processing. The analyzed results reveal the superior performance of our proposed RRISCN Method with higher pre-processing accuracy by 4% as well as lesser space complexity and pre-processing time by 22% and 13% when compared to using conventional techniques.

Index Terms—Marine weather forecasting, data pre-processing, data mining

J. Deepa Anbarasi and V. Radha are with Department of Computer Science, Avinashilingam Institute of Home Science and Higher Education for Women, Coimbatore, India. E-mail: (V.R.)
*Correspondence: (J.D.A.)


Cite:J. Deepa Anbarasi and V. Radha, "Ridge Regularized Imputed Scaled Clipping Normalization Based Pre-processing for Marine Weather Forecasting," International Journal of Computer Theory and Engineering vol. 15, no. 2, pp. 68-75, 2023.

Copyright © 2023 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Copyright © 2008-2023. International Association of Computer Science and Information Technology. All rights reserved.