Weather prediction is a computer program with meteorological information to forecast atmospheric conditions for specific location. Weather prediction is carried out using different techniques for managing the big data. Consequently, the existing technique reduced the feature selection accuracy with large time consumption. To enhance accuracy with lesser time, Fisher Kernelized Target Projective Feature Selection (FKTPFS) technique is introduced for weather prediction using higher accuracy as well as lesser time. In proposed FKTPFS technique, feature selection was carried out with Fisher Kernelized Target Projective Feature Selection for identifying significant features. The objective of Fisher Kernelized Target Projective Feature Selection is to give the large separation of class means while maintaining the in-class variance small. The feature selection process of proposed FKTPFS technique minimizes time complexity of the marine weather prediction. The results and discussion shows FKTPFS increases feature selection accuracy as well as minimize the error as well as feature selection time than the existing techniques.
Article Details
Unique Paper ID: 158277
Publication Volume & Issue: Volume 9, Issue 9
Page(s): 186 - 194
Article Preview & Download
Share This Article
Conference Alert
NCSST-2023
AICTE Sponsored National Conference on Smart Systems and Technologies
Last Date: 25th November 2023
SWEC- Management
LATEST INNOVATION’S AND FUTURE TRENDS IN MANAGEMENT