Implementation of Modified Cuckoo Search Algorithm on Functional Link Neural Network for Temperature and Relative Humidity Prediction

Abstract

The impact of temperature and relative humidity changes bringing a sharp warming climate. These changes can cause extreme consequences such as floods, hurricanes, heat waves and droughts. Therefore, prediction of temperature and relative humidity is an important factor to measure environmental changes. Neural network, especially the Multilayer Perceptron (MLP) which uses Back Propagation algorithm (BP) as a supervised learning method, has been successfully applied in various problem for meteorological prediction tasks. However, this architecture still facing problem where the convergence rate is very low due to the multilayering topology of the network. Thus, this study proposes an implementation of Functional Link Neural Network (FLNN) which composes of a single layer of tunable weight trained with the Modified Cuckoo Search algorithm (MCS). The FLNN is used to predict the daily temperatures and relative humidity of Batu Pahat region. Extensive simulation results have been compared with standard MLP trained with the BP, and FLNN with that of BP. Promising results have shown that FLNN when trained with the MCS has successfully outperformed other network models with reduced prediction error and fast convergence rate.