B. Murgante et al. (Eds.): ICCSA 2013, Part I, LNCS 7971, pp. 427–437, 2013. © Springer-Verlag Berlin Heidelberg 2013 Functional Link Neural Network – Artificial Bee Colony for Time Series Temperature Prediction Yana Mazwin Mohmad Hassim and Rozaida Ghazali Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia (UTHM), 86400 Batu Pahat, Johor, Malaysia {yana,rozaida}@uthm.edu.my Abstract. Higher Order Neural Networks (HONNs) have emerged as an important tool for time series prediction and have been successfully applied in many engineering and scientific problems. One of the models in HONNs is a Functional Link Neural Network (FLNN) known to be conveniently used for function approximation and can be extended for pattern recognition with faster convergence rate and lesser computational load compared to ordinary feedforward network like the Multilayer Perceptron (MLP). In training the FLNN, the mostly used algorithm is the Backpropagation (BP) learning algorithm. However, one of the crucial problems with BP learning algorithm is that it can be easily gets trapped on local minima. This paper proposed an alternative learning scheme for the FLNN to be applied on temperature forecasting by using Artificial Bee Colony (ABC) optimization algorithm. The ABC adopted in this work is known to have good exploration and exploitation capabilities in searching optimal weight especially in numerical optimization problems. The result of the prediction made by FLNN-ABC is compared with the original FLNN architecture and toward the end we found that FLNN-ABC gives better result in predicting the next-day ahead prediction. Keywords: Temperature prediction, Functional Link Neural Network, Artificial Bee Colony Algorithm. 1 Introduction Artificial Neural Networks (ANNs) have been known to be successfully applied in a variety of real world tasks includes prediction, classification, signal processing, image recognition and especially in industry, business and science [1, 2]. The most common architecture of ANNs is the Multi-layer feed forward network known as Multilayer perceptron (MLP). Since the MLP has multilayered structure, the network requires excessive training time for learning [3]. This is because, the number of weight and the training time will increase as the number of layers and the nodes in layer increases [3, 4]. In order to overcome the drawback of MLP, another type of network known as Higher Order Neural Networks (HONNs) have been introduced [5]. HONNs are a type of feed forward neural network which have single layer trainable weights that can help brought to you by CORE View metadata, citation and similar papers at core.ac.uk provided by UTHM Institutional Repository