Fog Forecasting Using Self Growing Neural Network 'CombNET-II: ' A Solution for Imbalanced Training Sets Problem

This paper proposes a method to solve problem that comes with imbalanced training sets which is often seen in the practical applications. We modied Self Growing Neural Network CombNET-II to deal with the imbalanced condition. This model is then applied to practical application which was launched in '99 Fog Forecasting Contest sponsored by Neurocomputing Technical Group of IEICE, Japan. In this contest, fog event should be predicted every 30 minutes based on the observation of meteorological condition. As the result of the contest, CombNET-II achieved the highest accuracy among the participants and was chosen as the winner of the contest. The advantage of this model is that the independency of the branch networks contribute to an eective way of training and the time can be reduced.

• Type: Conference
• Year: 2000
• Where: IJCNN
• Authors: Anto Satriyo Nugroho, Susumu Kuroyanagi, Akira Iwata
• Keywords: Fog Forecasting Contest, IJCNN 2000, Imbalanced Training Sets, Neural Networks, Practical Application