International Journal on Advanced Science, Engineering and Information Technology, Vol. 7 (2017) No. 6, pages: 2302-2307, DOI:10.18517/ijaseit.7.6.2632

Convolutional Neural Networks and Deep Belief Networks for Analysing Imbalanced Class Issue in Handwritten Dataset

A'inur A'fifah Amri, Amelia Ritahani Ismail, Abdullah Ahmad Zarir

Abstract

Imbalanced class is one of the trials in classifying materials of big data. Data disparity produces a biased output of a model regardless how recent the technology is. However, deep learning algorithms such as convolutional neural networks and deep belief networks have proven to provide promising results in many research domains, especially in image processing as well as time series forecasting, intrusion detection, and classification. Therefore, this paper will investigate the effect of imbalanced data discrepancy of classes in MNIST handwritten dataset using convolutional neural networks and deep belief networks. Based on the experiment conducted, the results show that although the algorithm is suitable for multiple domains and have shown stability, the imbalanced distribution of data still able to affect the overall performance of the models.

Keywords:

convolutional neural network; deep belief network; imbalanced class.

Viewed: 107 times (since Sept 4, 2017)

cite this paper     download