A fuzzy data augmentation technique to improve regularisation. Issue 8 (8th November 2021)

• Record Type: Journal Article
• Authors: Dabare, Rukshima; Wong, Kok Wai; Shiratuddin, Mohd Fairuz; Koutsakis, Polychronis
• Is Part Of: International journal of intelligent systems. Volume 37:Issue 8(2022)
• Page Start: 4561
• Page End: 4585
• Publication Date: 2021-11-08
• Subjects: classification -- deep neural networks -- fuzzification -- numerical data augmentation -- regularisation; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.22731
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: Deep learning (DL) has achieved superior classification in many applications due to its capability of extracting features from the data. However, the success of DL comes with the tradeoff of possible overfitting. The bias towards the data it has seen during the training process leads to poor generalisation. One way of solving this issue is by having enough training data so that the classifier is invariant to many data patterns. In the literature, data augmentation has been used as a type of regularisation method to reduce the chance for the model to overfit. However, most of the relevant works focus on image, sound or text data. There is not much work on numerical data augmentation, although many real‐world problems deal with numerical data. In this paper, we propose using a technique based on Fuzzy C ‐Means clustering and fuzzy membership grades. Fuzzy‐related techniques are used to address the variance problem by generating new data items based on fuzzy numbers and each data item's belongings to different fuzzy clusters. This data augmentation technique is used to improve the generalisation of a Deep Neural Network that is suitable for numerical data. By combining the proposed fuzzy data augmentation technique with the Dropout regularisation technique, we manage to balance the classification model's bias‐variance tradeoff. Our proposed technique is evaluated using four popular data sets and is shown to provide better regularisation and higher classification accuracy compared with popular regularisation approaches.