Towards Effective Classification of Imbalanced Data with Convolutional Neural Networks

Class imbalance in machine learning is a problem often found with real-world data, where data from one class clearly dominates the dataset. Most neural network classifiers fail to learn to classify such datasets correctly if class-to-class separability is poor due to a strong bias towards the majority class. In this paper we present an algorithmic solution, integrating different methods into a novel approach using a class- to-class separability score, to increase performance on poorly separable, imbalanced datasets using Cost Sensitive Neural Networks. We compare different cost functions and methods that can be used for training Convo- lutional Neural Networks on a highly imbalanced dataset of multi-channel time series data. Results show that, despite being imbalanced and poorly separable, performance metrics such as G-Mean as high as 92.8% could be reached by using cost sensitive Convolutional Neural Networks to detect patterns and correctly classify time series from 3 different datasets.

@InProceedings{RMW16, 
 	 author =  {Raj, Vidwath and Magg, Sven and Wermter, Stefan},  
 	 title = {Towards Effective Classification of Imbalanced Data with Convolutional Neural Networks}, 
 	 booktitle = {Artificial Neural Networks in Pattern Recognition},
 	 editors = {},
 	 number = {},
 	 volume = {},
 	 pages = {},
 	 year = {2016},
 	 month = {Sep},
 	 publisher = {Springer, Cham},
 	 doi = {https://doi.org/10.1007/978-3-319-46182-3_13}, 
 }