CostSensitive Convolution based Neural Networks for Imbalanced TimeSeries Classification
This topic contains 0 replies, has 1 voice, and was last updated by arXiv 1 year, 1 month ago.

CostSensitive Convolution based Neural Networks for Imbalanced TimeSeries Classification
Some deep convolutional neural networks were proposed for timeseries classification and class imbalanced problems. However, those models performed degraded and even failed to recognize the minority class of an imbalanced temporal sequences dataset. Minority samples would bring troubles for temporal deep learning classifiers due to the equal treatments of majority and minority class. Until recently, there were few works applying deep learning on imbalanced timeseries classification (ITSC) tasks. Here, this paper aimed at tackling ITSC problems with deep learning. An adaptive costsensitive learning strategy was proposed to modify temporal deep learning models. Through the proposed strategy, classifiers could automatically assign misclassification penalties to each class. In the experimental section, the proposed method was utilized to modify five neural networks. They were evaluated on a large volume, reallife and imbalanced timeseries dataset with six metrics. Each single network was also tested alone and combined with several mainstream data samplers. Experimental results illustrated that the proposed costsensitive modified networks worked well on ITSC tasks. Compared to other methods, the costsensitive convolution neural network and residual network won out in the terms of all metrics. Consequently, the proposed costsensitive learning strategy can be used to modify deep learning classifiers from costinsensitive to costsensitive. Those costsensitive convolutional networks can be effectively applied to address ITSC issues.
CostSensitive Convolution based Neural Networks for Imbalanced TimeSeries Classification
by Yue Geng, Xinyu Luo
https://arxiv.org/pdf/1801.04396v1.pdf
You must be logged in to reply to this topic.