Scalable ML Methods to Optimize KPIs in Real-World Manufacturing Processes

Abstract

Multivariate time series classification is an important and demanding task in sequence data mining. We focus on the multichannel representation of the time series and its corresponding convolutional neural network (CNN) classifier. The proposed method transforms multivariate time series into multichannel analogous image and it is fed into a pretrained multichannel CNN with transfer learning. To verify the efficacy of the proposed method, we compared it with recent deep learning-based time series classification models on five datasets with small amounts of training data. The results indicate that the proposed method provides improved performance on average compared with the other methods when incorporated with transfer learning.