BOSS Ensemble Classifier

This page was built in support of our paper "The BOSS is concerned about time series classification in the presence of noise" by Patrick Schäfer.

The paper is completely self-contained, the purpose of this webpage is to provide the BOSS code, the python-codes and the raw data to readers of the paper.

The BOSS model

Supporting Material

• The spreadsheet which shows the test and train accuracies of each classifier. This data was used to create the scatter plots. It additionally contains the test and train accuracy of the BOSS classifier for all UCR time series datasets.
• The spreadsheet used to create the Texas sharpshooter plot.
• The spreadsheet used to create the Golden Classifier plot.
• The spreadsheet used to justify the design decisions made to create the BOSS classifier.
• The python code to train and test the SVM classifier.
• The python code to train and test the random forest.
• Here is the c++ source code for the BOSS ensemble classifier.
• An alternative implementation using JAVA: Scalable Time Series Data Analytics using SFA, BOSS and BOSS VS