Automatic Detection and Correction of Multi-class Classification Errors Using System Whole-part Relationships

• Main Authors: Zhengzhang Chen, John Jenkins, Alok Choudhary, Jinfeng Rao, Fredrick Semazzi, Anatoli V. Melechko, Vipin Kumar, Nagiza F. Samatova
• Other Authors: The Pennsylvania State University CiteSeerX Archives
• Format: Text
• Language: English
• Subjects: North Atlantic
• Online Access: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.414.165; http://cucis.ece.northwestern.edu/publications/pdf/CheJen13.pdf

Real-world dynamic systems such as physical and atmosphereocean systems often exhibit a hierarchical system-subsystem structure. However, the paradigm of making this hierarchical/modular structure and the rich properties they encode a “first-class citizen” of machine learning algorithms is largely absent from the literature. Furthermore, traditional data mining approaches focus on designing new classifiers or ensembles of classifiers, while there is a lack of study on detecting and correcting prediction errors of existing forecasting (or classification) algorithms. In this paper, we propose DETECTOR, a hierarchical method for detecting and correcting forecast errors by employing the whole-part relationships between the target system and non-target systems. Experimental results show that DETECTOR can successfully detect and correct forecasting errors made by state-of-art classifier ensemble techniques and traditional single classifier methods at an average rate of 22%, corresponding to a 11 % average forecasting accuracy increase, in seasonal forecasting of hurricanes and landfalling hurricanes in North Atlantic and North African rainfall. 1