Interpretable Feature Recommendation for Signal Analytics

TL;DR

This paper introduces an automated, interpretable feature recommendation system for signal data analytics, especially useful in prognostics, offering better interpretability and efficiency than deep learning or PCA methods.

Contribution

It proposes a novel Wide Learning architecture that provides interpretable feature recommendations, enhancing understanding and reducing development time in signal analytics.

Findings

Effective feature recommendation and interpretation in prognostics datasets.

Significant reduction in solution development time.

Improved interpretability over deep learning and PCA methods.

Abstract

This paper presents an automated approach for interpretable feature recommendation for solving signal data analytics problems. The method has been tested by performing experiments on datasets in the domain of prognostics where interpretation of features is considered very important. The proposed approach is based on Wide Learning architecture and provides means for interpretation of the recommended features. It is to be noted that such an interpretation is not available with feature learning approaches like Deep Learning (such as Convolutional Neural Network) or feature transformation approaches like Principal Component Analysis. Results show that the feature recommendation and interpretation techniques are quite effective for the problems at hand in terms of performance and drastic reduction in time to develop a solution. It is further shown by an example, how this human-in-loop interpretation system can be used as a prescriptive system.