Interpretable Feature Recommendation for Signal Analytics
This addresses the need for interpretable features in signal analytics for domains like prognostics, offering a human-in-loop system, though it appears incremental as it builds on existing Wide Learning concepts.
The paper tackles the problem of interpretable feature recommendation for signal analytics, particularly in prognostics, by proposing an automated approach based on Wide Learning architecture that provides feature interpretation, which is not available with methods like Deep Learning or PCA, and results show effectiveness in performance and reduced development time.
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.