PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification

TL;DR

PatchX introduces an interpretable hybrid method combining deep neural networks and traditional machine learning for scalable, patch-wise time-series classification, improving interpretability and performance over existing approaches.

Contribution

The paper presents a novel hybrid approach that uses patch-wise processing with deep learning and traditional methods for better interpretability in time-series classification.

Findings

Effective patch-wise classification improves interpretability.

Hybrid approach outperforms traditional methods in scalability.

Sample-level classification enhances overall accuracy.

Abstract

The classification of time-series data is pivotal for streaming data and comes with many challenges. Although the amount of publicly available datasets increases rapidly, deep neural models are only exploited in a few areas. Traditional methods are still used very often compared to deep neural models. These methods get preferred in safety-critical, financial, or medical fields because of their interpretable results. However, their performance and scale-ability are limited, and finding suitable explanations for time-series classification tasks is challenging due to the concepts hidden in the numerical time-series data. Visualizing complete time-series results in a cognitive overload concerning our perception and leads to confusion. Therefore, we believe that patch-wise processing of the data results in a more interpretable representation. We propose a novel hybrid approach that utilizes deep neural networks and traditional machine learning algorithms to introduce an interpretable and scale-able time-series classification approach. Our method first performs a fine-grained classification for the patches followed by sample level classification.