Discovery of Shifting Patterns in Sequence Classification

TL;DR

This paper introduces a novel sequence classification approach that automatically detects shifting patterns in multi-variate data using multi-instance learning and LSTM, improving accuracy in real-world applications like cropland mapping and affective state recognition.

Contribution

The paper presents a new method combining multi-instance learning and LSTM to detect shifting patterns in sequence data, enhancing classification performance.

Findings

Outperforms traditional methods in cropland mapping and affective state recognition

Effectively detects discriminative shifting patterns in sequential data

Improves classification accuracy with limited training data

Abstract

In this paper, we investigate the multi-variate sequence classification problem from a multi-instance learning perspective. Real-world sequential data commonly show discriminative patterns only at specific time periods. For instance, we can identify a cropland during its growing season, but it looks similar to a barren land after harvest or before planting. Besides, even within the same class, the discriminative patterns can appear in different periods of sequential data. Due to such property, these discriminative patterns are also referred to as shifting patterns. The shifting patterns in sequential data severely degrade the performance of traditional classification methods without sufficient training data. We propose a novel sequence classification method by automatically mining shifting patterns from multi-variate sequence. The method employs a multi-instance learning approach to detect shifting patterns while also modeling temporal relationships within each multi-instance bag by an LSTM model to further improve the classification performance. We extensively evaluate our method on two real-world applications - cropland mapping and affective state recognition. The experiments demonstrate the superiority of our proposed method in sequence classification performance and in detecting discriminative shifting patterns.