On Principal Curve-Based Classifiers and Similarity-Based Selective Sampling in Time-Series

TL;DR

This paper introduces a principal curve-based classifier and a deterministic selective sampling algorithm that effectively handle time-span variations in time-series data, addressing limitations of recurrent neural networks and unreliable sampling methods.

Contribution

It proposes a novel principal curve-based classifier and a deterministic selective sampling algorithm, improving robustness to time variations and reliability over existing methods.

Findings

Handles any variation in time spans effectively

Provides a deterministic sampling algorithm with reliable performance

Improves classification robustness in time-series data

Abstract

Considering the concept of time-dilation, there exist some major issues with recurrent neural Architectures. Any variation in time spans between input data points causes performance attenuation in recurrent neural network architectures. Principal curve-based classifiers have the ability of handling any kind of variation in time spans. In other words, principal curve-based classifiers preserve the relativity of time while neural network architecture violates this property of time. On the other hand, considering the labeling costs and problems in online monitoring devices, there should be an algorithm that finds the data points which knowing their labels will cause in better performance of the classifier. Current selective sampling algorithms have lack of reliability due to the randomness of the proposed algorithms. This paper proposes a classifier and also a deterministic selective sampling algorithm with the same computational steps, both by use of principal curve as their building block in model definition.