Affinity-Based Hierarchical Learning of Dependent Concepts for Human Activity Recognition

TL;DR

This paper introduces an affinity-based hierarchical learning approach for human activity recognition, leveraging class relationships to improve classification accuracy and reduce data requirements.

Contribution

It proposes a novel method to organize overlapping classes into hierarchies using transfer affinity, enhancing performance over traditional flat classification methods.

Findings

Hierarchical organization improves classification accuracy.

The approach reduces the number of training examples needed.

Experimental results on SHL dataset validate effectiveness.

Abstract

In multi-class classification tasks, like human activity recognition, it is often assumed that classes are separable. In real applications, this assumption becomes strong and generates inconsistencies. Besides, the most commonly used approach is to learn classes one-by-one against the others. This computational simplification principle introduces strong inductive biases on the learned theories. In fact, the natural connections among some classes, and not others, deserve to be taken into account. In this paper, we show that the organization of overlapping classes (multiple inheritances) into hierarchies considerably improves classification performances. This is particularly true in the case of activity recognition tasks featured in the SHL dataset. After theoretically showing the exponential complexity of possible class hierarchies, we propose an approach based on transfer affinity among the classes to determine an optimal hierarchy for the learning process. Extensive experiments show improved performances and a reduction in the number of examples needed to learn.