Domain Adaptation Guided Drift Compensation

Abstract

This chapter addresses the sensor drift issue in E-nose from the viewpoint of machine learning. Traditional methods for drift compensation are laborious and costly due to the frequent acquisition and labeling process for gases samples recalibration. Extreme learning machines (ELMs) have been confirmed to be efficient and effective learning techniques for pattern recognition and regression. However, ELMs primarily focus on the supervised, semi-supervised, and unsupervised learning problems in single domain (i.e., source domain). Drift data and non-drift data can be recognized as cross-domain data. Therefore, this chapter proposes a unified framework, referred to as domain adaptation extreme learning machine (DAELM), which learns a cross-domain classifier with drift compensation. Experiments on the popular sensor drift data of multiple batches clearly demonstrate that the proposed DAELM significantly outperforms existing drift compensation methods.