XLearn

Abstract

Sensor-driven systems often need to map sensed data into meaningfully labelled activities to classify the phenomena being observed. A motivating and challenging example comes from human activity recognition in which smart home and other datasets are used to classify human activities to support applications such as ambient assisted living, health monitoring, and behavioural intervention. Building a robust and meaningful classifier needs annotated ground truth, labelled with what activities are actually being observed—and acquiring high-quality, detailed, continuous annotations remains a challenging, time-consuming, and error-prone task, despite considerable attention in the literature. In this article, we use knowledge-driven ensemble learning to develop a technique that can combine classifiers built from individually labelled datasets, even when the labels are sparse and heterogeneous. The technique both relieves individual users of the burden of annotation and allows activities to be learned individually and then transferred to a general classifier. We evaluate our approach using four third-party, real-world smart home datasets and show that it enhances activity recognition accuracies even when given only a very small amount of training data.

A Fine-Tuning Based Approach for Daily Activity Recognition between Smart Homes

“…Ye et al proposed a method called XLearn [9]. This method is based on ontology and feature migration.…”

A Dynamic Time Warping-Based Method for Similarity Evaluation Between Smart Homes

“…The entire data processing flow is illustrated in Figure 2. Here, "sn" represents the original sensor names, "resn" denotes the renamed sensor names after sensor mapping, " " represents the numerical vectors of "resn", and " " represents the numerical vectors of daily activity samples, composed of multiple numerical vectors of sensor names triggered by the daily activity [10].…”