Details

Autor(en) / Beteiligte

• Zhang, Mi
• Sawchuk, Alexander

Titel

USC-HAD: a daily activity dataset for ubiquitous activity recognition using wearable sensors

Ist Teil von

• Proceedings of the 2012 ACM Conference on ubiquitous computing, 2012, p.1036-1043

Ort / Verlag

ACM

Erscheinungsjahr

2012

Link zum Volltext

Quelle

ACM Digital Library (Association for Computing Machinery)

Beschreibungen/Notizen

• Many ubiquitous computing applications involve human activity recognition based on wearable sensors. Although this problem has been studied for a decade, there are a limited number of publicly available datasets to use as standard benchmarks to compare the performance of activity models and recognition algorithms. In this paper, we describe the freely available USC human activity dataset (USC-HAD), consisting of well-defined low-level daily activities intended as a benchmark for algorithm comparison particularly for healthcare scenarios. We briefly review some existing publicly available datasets and compare them with USC-HAD. We describe the wearable sensors used and details of dataset construction. We use high-precision well-calibrated sensing hardware such that the collected data is accurate, reliable, and easy to interpret. The goal is to make the dataset and research based on it repeatable and extendible by others.