Collecting complex activity datasets in highly rich networked sensor environments

TLDR

The study aims to use the dataset to develop sensor‑network self‑organization principles and machine‑learning techniques for activity recognition in opportunistic sensor configurations, and to make the dataset publicly available. The authors deployed 72 multimodal sensors across 15 wired and wireless networked systems, collected more than 25 hours of data from 12 subjects performing morning activities, and applied a systematic acquisition, synchronization, and curation methodology. Post‑processing revealed more than 13 000 object and 14 000 environment interactions, the data acquisition suffered less than 2.5 % packet loss after tuning, and the authors identified key challenges and best practices for large‑scale heterogeneous sensor deployments.

Abstract

We deployed 72 sensors of 10 modalities in 15 wireless and wired networked sensor systems in the environment, in objects, and on the body to create a sensor-rich environment for the machine recognition of human activities. We acquired data from 12 subjects performing morning activities, yielding over 25 hours of sensor data. We report the number of activity occurrences observed during post-processing, and estimate that over 13000 and 14000 object and environment interactions occurred. We describe the networked sensor setup and the methodology for data acquisition, synchronization and curation. We report on the challenges and outline lessons learned and best practice for similar large scale deployments of heterogeneous networked sensor systems. We evaluate data acquisition quality for on-body and object integrated wireless sensors; there is less than 2.5% packet loss after tuning. We outline our use of the dataset to develop new sensor network self-organization principles and machine learning techniques for activity recognition in opportunistic sensor configurations. Eventually this dataset will be made public.