作者: Mihai Marin-Perianu , Clemens Lombriser , Oliver Amft , Paul Havinga , Gerhard Tröster
DOI: 10.1007/978-3-540-69170-9_20
关键词:
摘要: Wireless sensor nodes can act as distributed detectors for recognizing activities online, with the final goal of assisting users in their working environment. We propose an activity recognition architecture based on fuzzy logic, through which multiple collaborate to produce a reliable result from unreliable data. As extension regular inference, we incorporate temporal order knowledge sequences operations involved activities. The performance evaluation is experimental data car assembly trial. system achieves overall 0.81 recall and 0.79 precision 0.85 when considering knowledge. also present early experiences implementing nodes. results show that algorithms run execution times 40ms, whole chain, memory overhead 1.5kB RAM.