TransAct: Transfer learning enabled activity recognition.

Go Back

Download PDF

Abstract:

Accurate estimation of localized occupancy related informa- tion in real time enables a broad range of intelligent smart environment applications. A large number of studies us- ing heterogeneous sensor arrays reflect the myriad require- ments of various emerging pervasive, ubiquitous and partic- ipatory sensing applications. In this paper, we introduce a zero-configuration and infrastructure-less smartphone based location specific occupancy estimation model. In our pro- posed model we combine acoustic (microphone), locomotive (accelerometer) and location (magnetometer) specific sensor of smartphone to derive fine-grained semantic location spe- cific occupancy information at zone/room level granularity. We opportunistically exploit smartphone’s acoustic sensors in a conversing environment and motion sensors in absence of any conversational data. We demonstrate a novel speaker estimation algorithm based on unsupervised clustering of overlapped and non-overlapped conversational data and a change point detection algorithm for locomotive motion of the users to infer the occupancy. We augment our occupancy detection model with a fingerprinting based methodology us- ing smartphone’s magnetometer sensor to accurately assim- ilate location information of any gathering. We postulate a novel crowdsourcing-based approach to annotate the seman- tic location of the occupancy. We evaluate our algorithms in different contexts; conversational, silence and mixed in presence of 10 domestic users. Our experimental results on real-life data traces in natural settings show that using this hybrid approach, we can achieve approximately 0.76 error count distance for occupancy detection accuracy on aver- age.