Abstract

Human activity recognition using multi-modal sensing tech-nologies to automatically collect and classify daily activities has become an active field of research. Given the prolifer-ation of smart and wearable devices and their greater ac-ceptance in human lives, the need for developing real time lightweight activity recognition algorithms become a viable and urgent avenue. Although variants of online and of-fline lightweight activity recognition algorithms have been developed, realizing them on real time to recognize peo-ple’s activities is still a challenging research problem due to the computational complexity of building, training, learning and storing activity models in resource constrained smart and wearable devices. To navigate the above challenges, we build Mobeacon: a mobile phone and iBeacon sensor-based smart home activity recognition system. We investi-gated the viability of extending Bagging Ensemble Learning (BEL) and Packaged Naive Bayes (PNB) classification al-gorithms for high-level activity recognition on smartphone. We incorporated the semantic knowledge of the testing en-vironment and used that with the built-in adaptive learning models on smartphone to ease the ground truth data annota-tion. We demonstrated that Mobeacon outperforms existing lightweight activity recognition techniques in terms of accu-racy (max. 94%) in a low resource setting and proves itself substantially efficient to reside on smartphones for recogniz-ing ADLs in real time.