Discovering Human Presence Activities with Smartphones Using Nonintrusive Wi-Fi Sniffer Sensors: The Big Data Prospective

With the explosive growth and wide-spread use of smartphones with Wi-Fi enabled, people are used to accessing the internet through Wi-Fi network interfaces of smartphones. Smartphones periodically transmit Wi-Fi messages, even when not connected to a network. In this paper, we describe the Mo-Fi system which monitors and aggregates large numbers of continuous Wi-Fi message transmissions from nearby smartphones in the area of interest using nonintrusive Wi-Fi sniffer sensors. In this paper, we propose an optimized Wi-Fi channel detection and selection method to switch the best channels automatically to aggregate the Wi-Fi messages based on channel data transmission weights and human presence activity classification method based on the features of human dwell duration sequences in order to evaluate the user engagement index. By deploying in the real-world office environment, we found that the performance of Wi-Fi messages aggregation of CAOCA and CACFA algorithms is over 3.8 times higher than the worst channel of FCA algorithms and about 76% of the best channel of FCA algorithms, and the human presence detection rate reached 87.4%. 1. Introduction Big data is leading a new prospective of data computation, storage, analysis, and mining in the recent years [1–3]. With the explosive growth and wide-spread use of smartphones with Wi-Fi enabled, people are used to accessing the internet, for example, watching videos on Youtube and chatting on Facebook through Wi-Fi network interfaces of smartphones in the area where Wi-Fi hotspots are deployed in order to save network traffic costs. In the meanwhile, about 40% to 70% of people always turn on Wi-Fi network interface of smartphones instead of turning it off for energy savings. Smartphones with Wi-Fi enabled periodically transit Wi-Fi probe messages, even when not connected to a Wi-Fi network [4]. When smartphones detect and connect to Wi-Fi hotspots in the area of interest, the background programs and services of operating systems in the smartphones can generate large numbers of data transmissions, for example, Apple iOS message push notification service and Android message notification service. As Wi-Fi network interface in the smartphones has the unique MAC address, it is possible to identify the smartphone’s owner and distinguish his presence in the area of interest. By deploying Wi-Fi sniffer sensors in the area of interest, it is possible to capture Wi-Fi message transmissions without disturbing the normal daily use of smartphones, and to analyze the situation of humans stay and even the coarse-grained