Meeting Room State Detection using Environmental Wi-Fi Signature

Abstract

The state of a meeting room (or of a classroom) provides important context to the level of interest (or participation level) in a meeting. For example, in one uninteresting meeting only one presenter presents text-filled slides, while other attendees are either checking their emails or even napping. In contrast, during a very interesting talk, all attendees are excited by the presentation and are involved in the discussions with frequent hand clapping. Thus, automatically detecting the state of a meeting room (or of a classroom) is an important and interesting problem. In this paper, we make the observation that the aforementioned group behaviors will have different motion signatures, as captured by a present Wi-Fi signal. Consequently, in this paper, we present a meeting room state detection approach leveraging environmental Wi-Fi signature. The Wi-Fi signal is provided by the existing access point (AP) in the meeting room and it is captured by one any Wi-Fi enabled device. The existing infrastructure provides all the information needed and no extra devices are needed. In our solution, different features are extracted from the raw Wi-Fi Received Signal Strength Indicator (RSSI) signal and four popular machine learning algorithms (e.g. support vector machine (SVM), decision tree, nearest neighbor and naive Bayes networks) are evaluated for detecting the state of a meeting room. Our approach is evaluated for two scenarios: classroom state detection and meeting room state detection. The experimental results show an accuracy of our proposed solution of 90.7% and 94.1% for classroom state detection and meeting/lab room state detection, respectively.