BeSense: Leveraging WiFi Channel Data and Computational Intelligence for Behavior Analysis

Abstract

The ever evolving informatics technology has gradually bounded human and computer in a compact way. Understanding user behavior becomes a key enabler in many fields such as sedentary-related healthcare, human-computer interaction (HCI) and affective computing. Traditional sensor-based and vision-based user behavior analysis approaches are obtrusive in general, hindering their usage in real world. Therefore, in this article, we first introduce WiFi signal as a new source instead of sensor and vision for unobtrusive user behaviors analysis. Then we design BeSense, a contactless behavior analysis system leveraging signal processing and computational intelligence over WiFi channel state information (CSI). We prototype BeSense on commodity low-cost WiFi devices and evaluate its performance in realworld environments. Experimental results have verified its effectiveness in recognizing user behaviors. their exercise time. Its side effects like sedentary behavior (SB) pose great threats to people's wellness [1]. Therefore, understanding user behavior, like knowing whether the user is working, gaming or surfing and how long s/he has been doing it, emerges as a key to spot such heath risk factors. Moreover, it constitutes a promising enabler to many other fields like human-computer interaction (HCI) and affective computing (AC).In general, there are two types of approaches to understand user behavior. The traditional vision-based approach leverages video as the main source, where cameras are deployed to record and infer user behavior [2]- [4]. The vision-based approach is effective because of the mature Computer Vision (CV) technology. However, it makes users to concern about their privacy. Also, inherent defects of CV like line-of-sight and illumination constraints further jeopardize its usage in practice. Sensor is another typical source, where wearable sensors are attached to the human body to capture body gestures and deduce the corresponding user behavior [5]- [7]. Sensor has a limited sensing range, and thus multiple sensors are needed at different parts of the human body to ensure a complete coverage of user gestures. Unfortunately, such deployment is obtrusive for the user, hindering its practicability in real-world scenarios.In this article, we introduce WiFi signal, which is insensible to users, as an alternative source to vision and sensor for perceiving user behavior. The key reason behind is that the human body reflects or absorbs WiFi signal, and thus changes the WiFi channel state information (CSI)[8]- [10]. The inherent research problem is how to exploit WiFi CSI that contains rich behavior information to retrieve micro-gestures like keystrokes and mouse movements for understanding the corresponding user behavior?Our response to the question is three-fold. Firstly, we explore signal processing to improve the sensing granularity of WiFi CSI. In particular, we build a Fresnel-zone based model to guide the antenna deployment to enhance minor signal changes caused by user's micro-gestures. Then, we design a ligh...

Construction of Internet TV Industry Ecosystem Based on Data Mining Technology

“…Therefore, the classification and identification of web pages clicked by users is an important part of analyzing users' behaviors and intentions. Using the DBN classification prediction system, SVM model, and literature [20] method, the same training data and test data are modeled and predicted, respectively. For each binary model, 10 repeated experiments of randomly selected test data are conducted, and the prediction accuracy is counted.…”

“…From these figures, whether it is binary classification or multiple classification, DBN classification prediction system, SVM classification model, and literature [20] method can achieve very high accuracy, but the DBN classification prediction system is better.…”

“…As the Internet has grown in popularity and information technology has advanced, a large amount of data has accumulated on the Internet. Literature [20] used crawling technology to collect more accurate Twitter data than previous studies and investigated the topology structure of the Twitter network, user ranking method, hot topic propagation mode, and other aspects, resulting in a quantitative analysis of the Twitter network and its information distribution. Literature [21] examines Twitter users' emotions and attitudes toward television programming, as well as the feasibility of gathering TV viewers' cognitive behaviors about programming from online social media.…”

WiFi gesture recognition method based on data enhancement

“…It covers the amplitude and phase information of each subcarrier in the frequency domain. This information can reflect a variety of phenomena such as amplitude attenuation, phase offset and delay [26,27,28] . For a given antenna pair at time t, the received signal on a subcarrier with frequency f is shown in formula 1.…”

Non-Contact Heart Rate Monitoring Method Based on Wi-Fi CSI Signal

“…The widespread availability of Wi-Fi devices and the convenience of wireless sensing technology have fostered the flourishing development of passive sensing research based on Wi-Fi [16][17][18]. Such studies typically focus on the Received Signal Strength Indicator (RSSI) or Channel State Information (CSI).…”