Wearable sensing devices can provide high-resolution data useful to characterise and identify complex human behaviours. Sensing human social interactions through wearable devices represents one of the emerging field in mobile social sensing, considering their impact on different user categories and on different social contexts. However, it is important to limit the collection and use of sensitive information characterising individual users and their social interactions in order to maintain the user compliance. For this reason, we decided to focus mainly on physical proximity and, specifically, on the analysis of BLE wireless signals commonly used by commercial mobile devices. In this work, we present the SocializeME framework designed to collect proximity information and to detect social interactions through heterogeneous personal mobile devices. We also present the results of an experimental data collection campaign conducted with real users, highlighting technical limitations and performances in terms of quality of RSS, packet loss, and channel symmetry, and how they are influenced by different configurations of the user’s body and the position of the personal device. Specifically, we obtained a dataset with more than 820.000 Bluetooth signals (BLE beacons) collected, with a total monitoring of over 11 h. The dataset collected reproduces 4 different configurations by mixing two user posture’s layouts (standing and sitting) and different positions of the receiver device (in hand, in the front pocket and in the back pocket). The large number of experiments in those different configurations, well cover the common way of holding a mobile device, and the layout of a dyad involved in a social interaction. We also present the results obtained by SME-D algorithm, designed to automatically detect social interactions based on the collected wireless signals, which obtained an overall accuracy of 81.56% and F-score 84.7%. The collected and labelled dataset is also released to the mobile social sensing community in order to evaluate and compare new algorithms.

可穿戴式传感设备可以提供高分辨率数据，这些数据可用于表征和识别复杂的人类行为。考虑到可穿戴设备对不同用户类别和不同社交环境的影响，通过可穿戴设备感知人类社交互动代表了移动社交感知领域的新兴领域之一。但是，重要的是限制收集和使用表征单个用户及其社交互动的敏感信息，以保持用户的依从性。因此，我们决定主要关注物理接近度，尤其是分析商用移动设备通常使用的BLE无线信号。在这项工作中，我们提出了SocializeME框架，该框架旨在收集邻近信息并通过异构个人移动设备检测社交互动。我们还介绍了与实际用户进行的实验性数据收集活动的结果，重点介绍了RSS的质量，丢包和通道对称性方面的技术局限性和性能，以及它们如何受到用户身体和位置的不同配置的影响个人设备的。具体来说，我们获得了一个收集了超过820.000个蓝牙信号（BLE信标）的数据集，总监控时间超过11小时。收集的数据集通过混合两个用户姿势的布局（站立和坐着）和接收器设备的不同位置（在手，在前口袋和后口袋中）来再现4种不同的配置。在这些不同配置下进行的大量实验很好地涵盖了手持移动设备的常见方式，以及参与社交互动的二分体的布局。我们还介绍了通过SME-D算法获得的结果，该算法旨在基于收集到的无线信号自动检测社交互动，从而获得了81.56％的整体准确度和F评分的84.7％。收集并标记的数据集也将发布到移动社交感知社区，以评估和比较新算法。