Sensing, tracking and contextualizing entities in ubiquitous computing
Antônio A. F. Loureiro · 2012
Information and Communications Technology is increasingly becoming a part of our daily activities. Nowadays, we are able to sense a broad range of entities in the world: from physical entities that comprise the Internet of Things (IoT) to social entities that include people in social networks. We can expect to have a ubiquitous sensing infrastructure in different environments, with varying needs and complexities. While these sensors/entities are mostly static, smart phones are taking center stage as the most widely adopted and ubiquitous computing device. Smart phones have enormous potential for the study of human social networks and human behavior "in vivo," in a natural context outside laboratories. Besides their computing power, smart phones are currently available with an increasing rich set of embedded sensors, such as GPS, accelerometer, microphone, camera, gyroscope and digital compass. Sensing vast areas becomes more feasible when people carrying their portable devices collect data and collaborate among themselves. Systems that enable sensed data in this way are named participatory sensing systems (PSSs). In those networks, the shared data is not limited to sensor readings passively generated by the device, but also includes proactive user observations. A challenge is how to obtain meaningful information from this large amount of data at different scales along the time. Some of the traditional techniques that have been used to process those distinct data sources are information fusion, data mining and machine learning. Notice that the consumers of such information can be, in one extreme, a large set of cooperating or non-cooperating entities, and, in the other, an individual or a "thing", for instance.