| dc.description.abstract | A user (or human) mobility context is defined as a type of user context that describes a type of whole body posture (e.g., standing versus sitting) and/or a type of travel or transportation mode (e.g., walking, cycling, travel by bus, etc). Such a context can be derived from low-level sensor data and spatial contexts, including location coordinates, 3D-orientation, direction (with respect to magnetic north), velocity and acceleration. Different value-added services can be adapted to users’ mobility contexts such as assessing how eco-friendly our travel is, and adapting travel information services such as maps to different transportation modes. Current sensor-based methods for user mobility detection have several key limitations: narrow range of recognition, coarse user mobility recognition capability, and low recognition accuracy. In this thesis, a new Foot-Force and GPS (FF+GPS) sensor method is proposed to overcome these challenges that leverages a set of wearable FF sensors in combination with mobile phone GPS. The novelty of this approach is that it provides a more comprehensive recognition capability in terms of reliably recognising various fine-grained human postures and transportation modes. In addition, by comparing the new FF+GPS method with both an accelerometer (ACC) method (62% accuracy) and an ACC+GPS based method (70% accuracy) as baseline methods, it obtains a higher accuracy (90%) with less computational complexity, when tested on a dataset obtained from ten individuals.
In addition, the new FF+GPS method has been further extended and evaluated. More specifically, the trade-off between the computation and resources needed to support lower versus higher number of features and sensors has been investigated. The improved FF+GPS method reduced the number of classification features from 31 to 12, reduced the number of FF sensors from 8 to 4, and reduced the use of GPS in mobility activity recognition. | en_US |
