Dealing with the Effects of Sensor Displacement in Wearable Activity Recognition

Most wearable activity recognition systems assume a predefined sensor deployment that remains unchanged during runtime. However, this assumption does not reflect real-life conditions. During the normal use of such systems, users may place the sensors in a position different from the predefined sensor placement. Also, sensors may move from their original location to a different one, due to a loose attachment. Activity recognition systems trained on activity patterns characteristic of a given sensor deployment may likely fail due to sensor displacements. In this work, we innovatively explore the effects of sensor displacement induced by both the intentional misplacement of sensors and self-placement by the user. The effects of sensor displacement are analyzed for standard activity recognition techniques, as well as for an alternate robust sensor fusion method proposed in a previous work. While classical recognition models show little tolerance to sensor displacement, the proposed method is proven to have notable capabilities to assimilate the changes introduced in the sensor position due to self-placement and provides considerable improvements for large misplacements.

Proof of Concept of Impact Detection in Composites Using Fiber Bragg Grating Arrays

Impact detection in aeronautical structures allows predicting their future reliability and performance. An impact can produce microscopic fissures that could evolve into fractures or even the total collapse of the structure, so it is important to know the location and severity of each impact. For this purpose, optical fibers with Bragg gratings are used to analyze each impact and the vibrations generated by them. In this paper it is proven that optical fibers with Bragg gratings can be used to detect impacts, and also that a high-frequency interrogator is necessary to collect valuable information about the impacts. The use of two interrogators constitutes the main novelty of this paper.