摘要：In the context of activity recognition, wearable devices are nowadays the preferablehardware thanks to their usability, user experience and performances; at the same time,these devices present limitations in terms of computational capability and memory, whichforce the algorithm design to be at the same time efficient and simple. In this work, we adoptSymbolic Aggregate Approximation (SAX), a symbolic approach for information retrieval intime series data that allows dimensionality and numerosity reduction; SAX is employed here,in combination with 1-Nearest Neighbor classifier, to identify activity phases in continuousrepetitive activities from inertial time-series data. The proposed appr
