Stream multi-class imbalance learning in smart home applications is an evolving learning area that incorporates the challenges of both multi-class imbalance and stream learning. Another reason for learning from imbalanced multi-class distributions that cause misleading classification outcomes, is the imbalanced ratio in a sensor data stream which is vigorously changing. Furthermore, segmenting sensor-based events to recognize activities which plays a main role in smart homes is another problem which needs to be considered. More specifically, it has many key challenges due to its unsupervised nature, the real-time requirements necessary for on-line event detection, and the possibility of having to recognise overlapping activities. A final challenge is to achieve robustness of classification due to sub-optimal choice of window size.
In this talk, we present a novel real-time recognition framework to address these problems. The proposed framework is divided into two phases: off-line modelling and on-line recognition. In the off-line phase a representation called Activity Features (AFs) are built from statistical information about the activities from annotated sensory data and a Naive Bayesian (NB) classifier is modelled accordingly. In the on-line phase, a dynamic multi-feature windowing approach using AFs and the learnt NB classifier is introduced to segment unlabelled sensor data as well as predicting the related activity. We illustrate the effectiveness of the proposed method on smart home testbed datasets.
Last modified: Tuesday, 09-May-2017 14:04:08 NZST
This page is maintained by the seminar list administrator.