Classification Filtering
This work addresses the challenge of real-time classification fusion for streaming signals, such as in wearable devices, but appears incremental as it builds on existing state-space models and filtering techniques.
The paper tackled the problem of fusing outputs from multiple classifiers in a streaming signal with temporal dependencies to improve classification accuracy, and demonstrated effectiveness in an activity classification application using IMU data from a wearable device.
We consider a streaming signal in which each sample is linked to a latent class. We assume that multiple classifiers are available, each providing class probabilities with varying degrees of accuracy. These classifiers are employed following a straightforward and fixed policy. In this setting, we consider the problem of fusing the output of the classifiers while incorporating the temporal aspect to improve classification accuracy. We propose a state-space model and develop a filter tailored for realtime execution. We demonstrate the effectiveness of the proposed filter in an activity classification application based on inertial measurement unit (IMU) data from a wearable device.