Feature selection for gesture recognition in Internet-of-Things for healthcare
This work addresses feature selection for gesture recognition in IoT healthcare, which is incremental as it builds on existing methods to improve efficiency and interpretability.
The paper tackled the problem of selecting relevant features for gesture recognition in IoT healthcare by proposing a new algorithm that robustly extracts and retains meaningful features, aiming to simplify recording setups and reduce data traffic.
Internet of Things is rapidly spreading across several fields, including healthcare, posing relevant questions related to communication capabilities, energy efficiency and sensors unobtrusiveness. Particularly, in the context of recognition of gestures, e.g., grasping of different objects, brain and muscular activity could be simultaneously recorded via EEG and EMG, respectively, and analyzed to identify the gesture that is being accomplished, and the quality of its performance. This paper proposes a new algorithm that aims (i) to robustly extract the most relevant features to classify different grasping tasks, and (ii) to retain the natural meaning of the selected features. This, in turn, gives the opportunity to simplify the recording setup to minimize the data traffic over the communication network, including Internet, and provide physiologically significant features for medical interpretation. The algorithm robustness is ensured both by consensus clustering as a feature selection strategy, and by nested cross-validation scheme to evaluate its classification performance.