Spectral Collaborative Representation based Classification for hand gestures recognition on electromyography signals

Abstract

a b s t r a c tThe classification of the bio-signal has been used for various purposes in the literature as they are versatile in diagnosis of anomalies, improvement of overall health and sport performance and creating intuitive human computer interfaces. However, automatic identification of the signal patterns on a streaming real-time signal requires a series of complex procedures. A plethora of heuristic methods, such as neural networks and fuzzy systems, have been proposed as a solution. These methods stipulate certain conditions, such as preconditioning the signals, manual feature selection and large number of training samples.In this study, we introduce a novel variant and application of the Collaborative Representation based Classification (CRC) in spectral domain for recognition of hand gestures using raw surface electromyography (EMG) signals. The CRC based methods do not require large number of training samples for an efficient pattern classification. Additionally, we present a training procedure in which a high end subspace clustering method is employed for clustering the representative samples into their corresponding class labels. Thereby, the need for feature extraction and spotting patterns manually on the training samples is obviated.We presented the intuitive use of spectral features via circulant matrices. The proposed Spectral Collaborative Representation based Classification (SCRC) is able to recognize gestures with higher levels of accuracy for a fairly rich gesture set compared to the available methods. The worst recognition result which is the best in the literature is obtained as 97.3% among the four sets of the experiments for each hand gestures. The recognition results are reported with a substantial number of experiments and labeling computation.

On the robustness of real-time myoelectric control investigations: a multiday Fitts’ law approach

“…The signal from the hardware is transmitted wirelessly to a computer using the Bluetooth Low Energy (BLE) protocol. This system provides a good research platform and has now been used in different studies [36][37][38]. In each experimental session, subjects were first guided about the experimental protocol and they were asked to produce a medium level contraction from rest to motion, prompted by the image of the selected motion using a custom-made Graphical User Interface (Figure 1b).…”

Review of Three-Dimensional Human-Computer Interaction with Focus on the Leap Motion Controller

“…Matos et al [ 76 ] identified leg gestures with the Myo sensor (see Section 2.2 ) by division of gestures into five moments and a ranking approach to provide a HCI solution for upper limb amputees. Boyali et al [ 159 ] use the Myo sensor to detect the eight Myo hand gestures (s. Section 2.2 ). Spectral Collaborative Representation based Classification (CRC) using the Eigenvalues of observed signals as features is used for gesture recognition with an accuracy of more than 97.3%.…”

Gesture recognition based on sparse representation

“…Given n k training samples from k-th class as columns of a matrix But the problem of finding the solution of l 0 -norm is NP-hard, so approximate solutions are adopted generally. Algorithms of research include: greedy algorithm, including matching tracking algorithm, orthogonal matching pursuit algorithm, etc., to realise signal approximation through choosing appropriate atoms and a series of progressively increasing method (Boyali and Hashimoto, 2016). Convex optimisation algorithm, including gradient projection method, tracking methods the minimum point of regression method, etc., put the l 0 -norm relax to l 1 -norm by solving linear programming (Khan and Raja, 2016).…”