Multiclassifier system with hybrid learning applied to the control of bioprosthetic hand

sEMG-Based Natural Control Interface for a Variable Stiffness Transradial Hand Prosthesis

We propose, implement, and evaluate a natural human-machine control interface for a variable stiffness transradial hand prosthesis that achieves tele-impedance control through surface electromyography (sEMG) signals. This interface, together with variable stiffness actuation (VSA), enables an amputee to modulate the impedance of the prosthetic limb to properly match the requirements of a task while performing activities of daily living (ADL). Both the desired position and stiffness references are estimated through sEMG signals and used to control the VSA hand prosthesis. In particular, regulation of hand impedance is managed through the impedance measurements of the intact upper arm; this control takes place naturally and automatically as the amputee interacts with the environment, while the position of the hand prosthesis is regulated intentionally by the amputee through the estimated position of the shoulder. The proposed approach is advantageous since the impedance regulation takes place naturally without requiring amputees' attention and diminishing their functional capability. Consequently, the proposed interface is easy to use, does not require long training periods or interferes with the control of intact body segments. This control approach is evaluated through human subject experiments conducted over able volunteers where adequate estimation of references and independent control of position and stiffness are demonstrated.

A Correction Method of a Base Classifier Applied to Imbalanced Data Classification

In this paper, the issue of tailoring the soft confusion matrix classifier to deal with imbalanced data is addressed. This is done by changing the definition of the soft neighbourhood of the classified object. The first approach is to change the neighbourhood to be more local by changing the Gaussian potential function approach to the nearest neighbour rule. The second one is to weight the instances that are included in the neighbourhood. The instances are weighted inversely proportional to the a priori class probability. The experimental results show that for one of the investigated base classifiers, the usage of the KNN neighbourhood significantly improves the classification results. What is more, the application of the weighting schema also offers a significant improvement.

A Correction Method of a Binary Classifier Applied to Multi-Label Pairwise Models

In the paper, the problem of multi-label (ML) classification using the label-pairwise (LPW) scheme is addressed. For this approach, the method of correction of binary classifiers which constitute the LPW ensemble is proposed. The correction is based on a probabilistic (randomized) model of a classifier that assesses the local class-specific probabilities of correct classification and misclassification. These probabilities are determined using the original concepts of a randomized reference classifier (RRC) and a local soft confusion matrix. Additionally, two special cases that deal with imbalanced labels and double labeled instances are considered. The proposed methods were evaluated using 29 benchmark datasets. In order to assess the efficiency of the introduced models and the proposed correction scheme, they were compared against original binary classifiers working in the LPW ensemble. The comparison was performed using four different ML evaluation measures: macro and micro-averaged [Formula: see text] loss, zero-one loss and Hamming loss. Moreover, relations between classification quality and the characteristics of ML datasets such as average imbalance ratio or label density were investigated. The experimental study reveals that the correction approaches significantly outperform the reference method in terms of zero-one loss and Hamming loss.

Computer-aided training sensorimotor cortex functions in humans before the upper limb transplantation using virtual reality and sensory feedback

One of the biggest problems of upper limb transplantation is lack of certainty as to whether a patient will be able to control voluntary movements of transplanted hands. Based on findings of the recent research on brain cortex plasticity, a premise can be drawn that mental training supported with visual and sensory feedback can cause structural and functional reorganization of the sensorimotor cortex, which leads to recovery of function associated with the control of movements performed by the upper limbs. In this study, authors - based on the above observations - propose the computer-aided training (CAT) system, which generating visual and sensory stimuli, should enhance the effectiveness of mental training applied to humans before upper limb transplantation. The basis for the concept of computer-aided training system is a virtual hand whose reaching and grasping movements the trained patient can observe on the VR headset screen (visual feedback) and whose contact with virtual objects the patient can feel as a touch (sensory feedback). The computer training system is composed of three main components: (1) the system generating 3D virtual world in which the patient sees the virtual limb from the perspective as if it were his/her own hand; (2) sensory feedback transforming information about the interaction of the virtual hand with the grasped object into mechanical vibration; (3) the therapist's panel for controlling the training course. Results of the case study demonstrate that mental training supported with visual and sensory stimuli generated by the computer system leads to a beneficial change of the brain activity related to motor control of the reaching in the patient with bilateral upper limb congenital transverse deficiency.