Andrzej Wolczowski

Human–machine interface in bioprosthesis control using EMG signal classification

: We present a concept of human–machine interface intended for the task of bioprosthesis decision control by means of sequential recognition of the patients intent based on the electromyography (EMG) signal acquired from his/her body. The EMG signal characteristics, the problem of processing the signals including acquisition and feature extraction and their classification are discussed. The contextual (sequential) recognition via fuzzy relations for the classification of the patients intent is considered and the implied decision algorithms are presented. In the proposed method, the fuzzy relation is determined on the basis of the learning set as a solution of an appropriate optimization problem and then this relation is used in the form of a matrix of membership degrees at successive instants of the sequential decision process. Three algorithms of sequential classification which differ from one another in the sets of input data and procedure are described. The proposed algorithms were experimentally tested in the recognition of phases of the grasping process of the hand on the basis of the EMG signal, where the real-coded genetic algorithm was used as an optimization procedure. The concept of the measurement stand which was the source of information exploited in the experimental investigations of the algorithms is also described.

Brief paper: Hand movement recognition based on biosignal analysis

This paper proposes a methodology that analyses and classifies the electromyographic (EMG) signals using neural networks to control multifunction prostheses. The control of these prostheses can be made using myoelectric signals taken from surface electrodes. Finger motions discrimination is the key problem in this study. Thus the emphasis, in the proposed work, is put on myoelectric signal processing approaches. The EMG signals classification system was established using the linear neural network. The experimental results show a promising performance in classification of motions based on biosignal patterns.

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

In this paper the problem of recognition of the intended hand movements for the control of bio-prosthetic hand is addressed. The proposed method is based on recognition of electromiographic (EMG) and mechanomiographic (MMG) biosignals using a multiclassifier system (MCS) working in a two-level structure with a dynamic ensemble selection (DES) scheme and original concepts of competence function. Additionally, feedback information coming from bioprosthesis sensors on the correct/incorrect classification is applied to the adjustment of the combining mechanism during MCS operation through adaptive tuning competences of base classifiers depending on their decisions. Three MCS systems operating in decision tree structure and with different tuning algorithms are developed. In the MCS1 system, competence is uniformly allocated to each class belonging to the group indicated by the feedback signal. In the MCS2 system, the modification of competence depends on the node of decision tree at which a correct/incorrect classification is made. In the MCS3 system, the randomized model of classifier and the concept of cross-competence are used in the tuning procedure. Experimental investigations on the real data and computer-simulated procedure of generating feedback signals are performed. In these investigations classification accuracy of the MCS systems developed is compared and furthermore, the MCS systems are evaluated with respect to the effectiveness of the procedure of tuning competence. The results obtained indicate that modification of competence of base classifiers during the working phase essentially improves performance of the MCS system and that this improvement depends on the MCS system and tuning method used.

Control of Dexterous Hand Via Recognition of EMG Signals Using Combination of Decision-Tree and Sequential Classifier

The paper presents a concept of bioprosthesis control via recognition of user’s intent. The set of elementary actions has been defined. We assume that each prosthesis operation consists of specific sequence of elementary actions. An example of prosthesis operations that can be composed into a decision tree is also presented. As a classifier the multistage recognition system is proposed, which combines sequential and decision-tree classifiers and its decisions are made on the basis of EMG signal analysis.

Control of Artificial Hand via Recognition of EMG Signals

The paper presents a concept of bioprosthesis control via recognition of user intent on the basis of myopotentials acquired from his body. The EMG signals characteristics and the problems of their measurement have been discussed. The contextual recognition has been considered and three description method for such approach (respecting 1st and 2nd -order context), using: Markov chains, fuzzy rules, neural networks, as well as the involved decision algorithms have been described. The algorithms have been experimentally tested as far as the decision quality is concerned.

Hardware approach to the artificial hand control algorithm realization

The concept of the bioprosthesis control system implementation in the dedicated hardware is presented. The complete control algorithm was analysed and the decomposition revealing the parts which could be calculated concurrently was made. Specialized digital circuits providing the wavelet transform and the neural network calculations were designed and successfully verified. The experiment results show that the proposed solution provides the desired dexterity and agility of the artificial hand.

Control system of bioprosthetic hand based on advanced analysis of biosignals and feedback from the prosthesis sensors

The paper presents an advanced method of recognition of patients intention to move of multijoint hand prosthesis during the grasping and manipulation of objects in a dexterous manner. The proposed method is based on two-level multiclassifier system with heterogeneous base classifiers dedicated to particular types of biosignals (EMG, MMG and EEG) and with combining mechanism using a dynamic ensemble selection scheme and probabilistic competence fuction. Additionally, the feedback signal derived from the prosthesis sensors is applied to the correction algorithm of classification results. The classification methodology developed can be practically applied to the design of dexterous bioprosthetic hand and in the computer system for learning motor coordination, dedicated to individuals preparing for a prosthesis or waiting for a hand transplantation.

Two-Stage Multiclassifier System with Correction of Competence of Base Classifiers Applied to the Control of Bioprosthetic Hand

The paper presents an advanced method of recognition of patients intention to move hand prosthesis during the grasping and manipulation of objects in a dexterous manner. The proposed method is based on recognition of electromiographic (EMG) and mechanomiographic (MMG) bio signals using two-stage hierarchical multiclassifier system (MCS) with dynamic ensemble selection scheme (DES) and probabilistic competence function. Additionally, the feedback signals derived from the prosthesis sensors are applied to the correction of competences of base classifiers during MCS operation. The performance of proposed MCS was experimetally compared against MCSs without feedback information and with one-stage structure using real data concerning the recognition of five types of grasping movements. The system developed achieved the highest classification accuracy demonstrating the potential of two-stage MCS with feedback signals from prosthesis sensors for the control of bio prosthetic hand.

Hetero- and Homogeneous Multiclassifier Systems Based on Competence Measure Applied to the Recognition of Hand Grasping Movements

The paper presents an advanced method of recognition of patient’s intention to move of multijoint hand prosthesis during the grasping and manipulating objects in a dexterous manner. The proposed method is based on a two-level multiclassifier system (MCS) with heterogeneous and homogeneous base classifiers dedicated to EMG and MMG biosignals and with combining mechanism using a dynamic ensemble selection scheme and probabilistic competence function. The performances of two MCSs with the proposed competence function and combining procedure were experimetally compared against three benchmark MCSs using real data concerning the recognition of six types of grasping movements. The systems developed achieved the highest classification accuracies demonstrating the potential of multiple classifier systems with multimodal biosignals for the control of bioprosthetic hand.

Control of dexterous hand - algorithm implementation issues

This paper relates to the research on a dexterous hand prosthesis conducted at the Wroclaw University of Technology. The possibility of aiding the prosthesis control system by utilization of application specific digital circuits is presented. Several exemplary designs, prepared during some of to-date works conducted by authors, have been presented. Discussed solutions are part of a bigger project that is still ongoing and are still being developed.