Combining Pattern Classifiers: Methods and Algorithms
Combining Pattern Classifiers: Methods and Algorithms
A Measure of Competence Based on Randomized Reference Classifier for Dynamic Ensemble Selection
ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition
A probabilistic model of classifier competence for dynamic ensemble selection
Pattern Recognition
HAIS'11 Proceedings of the 6th international conference on Hybrid artificial intelligent systems - Volume Part II
Hi-index | 0.00 |
The paper presents an advanced method of recognition of patient's 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.