18 April 2013 in IEEE Sensors Journal
This paper proposes and evaluates methods of nonlinear feature extraction and nonlinear classification to identify different hand manipulations based on surface electromyography (sEMG) signals. The nonlinear measures are achieved based on the recurrence plot to represent dynamical characteristics of sEMG during hand movements. Fuzzy Gaussian Mixture Models (FGMMs) are proposed and employed as a nonlinear classifier to recognise different hand grasps and in-hand manipulations captured from different subjects. Various experiments are conducted to evaluate their performance by comparing 14 individual features, 19 multifeatures and 4 different classifiers. The experimental results demonstrate the proposed nonlinear measures provide important supplemental information and they are essential to the good performance in multifeatures. It is also shown that FGMMs outperform commonly used approaches including Linear Discriminant Analysis, Gaussian Mixture Models and Support Vector Machine in terms of the recognition rate. The best performance with the recognition rate of 96.7% is achieved by using FGMMs with the multifeature combining Willison Amplitude and Determinism.
18 April 2013 in Systems Research and Behavioral Science
27 June 2013 in IEEE Systems Journal
Decision-making processes in complex systems generally require the mechanisms to make the tradeoff among contradicting design criteria. When multiple objectives are involved in decision making or machine learning, a crucial step is to determine the weights of individual objectives to the system-level performance. Determining the weights of multiobjectives is an evaluation process, and it has been often treated as an optimization problem. However, our preliminary investigation has shown that existing methodologies in dealing with the weights of multiobjectives have some obvious limitations in the sense that the determination of weights is tackled as a single optimization problem, a result based on such an optimization is incomprehensive, and it can even be unreliable when the information about multiple objectives is incomplete such as an incompleteness caused by poor data. The constraints of weights are also discussed. Variable weights are natural in decision-making processes. Therefore, we are motivated to develop a systematic methodology in determining variable weights of multiobjectives. The roles of weights in an original multiobjective decision-making or machine-learning problem are analyzed, and the weights are determined with the aid of a modular neural network. The inconsistency issue of weights is particularly discussed.
8 April 2013 in Systems Research and Behavioral Science