A log-linearized Gaussian mixture network and its application to EEG pattern classification

Lecture Notes in Computer Science

2005

Abstract. Feature extraction is an important issue in electromyography (EMG) pattern classification, where feature sets of high dimensionality are always used. This paper proposes a novel classification method to deal with high-dimensional EMG patterns, using a probabilistic neural network, a reduced-dimensional log-linearized Gaussian mixture network (RD-LLGMN) [1]. Since RD-LLGMN merges feature extraction and pattern classification processes into its structure, lower-dimensional feature set consistent with classification purposes can be extracted, so that, better classification performance is possible. To verify feasibility of the proposed method, phoneme classification experiments were conducted using frequency features of EMG signals measured from mimetic and cervical muscles. Filter banks are used to extract frequency features, and dimensionality of the features grows significantly when we increase resolution of frequency. In these experiments, the proposed method achieved considerably high classification rates, and outperformed traditional methods that are based on principle component analysis (PCA).

Section: Comparison Experimentsmentioning

confidence: 99%

A Novel Pattern Classification Method for Multivariate EMG Signals Using Neural Network

Arita

Lecture Notes in Computer Science

2005

“…In this method, a probabilistic NN that is derived from the Gaussian mixture model (GMM), called a log-linearized Gaussian mixture network (LLGMN) [2], is utilized for partition at each non-terminal node. The proposed method can estimate the number of terminal nodes corresponding to the number of classes according to the statistical information obtained solely from the training data.…”

Section: Fig 1 Structure Of Llgmnmentioning

confidence: 99%

“…In order to discriminate an operater's intentions from bioelectric signals efficiently, several attempts have been made so far [1], [2]. Generally, such pattern discrimination is performed by estimating the relationship between the bioelectric signals as feature vectors and the corresponding intentions as class labels.…”

Section: Introductionmentioning

confidence: 99%

“…However, when parameters in this method were not set up appropriately, such method may fail to perform satisfying clustering for complicated data. Oc,m (2) OC, M C…”

Section: Introductionmentioning

confidence: 99%

“…This paper proposes a novel hierarchical clustering method that can classify given data without specified knowledge of the number of classes. In this method, at each node of a hierarchical classification tree, log-linearized Gaussian mixture networks [2] are utilized as classifiers to divide data into two subclasses based on statistical information, which are then classified into secondary subclasses and so on. Also, unnecessary structure of the tree can be avoided by training in a cross-validation manner.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Unsupervised Learning for Hierarchical Clustering Using Statistical Information

Okamoto

Advances in Neural Networks – ISNN 2004

2004

Abstract. This paper proposes a novel hierarchical clustering method that can classify given data without specified knowledge of the number of classes. In this method, at each node of a hierarchical classification tree, log-linearized Gaussian mixture networks [2] are utilized as classifiers to divide data into two subclasses based on statistical information, which are then classified into secondary subclasses and so on. Also, unnecessary structure of the tree can be avoided by training in a cross-validation manner. Validity of the proposed method is demonstrated with classification experiments on artificial data.

Pattern classification of time-series EMG signals using neural networks

Int. J. Adapt. Control Signal Process.

Fukuda

Kaneko

et al. 2000

This paper proposes a pattern classification method of time‐series EMG signals for prosthetic control. To achieve successful classification for non‐stationary EMG signals, a new neural network structure that combines a common back‐propagation neural network with recurrent neural filters is used. A convergence time of the network learning can be regulated by a new learning method based on dynamics of a terminal attractor. The experiments of pattern classification and prosthetic control are carried out for several subjects including an amputee. It is shown from the results that the proposed method improves learning/classification ability for stationary and non‐stationary EMG signals during a series of continuous motions. Copyright © 2000 John Wiley & Sons, Ltd.