EMG classification in obstructive sleep apnea syndrome and periodic limb movement syndrome patients by using wavelet packet transform and extreme learning machine
Electromyogram (EMG) signals, measured at the skin surface, provide crucial access to the muscle tones of a body. Some diseases, such as obstructive sleep apnea syndrome (OSAS) and periodic limb movement syndrome (PLMS), are closely associated with the electrical activity of muscle tones. In this paper, a hybrid model containing wavelet packet transform (WPT) plus an extreme learning machine (ELM) was proposed to classify EMG signals in OSAS and PLMS patients. At first, the WPT was used to extract the features of the EMG signal, and then these features were fed to the ELM classifier. The mean classification accuracy of the ELM was 96.85%. The obtained overall results were significant enough for specialists to diagnose OSAS and PLMS diseases. Furthermore, a remarkable relationship between OSAS and PLMS has been revealed.
EMG classification in obstructive sleep apnea syndrome and periodic limb movement syndrome patients by using wavelet packet transform and extreme learning machine
Electromyogram (EMG) signals, measured at the skin surface, provide crucial access to the muscle tones of a body. Some diseases, such as obstructive sleep apnea syndrome (OSAS) and periodic limb movement syndrome (PLMS), are closely associated with the electrical activity of muscle tones. In this paper, a hybrid model containing wavelet packet transform (WPT) plus an extreme learning machine (ELM) was proposed to classify EMG signals in OSAS and PLMS patients. At first, the WPT was used to extract the features of the EMG signal, and then these features were fed to the ELM classifier. The mean classification accuracy of the ELM was 96.85%. The obtained overall results were significant enough for specialists to diagnose OSAS and PLMS diseases. Furthermore, a remarkable relationship between OSAS and PLMS has been revealed.
___
- 4% and 81.4% for apnea and hypopnea detection, respectively. In [25], Maier et al. used a single channel of
- an ECG signal and a second-order polynomial classifier for apnea detection. They found an accuracy rate of 93%. Unlike some previous studies [1,14–16], in the present study, EMG signals were classified with a simple
- and effective model in OSAS and PLMS patients. The overall classification accuracy was 96.85% using training
- and testing sections of 50% and 50%. Furthermore, the network is very fast both in the training and testing
- phases according to the conventional machine learning methods. The diagnosis accuracy and time of the model
- for OSAS and PLMS patients is presented in Table 5. For comparison, the results of the SVM and ANN are
- also presented in Table 5. The ELM can both result in higher classification accuracy and give the decision faster
- than conventional learning methods. It is thought that the proposed model will be a helpful tool for experts with their final decision-making
- in order to classify or diagnose some medical diseases such as OSAS and PLMS.