Motor imagery (MI) electroencephalography (EEG) signals are widely used in BCI systems. MI tasks are performed by imagining doing a specific task and classifying MI through EEG signal processing. However, it is a challenging task to classify EEG signals accurately. In this study, we propose a LSTM-based classification framework to enhance classification accuracy of four-class MI signals. To obtain time-varying data of EEG signals, a sliding window technique is used, and an overlapping-band-based FBCSP is applied to extract the subject-specific spatial features. Experimental results on BCI competition IV dataset 2a showed an average accuracy of 97% and kappa value of 0.95 in all subjects. It is demonstrated that the proposed method outperforms the existing algorithms for classifying the four-class MI EEG, and it also illustrates the robustness on the variability of inter-trial and inter-session of MI data. Furthermore, the extended experimental results for channel selection showed the best performance of classification accuracy when using all twenty-two channels by the proposed method, but an average kappa value of 0.93 was achieved with only seven channels.

Background: Metabolic syndrome is closely related to cardiovascular disease, and the prevalence of metabolic syndrome in postmenopausal women is increasing rapidly. Objective: The purpose of this study is to investigate the association between the number of breastfed children and the risk factors for metabolic syndrome in postmenopausal women and to evaluate the association between metabolic syndrome and bone mineral density and body composition variables in postmenopausal women depending on the number of breastfed children. Method: Data from KNHANES V-1 and 2 (2010-2011) were used, and a total of 939 PM women with 1 to 6 breastfed children aged 65-80 years participated in this study. We divided these women into three groups (group1 with 1-2, group2 with 3-4, group3 with 5-6) depending on the number of breastfed children. Result: In analysis of the associations between metabolic syndrome and its risk factors, high-density lipoprotein cholesterol was the most negatively strongly associated with group1 (OR=0.103 [0.047-0.225]), triglyceride showed the highest association with group2 (OR=7.760 [3.770-15.97]) and group3 (OR=7.668 [4.102-14.33]). The risk factors of metabolic syndrome except for high-density lipoprotein cholesterol and triglyceride was not associated with group1, while all risk factors of metabolic syndrome displayed a high association with group2 and group3. Conclusion: The findings of the present study suggest that the number of breastfed children is significantly associated with a greater number of risk factors of metabolic syndrome in postmenopausal women, and the association between metabolic syndrome and body composition variables may differ depending on the number of breastfed children.