نوع مقاله : مقاله های پژوهشی
1 دانشجوی دکتری، گروه مهندسی پزشکی، دانشکدهی زیست فناوری، دانشگاه سمنان، سمنان، ایران
2 استادیار، گروه مهندسی پزشکی، دانشکدهی زیست فناوری، دانشگاه سمنان، سمنان، ایران
عنوان مقاله [English]
Background: Stress detection is essential and important in order to control, manage, and reduce it. On the other hand, there are many theories about the stress-related back pain. The most important point in all of these theories, is the psychological and emotional factors that cause some kinds of physiological changes, and as a result, back pain. Therefore, it seems that the electromyogram (EMG) signal of the lower back muscles can be used as a marker for stress detection.Methods: In this research, stress was detected using the electromyogram signal of erector spinae muscles. The signals of 15 persons were recorded from left and right erector spinae muscles. After extracting seven time and frequency domain features, stress was detected in two-level (stress and no stress) and four-level (no stress, low stress, moderate stress, and high stress) modes applying an efficient support vector machine (SVM) classifier. It was also attempted to improve the performance of the proposed approach by using feature selection methods.Findings: In two-level mode, stress was detected with 100% of accuracy. In the four-level mode, the efficiency of the right erector spinae muscle was higher and reached 100% of accuracy.Conclusion: The results denote that the electromyogram of the erector spinae muscles is an appropriate indicator of stress. The right erector spinae muscle is more effective than the left one. Furthermore, feature selection reduces the computation amount, and improves the efficiency of stress detection. The findings of this study can be used to detect stress for controlling and managing it.