Development of a driver drowsiness monitoring system using electrocardiogram
Driver drowsiness has become a common issue that leads to road accidents and death. Accidents not only affect the physical body of the driver, but it also affects people in the surrounding, physical road conditions, and environments. It is proven in previous studies that biological signal are closel...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Faculty of Electronic and Computer Engineering (FKEKK), Universiti Teknikal Malaysia Melaka (UTeM)
2018
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/63338/ http://irep.iium.edu.my/63338/ http://irep.iium.edu.my/63338/1/3655-9759-1-SM.pdf http://irep.iium.edu.my/63338/7/63338%20Development%20of%20a%20driver%20drowsiness%20monitoring%20system%20using%20electrocardiogram%20SCOPUS.pdf |
| Summary: | Driver drowsiness has become a common issue that leads to road accidents and death. Accidents not only affect the physical body of the driver, but it also affects people in the surrounding, physical road conditions, and environments. It is proven in previous studies that biological signal are closely related to a person’s reaction. Electrocardiogram (ECG), which is an electrical indicator of the heart, provides such criteria as it reflects the heart activity. Morphological signal of the heart is strongly correlated to our actions which relates to our emotions and reactions. Thus, this study proposed a non-intrusive detector to detect driver drowsiness by using the ECG. A total of 10 subjects were obtained from The Cyclic Alternating Pattern (CAP) Sleep database. The signals are later processed using low pass Butterworth filter with 0.1 cutoff frequency. Then, QRS complexes are extracted from the acquired ECG signal. Classification techniques such as RR interval and different of amplitude at R peak were used in order to differentiate between normal and drowsy ECG signal. Cardioid based graph was used to support the argument made in analyzing area and circumference of both normal and drowsy graph. The result shows that RR Interval of a drowsy state increased almost 22% rather than in normal state. The percentage different of amplitude difference at R peak between normal and drowsy state can reach up to 36.33%. In terms of cardioid, area, perimeter and Euclidean distance of the centroid are always higher than drowsy. Thus, from the outcomes that been suggested for drowsiness detection using RR interval and amplitude of R are able to become as the most efficient drowsiness detection. |
|---|