Health parameters such as heart rhythm could be measure with Photoplethysmography (PPG)signal. The advent in the smartphone camera sensors has enabled extracting PPG signals using smartphones. Smartphone PPG signals are exposed to motion and noise artifact (MNA) which could generate unreliable heart rate measurement. In addition, PPG signals are known as biometric signals since they have unique behavior for each individual. However, in previous MNA detection studies this personalized characteristic has not been considered. In this paper we propose a novel personalized MNA detection method by applying a probabilistic neural network as a classifier. The performance of our personalized method is evaluated by 25 subjects in terms of accuracy, specificity, and sensitivity and compared with the generalized method. The average accuracy of our personalized method is 97.96%, while it is 92.94% in the generalized one. The average values of personalized specificity and sensitivity are 99.69% and 93.91%. These values are 95.38% and 87.4% for the generalized classifier.
No information added