Onset and Peak Pattern Recognition on Photoplethysmographic Signals Using Neural Networks Alvaro D. Orjuela-Ca˜ n´on 1 , Denis Delisle-Rodr´ ıguez 2 , Alberto L´ opez-Delis 2 , Ram´on Fernandez de la Vara-Prieto 2 , and Manuel B. Cuadra-Sanz 3 1 GIBIO - Electronic and Biomedical Faculty, Universidad Antonio Nari˜ no, Bogot´ a D.C., Colombia alvorjuela@uan.edu.co 2 Center of Medical Biophysics, Universidad de Oriente, Santiago de Cuba, Cuba {denis.delisle,ramon.fernandez,alberto.lopez}@cbiomed.cu 3 CIDEI (Research and Technologic Development Center for the Electro-Electronics and Informatics Industry), Bogot´ a D.C., Colombia mqadra2013@yahoo.es Abstract. Traditional methodologies use electrocardiographic (ECG) signals to develop automatic methods for onset and peak detection on the arterial pulse wave. In the present work a Multilayer Perceptron (MLP) neural network is used for classifying fiducial points on photo- plethysmographic (PPG) signals. System was trained with a dataset of temporal segments from signals located based on information about onset and peak points. Different segments sizes and units in the neural network were used for the classification, and optimal values were searched. Re- sults of the classification reach 98.1% in worse of cases. This proposal takes advantages from MLP neural networks for pattern classification. Additionally, the use of ECG signal was avoided in the presented method- ology, making the system robust, less expensive and portable in front of this problem. Keywords: Arterial Pulse Wave, Artificial Neural Networks, Multilayer Perceptron, Onset Classification, Peak Classification. 1 Introduction The photoplethysmography (PPG) signal has been used as a simple and low-cost optical technique, which is used for measuring blood volume changes through of the light intensity during the emission and reception on the skin surface. Peripheral body sites such as fingers, ears, toes and forehead are used to obtain these kind of signals, approaching blood volume and perfusion changes due to the dissemination or absorption of the incident light, providing the dynamical part of the signal [1,2]. J. Ruiz-Shulcloper and G. Sanniti di Baja (Eds.): CIARP 2013, Part I, LNCS 8258, pp. 543–550, 2013. c  Springer-Verlag Berlin Heidelberg 2013