{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T12:06:07Z","timestamp":1771329967467,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,11,25]],"date-time":"2021-11-25T00:00:00Z","timestamp":1637798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/00066\/2020 (FCT)"],"award-info":[{"award-number":["UIDB\/00066\/2020 (FCT)"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e Tecnologia","doi-asserted-by":"publisher","award":["PD\/BDE\/150312\/2019"],"award-info":[{"award-number":["PD\/BDE\/150312\/2019"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NMT, S.A.","award":["PD\/BDE\/150312\/2019"],"award-info":[{"award-number":["PD\/BDE\/150312\/2019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Photoplethysmography (PPG) is widely used in wearable devices due to its conveniency and cost-effective nature. From this signal, several biomarkers can be collected, such as heart and respiration rate. For the usual acquisition scenarios, PPG is an artefact-ridden signal, which mandates the need for the designated classification algorithms to be able to reduce the noise component effect on the classification. Within the selected classification algorithm, the hyperparameters\u2019 adjustment is of utmost importance. This study aimed to develop a deep learning model for robust PPG wave detection, which includes finding each beat\u2019s temporal limits, from which the peak can be determined. A study database consisting of 1100 records was created from experimental PPG measurements performed in 47 participants. Different deep learning models were implemented to classify the PPG: Long Short-Term Memory (LSTM), Bidirectional LSTM, and Convolutional Neural Network (CNN). The Bidirectional LSTM and the CNN-LSTM were investigated, using the PPG Synchrosqueezed Fourier Transform (SSFT) as the models\u2019 input. Accuracy, precision, recall, and F1-score were evaluated for all models. The CNN-LSTM algorithm, with an SSFT input, was the best performing model with accuracy, precision, and recall of 0.894, 0.923, and 0.914, respectively. This model has shown to be competent in PPG detection and delineation tasks, under noise-corrupted signals, which justifies the use of this innovative approach.<\/jats:p>","DOI":"10.3390\/computers10120158","type":"journal-article","created":{"date-parts":[[2021,11,28]],"date-time":"2021-11-28T22:19:16Z","timestamp":1638137956000},"page":"158","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["The Application of Deep Learning Algorithms for PPG Signal Processing and Classification"],"prefix":"10.3390","volume":"10","author":[{"given":"Filipa","family":"Esgalhado","sequence":"first","affiliation":[{"name":"NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"},{"name":"LIBPhys-Laboratory of Instrumentation, Biomedical Engineering and Radiation Physics, 2829-516 Caparica, Portugal"},{"name":"NMT, S.A., Parque Tecnol\u00f3gico de Cantanhede, N\u00facleo 04, Lote 3, 3060-197 Cantanhede, Portugal"}]},{"given":"Beatriz","family":"Fernandes","sequence":"additional","affiliation":[{"name":"NMT, S.A., Parque Tecnol\u00f3gico de Cantanhede, N\u00facleo 04, Lote 3, 3060-197 Cantanhede, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7913-7047","authenticated-orcid":false,"given":"Valentina","family":"Vassilenko","sequence":"additional","affiliation":[{"name":"NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"},{"name":"LIBPhys-Laboratory of Instrumentation, Biomedical Engineering and Radiation Physics, 2829-516 Caparica, Portugal"},{"name":"NMT, S.A., Parque Tecnol\u00f3gico de Cantanhede, N\u00facleo 04, Lote 3, 3060-197 Cantanhede, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2287-4265","authenticated-orcid":false,"given":"Arnaldo","family":"Batista","sequence":"additional","affiliation":[{"name":"NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"},{"name":"UNINOVA CTSNOVA, School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"}]},{"given":"Sara","family":"Russo","sequence":"additional","affiliation":[{"name":"NOVA School of Science and Technology, NOVA University Lisbon, 2829-516 Caparica, Portugal"}]}],"member":"1968","published-online":{"date-parts":[[2021,11,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"R1","DOI":"10.1088\/0967-3334\/28\/3\/R01","article-title":"Photoplethysmography and its application in clinical physiological measurement","volume":"28","author":"Allen","year":"2007","journal-title":"Physiol. Meas."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"14","DOI":"10.2174\/157340312801215782","article-title":"On the Analysis of Fingertip Photoplethysmogram Signals","volume":"8","author":"Elgendi","year":"2012","journal-title":"Curr. Cardiol. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1109\/TIM.2011.2175832","article-title":"A Novel Approach for Motion Artifact Reduction in PPG Signals Based on AS-LMS Adaptive Filter","volume":"61","author":"Ram","year":"2012","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Jang, D.-G., Park, S., Hahn, M., and Park, S.-H. (2014). A Real-Time Pulse Peak Detection Algorithm for the Photoplethysmogram. Int. J. Electron. Electr. Eng., 45\u201349.","DOI":"10.12720\/ijeee.2.1.45-49"},{"key":"ref_5","first-page":"42","article-title":"The mountaineer\u2019s method for peak detection in photoplethysmographic signals","volume":"90","year":"2019","journal-title":"Rev. Fac. Ing. Univ. Antioquia"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1109\/TIM.2018.2857878","article-title":"A Robust Pulse Onset and Peak Detection Method for Automated PPG Signal Analysis System","volume":"68","author":"Vadrevu","year":"2019","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1038\/s41569-020-00503-2","article-title":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","volume":"18","author":"Siontis","year":"2021","journal-title":"Nat. Rev. Cardiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/s13534-019-00097-w","article-title":"Current progress of photoplethysmography and SPO2 for health monitoring","volume":"9","author":"Tamura","year":"2019","journal-title":"Biomed. Eng. Lett."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cardoso, F.E., Vassilenko, V., Batista, A., Bonif\u00e1cio, P., Martin, S.R., Mu\u00f1oz-Torrero, J., and Ortigueira, M. (2021, January 7\u20139). Improvements on Signal Processing Algorithm for the VOPITB Equipment. Proceedings of the DoCEIS: Doctoral Conference on Computing, Electrical and Industrial Systems, Costa de Caparica, Portugal.","DOI":"10.1007\/978-3-030-78288-7_31"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1760","DOI":"10.1038\/s41467-020-15432-4","article-title":"Automatic diagnosis of the 12-lead ECG using a deep neural network","volume":"11","author":"Ribeiro","year":"2020","journal-title":"Nat. Commun."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"Hannun","year":"2019","journal-title":"Nat. Med."},{"key":"ref_12","first-page":"58","article-title":"Artificial Neural Networks (ANN) Approach to PPG Signal Classification","volume":"2","author":"Soltane","year":"2004","journal-title":"Int. J. Comput. Inf. Sci."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, S.-H., Li, R.-X., Wang, J.-J., Chen, W., and Su, C.-H. (2020). Classification of Photoplethysmographic Signal Quality with Deep Convolution Neural Networks for Accurate Measurement of Cardiac Stroke Volume. Appl. Sci., 10.","DOI":"10.3390\/app10134612"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1177\/00202940211001904","article-title":"Deep learning algorithm evaluation of hypertension classification in less photoplethysmography signals conditions","volume":"54","author":"Yen","year":"2021","journal-title":"Meas. Control"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"14941","DOI":"10.1109\/JSEN.2021.3073047","article-title":"NAS-PPG: PPG-Based Heart Rate Estimation Using Neural Architecture Search","volume":"21","author":"Song","year":"2021","journal-title":"IEEE Sens. J."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Alessandrini, M., Biagetti, G., Crippa, P., Falaschetti, L., and Turchetti, C. (2021). Recurrent Neural Network for Human Activity Recognition in Embedded Systems Using PPG and Accelerometer Data. Electronics, 10.","DOI":"10.3390\/electronics10141715"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, Y.-H., Harfiya, L.N., Purwandari, K., and Lin, Y.-D. (2020). Real-Time Cuffless Continuous Blood Pressure Estimation Using Deep Learning Model. Sensors, 20.","DOI":"10.3390\/s20195606"},{"key":"ref_18","unstructured":"Laitala, J., Jiang, M., Syrj\u00e4l\u00e4, E., Naeini, E.K., Airola, A., Rahmani, A.M., Dutt, N.D., and Liljeberg, P. (April, January 30). Robust ECG R-peak detection using LSTM. Proceedings of the 35th Annual ACM Symposium on Applied Computing, Brno, Czech Republic."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kim, B.-H., and Pyun, J.-Y. (2020). ECG Identification for Personal Authentication Using LSTM-Based Deep Recurrent Neural Networks. Sensors, 20.","DOI":"10.3390\/s20113069"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.icte.2020.04.004","article-title":"Supervised ECG wave segmentation using convolutional LSTM","volume":"6","author":"Malali","year":"2020","journal-title":"ICT Express"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"569050","DOI":"10.3389\/fphys.2020.569050","article-title":"Deep Learning Algorithm Classifies Heartbeat Events Based on Electrocardiogram Signals","volume":"11","author":"Liang","year":"2020","journal-title":"Front. Physiol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"806","DOI":"10.3389\/fneur.2019.00806","article-title":"Deep Learning with EEG Spectrograms in Rapid Eye Movement Behavior Disorder","volume":"10","author":"Ruffini","year":"2019","journal-title":"Front. Neurol."},{"key":"ref_23","unstructured":"Boashash, B. (2016). Time-Frequency Signal Analysis and Processing, Academic Press."},{"key":"ref_24","unstructured":"Alam, M.Z., Rahman, M.S., Parvin, N., and Sobhan, M.A. (2012, January 18\u201319). Time-frequency representation of a signal through non-stationary multipath fading channel. Proceedings of the 2012 International Conference on Informatics, Electronics & Vision (ICIEV), Dhaka, Bangladesh."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"6674695","DOI":"10.1155\/2021\/6674695","article-title":"Extreme Learning Machine for Heartbeat Classification with Hybrid Time-Domain and Wavelet Time-Frequency Features","volume":"2021","author":"Xu","year":"2021","journal-title":"J. Healthc. Eng."},{"key":"ref_26","unstructured":"Allen, J., and Murray, A. (2004, January 19\u201322). Effects of filtering on multi-site photoplethysmography pulse waveform characteristics. Proceedings of the Computers in Cardiology, Chicago, IL, USA."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"102589","DOI":"10.1016\/j.bspc.2021.102589","article-title":"The minimal sampling frequency of the photoplethysmogram for accurate pulse rate variability parameters in healthy volunteers","volume":"68","author":"Hejjel","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_28","unstructured":"Gasparini, F., Grossi, A., and Bandini, S. (July, January 29). A Deep Learning Approach to Recognize Cognitive Load using PPG Signals. Proceedings of the 14th PErvasive Technologies Related to Assistive Environments Conference, Corfu, Greece."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1109\/MSP.2013.2265316","article-title":"Time-Frequency Reassignment and Synchrosqueezing: An Overview","volume":"30","author":"Auger","year":"2013","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1109\/LSP.2017.2657381","article-title":"Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification","volume":"24","author":"Salamon","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.acha.2010.08.002","article-title":"Synchrosqueezed wavelet transforms: An empirical mode decomposition-like tool","volume":"30","author":"Daubechies","year":"2011","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1137\/100798818","article-title":"Synchrosqueezing-Based Recovery of Instantaneous Frequency from Nonuniform Samples","volume":"43","author":"Thakur","year":"2011","journal-title":"SIAM J. Math. Anal."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1109\/JBHI.2019.2911367","article-title":"LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices","volume":"24","author":"Saadatnejad","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"107065","DOI":"10.1016\/j.compeleceng.2021.107065","article-title":"Deep recurrent neural network-based autoencoder for photoplethysmogram artifacts filtering","volume":"92","author":"Azar","year":"2021","journal-title":"Comput. Electr. Eng."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.1007\/s11063-020-10319-3","article-title":"Time Series Prediction Method Based on Variant LSTM Recurrent Neural Network","volume":"52","author":"Hu","year":"2020","journal-title":"Neural Process. Lett."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"162","DOI":"10.21629\/JSEE.2017.01.18","article-title":"Convolutional neural networks for time series classification","volume":"28","author":"Zhao","year":"2017","journal-title":"J. Syst. Eng. Electron."},{"key":"ref_38","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_39","unstructured":"Fredriksson, D., and Glandberger, O. (2020). Neural Network Regularization for Generalized Heart Arrhythmia Classification. [Master\u2019s Thesis, Blekinge Institute of Technology]."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1007\/s42979-020-00225-9","article-title":"DeepFake Video Detection: A Time-Distributed Approach","volume":"1","author":"Singh","year":"2020","journal-title":"SN Comput. Sci."},{"key":"ref_41","first-page":"37","article-title":"Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation","volume":"2","author":"Powers","year":"2011","journal-title":"J. Mach. Learn. Technol."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Lipton, Z.C., Elkan, C., and Naryanaswamy, B. (2014, January 14\u201318). Optimal Thresholding of Classifiers to Maximize F1 Measure. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Nancy, France.","DOI":"10.1007\/978-3-662-44851-9_15"},{"key":"ref_43","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA."},{"key":"ref_44","unstructured":"Nwankpa, C., Ijomah, W., Gachagan, A., and Marshall, S. (2018). Activation Functions: Comparison of trends in Practice and Research for Deep Learning. arXiv."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2795","DOI":"10.1007\/s00521-017-3230-2","article-title":"A facial expression recognition method based on ensemble of 3D convolutional neural networks","volume":"31","author":"Sun","year":"2019","journal-title":"Neural Comput. Appl."}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/10\/12\/158\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:35:39Z","timestamp":1760168139000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/10\/12\/158"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,25]]},"references-count":45,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["computers10120158"],"URL":"https:\/\/doi.org\/10.3390\/computers10120158","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,25]]}}}