تولید سیگنال فوتوپلتیسموگرام (PPG) مصنوعی با استفاده از مدل سازنده مبتنی بر برنامه‌نویسی ژنتیک
الموضوعات :فاطمه قاسمی 1 , فردین ابدالی محمدی 2
1 - گروه مهندسی کامپیوتر و فناوری اطلاعات، دانشکده فنی و مهندسی، دانشگاه رازی، کرمانشاه، ایران
2 - هیات علمی
الکلمات المفتاحية: فوتوپلتیسموگرام, مدل سازنده, برنامه‌نویسی ژنتیک, مقیاس‌پذیری, مدل ریاضی,
ملخص المقالة :
امروزه تحولات فناوری اطلاعات و ارتباطات در حوزه سلامت، به‌ویژه در نظارت بر فعالیت‌های قلبی، به افزایش استفاده از تکنولوژی فوتوپلتیسموگرام (PPG: Photoplethysmogram) در دستگاه‌های هوشمند و تلفن‌های همراه منجر شده است. توسعۀ مدل‌های سازنده به جهت تولید سیگنال‌های مصنوعی PPG نیازمند حل چالش‌هایی مانند کمبود تنوع و محدودیت داده‌ها در آموزش مدل‌های یادگیری عمیق است. این مقاله، یک رویکرد مبتنی بر برنامه‌نویسی ژنتیک (GP: Genetic Programming) را به کار می‌گیرد تا مدل سازنده‌ای را ارائه دهد که با کمک یک نمونۀ اولیه از سیگنال PPG، قادر به تولید داده‌هایی با تنوع بیشتر و دقت افزوده‌شده باشد. برخلاف رگرسیون معمول، در برنامه‌نویسی ژنتیک ساختار و ترکیبات مدل ریاضی به‌صورت خودکار تعیین میگردد. رویکرد پیشنهادی، با داشتن اندازه خطای میانگین (MSE: Mean Squared Error) برابر با 0.0001، ریشه میانگین مربعات خطا (RMSE: Root Mean Squared Error) به‌اندازه 0.01 و همبستگی 0.999 نشان می‌دهد که به دلیل بهینگی مناسب و دقت قابل‌قبول در تولید داده‌های PPG مصنوعی، نسبت به دیگر روش‌ها برتری دارد و ازنظر کارایی و قابلیت اجرا در محیط‌های با منابع محدود نیز مؤثر عمل می کند.
[1] M. Nardelli and R. Bailón, "Advances in Wearable Photoplethysmography Applications in Health Monitoring," (in eng), Sensors (Basel), vol. 23, no. 16, Aug 10 2023, doi: https://doi.org/10.3390/s23167064.
[2] K. B. Kim and H. J. Baek, "Photoplethysmography in Wearable Devices: A Comprehensive Review of Technological Advances, Current Challenges, and Future Directions," Electronics, vol. 12, no. 13, p. 2923, 2023, doi: https://doi.org/10.3390/electronics12132923.
[3] B. Tarifi, A. Fainman, A. Pantanowitz, and D. M. Rubin, "A Machine Learning Approach to the Non-Invasive Estimation of Continuous Blood Pressure Using Photoplethysmography," Applied Sciences, vol. 13, no. 6, p. 3955, 2023. [Online]. Available: https://www.mdpi.com/2076-3417/13/6/3955.
[4] M. A. Noor Faris Ali, "An efficient hybrid LSTM-ANN joint classification-regression model for PPG based blood pressure monitoring," Biomedical Signal Processing and Control, vol. 84, 2023, doi: https://doi.org/10.1016/j.bspc.2023.104782.
[5] H. a. S. Asgharnezhad, Afshar and Bakhshayeshi, Ivan and Alizadehsani, Roohallah and Chamaani, Somayyeh and Alinejad-Rokny, Hamid, "Improving PPG Signal Classification with Machine Learning: The Power of a Second Opinion," 2023, pp. 1-5, doi: https://doi.org/10.1109/DSP58604.2023.10167869.
[6] D. a. C. Jarchi, Alex, "Description of a Database Containing Wrist PPG Signals Recorded during Physical Exercise with Both Accelerometer and Gyroscope Measures of Motion," Data, vol. 2, 2016, doi: 10.3390/data2010001.
[7] U. Yadav, S. N. Abbas, and D. Hatzinakos, "Evaluation of PPG Biometrics for Authentication in Different States," 2018 International Conference on Biometrics (ICB), pp. 277-282, 2017, doi: https://doi.org/10.1109/ICB2018.2018.00049.
[8] Y. a. C. Liang, Zhencheng and Liu, Guiyong and Elgendi, Mohamed, "A new, short-recorded photoplethysmogram dataset for blood pressure monitoring in China," Scientific Data, vol. 5, p. 180020, 2018, doi: https://doi.org/10.1038/sdata.2018.20.
[9] A. a. I. Reiss, Ina and Schmidt, Philip and Van Laerhoven, Kristof, "Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks," Sensors, vol. 19, p. 3079, 2019, doi: https://doi.org/10.3390/s19143079.
[10] O. a. R. Mazumder, Dibyendu and Bhattacharya, Sakyajit and Sinha, Aniruddha and Pal, Arpan, "Synthetic PPG generation from haemodynamic model with baroreflex autoregulation: a Digital twin of cardiovascular system," in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2019, pp. 5024-5029, doi: https://doi.org/10.1109/EMBC.2019.8856691.
[11] T. W. C. Fanny, "Deep Learning for Imbalance Data Classification using Class Expert Generative Adversarial Network," Procedia Computer Science, vol. 135, pp. 60-67, 2018, doi: https://doi.org/10.1016/j.procs.2018.08.150.
[12] J. M. Johnson, Khoshgoftaar, T.M, "Survey on deep learning with class imbalance," Journal of Big Data, vol. 6, 2019, doi: https://doi.org/10.1186/s40537-019-0192-5.
[13] O. a. C. Sayadi, Gari, "Synthetic ECG Generation and Bayesian Filtering Using a Gaussian Wave-Based Dynamical Model," Physiological measurement, vol. 31, pp. 1309-29, 2010, doi: https://doi.org/10.1088/0967-3334/31/10/002.
[14] D. Martin-Martinez, P. Casaseca-de-la-Higuera, M. Martin-Fernandez, and C. Alberola-Lopez, "Stochastic modeling of the PPG signal: a synthesis-by-analysis approach with applications," (in eng), IEEE Trans Biomed Eng, vol. 60, no. 9, pp. 2432-41, Sep 2013, doi: https://doi.org/10.1109/TBME.2013.2257770.
[15] L. Wang, L. Xu, S. Feng, M. Q. Meng, and K. Wang, "Multi-Gaussian fitting for pulse waveform using Weighted Least Squares and multi-criteria decision making method," (in eng), Comput Biol Med, vol. 43, no. 11, pp. 1661-72, Nov 2013, doi: https://doi.org/10.1016/j.compbiomed.2013.08.004.
[16] Y. Luo, W. Li, W. Rao, X. Fu, L. Yang, and Y. Zhang, "A New Modeling Method of Photoplethysmography Signal Based on Lognormal Basis," in International Conference on Internet and Distributed Computing Systems, 2016.
[17] Q. Tang, Z. Chen, R. Ward, and M. Elgendi, "Synthetic photoplethysmogram generation using two Gaussian functions," (in eng), Sci Rep, vol. 10, no. 1, p. 13883, Aug 17 2020, doi: https://doi.org/10.1038/s41598-020-69076-x.
[18] M. M. Alankrita Aggarwal, Gopi Battineni, "Generative adversarial network: An overview of theory and applications," International Journal of Information Management Data Insights, vol. 1, no. 1, 2021, doi: https://doi.org/10.1016/j.jjimei.2020.100004.
[19] E. Brophy, Z. Wang, and T. E. Ward, "Quick and Easy Time Series Generation with Established Image-based GANs," ArXiv, vol. abs/1902.05624, 2019, doi: https://doi.org/10.48550/arXiv.1902.05624.
[20] D. a. T. Kiyasseh, Girmaw Abebe and Le Nguyen Thanh, Nhan and Van, Tan and Thwaites, Louise and Zhu, Tingting and Clifton, David, "PlethAugment: GAN-Based PPG Augmentation for Medical Diagnosis in Low-Resource Settings," IEEE Journal of Biomedical and Health Informatics, vol. PP, pp. 1-1, 2020, doi: 10.1109/JBHI.2020.2979608.
[21] J. M. L. Alcaraz and N. Strodthoff, "Diffusion-based conditional ECG generation with structured state space models," (in eng), Comput Biol Med, vol. 163, p. 107115, Sep 2023, doi: https://doi.org/10.1016/j.compbiomed.2023.107115.
[22] M. A. Quiroz-Juárez, O. Jiménez-Ramírez, R. Vázquez-Medina, V. F. Breña-medina, J. L. Aragón, and R. A. Barrio, "Generation of ECG signals from a reaction-diffusion model spatially discretized," Scientific Reports, vol. 9, 2019, doi: https://doi.org/10.1038/s41598-019-55448-5.
[23] Q. Zhang, D. Zhou, and X. Zeng, "Highly wearable cuff-less blood pressure and heart rate monitoring with single-arm electrocardiogram and photoplethysmogram signals," (in eng), Biomed Eng Online, vol. 16, no. 1, p. 23, Feb 6 2017, doi: https://doi.org/10.1186/s12938-017-0317-z.
[24] M. M. E. Maryam Amir Haeri, Gianluigi Folino, "Statistical genetic programming for symbolic regression," Applied Soft Computing, vol. 60, pp. 447-469, 2017, doi: https://doi.org/10.1016/j.asoc.2017.06.050.
[25] F. A.-M. Majid Sepahvand, "A novel multi-lead ECG personal recognition based on signals functional and structural dependencies using time-frequency representation and evolutionary morphological CNN," Biomedical Signal Processing and Control, vol. 68, 2021, doi: https://doi.org/10.1016/j.bspc.2021.102766.
[26] m. amintoosi and H. Ezzati, "The aware genetic algorithm of the best member, applied to graph coloring and metric-dimension of the graph problems," Journal of Information and Communication Technology, vol. 12, no. 43, pp. 143-154, 2020. [Online]. Available: http://rimag.ir/fa/Article/13601.
[27] S. Katoch, Chauhan, S.S. & Kumar, V, "A review on genetic algorithm: past, present, and future," Multimed Tools Appl, vol. 80, pp. 8091–8126 2021, doi: https://doi.org/10.1007/s11042-020-10139-6.
[28] S. Bakhtiari and M. Khosroshahi, "A Multi-Objective Differential Evolutionary Algorithm-based Approach for Resource Allocation in Cloud Computing Environment," Journal of Information and Communication Technology, vol. 14, no. 51, pp. 113-128, 2022. [Online]. Available: http://rimag.ir/fa/Article/39235.
[29] F. A.-M. Majid Sepahvand, "A novel representation in genetic programming for ensemble classification of human motions based on inertial signals," Expert Systems with Applications, vol. 185, 2021, doi: https://doi.org/10.1016/j.eswa.2021.115624.
[30] L. a. J. Tan, Jean, Image Processing Basics. 2019.
[31] m. nikseresht and M. Raji, "A Task Mapping and Scheduling Algorithm based on Genetic Algorithm for Embedded System Design," Journal of Information and Communication Technology, vol. 13, no. 47, pp. 186-197, 2021. [Online]. Available: http://rimag.ir/fa/Article/16369.
[32] W. K. W. Pauline Wong, Filbert H. Juwono, Basil Andy Lease, Lenin Gopal, I.M. Chew, "Sensor abnormality detection in multistage compressor units: A “white box” approach using tree-based genetic programming," e-Prime - Advances in Electrical Engineering, Electronics and Energy, vol. 5, 2023, doi: https://doi.org/10.1016/j.prime.2023.100209.
[33] M. P. Aghababa and a. b. baghbaderani, "Routing of Multipartite Computer Networks Using Ant Genetic Algorithm," Journal of Information and Communication Technology, vol. 9, no. 31, pp. 1-12, 2017. [Online]. Available: http://rimag.ir/fa/Article/8199.
[34] A. E. Johnson et al., "MIMIC-III, a freely accessible critical care database," (in eng), Sci Data, vol. 3, p. 160035, May 24 2016, doi: https://doi.org/10.1038/sdata.2016.35.
[35] B. F. Jernej Zupančič, Matjaž Gams, "Genetic-programming-based multi-objective optimization of strategies for home energy-management systems," Energy, vol. 203, 2020, doi: https://doi.org/10.1016/j.energy.2020.117769.
[36] A. Kianimajd et al., "Comparison of different methods of measuring similarity in physiologic time series," IFAC-PapersOnLine, vol. 50, pp. 11005-11010, 2017, doi: https://doi.org/10.1016/j.ifacol.2017.08.2479.
[37] A. a. P. Sološenko, Andrius and Marozas, Vaidotas and Sörnmo, Leif, "Photoplethysmogram Modeling During Paroxysmal Atrial Fibrillation," Computers in Biology and Medicine, vol. 81, 2017, doi: 10.22489/CinC.2017.049-011.
[38] M. a. A.-M. Feli, Fardin, "12 lead Electrocardiography signals compression by a new genetic programming based mathematical modeling algorithm," Biomedical Signal Processing and Control, vol. 54, pp. 1-20, 2019, doi: 10.1016/j.bspc.2019.101596.
