{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:08:15Z","timestamp":1778947695617,"version":"3.51.4"},"reference-count":30,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Technological Institute of Mexico (TECNM) research project","award":["14284.22-P"],"award-info":[{"award-number":["14284.22-P"]}]},{"name":"National Technological Institute of Mexico (TECNM) research project","award":["ITTIJ-CA-9"],"award-info":[{"award-number":["ITTIJ-CA-9"]}]},{"name":"Program for Teacher Professional Development (PRODEP)","award":["14284.22-P"],"award-info":[{"award-number":["14284.22-P"]}]},{"name":"Program for Teacher Professional Development (PRODEP)","award":["ITTIJ-CA-9"],"award-info":[{"award-number":["ITTIJ-CA-9"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A good approximation to power amplifier (PA) behavioral modeling requires precise baseband models to mitigate nonlinearities. Since digital predistortion (DPD) is used to provide the PA linearization, a framework is necessary to validate the modeling figures of merit support under signal conditioning and transmission restrictions. A field-programmable gate array (FPGA)-based testbed is developed to measure the wide-band PA behavior using a single-carrier 64-quadrature amplitude modulation (QAM) multiplexed by orthogonal frequency-division multiplexing (OFDM) based on long-term evolution (LTE) as a stimulus, with different bandwidths signals. In the search to provide a heuristic target approach modeling, this paper introduces a feature extraction concept to find an appropriate complexity solution considering the high sparse data issue in amplitude to amplitude (AM-AM) and amplitude to phase AM-PM models extraction, whose penalties are associated with overfitting and hardware complexity in resulting functions. Thus, experimental results highlight the model performance for a high sparse data regime and are compared with a regression tree (RT), random forest (RF), and cubic-spline (CS) model accuracy capabilities for the signal conditioning to show a reliable validation, low-complexity, according to the peak-to-average power ratio (PAPR), complementary cumulative distribution function (CCDF), coefficients extraction, normalized mean square error (NMSE), and execution time figures of merit. The presented models provide a comparison with original data that aid to compare the dimension and robustness for each surrogate model where (i) machine learning (ML)-based and (ii) CS interpolate-based where high sparse data are present, NMSE between the CS interpolated based are also compared to demonstrate the efficacy in the prediction methods with lower convergence times and complexities.<\/jats:p>","DOI":"10.3390\/s22197461","type":"journal-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T03:07:28Z","timestamp":1665371248000},"page":"7461","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Comparison of Surrogate Behavioral Models for Power Amplifier Linearization under High Sparse Data"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6550-124X","authenticated-orcid":false,"given":"Jose Alejandro","family":"Galaviz-Aguilar","sequence":"first","affiliation":[{"name":"Tecnologico de Monterrey, School of Engineering and Sciences, Monterrey 64849, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1770-471X","authenticated-orcid":false,"given":"Cesar","family":"Vargas-Rosales","sequence":"additional","affiliation":[{"name":"Tecnologico de Monterrey, School of Engineering and Sciences, Monterrey 64849, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5437-8215","authenticated-orcid":false,"given":"Jos\u00e9 Ricardo","family":"C\u00e1rdenas-Valdez","sequence":"additional","affiliation":[{"name":"IT de Tijuana, Tecnol\u00f3gico Nacional de M\u00e9xico, Tijuana 22435, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8164-0963","authenticated-orcid":false,"given":"Daniel Santiago","family":"Aguila-Torres","sequence":"additional","affiliation":[{"name":"IT de Tijuana, Tecnol\u00f3gico Nacional de M\u00e9xico, Tijuana 22435, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3497-4842","authenticated-orcid":false,"given":"Leonardo","family":"Flores-Hern\u00e1ndez","sequence":"additional","affiliation":[{"name":"IT de Tijuana, Tecnol\u00f3gico Nacional de M\u00e9xico, Tijuana 22435, Mexico"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,10,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"C\u00e1rdenas-Valdez, J.R., Galaviz-Aguilar, J.A., Vargas-Rosales, C., Inzunza-Gonz\u00e1lez, E., and Flores-Hern\u00e1ndez, L. (2022). A Crest Factor Reduction Technique for LTE Signals with Target Relaxation in Power Amplifier Linearization. Sensors, 22.","DOI":"10.3390\/s22031176"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Galaviz-Aguilar, J.A., Vargas-Rosales, C., C\u00e1rdenas-Valdez, J.R., Mart\u00ednez-Reyes, Y., Inzunza-Gonz\u00e1lez, E., Sandoval-Ibarra, Y., and N\u00fa\u00f1ez-P\u00e9rez, J.C. (2021). A Weighted Linearization Method for Highly RF-PA Nonlinear Behavior Based on the Compression Region Identification. Appl. Sci., 11.","DOI":"10.3390\/app11072942"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Khusro, A., Hashmi, M.S., Ansari, A.Q., and Auyenur, M. (2019, January 4\u20137). A new and Reliable Decision Tree Based Small-Signal Behavioral Modeling of GaN HEMT. Proceedings of the IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), Dallas, TX, USA.","DOI":"10.1109\/MWSCAS.2019.8885334"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kant, S., Bengtsson, M., Fodor, G., G\u00f6ransson, B., and Fischione, C. (2022). EVM Mitigation with PAPR and ACLR Constraints in Large-Scale MIMO-OFDM Using TOP-ADMM. IEEE Trans. Wirel. Commun.","DOI":"10.1109\/TWC.2022.3177136"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.1007\/s00034-017-0700-9","article-title":"A Novel Generalized Parallel Two-Box Structure for Behavior Modeling and Digital Predistortion of RF Power Amplifiers at LTE Applications","volume":"37","author":"Belabad","year":"2018","journal-title":"Circuits Syst. Signal Process."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Becerra, J.A., Madero-Ayora, M.J., Marqu\u00e9s-Valderrama, E., Nogales, M., and Crespo-Cadenas, C. (2022, January 16\u201319). Preconditioning the Regression of Power Amplifier Behavioral Models and Digital Predistorters. Proceedings of the IEEE Topical Conference on RF\/Microwave Power Amplifiers for Radio and Wireless Applications (PAWR), Las Vegas, NV, USA.","DOI":"10.1109\/PAWR53092.2022.9719703"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1109\/TCSI.2020.3034825","article-title":"Gradient-Adaptive Spline-Interpolated LUT Methods for Low-Complexity Digital Predistortion","volume":"68","author":"Campo","year":"2021","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1049\/mia2.12220","article-title":"Highly non-linear and wide-band mmWave active array OTA linearisation using neural network","volume":"16","author":"Jalili","year":"2022","journal-title":"IET Microwaves Antennas Propag."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, C.Y., Zhu, Y.Y., Cheng, Q.F., Fu, H.P., Ma, J.-G., and Zhang, Q.J. (2017, January 4\u20139). Extreme learning machine for the behavioral modeling of RF power amplifiers. Proceedings of the IEEE MTT-S International Microwave Symposium (IMS), Honololu, HI, USA.","DOI":"10.1109\/MWSYM.2017.8058626"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lu, G., Huang, S., Ying, S., Zeng, Y., Yao, Y., Ning, F., and Feng, Z. (2019, January 9\u201313). Low-Complexity Power Amplifier Model Driven Wireless Emitter Identification Using Random Forest. Proceedings of the 2019 IEEE Globecom Workshops (GC Wkshps), Waikoloa, HI, USA.","DOI":"10.1109\/GCWkshps45667.2019.9024451"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"\u00c1lvarez-L\u00f3pez, L., Becerra, J.A., Madero-Ayora, M.J., and Crespo-Cadenas, C. (2020, January 26\u201329). Determining a Digital Predistorter Model Structure for Wideband Power Amplifiers through Random Forest. Proceedings of the IEEE Topical Conference on RF\/Microwave Power Amplifiers for Radio and Wireless Applications (PAWR), San Antonio, TX, USA.","DOI":"10.1109\/PAWR46754.2020.9036004"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e22825","DOI":"10.1002\/mmce.22825","article-title":"Measurement results for compensation of impairments of LTE stimulated direct-conversion transmitter through augmented MoE","volume":"31","author":"Bhatt","year":"2021","journal-title":"Int. J. RF Microw. Comput.-Aided Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TMTT.2021.3098867","article-title":"Mixture of Experts Approach for Piecewise Modeling and Linearization of RF Power Amplifiers","volume":"70","author":"Brihuega","year":"2022","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Barry, A., Li, W., Becerra, J.A., and Gilabert, P.L. (2021). Comparison of feature selection techniques for power amplifier behavioral modeling and digital predistortion linearization. Sensors, 21.","DOI":"10.3390\/s21175772"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sani, H.M., Lei, C., and Neagu, D. (2018, January 11\u201313). Computational Complexity Analysis of Decision Tree Algorithms. Proceedings of the Artificial Intelligence XXXV\u2014SGAI 2018, Cambridge, UK.","DOI":"10.1007\/978-3-030-04191-5_17"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Breiman, L., Friedman, J., Stone, C.J., and Olshen, R.A. (2017). Classification and Regression Trees, Chapman and Hall\/CRC.","DOI":"10.1201\/9781315139470"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4570","DOI":"10.1109\/TMTT.2020.3016967","article-title":"Sparse Identification of Volterra Models for Power Amplifiers Without Pseudoinverse Computation","volume":"68","author":"Becerra","year":"2020","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4218","DOI":"10.1109\/TMTT.2022.3157586","article-title":"A Sparse-Bayesian Approach for the Design of Robust Digital Predistorters Under Power-Varying Operation","volume":"70","author":"Becerra","year":"2022","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4323","DOI":"10.1109\/TMTT.2006.883243","article-title":"Dynamic Deviation Reduction-Based Volterra Behavioral Modeling of RF Power Amplifiers","volume":"54","author":"Zhu","year":"2006","journal-title":"IEEE Trans. Microw. Theory Tech."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Aguila-Torres, D.S., Galaviz-Aguilar, J.A., and C\u00e1rdenas-Valdez, J.R. (June, January 29). Reliable comparison for power amplifiers nonlinear behavioral modeling based on regression trees and random forest. Proceedings of the 2022 IEEE International Symposium on Circuits and Systems (ISCAS), Austin, TX, USA.","DOI":"10.1109\/ISCAS48785.2022.9937863"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s11750-021-00594-1","article-title":"Mathematical optimization in classification and regression trees","volume":"29","author":"Carrizosa","year":"2021","journal-title":"TOP"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.eswa.2019.05.028","article-title":"A comparison of random forest variable selection methods for classification prediction modeling","volume":"134","author":"Speiser","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"A random forest guided tour","volume":"25","author":"Biau","year":"2016","journal-title":"TEST"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s40996-017-0083-y","article-title":"A Family of Cubic B-Spline Direct Integration Algorithms with Controllable Numerical Dissipation and Dispersion for Structural Dynamics","volume":"42","author":"Rostami","year":"2018","journal-title":"Iran J. Sci. Technol. Trans. Civ. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"De Boor, C. (1978). A Practical Guide to Splines, Applied Mathematical Sciences. [3rd ed.].","DOI":"10.1007\/978-1-4612-6333-3"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Amanatidis, D., and Dossis, M. (2019, January 20\u201322). High Level Synthesis of CART. Proceedings of the 2019 4th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM), Piraeus, Greece.","DOI":"10.1109\/SEEDA-CECNSM.2019.8908494"},{"key":"ref_27","first-page":"74","article-title":"Study and analysis of decision tree based classification algorithms","volume":"10","author":"Patel","year":"2018","journal-title":"Int. J. Comput. Sci. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Dikmese, S., Anttila, L., Campo, P.P., Valkama, M., and Renfors, M. (2019, January 15\u201316). Behavioral modeling of power amplifiers with modern machine learning techniques. Proceedings of the 2019 IEEE MTT-S International Microwave Conference on Hardware and Systems for 5G and Beyond (IMC-5G), Atlanta, GA, USA.","DOI":"10.1109\/IMC-5G47857.2019.9160381"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1109\/LMWC.2022.3142423","article-title":"Chebyshev Polynomial-LSTM Model for 5G Millimeter-Wave Power Amplifier Linearization","volume":"21","author":"Xu","year":"2022","journal-title":"IEEE Microw. Wirel. Components Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"91559","DOI":"10.1109\/ACCESS.2019.2927875","article-title":"Vector decomposition based time-delay neural network behavioral model for digital predistortion of RF power amplifiers","volume":"7","author":"Zhang","year":"2019","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7461\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:45:06Z","timestamp":1760143506000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":30,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197461"],"URL":"https:\/\/doi.org\/10.3390\/s22197461","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}