{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T20:13:30Z","timestamp":1769458410214,"version":"3.49.0"},"reference-count":38,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T00:00:00Z","timestamp":1669075200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2019s Horizon 2020 research and innovation program","award":["101017109"],"award-info":[{"award-number":["101017109"]}]},{"name":"European Union\u2019s Horizon 2020 research and innovation program","award":["CT 80740-035-2022"],"award-info":[{"award-number":["CT 80740-035-2022"]}]},{"name":"Colombian Ministry of Science Technology and Innovation (Minciencias)","award":["101017109"],"award-info":[{"award-number":["101017109"]}]},{"name":"Colombian Ministry of Science Technology and Innovation (Minciencias)","award":["CT 80740-035-2022"],"award-info":[{"award-number":["CT 80740-035-2022"]}]},{"name":"Communications Regulation Commission (CRC)","award":["101017109"],"award-info":[{"award-number":["101017109"]}]},{"name":"Communications Regulation Commission (CRC)","award":["CT 80740-035-2022"],"award-info":[{"award-number":["CT 80740-035-2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>Next-generation communication systems will face new challenges related to efficiently managing the available resources, such as the radio spectrum. DL is one of the optimization approaches to address and solve these challenges. However, there is a gap between research and industry. Most AI models that solve communication problems cannot be implemented in current communication devices due to their high computational capacity requirements. New approaches seek to reduce the size of DL models through quantization techniques, changing the traditional method of operations from a 32 (or 64) floating-point representation to a fixed point (usually small) one. However, there is no analytical method to determine the level of quantification that can be used to obtain the best trade-off between the reduction of computational costs and an acceptable accuracy in a specific problem. In this work, we propose an analysis methodology to determine the degree of quantization in a DNN model to solve the problem of AMR in a radio system. We use the Brevitas framework to build and analyze different quantized variants of the DL architecture VGG10 adapted to the AMR problem. The evaluation of the computational cost is performed with the FINN framework of Xilinx Research Labs to obtain the computational inference cost. The proposed design methodology allows us to obtain the combination of quantization bits per layer that provides an optimal trade-off between the model performance (i.e., accuracy) and the model complexity (i.e., size) according to a set of weights associated with each optimization objective. For example, using the proposed methodology, we found a model architecture that reduced 75.8% of the model size compared to the non-quantized baseline model, with a performance degradation of only 0.06%.<\/jats:p>","DOI":"10.3390\/a15120441","type":"journal-article","created":{"date-parts":[[2022,11,22]],"date-time":"2022-11-22T08:27:29Z","timestamp":1669105649000},"page":"441","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["A Methodology to Design Quantized Deep Neural Networks for Automatic Modulation Recognition"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7658-0994","authenticated-orcid":false,"given":"David","family":"G\u00f3ez","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Antwerp-imec, 2000 Antwerp, Belgium"},{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5906-6424","authenticated-orcid":false,"given":"Paola","family":"Soto","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp-imec, 2000 Antwerp, Belgium"},{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}]},{"given":"Steven","family":"Latr\u00e9","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp-imec, 2000 Antwerp, Belgium"}]},{"given":"Natalia","family":"Gaviria","sequence":"additional","affiliation":[{"name":"Department of Telecommunications Engineering, Universidad de Antioquia, Medell\u00edn 050010, Colombia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8152-7143","authenticated-orcid":false,"given":"Miguel","family":"Camelo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Antwerp-imec, 2000 Antwerp, Belgium"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/SURV.2012.100412.00017","article-title":"A Survey on Machine-Learning Techniques in Cognitive Radios","volume":"15","author":"Bkassiny","year":"2013","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_2","unstructured":"Garhwal, A., and Bhattacharya, P.P. (2012). A survey on dynamic spectrum access techniques for cognitive radio. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhu, Z., and Nandi, A.K. (2014). Automatic Modulation Classification: Principles, Algorithms and Applications, John Wiley & Sons.","DOI":"10.1002\/9781118906507"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/MIM.2015.7066677","article-title":"Signal identification for emerging intelligent radios: Classical problems and new challenges","volume":"18","author":"Dobre","year":"2015","journal-title":"IEEE Instrum. Meas. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Jayne, C., and Iliadis, L. (2016). Convolutional Radio Modulation Recognition Networks. Proceedings of the Engineering Applications of Neural Networks, Springer International Publishing.","DOI":"10.1007\/s00521-016-2318-4"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1049\/iet-com:20050176","article-title":"Survey of automatic modulation classification techniques: Classical approaches and new trends","volume":"1","author":"Dobre","year":"2007","journal-title":"IET Commun."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Liu, X., Yang, D., and Gamal, A.E. (November, January 29). Deep neural network architectures for modulation classification. Proceedings of the 2017 51st Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA.","DOI":"10.1109\/ACSSC.2017.8335483"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"718","DOI":"10.1109\/TNNLS.2018.2850703","article-title":"Modulation Classification Based on Signal Constellation Diagrams and Deep Learning","volume":"30","author":"Peng","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_9","unstructured":"Mao, Y., Dong, Y.Y., Sun, T., Rao, X., and Dong, C.X. (2021). Attentive Siamese Networks for Automatic Modulation Classification Based on Multitiming Constellation Diagrams. IEEE Trans. Neural Netw. Learn. Syst., 1\u201315."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/MSPEC.2019.8727143","article-title":"Will rule the airwaves: A DARPA grand challenge seeks autonomous radios to manage the wireless spectrum","volume":"56","author":"Tilghman","year":"2019","journal-title":"IEEE Spectr."},{"key":"ref_11","unstructured":"Camelo, M., Soto, P., and Latr\u00e9, S. (2021). A General Approach for Traffic Classification in Wireless Networks using Deep Learning. IEEE Trans. Netw. Serv. Manag., 1."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Garcia-Saavedra, A., and Costa-P\u00e9rez, X. (2021). O-RAN: Disrupting the Virtualized RAN Ecosystem. IEEE Commun. Stand. Mag., 1\u20138.","DOI":"10.1109\/MCOMSTD.101.2000014"},{"key":"ref_13","unstructured":"Budgett, S., and de Waard, P. (June, January 3). Quantized neural networks for modulation recognition. Proceedings of the Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV SPIE, Orlando, FL, USA."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3242897","article-title":"FINN-R: An end-to-end deep-learning framework for fast exploration of quantized neural networks","volume":"11","author":"Blott","year":"2018","journal-title":"ACM Trans. Reconfigurable Technol. Syst. (TRETS)"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2062","DOI":"10.1109\/LCOMM.2022.3184771","article-title":"Automatic Modulation Recognition: An FPGA Implementation","volume":"26","author":"Kumar","year":"2022","journal-title":"IEEE Commun. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"214882","DOI":"10.1109\/ACCESS.2020.3041463","article-title":"Software-defined radio transceiver design using FPGA-based system-on-chip embedded platform with adaptive digital predistortion","volume":"8","author":"Kumar","year":"2020","journal-title":"IEEE Access"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Umuroglu, Y., Fraser, N.J., Gambardella, G., Blott, M., Leong, P., Jahre, M., and Vissers, K. (2017, January 22\u201324). Finn: A framework for fast, scalable binarized neural network inference. Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, Monterey, CA, USA.","DOI":"10.1145\/3020078.3021744"},{"key":"ref_18","unstructured":"Pappalardo, A., Umuroglu, Y., Blott, M., Mitrevski, J., Hawks, B., Tran, N., Loncar, V., Summers, S., Borras, H., and Muhizi, J. (2022). QONNX: Representing Arbitrary-Precision Quantized Neural Networks. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"69464","DOI":"10.1109\/ACCESS.2019.2919978","article-title":"FPGA-SDR integration and experimental validation of a joint DA ML SNR and doppler spread estimator for 5G cognitive transceivers","volume":"7","author":"Haggui","year":"2019","journal-title":"IEEE Access"},{"key":"ref_20","unstructured":"Reiter, P., Karagiannakis, P., Ireland, M., Greenland, S., and Crockett, L. (2020, January 21\u201323). FPGA acceleration of a quantized neural network for remote-sensed cloud detection. Proceedings of the 7th International Workshop on On-Board Payload Data Compression, Virtual."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhao, H., Tu, Y., Mao, S., and Dou, Z. (2020, January 6\u20139). Threats of adversarial attacks in DNN-based modulation recognition. Proceedings of the IEEE INFOCOM 2020-IEEE Conference on Computer Communications, Toronto, ON, Canada.","DOI":"10.1109\/INFOCOM41043.2020.9155389"},{"key":"ref_22","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"197532","DOI":"10.1109\/ACCESS.2020.3033989","article-title":"Lightweight deep learning model for automatic modulation classification in cognitive radio networks","volume":"8","author":"Kim","year":"2020","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Hiremath, S.M., Behura, S., Kedia, S., Deshmukh, S., and Patra, S.K. (2019, January 20\u201323). Deep learning-based modulation classification using time and stockwell domain channeling. Proceedings of the 2019 National Conference on Communications (NCC), Bangalore, India.","DOI":"10.1109\/NCC.2019.8732258"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"4074","DOI":"10.1109\/TVT.2019.2900460","article-title":"Data-driven deep learning for automatic modulation recognition in cognitive radios","volume":"68","author":"Wang","year":"2019","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6416019","DOI":"10.1155\/2017\/6416019","article-title":"Modulation classification based on extensible neural networks","volume":"2017","year":"2017","journal-title":"Math. Probl. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhang, D., Ding, W., Zhang, B., Xie, C., Li, H., Liu, C., and Han, J. (2018). Automatic modulation classification based on deep learning for unmanned aerial vehicles. Sensors, 18.","DOI":"10.3390\/s18030924"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"7795","DOI":"10.1109\/JIOT.2020.2991052","article-title":"Automatic modulation classification using gated recurrent residual network","volume":"7","author":"Huang","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1109\/TCCN.2021.3089178","article-title":"Lightweight automatic modulation classification based on decentralized learning","volume":"8","author":"Fu","year":"2021","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1374","DOI":"10.1109\/TCCN.2022.3169740","article-title":"NAS-AMR: Neural Architecture Search Based Automatic Modulation Recognition for Integrated Sensing and Communication Systems","volume":"8","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.dsp.2017.09.005","article-title":"Automatic modulation classification of digital modulation signals with stacked autoencoders","volume":"71","author":"Ali","year":"2017","journal-title":"Digit. Signal Process."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1109\/LWC.2019.2963828","article-title":"Modulation recognition with graph convolutional network","volume":"9","author":"Liu","year":"2020","journal-title":"IEEE Wirel. Commun. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"58113","DOI":"10.1109\/ACCESS.2019.2913945","article-title":"Deep neural network compression technique towards efficient digital signal modulation recognition in edge device","volume":"7","author":"Tu","year":"2019","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1002\/wics.27","article-title":"Fractional factorial design","volume":"1","author":"Gunst","year":"2009","journal-title":"Wiley Interdiscip. Rev. Comput. Stat."},{"key":"ref_35","unstructured":"Ducasse, Q., Cotret, P., Lagadec, L., and Stewart, R. (2021, January 5). Benchmarking Quantized Neural Networks on FPGAs with FINN. Proceedings of the DATE Friday Workshop on System-Level Design Methods for Deep Learning on Heterogeneous Architectures, Virtual."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Bacchus, P., Stewart, R., and Komendantskaya, E. (2020). Accuracy, training time and hardware efficiency trade-offs for quantized neural networks on fpgas. Proceedings of the International Symposium on Applied Reconfigurable Computing, Springer.","DOI":"10.1007\/978-3-030-44534-8_10"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/JSTSP.2018.2797022","article-title":"Over-the-Air Deep Learning Based Radio Signal Classification","volume":"12","author":"Roy","year":"2018","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_38","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/12\/441\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:23:22Z","timestamp":1760145802000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/15\/12\/441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,22]]},"references-count":38,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["a15120441"],"URL":"https:\/\/doi.org\/10.3390\/a15120441","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,22]]}}}