{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:49:40Z","timestamp":1764874180938,"version":"build-2065373602"},"reference-count":59,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Office of the Director of National Intelligence (ODNI)"},{"name":"Intelligence Advanced Research Projects Activity (IARPA)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>Transfer learning (TL) techniques, which leverage prior knowledge gained from data with different distributions to achieve higher performance and reduced training time, are often used in computer vision (CV) and natural language processing (NLP), but have yet to be fully utilized in the field of radio frequency machine learning (RFML). This work systematically evaluates how the training domain and task, characterized by the transmitter (Tx)\/receiver (Rx) hardware and channel environment, impact radio frequency (RF) TL performance for example automatic modulation classification (AMC) and specific emitter identification (SEI) use-cases. Through exhaustive experimentation using carefully curated synthetic and captured datasets with varying signal types, channel types, signal to noise ratios (SNRs), carrier\/center frequencys (CFs), frequency offsets (FOs), and Tx and Rx devices, actionable and generalized conclusions are drawn regarding how best to use RF TL techniques for domain adaptation and sequential learning. Consistent with trends identified in other modalities, our results show that RF TL performance is highly dependent on the similarity between the source and target domains\/tasks, but also on the relative difficulty of the source and target domains\/tasks. Results also discuss the impacts of channel environment and hardware variations on RF TL performance and compare RF TL performance using head re-training and model fine-tuning methods.<\/jats:p>","DOI":"10.3390\/make6020057","type":"journal-article","created":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T12:29:47Z","timestamp":1717417787000},"page":"1210-1242","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["An Analysis of Radio Frequency Transfer Learning Behavior"],"prefix":"10.3390","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5896-0176","authenticated-orcid":false,"given":"Lauren J.","family":"Wong","sequence":"first","affiliation":[{"name":"Intel AI Lab, Santa Clara, CA 95054, USA"},{"name":"National Security Institute, Virginia Tech, Blacksburg, VA 24060, USA"},{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24060, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2040-3101","authenticated-orcid":false,"given":"Braeden","family":"Muller","sequence":"additional","affiliation":[{"name":"National Security Institute, Virginia Tech, Blacksburg, VA 24060, USA"},{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24060, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6244-6038","authenticated-orcid":false,"given":"Sean","family":"McPherson","sequence":"additional","affiliation":[{"name":"Intel AI Lab, Santa Clara, CA 95054, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2437-3410","authenticated-orcid":false,"given":"Alan J.","family":"Michaels","sequence":"additional","affiliation":[{"name":"National Security Institute, Virginia Tech, Blacksburg, VA 24060, USA"},{"name":"Bradley Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA 24060, USA"}]}],"member":"1968","published-online":{"date-parts":[[2024,6,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"137184","DOI":"10.1109\/ACCESS.2019.2942390","article-title":"Machine Learning for 5G\/B5G Mobile and Wireless Communications: Potential, Limitations, and Future Directions","volume":"7","author":"Lee","year":"2019","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2243","DOI":"10.1109\/OJCOMS.2021.3112939","article-title":"An RFML Ecosystem: Considerations for the Application of Deep Learning to Spectrum Situational Awareness","volume":"2","author":"Wong","year":"2021","journal-title":"IEEE Open J. Commun. Soc."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1177\/1548512921991245","article-title":"Training data augmentation for deep learning radio frequency systems","volume":"18","author":"Clark","year":"2021","journal-title":"J. Def. Model. Simul."},{"unstructured":"Hauser, S.C. (2018). Real-World Considerations for Deep Learning in Spectrum Sensing. [Master\u2019s Thesis, Virginia Tech].","key":"ref_4"},{"doi-asserted-by":"crossref","unstructured":"Sankhe, K., Belgiovine, M., Zhou, F., Riyaz, S., Ioannidis, S., and Chowdhury, K. (May, January 29). ORACLE: Optimized Radio Classification through Convolutional Neural Networks. Proceedings of the IEEE INFOCOM 2019-IEEE Conference on Computer Communications, Paris, France.","key":"ref_5","DOI":"10.1109\/INFOCOM.2019.8737463"},{"unstructured":"Sarkar, A., and Strube, M. Transfer Learning in Natural Language Processing. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials.","key":"ref_6"},{"unstructured":"Zhu, Y., Chen, Y., Lu, Z., Pan, S., Xue, G.R., Yu, Y., and Yang, Q. (2011, January 7\u201311). Heterogeneous transfer learning for image classification. Proceedings of the AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","key":"ref_7"},{"doi-asserted-by":"crossref","unstructured":"Zamir, A.R., Sax, A., Shen, W., Guibas, L.J., Malik, J., and Savarese, S. (2018, January 18\u201323). Taskonomy: Disentangling task transfer learning. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","key":"ref_8","DOI":"10.1109\/CVPR.2018.00391"},{"doi-asserted-by":"crossref","unstructured":"Cui, Y., Song, Y., Sun, C., Howard, A., and Belongie, S. (2018, January 18\u201323). Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","key":"ref_9","DOI":"10.1109\/CVPR.2018.00432"},{"doi-asserted-by":"crossref","unstructured":"Olivas, E.S., Guerrero, J.D.M., Martinez-Sober, M., Magdalena-Benedito, J.R., and L\u00f3pez, A.J.S. (2009). Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, IGI Global.","key":"ref_10","DOI":"10.4018\/978-1-60566-766-9"},{"doi-asserted-by":"crossref","unstructured":"Wong, L.J., and Michaels, A.J. (2022). Transfer Learning for Radio Frequency Machine Learning: A Taxonomy and Survey. Sensors, 22.","key":"ref_11","DOI":"10.3390\/s22041416"},{"doi-asserted-by":"crossref","unstructured":"Robinson, J., and Kuzdeba, S. (2021, January 9\u201312). RiftNet: Radio Frequency Classification for Large Populations. Proceedings of the 2021 IEEE 18th Annual Consumer Communications Networking Conference (CCNC), Las Vegas, NV, USA.","key":"ref_12","DOI":"10.1109\/CCNC49032.2021.9369455"},{"unstructured":"Rondeau, T. (2022, November 22). Radio Frequency Machine Learning Systems (RFMLS). Available online: https:\/\/www.darpa.mil\/program\/radio-frequency-machine-learning-systems.","key":"ref_13"},{"key":"ref_14","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_15","first-page":"113","article-title":"Specific emitter identification and verification","volume":"113","author":"Talbot","year":"2003","journal-title":"Technol. Rev."},{"doi-asserted-by":"crossref","unstructured":"West, N.E., and O\u2019Shea, T. (2017, January 6\u20139). Deep architectures for modulation recognition. Proceedings of the 2017 IEEE Int. Symp. on Dynamic Spectrum Access Networks (DySPAN), Baltimore, MD, USA.","key":"ref_16","DOI":"10.1109\/DySPAN.2017.7920754"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/MCOM.2018.1800153","article-title":"Deep Learning Convolutional Neural Networks for Radio Identification","volume":"56","author":"Riyaz","year":"2018","journal-title":"IEEE Commun. Mag."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A Survey on Transfer Learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans. Knowl. Data Eng."},{"doi-asserted-by":"crossref","unstructured":"Ruder, S. (2019). Neural Transfer Learning for Natural Language Processing. [Ph.D. Thesis, NUI Galway].","key":"ref_19","DOI":"10.18653\/v1\/N19-5004"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"89256","DOI":"10.1109\/ACCESS.2019.2925569","article-title":"Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"164529","DOI":"10.1109\/ACCESS.2020.3022513","article-title":"A Deep Convolutional Neural Network Based Transfer Learning Method for Non-Cooperative Spectrum Sensing","volume":"8","author":"Pati","year":"2020","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Kuzdeba, S., Robinson, J., and Carmack, J. (2021, January 9\u201312). Transfer Learning with Radio Frequency Signals. Proceedings of the 2021 IEEE 18th Annual Consumer Communications Networking Conference (CCNC), Las Vegas, NV, USA.","key":"ref_22","DOI":"10.1109\/CCNC49032.2021.9369550"},{"key":"ref_23","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_24","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1109\/JSTSP.2017.2784180","article-title":"Deep Learning Based Communication Over the Air","volume":"12","author":"Cammerer","year":"2018","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"138","DOI":"10.23919\/JCC.2020.02.012","article-title":"Spectrum sensing based on deep learning classification for cognitive radios","volume":"17","author":"Zheng","year":"2020","journal-title":"China Comm."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1109\/LWC.2019.2940579","article-title":"Robust Deep Sensing Through Transfer Learning in Cognitive Radio","volume":"9","author":"Peng","year":"2020","journal-title":"IEEE Wirel. Comm. Lett."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2208","DOI":"10.1109\/TWC.2019.2963185","article-title":"DeepNOMA: A Unified Framework for NOMA Using Deep Multi-Task Learning","volume":"19","author":"Ye","year":"2020","journal-title":"IEEE Trans. Wirel. Comm."},{"doi-asserted-by":"crossref","unstructured":"Clark, W.H., Arndorfer, V., Tamir, B., Kim, D., Vives, C., Morris, H., Wong, L., and Headley, W.C. (2019, January 12\u201314). Developing RFML Intuition: An Automatic Modulation Classification Architecture Case Study. Proceedings of the 2019 IEEE Military Comm. Conference (MILCOM), Norfolk, VA, USA.","key":"ref_28","DOI":"10.1109\/MILCOM47813.2019.9020949"},{"unstructured":"Merchant, K. (2019). Deep Neural Networks for Radio Frequency Fingerprinting. [Ph.D. Thesis, University of Maryland].","key":"ref_29"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"10443","DOI":"10.1109\/ACCESS.2020.2965089","article-title":"Neural network generalization: The impact of camera parameters","volume":"8","author":"Liu","year":"2020","journal-title":"IEEE Access"},{"unstructured":"Gaeddert, J. (2020, November 17). liquid-dsp. Available online: https:\/\/github.com\/jgaeddert\/liquid-dsp.","key":"ref_31"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"110023","DOI":"10.1109\/ACCESS.2023.3322105","article-title":"A Real-World Dataset Generator for Specific Emitter Identification","volume":"11","author":"Muller","year":"2023","journal-title":"IEEE Access"},{"unstructured":"Gadgets, G.S. (2023, March 05). YARD Stick One, 2023. Available online: https:\/\/greatscottgadgets.com\/yardstickone\/.","key":"ref_33"},{"unstructured":"(2023, March 05). Texas Instruments. Low-Power SoC (System-on-Chip) with MCU, Memory, Sub-1 GHz RF Transceiver, and USB Controller, 2013. Available online: https:\/\/www.ti.com\/lit\/ds\/symlink\/cc1110-cc1111.pdf.","key":"ref_34"},{"unstructured":"Wong, L.J., McPherson, S., and Michaels, A.J. (2022). Transfer Learning for RF Domain Adaptation\u2014Synthetic Dataset. arXiv.","key":"ref_35"},{"unstructured":"Hilburn, B., West, N., O\u2019Shea, T., and Roy, T. (2018, January 17\u201321). SigMF: The signal metadata format. Proceedings of the GNU Radio Conference, Henderson, NV, USA.","key":"ref_36"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/IOTM.0001.1900065","article-title":"Deep Learning for RF Fingerprinting: A Massive Experimental Study","volume":"3","author":"Jian","year":"2020","journal-title":"IEEE Internet Things Mag."},{"unstructured":"Boegner, L., Gulati, M., Vanhoy, G., Vallance, P., Comar, B., Kokalj-Filipovic, S., Lennon, C., and Miller, R.D. (2022). Large Scale Radio Frequency Signal Classification. arXiv, Available online: http:\/\/arxiv.org\/abs\/2207.09918.","key":"ref_38"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"4228","DOI":"10.1109\/TWC.2023.3316197","article-title":"Data and Knowledge Dual-Driven Automatic Modulation Classification for 6G Wireless Communications","volume":"23","author":"Ding","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"unstructured":"Flowers, B., and Headley, W.C. (2019, January 12\u201314). Adversarial Radio Frequency Machine Learning (RFML) with PyTorch. Proceedings of the MILCOM 2019\u20142019 IEEE Military Communications Conference (MILCOM) Workshops, Norfolk, VA, USA.","key":"ref_40"},{"unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.","key":"ref_41"},{"unstructured":"(2022, September 12). Cross Entropy Loss. Available online: https:\/\/pytorch.org\/docs\/stable\/generated\/torch.nn.CrossEntropyLoss.html.","key":"ref_42"},{"key":"ref_43","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"unstructured":"Michaels, A.J., and Wong, L.J. (2021, January 27\u201330). Multinomial-Based Decision Synthesis of ML Classification Outputs. Proceedings of the Modeling Decisions for Artificial Intelligence: 18th International Conference, MDAI 2021, Ume\u00e5, Sweden. Proceedings 18.","key":"ref_44"},{"unstructured":"Rosenstein, M.T., Marx, Z., Kaelbling, L.P., and Dietterich, T.G. (2005, January 9). To transfer or not to transfer. Proceedings of the NIPS 2005 Workshop on Transfer Learning, Whistler, BC, Canada.","key":"ref_45"},{"doi-asserted-by":"crossref","unstructured":"Ying, S., Huang, S., Chang, S., He, J., and Feng, Z. (2023). AMSCN: A Novel Dual-Task Model for Automatic Modulation Classification and Specific Emitter Identification. Sensors, 23.","key":"ref_46","DOI":"10.3390\/s23052476"},{"doi-asserted-by":"crossref","unstructured":"Felbo, B., Mislove, A., S\u00f8gaard, A., Rahwan, I., and Lehmann, S. (2017, January 7\u201311). Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Copenhagen, Denmark.","key":"ref_47","DOI":"10.18653\/v1\/D17-1169"},{"unstructured":"Howard, J., and Ruder, S. (2018). Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Melbourne, Australia, Association for Computational Linguistics.","key":"ref_48"},{"unstructured":"Liu, C.C., Pfeiffer, J., Vuli\u0107, I., and Gurevych, I. (2023). Improving Generalization of Adapter-Based Cross-lingual Transfer with Scheduled Unfreezing. arXiv.","key":"ref_49"},{"unstructured":"Nguyen, C., Hassner, T., Seeger, M., and Archambeau, C. (2020, January 13\u201318). LEEP: A new measure to evaluate transferability of learned representations. Proceedings of the International Conference on Machine Learning, PMLR, Virtual.","key":"ref_50"},{"unstructured":"You, K., Liu, Y., Long, M., and Wang, J. (2021). LogME: Practical Assessment of Pre-trained Models for Transfer Learning. arXiv.","key":"ref_51"},{"doi-asserted-by":"crossref","unstructured":"Tan, Y., Li, Y., and Huang, S.L. (2021, January 20\u201325). OTCE: A Transferability Metric for Cross-Domain Cross-Task Representations. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","key":"ref_52","DOI":"10.1109\/CVPR46437.2021.01552"},{"unstructured":"Huang, L.K., Wei, Y., Rong, Y., Yang, Q., and Huang, J. (2021). Frustratingly Easy Transferability Estimation. arXiv.","key":"ref_53"},{"doi-asserted-by":"crossref","unstructured":"P\u00e1ndy, M., Agostinelli, A., Uijlings, J., Ferrari, V., and Mensink, T. (2021). Transferability Estimation using Bhattacharyya Class Separability. arXiv.","key":"ref_54","DOI":"10.1109\/CVPR52688.2022.00896"},{"unstructured":"Rabanser, S., G\u00fcnnemann, S., and Lipton, Z. (2019). Failing loudly: An empirical study of methods for detecting dataset shift. Adv. Neural Inf. Process. Syst., 32.","key":"ref_55"},{"unstructured":"Ndiour, I., Ahuja, N., and Tickoo, O. (2020). Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features. arXiv, Available online: http:\/\/arxiv.org\/abs\/2012.04250.","key":"ref_56"},{"doi-asserted-by":"crossref","unstructured":"Dong, X., Guo, J., Li, A., Ting, W.T., Liu, C., and Kung, H. (2022, January 18\u201324). Neural mean discrepancy for efficient out-of-distribution detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","key":"ref_57","DOI":"10.1109\/CVPR52688.2022.01862"},{"unstructured":"Guo, C., Pleiss, G., Sun, Y., and Weinberger, K.Q. (2017, January 6\u201311). On calibration of modern neural networks. Proceedings of the 34th International Conference on Machine Learning-Volume 70, Sydney, NSW, Australia.","key":"ref_58"},{"unstructured":"Gal, Y., and Ghahramani, Z. (2016, January 19\u201324). Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. Proceedings of the 33rd International Conference on International Conference on Machine Learning-Volume 48, New York, NY, USA.","key":"ref_59"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/6\/2\/57\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:53:02Z","timestamp":1760107982000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/6\/2\/57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":59,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6]]}},"alternative-id":["make6020057"],"URL":"https:\/\/doi.org\/10.3390\/make6020057","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2024,6,3]]}}}