{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:23:01Z","timestamp":1780510981252,"version":"3.54.1"},"reference-count":41,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T00:00:00Z","timestamp":1627430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001632","name":"Ulster University","doi-asserted-by":"publisher","award":["Vice-Chancellor Research Scholarship"],"award-info":[{"award-number":["Vice-Chancellor Research Scholarship"]}],"id":[{"id":"10.13039\/501100001632","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Large-scale fading models play an important role in estimating radio coverage, optimizing base station deployments and characterizing the radio environment to quantify the performance of wireless networks. In recent times, multi-frequency path loss models are attracting much interest due to their expected support for both sub-6 GHz and higher frequency bands in future wireless networks. Traditionally, linear multi-frequency path loss models like the ABG model have been considered, however such models lack accuracy. The path loss model based on a deep learning approach is an alternative method to traditional linear path loss models to overcome the time-consuming path loss parameters predictions based on the large dataset at new frequencies and new scenarios. In this paper, we proposed a feed-forward deep neural network (DNN) model to predict path loss of 13 different frequencies from 0.8 GHz to 70 GHz simultaneously in an urban and suburban environment in a non-line-of-sight (NLOS) scenario. We investigated a broad range of possible values for hyperparameters to search for the best set of ones to obtain the optimal architecture of the proposed DNN model. The results show that the proposed DNN-based path loss model improved mean square error (MSE) by about 6 dB and achieved higher prediction accuracy R2 compared to the multi-frequency ABG path loss model. The paper applies the XGBoost algorithm to evaluate the importance of the features for the proposed model and the related impact on the path loss prediction. In addition, the effect of hyperparameters, including activation function, number of hidden neurons in each layer, optimization algorithm, regularization factor, batch size, learning rate, and momentum, on the performance of the proposed model in terms of prediction error and prediction accuracy are also investigated.<\/jats:p>","DOI":"10.3390\/s21155100","type":"journal-article","created":{"date-parts":[[2021,7,28]],"date-time":"2021-07-28T21:21:04Z","timestamp":1627507264000},"page":"5100","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["A Deep Neural Network-Based Multi-Frequency Path Loss Prediction Model from 0.8 GHz to 70 GHz"],"prefix":"10.3390","volume":"21","author":[{"given":"Chi","family":"Nguyen","sequence":"first","affiliation":[{"name":"SenComm Research Lab, School of Engineering, Jordanstown Campus, Ulster University, Newtownabbey BT37 0QB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2338-6247","authenticated-orcid":false,"given":"Adnan Ahmad","family":"Cheema","sequence":"additional","affiliation":[{"name":"SenComm Research Lab, School of Engineering, Jordanstown Campus, Ulster University, Newtownabbey BT37 0QB, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,7,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"101366","DOI":"10.1109\/ACCESS.2019.2931072","article-title":"Path Loss Exponent and Shadowing Factor Prediction from Satellite Images Using Deep Learning","volume":"7","author":"Ates","year":"2019","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"156110","DOI":"10.1109\/ACCESS.2019.2949437","article-title":"Rain Statistics Investigation and Rain Attenuation Modeling for Millimeter Wave Short-Range Fixed Links","volume":"7","author":"Huang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"77293","DOI":"10.1109\/ACCESS.2019.2921411","article-title":"Path Loss Predictions in the VHF and UHF Bands within Urban Environments: Experimental Investigation of Empirical, Heuristics and Geospatial Models","volume":"7","author":"Faruk","year":"2019","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2388","DOI":"10.1109\/ACCESS.2015.2486778","article-title":"Indoor office wideband millimeter-wave propagation measurements and channel models at 28 and 73 GHz for Ultra-Dense 5G Wireless Networks","volume":"3","author":"MacCartney","year":"2015","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Turan, B., and Coleri, S. (2020). Machine Learning Based Channel Modeling for Vehicular Visible Light Communication. arXiv.","DOI":"10.1109\/TVT.2021.3107835"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1109\/SURV.2012.022412.00172","article-title":"A Survey of Wireless Path Loss Prediction and Coverage Mapping Methods","volume":"15","author":"Phillips","year":"2013","journal-title":"IEEE Commun. Surv.Tutor."},{"key":"ref_7","unstructured":"Park, C., Tettey, D.K., and Jo, H.-S. (2019). Artificial Neural Network Modeling for Path Loss Prediction in Urban Environments. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Aldossari, S., and Chen, K.C. (2020). Predicting the Path Loss of Wireless Channel Models Using Machine Learning Techniques in MmWave Urban Communications. arXiv.","DOI":"10.1109\/WPMC48795.2019.9096057"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wen, J., Yang, G., He, Z., and Wang, J. (2019). Path Loss Prediction Based on Machine Learning: Principle, Method, and Data Expansion. Appl. Sci., 9.","DOI":"10.3390\/app9091908"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1109\/COMST.2020.3024783","article-title":"Enabling AI in Future Wireless Networks: A Data Life Cycle Perspective","volume":"23","author":"Nguyen","year":"2021","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, J., Guo, Q., Wang, D., Zhong, Z., and Li, C. (2018, January 12\u201314). Model accuracy and sensitivity assessment based on dual-band large-scale channel measurement. Proceedings of the 2018 24th Asia-Pacific Conference on Communications (APCC), Ningbo, China.","DOI":"10.1109\/APCC.2018.8633464"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1109\/LAWP.2010.2041523","article-title":"Simplified Characterization of the Urban Propagation Environment for Path Loss Calculation","volume":"9","author":"Fernandes","year":"2010","journal-title":"IEEE Antennas Wirel. Propag Lett."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"5404","DOI":"10.1109\/TAP.2016.2617379","article-title":"Improvement of Outdoor Signal Strength Prediction in UHF Band by Artificial Neural Network","volume":"64","author":"Ferreira","year":"2016","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Kalakh, M., Kandil, N., and Hakem, N. (2012, January 6\u20139). Neural networks model of an UWB channel path loss in a mine environment. Proceedings of the 2012 IEEE 75th Vehicular Technology Conference (VTC Spring), Yokohama, Japan.","DOI":"10.1109\/VETECS.2012.6240318"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"150462","DOI":"10.1109\/ACCESS.2019.2947009","article-title":"Determination of neural network parameters for path loss prediction in very high frequency wireless channel","volume":"7","author":"Popoola","year":"2019","journal-title":"IEEE Access"},{"key":"ref_16","first-page":"1","article-title":"Channel Path-Loss Measurement and Modeling in Wireless Data Network (IEEE 802.11n) Using Artificial Neural Network","volume":"4","author":"Olajide","year":"2020","journal-title":"Eur. J. Electr. Eng. Comput. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7925","DOI":"10.1109\/ACCESS.2020.2964103","article-title":"Model-aided deep learning method for path loss prediction in mobile communication systems at 2.6 GHz","volume":"8","author":"Thrane","year":"2020","journal-title":"IEEE Access"},{"key":"ref_18","first-page":"795","article-title":"Artificial Neural Network model for the determination of GSM Rxlevel from atmospheric parameters","volume":"20","author":"Eichie","year":"2017","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1444345","DOI":"10.1080\/23311916.2018.1444345","article-title":"Optimal model for path loss predictions using feed-forward neural networks","volume":"5","author":"Popoola","year":"2018","journal-title":"Cogent Eng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Singh, H., Gupta, S., Dhawan, C., and Mishra, A. (2020). Path Loss Prediction in Smart Campus Environment: Machine Learning-based Approaches. IEEE Veh. Technol. Conf., 1\u20135.","DOI":"10.1109\/VTC2020-Spring48590.2020.9129444"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sotiroudis, S.P. (2019, January 13\u201315). Neural Networks and Random Forests: A Comparison Regarding Prediction of Propagation Path Loss for NB-IoT Networks. Proceedings of the 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST), Thessaloniki, Greece.","DOI":"10.1109\/MOCAST.2019.8741751"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"2735","DOI":"10.1109\/TVT.2010.2050502","article-title":"Macrocell Path-Loss Prediction Using Artificial Neural Networks","volume":"59","author":"Suzuki","year":"2010","journal-title":"IEEE Trans. Vehic. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"159251","DOI":"10.1109\/ACCESS.2019.2950634","article-title":"Path Loss Prediction Based on Machine Learning Methods for Aircraft Cabin Environments","volume":"7","author":"Wen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3675","DOI":"10.1109\/TAP.2017.2705112","article-title":"A UHF Path Loss Model Using Learning Machine for Heterogeneous Networks","volume":"65","author":"Ayadi","year":"2017","journal-title":"IEEE Trans. Antennas Propag."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Jo, H.S., Park, C., Lee, E., Choi, H.K., and Park, J. (2020). Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process. Sensors, 20.","DOI":"10.3390\/s20071927"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1007\/s13369-015-1949-6","article-title":"A Multi-wall and Multi-frequency Indoor Path Loss Prediction Model Using Artificial Neural Networks","volume":"41","author":"Zineb","year":"2016","journal-title":"Arab. J. Sci. Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1007\/s11045-015-0380-1","article-title":"Fading channel modelling using single-hidden layer feedforward neural networks","volume":"28","author":"Liu","year":"2017","journal-title":"Multidimens. Syst. Signal Process."},{"key":"ref_28","unstructured":"Yu, T., and Zhu, H. (2020). Hyper-parameter optimization: A review of algorithms and applications. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"53040","DOI":"10.1109\/ACCESS.2019.2912200","article-title":"Review of Deep Learning Algorithms and Architectures","volume":"7","author":"Shrestha","year":"2019","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.1109\/JPROC.2017.2761740","article-title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","volume":"105","author":"Sze","year":"2017","journal-title":"Proc. IEEE"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s42979-021-00535-6","article-title":"Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective","volume":"2","author":"Sarker","year":"2021","journal-title":"SN Comput. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2595","DOI":"10.1109\/COMST.2018.2846401","article-title":"Deep learning for intelligent wireless networks: A comprehensive survey","volume":"20","author":"Mao","year":"2018","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kulin, M., Kazaz, T., Moerman, I., and de Poorter, E. (2020). A survey on machine learning-based performance improvement of wireless networks: PHY, MAC and Network layer. arXiv.","DOI":"10.3390\/electronics10030318"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"6497340","DOI":"10.1155\/2018\/6497340","article-title":"The Rayleigh Fading Channel Prediction via Deep Learning","volume":"2018","author":"Liao","year":"2018","journal-title":"Wirel. Commun. Mob. Comput."},{"key":"ref_35","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1029\/2019RS006924","article-title":"Radio propagation measurements and modeling for standardization of the site general path loss model in International Telecommunications Union recommendations for 5G wireless networks","volume":"55","author":"Salous","year":"2020","journal-title":"Radio Sci."},{"key":"ref_37","first-page":"1689","article-title":"XGboost with python Gradient boosted trees with XGBoost and scikit-learn","volume":"53","author":"Brownlee","year":"2015","journal-title":"Acta Univ. Agric. Silvic. Mendel. Brun."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Niu, Y. (November, January 30). Walmart Sales Forecasting using XGBoost algorithm and Feature engineering. Proceedings of the 2020 International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE, Bangkok, Thailand.","DOI":"10.1109\/ICBASE51474.2020.00103"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ouadjer, Y. (2021, January 9\u201310). Feature Importance Evaluation of Smartphone Touch Gestures for Biometric Authentication. Proceedings of the 2020 2nd International Workshop on Human-Centric Smart Environments for Health and Well-being (IHSH), Boumerdes, Algeria.","DOI":"10.1109\/IHSH51661.2021.9378750"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"7331","DOI":"10.1109\/TCOMM.2019.2924010","article-title":"Wireless networks design in the era of deep learning: Model-based, AI-based, or both?","volume":"67","author":"Zappone","year":"2019","journal-title":"IEEE Trans. Commun."},{"key":"ref_41","unstructured":"(2021, June 01). Qualcomm Global Update on Spectrum for 4G & 5G. Available online: https:\/\/www.qualcomm.com\/media\/documents\/files\/spectrum-for-4g-and-5g.pdf."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/15\/5100\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:36:11Z","timestamp":1760164571000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/15\/5100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,28]]},"references-count":41,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2021,8]]}},"alternative-id":["s21155100"],"URL":"https:\/\/doi.org\/10.3390\/s21155100","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,28]]}}}