{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T19:07:19Z","timestamp":1768590439187,"version":"3.49.0"},"reference-count":28,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T00:00:00Z","timestamp":1768435200000},"content-version":"vor","delay-in-days":14,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Communications"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>We employ convolutional neural networks (CNNs) with distance feature and satellite image for path loss (PL) estimation at sub\u20106 GHz and millimetre wave (mmWave) frequencies. In order to avoid complex preprocessing of embedding distance feature into the image, we append this feature at the earliest, after the convolutional blocks of a CNN\u2010based VGG\u201016 architecture. This is intuitive since the following fully\u2010connected (FC) layer performs feature aggregation, thus, it combines the injected distance feature with the extracted features from the image. We propose three VGG\u201016 structures which vary in how the distance information is included. Performance is then evaluated in terms of training and prediction times, root mean square error (RMSE) and correlation coefficient, while performance without appended distance serves as benchmark. We observe that the inclusion of distance parameter gives more accurate estimation in terms of RMSE and a very strong correlation between the predicted and estimated PL values. Moreover, the proposed structures typically converge more quickly. Among the proposed structures, the one aided by a logarithm\u2010of\u2010distance model, is the most computationally efficient, leading to  and  reduction of training time and prediction time, respectively. Additionally, the VGG\u201016\u2010based PL predictors yield lower RMSE by up to 2.4 dB and  higher correlation compared to the 3GPP 38.901 urban macro cell (UMa) empirical\u00a0model.<\/jats:p>","DOI":"10.1049\/cmu2.70132","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:06:01Z","timestamp":1768547161000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing CNN Path Loss Estimation Performance using Satellite Image and Distance Feature"],"prefix":"10.1049","volume":"20","author":[{"given":"Renata Nur","family":"Afifah","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung West Java Indonesia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1556-3589","authenticated-orcid":false,"given":"Irma","family":"Zakia","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung West Java Indonesia"}]}],"member":"265","published-online":{"date-parts":[[2026,1,15]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet\u2010com.2018.5448"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2016.2523924"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3132609"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3465653"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1049\/cmu2.12369"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2924010"},{"key":"e_1_2_10_8_1","doi-asserted-by":"crossref","unstructured":"S.Limmer A. M.Alba andN.Michailow \u201cPhysics\u2010Informed Neural Networks for Pathloss Prediction \u201d in2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP)(IEEE 2023) 1\u20135 https:\/\/doi.org\/10.1109\/MLSP55844.2023.10285952.","DOI":"10.1109\/MLSP55844.2023.10285952"},{"key":"e_1_2_10_9_1","doi-asserted-by":"crossref","unstructured":"R. N.AfifahandI.Zakia \u201cSurvey on Path Loss Estimation of 5G mmWave Using Deep Learning \u201d in2024 International Conference on ICT for Smart Society (ICISS)(IEEE 2024) 1\u20135 https:\/\/doi.org\/10.1109\/ICISS62896.2024.10751194.","DOI":"10.1109\/ICISS62896.2024.10751194"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2985929"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2931072"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2964103"},{"key":"e_1_2_10_13_1","doi-asserted-by":"crossref","unstructured":"J.Thrane B.Sliwa C.Wietfeld andH. L.Christiansen \u201cDeep Learning\u2010Based Signal Strength Prediction Using Geographical Images And Expert Knowledge \u201d in2020 IEEE Global Communications Conference (Globecom)(IEEE 2020) 1\u20136 https:\/\/doi.org\/10.1109\/GLOBECOM42002.2020.9322089.","DOI":"10.1109\/GLOBECOM42002.2020.9322089"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/LAWP.2020.3014314"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAP.2022.3209229"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3418900"},{"key":"e_1_2_10_17_1","unstructured":"K.SimonyanandA.Zisserman \u201cVery Deep Convolutional Networks for Large\u2010scale Image Recognition \u201dpreprint arXiv 2014 https:\/\/arxiv.org\/abs\/1409.1556."},{"key":"e_1_2_10_18_1","unstructured":"Study Channel Model for Frequencies From 0.5 to 100 GHz (Release 17) Technical Report 38.901 V17.0.0 (3rd Generation Partnership Project 2022)."},{"key":"e_1_2_10_19_1","volume-title":"Wireless Communications: Principles and Practice","author":"Rappaport T. S.","year":"2002"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511841224"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0163034"},{"key":"e_1_2_10_22_1","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3264230"},{"key":"e_1_2_10_24_1","doi-asserted-by":"crossref","unstructured":"T.\u2010W.LiandG.\u2010C.Lee \u201cPerformance Analysis of Fine\u2010Tune Transferred Deep Learning \u201d in2021 IEEE 3rd Eurasia Conference on IOT Communication and Engineering (ECICE)(IEEE 2021) 315\u2013319 https:\/\/doi.org\/10.1109\/ECICE52819.2021.9645649.","DOI":"10.1109\/ECICE52819.2021.9645649"},{"key":"e_1_2_10_25_1","unstructured":"A.G\u00e9ron \u201cCustom Models and Training with TensorFlow \u201d inHands\u2010On Machine Learning With Scikit\u2010Learn Keras and TensorFlow 2nd ed.(O'Reilly Media Sebastopol 2019) 448\u2013450."},{"key":"e_1_2_10_26_1","volume-title":"Statistics at Square One","author":"Campbell M. J.","year":"2011"},{"key":"e_1_2_10_27_1","volume-title":"Mathematical Statistics and Data Analysis","author":"Rice J. A.","year":"1995"},{"key":"e_1_2_10_28_1","volume-title":"Nonparametric Statistical Methods","author":"Hollander M.","year":"2013"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/LAWP.2021.3124233"}],"container-title":["IET Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70132","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cmu2.70132","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cmu2.70132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T07:06:15Z","timestamp":1768547175000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cmu2.70132"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1049\/cmu2.70132"],"URL":"https:\/\/doi.org\/10.1049\/cmu2.70132","archive":["Portico"],"relation":{},"ISSN":["1751-8628","1751-8636"],"issn-type":[{"value":"1751-8628","type":"print"},{"value":"1751-8636","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-04-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70132"}}