{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:12:31Z","timestamp":1778001151431,"version":"3.51.4"},"reference-count":54,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"vor","delay-in-days":236,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Applied Computational Intelligence and Soft Computing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:p>The accurate prediction of subscriber traffic is a critical challenge in telecommunication networks, as it is essential for making informed decisions to maintain consistent service quality. Various artificial intelligence (AI) methods have been explored for this purpose, with recurrent neural networks (RNNs) being particularly popular. However, RNNs often suffer from the gradient vanishing problem, which reduces their effectiveness in processing long sequences of data. Long short\u2013term memory (LSTM) networks partially address this issue by controlling the propagation of learning errors, but they still face challenges related to convergence speed and residual learning errors. To address these limitations, this study proposes a new hybrid RNN architecture that combines features of Jordan and Frasconi networks for improved subscriber traffic prediction. The proposed architecture integrates two sublayers, a sigmoid and a Gaussian function, within a hidden layer that forms a loop. This configuration enables the network to leverage incremental learning through restricted Coulomb energy (RCE) at the local level, while also benefiting from global learning through backpropagation. The architecture was tested on a dataset consisting of cellular traffic data collected from a telecommunication operator in Cameroon. The results demonstrated that the hybrid RNN model outperforms traditional Jordan and Frasconi networks, achieving a root mean square error (RMSE) of 14.18 and a mean absolute error (MAE) of 8.61 using the Adam optimizer with a batch size of 64. In addition, the hybrid model showed superior performance in terms of RMSE, MAE, and convergence speed compared to the existing models. These findings suggest that the proposed model could support telecom operators in proactive congestion management and resource optimization.<\/jats:p>","DOI":"10.1155\/acis\/7322398","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T12:19:24Z","timestamp":1756124364000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Hybrid Recurrent Neural Network Architecture for the Prediction of Subscriber Traffic in a Mobile Telecommunication Network"],"prefix":"10.1155","volume":"2025","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4655-8294","authenticated-orcid":false,"given":"Giquel Therance","family":"Sassa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9735-6016","authenticated-orcid":false,"given":"Aurelle Tchagna","family":"Kouanou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9803-6981","authenticated-orcid":false,"given":"Jean Louis Kedieng Ebongue","family":"Fendji","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3549-0516","authenticated-orcid":false,"given":"Arnauld Nzegha","family":"Fountsop","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2453-0378","authenticated-orcid":false,"given":"Thomas Bouetou","family":"Bouetou","sequence":"additional","affiliation":[]},{"given":"Yves S\u00e9bastien","family":"Emvudu","sequence":"additional","affiliation":[]}],"member":"311","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"e_1_2_11_1_2","doi-asserted-by":"crossref","unstructured":"LoumiotisI. AdamopoulouE. DemestichasK. KosmidesP. andTheologouM. Artificial Neural Networks for Traffic Prediction in 4G Networks Wireless Internet: 8Th International Conference WICON 2014 Lisbon Portugal November 2014 Springer 141\u2013146.","DOI":"10.1007\/978-3-319-18802-7_20"},{"key":"e_1_2_11_2_2","doi-asserted-by":"publisher","DOI":"10.3390\/telecom2040029"},{"key":"e_1_2_11_3_2","unstructured":"HamoudaM. Z. B. Conception Et Optimisation Robuste Des R\u00e9seaux De T\u00e9l\u00e9communications 2010."},{"key":"e_1_2_11_4_2","doi-asserted-by":"publisher","DOI":"10.3390\/mca27050077"},{"key":"e_1_2_11_5_2","article-title":"Adaptive Computation and Machine","author":"Goodfellow I.","year":"2016","journal-title":"Learning Series (Deep Learning)"},{"key":"e_1_2_11_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56904-8_14"},{"key":"e_1_2_11_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2016.07.002"},{"key":"e_1_2_11_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-016-2448-8"},{"key":"e_1_2_11_9_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0191939"},{"key":"e_1_2_11_10_2","doi-asserted-by":"crossref","unstructured":"DalgkitsisA. LoutaM. andKaretsosG. T. Traffic Forecasting in Cellular Networks Using the LSTM RNN Proceedings of the 22nd Pan-Hellenic Conference on Informatics 2018 28\u201333 https:\/\/doi.org\/10.1145\/3291533.3291540 2-s2.0-85060879641.","DOI":"10.1145\/3291533.3291540"},{"key":"e_1_2_11_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-021-04761-8"},{"key":"e_1_2_11_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/fi14080230"},{"key":"e_1_2_11_13_2","doi-asserted-by":"crossref","unstructured":"SainiK.andSharmaS. Gated Recurrent Unit (GRU) in RNN for Traffic Forecasting Based on time-series Data 2nd International Conference on Innovative Sustainable Computational Technologies (CISCT) 2022 Dehradun India 1\u20134 https:\/\/doi.org\/10.1109\/CISCT55310.2022.10046484.","DOI":"10.1109\/CISCT55310.2022.10046484"},{"key":"e_1_2_11_14_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"e_1_2_11_15_2","article-title":"Serial Order: a Parallel Distributed Processing Approach","author":"Jordan M. I.","year":"1986","journal-title":"Institute for Cognitive Science"},{"key":"e_1_2_11_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-e"},{"key":"e_1_2_11_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2005.01.005"},{"key":"e_1_2_11_18_2","first-page":"471","volume-title":"Advances in Psychology","author":"Jordan M. I.","year":"1997"},{"key":"e_1_2_11_19_2","article-title":"Neural Machine Translation by Jointly Learning to Align and Translate","author":"Bahdanau D.","year":"2014","journal-title":"arXiv preprint arXiv:1409.0473"},{"key":"e_1_2_11_20_2","volume-title":"Neural Information Processing Systems","author":"Lapedes A.","year":"1987"},{"key":"e_1_2_11_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0053993"},{"key":"e_1_2_11_22_2","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_11_23_2","unstructured":"HochreiterS. BengioY. FrasconiP. andSchmidhuberJ. Gradient Flow in Recurrent Nets: the Difficulty of Learning long-term Dependencies 2001."},{"key":"e_1_2_11_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s42486-020-00039-x"},{"key":"e_1_2_11_25_2","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4860"},{"key":"e_1_2_11_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4394"},{"key":"e_1_2_11_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-021-10471-4"},{"key":"e_1_2_11_28_2","doi-asserted-by":"crossref","unstructured":"AlizadehM. BeheshtiM. T. RamezaniA. andSaadatinezhadH. Network Traffic Forecasting Based on Fixed Telecommunication Data Using Deep Learning 2020 6th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS) IEEE 2020 1\u20137 https:\/\/doi.org\/10.1109\/icspis51611.2020.9349573.","DOI":"10.1109\/ICSPIS51611.2020.9349573"},{"key":"e_1_2_11_29_2","doi-asserted-by":"crossref","unstructured":"AlizadehM. MousaviS. E. BeheshtiM. T. andOstadiA. Combination of Feature Selection and Hybrid Classifier as to Network Intrusion Detection System Adopting FA GWO and BAT Optimizers 2021 7th International Conference on Signal Processing and Intelligent Systems (ICSPIS) IEEE 2021 1\u20137 https:\/\/doi.org\/10.1109\/icspis54653.2021.9729365.","DOI":"10.1109\/ICSPIS54653.2021.9729365"},{"key":"e_1_2_11_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.10.017"},{"key":"e_1_2_11_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10143-2"},{"key":"e_1_2_11_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117163"},{"key":"e_1_2_11_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3361037"},{"key":"e_1_2_11_34_2","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0054"},{"key":"e_1_2_11_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.08.030"},{"key":"e_1_2_11_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/69.842255"},{"key":"e_1_2_11_37_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01716-1"},{"key":"e_1_2_11_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-022-00916-9"},{"key":"e_1_2_11_39_2","doi-asserted-by":"publisher","DOI":"10.1155\/2011\/289398"},{"key":"e_1_2_11_40_2","first-page":"98","volume-title":"Actes De La Conf\u00e9rence Conjointe JEP-TALN-RECITAL 2016","author":"Dinarelli M.","year":"2016"},{"key":"e_1_2_11_41_2","doi-asserted-by":"publisher","DOI":"10.1162\/153244304773936054"},{"key":"e_1_2_11_42_2","unstructured":"JozefowiczR. ZarembaW. andSutskeverI. An Empirical Exploration of Recurrent Network Architectures International Conference on Machine Learning 2015 PMLR 2342\u20132350."},{"key":"e_1_2_11_43_2","first-page":"13","article-title":"Mod\u00e9lisation de D\u00e9pendances Entre \u00c9tiquettes Dans Les R\u00e9seaux Neuronaux R\u00e9currents [Tag Dependency Modeling in Recurrent Neural Networks]","volume":"58","author":"Dinarelli M.","year":"2017","journal-title":"Traitement Automatique des Langues"},{"key":"e_1_2_11_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_2_11_45_2","doi-asserted-by":"crossref","unstructured":"YuanM. L.andXieM. An Incremental Representation of Conceptual Symbols Using RCE Neural Network Proceedings 2nd International Conference on Development and Learning. ICDL 2002 2002 IEEE 102\u2013107.","DOI":"10.1109\/DEVLRN.2002.1011809"},{"key":"e_1_2_11_46_2","doi-asserted-by":"crossref","unstructured":"K\u00f6nigA. KornA. QuintF. andGlesnerM. Two Neural Models for Fast Category Learning\u2014Neural Associative Memories and the Restricted Coulomb Energy Model ICANN\u201993: Proceedings of the International Conference on Artificial Neural Networks Amsterdam 1993 Springer.","DOI":"10.1007\/978-1-4471-2063-6_223"},{"key":"e_1_2_11_47_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100335"},{"key":"e_1_2_11_48_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-93656-0"},{"key":"e_1_2_11_49_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21165379"},{"key":"e_1_2_11_50_2","unstructured":"KouanouA. T. Cell 4G Peaks Dataset https:\/\/github.com\/AurelleK\/Hybrid-RNN-Telecom-network."},{"key":"e_1_2_11_51_2","article-title":"A Machine Learning Algorithm for Biomedical Images Compression Using Orthogonal Transforms","volume":"11","author":"Kouanou A. T.","year":"2018","journal-title":"International Journal of Image, Graphics and Signal Processing"},{"key":"e_1_2_11_52_2","first-page":"81","article-title":"Real-Time Image Compression System Using an Embedded Board","volume":"7","author":"Kouanou A. T.","year":"2018","journal-title":"Science Journal of Circuits, Systems and Signal Processing"},{"key":"e_1_2_11_53_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2023.101423"},{"key":"e_1_2_11_54_2","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ada1da"}],"container-title":["Applied Computational Intelligence and Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/acis\/7322398","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1155\/acis\/7322398","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/acis\/7322398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T11:47:21Z","timestamp":1772970441000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/acis\/7322398"}},"subtitle":[],"editor":[{"given":"Pramita","family":"Mishra","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":54,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1155\/acis\/7322398"],"URL":"https:\/\/doi.org\/10.1155\/acis\/7322398","archive":["Portico"],"relation":{},"ISSN":["1687-9724","1687-9732"],"issn-type":[{"value":"1687-9724","type":"print"},{"value":"1687-9732","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2024-06-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7322398"}}