Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments
Modern cellular communication networks are already being perturbed by large and steadily increasing mobile subscribers in high demand for better service quality. To constantly and reliably deploy and optimally manage such mobile cellular networks, the radio signal attenuation loss between the path l...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/11/5713 |
| _version_ | 1797494045607460864 |
|---|---|
| author | Joseph Isabona Agbotiname Lucky Imoize Stephen Ojo Olukayode Karunwi Yongsung Kim Cheng-Chi Lee Chun-Ta Li |
| author_facet | Joseph Isabona Agbotiname Lucky Imoize Stephen Ojo Olukayode Karunwi Yongsung Kim Cheng-Chi Lee Chun-Ta Li |
| author_sort | Joseph Isabona |
| collection | DOAJ |
| description | Modern cellular communication networks are already being perturbed by large and steadily increasing mobile subscribers in high demand for better service quality. To constantly and reliably deploy and optimally manage such mobile cellular networks, the radio signal attenuation loss between the path lengths of a base transmitter and the mobile station receiver must be appropriately estimated. Although many log-distance-based linear models for path loss prediction in wireless cellular networks exist, radio frequency planning requires advanced non-linear models for more accurate predictive path loss estimation, particularly for complex microcellular environments. The precision of the conventional models on path loss prediction has been reported in several works, generally ranging from 8–12 dB in terms of Root Mean Square Error (RMSE), which is too high compared to the acceptable error limit between 0 and 6 dB. Toward this end, the need for near-precise machine learning-based path loss prediction models becomes imperative. This work develops a distinctive multi-layer perception (MLP) neural network-based path loss model with well-structured implementation network architecture, empowered with the grid search-based hyperparameter tuning method. The proposed model is designed for optimal path loss approximation between mobile station and base station. The hyperparameters examined include the neuron number, learning rate and hidden layers number. In detail, the developed MLP model prediction accuracy level using different learning and training algorithms with the tuned best values of the hyperparameters have been applied for extensive path loss experimental datasets. The experimental path loss data is acquired via a field drive test conducted over an operational 4G LTE network in an urban microcellular environment. The results were assessed using several first-order statistical performance indicators. The results show that prediction errors of the proposed MLP model compared favourably with measured data and were better than those obtained using conventional log-distance-based path loss models. |
| first_indexed | 2024-03-10T01:28:40Z |
| format | Article |
| id | doaj.art-5b71e1f15a2b45229282d178b084f236 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T01:28:40Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-5b71e1f15a2b45229282d178b084f2362023-11-23T13:46:37ZengMDPI AGApplied Sciences2076-34172022-06-011211571310.3390/app12115713Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio EnvironmentsJoseph Isabona0Agbotiname Lucky Imoize1Stephen Ojo2Olukayode Karunwi3Yongsung Kim4Cheng-Chi Lee5Chun-Ta Li6Department of Physics, Federal University Lokoja, Lokoja 260101, NigeriaDepartment of Electrical and Electronics Engineering, Faculty of Engineering, University of Lagos, Akoka, Lagos 100213, NigeriaDepartment of Electrical and Computer Engineering, College of Engineering, Anderson University, Anderson, SC 29621, USACollege of Arts and Sciences, Anderson University, Anderson, SC 29621, USADepartment of Technology Education, Chungnam National University, Daejeon 34134, KoreaResearch and Development Center for Physical Education, Health and Information Technology, Department of Library and Information Science, Fu Jen Catholic University, New Taipei City 24205, TaiwanDepartment of Information Management, Tainan University of Technology, 529 Zhongzheng Road, Tainan City 710, TaiwanModern cellular communication networks are already being perturbed by large and steadily increasing mobile subscribers in high demand for better service quality. To constantly and reliably deploy and optimally manage such mobile cellular networks, the radio signal attenuation loss between the path lengths of a base transmitter and the mobile station receiver must be appropriately estimated. Although many log-distance-based linear models for path loss prediction in wireless cellular networks exist, radio frequency planning requires advanced non-linear models for more accurate predictive path loss estimation, particularly for complex microcellular environments. The precision of the conventional models on path loss prediction has been reported in several works, generally ranging from 8–12 dB in terms of Root Mean Square Error (RMSE), which is too high compared to the acceptable error limit between 0 and 6 dB. Toward this end, the need for near-precise machine learning-based path loss prediction models becomes imperative. This work develops a distinctive multi-layer perception (MLP) neural network-based path loss model with well-structured implementation network architecture, empowered with the grid search-based hyperparameter tuning method. The proposed model is designed for optimal path loss approximation between mobile station and base station. The hyperparameters examined include the neuron number, learning rate and hidden layers number. In detail, the developed MLP model prediction accuracy level using different learning and training algorithms with the tuned best values of the hyperparameters have been applied for extensive path loss experimental datasets. The experimental path loss data is acquired via a field drive test conducted over an operational 4G LTE network in an urban microcellular environment. The results were assessed using several first-order statistical performance indicators. The results show that prediction errors of the proposed MLP model compared favourably with measured data and were better than those obtained using conventional log-distance-based path loss models.https://www.mdpi.com/2076-3417/12/11/5713path loss modelslog-distance modelsneural networks modelsMLP-based modelsoptimal predictive modellingmulti-layer perception neural network |
| spellingShingle | Joseph Isabona Agbotiname Lucky Imoize Stephen Ojo Olukayode Karunwi Yongsung Kim Cheng-Chi Lee Chun-Ta Li Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments Applied Sciences path loss models log-distance models neural networks models MLP-based models optimal predictive modelling multi-layer perception neural network |
| title | Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments |
| title_full | Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments |
| title_fullStr | Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments |
| title_full_unstemmed | Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments |
| title_short | Development of a Multilayer Perceptron Neural Network for Optimal Predictive Modeling in Urban Microcellular Radio Environments |
| title_sort | development of a multilayer perceptron neural network for optimal predictive modeling in urban microcellular radio environments |
| topic | path loss models log-distance models neural networks models MLP-based models optimal predictive modelling multi-layer perception neural network |
| url | https://www.mdpi.com/2076-3417/12/11/5713 |
| work_keys_str_mv | AT josephisabona developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments AT agbotinameluckyimoize developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments AT stephenojo developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments AT olukayodekarunwi developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments AT yongsungkim developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments AT chengchilee developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments AT chuntali developmentofamultilayerperceptronneuralnetworkforoptimalpredictivemodelinginurbanmicrocellularradioenvironments |