Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels
Unlimited access to information and data sharing wherever and at any time for anyone and anything is a fundamental component of fifth-generation (5G) wireless communication and beyond. Therefore, it has become inevitable to exploit the super-high frequency (SHF) and millimeter-wave (mmWave) frequenc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/13/4967 |
| _version_ | 1797441875972456448 |
|---|---|
| author | Mohamed K. Elmezughi Omran Salih Thomas J. Afullo Kevin J. Duffy |
| author_facet | Mohamed K. Elmezughi Omran Salih Thomas J. Afullo Kevin J. Duffy |
| author_sort | Mohamed K. Elmezughi |
| collection | DOAJ |
| description | Unlimited access to information and data sharing wherever and at any time for anyone and anything is a fundamental component of fifth-generation (5G) wireless communication and beyond. Therefore, it has become inevitable to exploit the super-high frequency (SHF) and millimeter-wave (mmWave) frequency bands for future wireless networks due to their attractive ability to provide extremely high data rates because of the availability of vast amounts of bandwidth. However, due to the characteristics and sensitivity of wireless signals to the propagation effects in these frequency bands, more accurate path loss prediction models are vital for the planning, evaluating, and optimizing future wireless communication networks. This paper presents and evaluates the performance of several well-known machine learning methods, including multiple linear regression (MLR), polynomial regression (PR), support vector regression (SVR), as well as the methods using decision trees (DT), random forests (RF), K-nearest neighbors (KNN), artificial neural networks (ANN), and artificial recurrent neural networks (RNN). RNNs are mainly based on long short-term memory (LSTM). The models are compared based on measurement data to provide the best fitting machine-learning-based path loss prediction models. The main results obtained from this study show that the best root-mean-square error (RMSE) performance is given by the ANN and RNN-LSTM methods, while the worst is for the MLR method. All the RMSE values for the given learning techniques are in the range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.0216</mn></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.9008</mn></mrow></semantics></math></inline-formula> dB. Furthermore, this work shows that the models (except for the MLR model) perform excellently in fitting actual measurement data for wireless communications in enclosed indoor environments since they provide R-squared and correlation values higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.91</mn></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.96</mn></mrow></semantics></math></inline-formula>, respectively. The paper shows that these learning methods could be used as accurate and stable models for predicting path loss in the mmWave frequency regime. |
| first_indexed | 2024-03-09T12:32:29Z |
| format | Article |
| id | doaj.art-146507658b5f4fc0888626d1811330ee |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:32:29Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-146507658b5f4fc0888626d1811330ee2023-11-30T22:28:08ZengMDPI AGSensors1424-82202022-06-012213496710.3390/s22134967Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor ChannelsMohamed K. Elmezughi0Omran Salih1Thomas J. Afullo2Kevin J. Duffy3The Discipline of Electrical, Electronic and Computer Engineering, University of KwaZulu-Natal, Durban 4041, South AfricaInstitute of Systems Science, Durban University of Technology, Durban 4000, South AfricaThe Discipline of Electrical, Electronic and Computer Engineering, University of KwaZulu-Natal, Durban 4041, South AfricaInstitute of Systems Science, Durban University of Technology, Durban 4000, South AfricaUnlimited access to information and data sharing wherever and at any time for anyone and anything is a fundamental component of fifth-generation (5G) wireless communication and beyond. Therefore, it has become inevitable to exploit the super-high frequency (SHF) and millimeter-wave (mmWave) frequency bands for future wireless networks due to their attractive ability to provide extremely high data rates because of the availability of vast amounts of bandwidth. However, due to the characteristics and sensitivity of wireless signals to the propagation effects in these frequency bands, more accurate path loss prediction models are vital for the planning, evaluating, and optimizing future wireless communication networks. This paper presents and evaluates the performance of several well-known machine learning methods, including multiple linear regression (MLR), polynomial regression (PR), support vector regression (SVR), as well as the methods using decision trees (DT), random forests (RF), K-nearest neighbors (KNN), artificial neural networks (ANN), and artificial recurrent neural networks (RNN). RNNs are mainly based on long short-term memory (LSTM). The models are compared based on measurement data to provide the best fitting machine-learning-based path loss prediction models. The main results obtained from this study show that the best root-mean-square error (RMSE) performance is given by the ANN and RNN-LSTM methods, while the worst is for the MLR method. All the RMSE values for the given learning techniques are in the range of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.0216</mn></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.9008</mn></mrow></semantics></math></inline-formula> dB. Furthermore, this work shows that the models (except for the MLR model) perform excellently in fitting actual measurement data for wireless communications in enclosed indoor environments since they provide R-squared and correlation values higher than <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.91</mn></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.96</mn></mrow></semantics></math></inline-formula>, respectively. The paper shows that these learning methods could be used as accurate and stable models for predicting path loss in the mmWave frequency regime.https://www.mdpi.com/1424-8220/22/13/4967wireless communicationschannel modelingpath losspropagation characteristicsmachine learningneural network |
| spellingShingle | Mohamed K. Elmezughi Omran Salih Thomas J. Afullo Kevin J. Duffy Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels Sensors wireless communications channel modeling path loss propagation characteristics machine learning neural network |
| title | Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels |
| title_full | Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels |
| title_fullStr | Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels |
| title_full_unstemmed | Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels |
| title_short | Comparative Analysis of Major Machine-Learning-Based Path Loss Models for Enclosed Indoor Channels |
| title_sort | comparative analysis of major machine learning based path loss models for enclosed indoor channels |
| topic | wireless communications channel modeling path loss propagation characteristics machine learning neural network |
| url | https://www.mdpi.com/1424-8220/22/13/4967 |
| work_keys_str_mv | AT mohamedkelmezughi comparativeanalysisofmajormachinelearningbasedpathlossmodelsforenclosedindoorchannels AT omransalih comparativeanalysisofmajormachinelearningbasedpathlossmodelsforenclosedindoorchannels AT thomasjafullo comparativeanalysisofmajormachinelearningbasedpathlossmodelsforenclosedindoorchannels AT kevinjduffy comparativeanalysisofmajormachinelearningbasedpathlossmodelsforenclosedindoorchannels |