Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning
Optimal network planning for wireless communication systems requires the detailed knowledge of the channel parameters of the target coverage area. Channel parameters can be estimated through extensive measurements in the environment. Alternatively, ray tracing simulations can be done if the 3D model...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8772043/ |
| _version_ | 1818642895120367616 |
|---|---|
| author | Hasan F. Ates Syed Muhammad Hashir Tuncer Baykas Bahadir K. Gunturk |
| author_facet | Hasan F. Ates Syed Muhammad Hashir Tuncer Baykas Bahadir K. Gunturk |
| author_sort | Hasan F. Ates |
| collection | DOAJ |
| description | Optimal network planning for wireless communication systems requires the detailed knowledge of the channel parameters of the target coverage area. Channel parameters can be estimated through extensive measurements in the environment. Alternatively, ray tracing simulations can be done if the 3D model of the environment is available. One drawback of ray tracing simulations is the high computational complexity; therefore, ray tracing is not suitable for real-time coverage optimization. In this paper, we present a deep convolutional neural network-based approach to estimate channel parameters (specifically, path loss exponent and standard deviation of shadowing) directly from 2D satellite images. While deep learning methods require high computational resources for training and large amount of training data, once trained, the network can make predictions fast. Also, unlike the ray tracing simulations, there is no need for 3D model generation, and therefore, it can be applied easily using the images obtained from satellites or aerial vehicles. These make the proposed method a computationally efficient and reliable alternative to ray tracing simulations. The experimental results show that path loss exponent and large-scale shadowing factor at 900 MHz can be correctly classified by 88% and 76% accuracy, respectively. |
| first_indexed | 2024-12-16T23:50:19Z |
| format | Article |
| id | doaj.art-6bd0d04d04a7411d914baec24d7fb94f |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T23:50:19Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6bd0d04d04a7411d914baec24d7fb94f2022-12-21T22:11:21ZengIEEEIEEE Access2169-35362019-01-01710136610137510.1109/ACCESS.2019.29310728772043Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep LearningHasan F. Ates0Syed Muhammad Hashir1https://orcid.org/0000-0001-7614-3508Tuncer Baykas2Bahadir K. Gunturk3https://orcid.org/0000-0003-0779-9620School of Engineering and Natural Sciences, Istanbul Medipol University, Istanbul, TurkeySchool of Engineering and Natural Sciences, Istanbul Medipol University, Istanbul, TurkeySchool of Engineering and Natural Sciences, Istanbul Medipol University, Istanbul, TurkeySchool of Engineering and Natural Sciences, Istanbul Medipol University, Istanbul, TurkeyOptimal network planning for wireless communication systems requires the detailed knowledge of the channel parameters of the target coverage area. Channel parameters can be estimated through extensive measurements in the environment. Alternatively, ray tracing simulations can be done if the 3D model of the environment is available. One drawback of ray tracing simulations is the high computational complexity; therefore, ray tracing is not suitable for real-time coverage optimization. In this paper, we present a deep convolutional neural network-based approach to estimate channel parameters (specifically, path loss exponent and standard deviation of shadowing) directly from 2D satellite images. While deep learning methods require high computational resources for training and large amount of training data, once trained, the network can make predictions fast. Also, unlike the ray tracing simulations, there is no need for 3D model generation, and therefore, it can be applied easily using the images obtained from satellites or aerial vehicles. These make the proposed method a computationally efficient and reliable alternative to ray tracing simulations. The experimental results show that path loss exponent and large-scale shadowing factor at 900 MHz can be correctly classified by 88% and 76% accuracy, respectively.https://ieeexplore.ieee.org/document/8772043/Channel parameter estimationpath loss exponentshadowing factordeep learning |
| spellingShingle | Hasan F. Ates Syed Muhammad Hashir Tuncer Baykas Bahadir K. Gunturk Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning IEEE Access Channel parameter estimation path loss exponent shadowing factor deep learning |
| title | Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning |
| title_full | Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning |
| title_fullStr | Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning |
| title_full_unstemmed | Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning |
| title_short | Path Loss Exponent and Shadowing Factor Prediction From Satellite Images Using Deep Learning |
| title_sort | path loss exponent and shadowing factor prediction from satellite images using deep learning |
| topic | Channel parameter estimation path loss exponent shadowing factor deep learning |
| url | https://ieeexplore.ieee.org/document/8772043/ |
| work_keys_str_mv | AT hasanfates pathlossexponentandshadowingfactorpredictionfromsatelliteimagesusingdeeplearning AT syedmuhammadhashir pathlossexponentandshadowingfactorpredictionfromsatelliteimagesusingdeeplearning AT tuncerbaykas pathlossexponentandshadowingfactorpredictionfromsatelliteimagesusingdeeplearning AT bahadirkgunturk pathlossexponentandshadowingfactorpredictionfromsatelliteimagesusingdeeplearning |