Comparison of Path Loss Prediction Models for UAV and IoT Air-to-Ground Communication System in Rural Precision Farming Environment

Duangsuwan, Sarun; District, Pathio Chumcoo; Maw, Myo Myint

doi:10.12720/jcm.16.2.60-66

Cited by 30 publications

(13 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The crossover % values were changed between 0.5, 0.7, and 0.9, and the mutation % values were varied between 0.3, 0.5, and 0.7. Table IV shows that the best composition of variables achieved was using the variable numbers [2,3,4,5,9,10,11,15,18]. These variables are frequency, TX height, RX height, RX vertical angle from TX main beam, distance between buildings, barometric pressure, temperature, slope contour, and border to user distance (water).…”

Section: B Results Of Feature Selection Processmentioning

confidence: 99%

“…Various other research has been developed in different places with a special measuring field, such as the research of [16] which focuses on a vegetation area, and [17], which focuses on the study of path loss prediction in the indoor area of an aircraft cabin. Other studies, such as those by [18], [19], and [20], use an unmanned aerial vehicle (UAV), while the research of [21] focuses on a mixed city-river area. Only a small number of studies have been carried out on path loss prediction in a mixed city-river area.…”

Section: Related Workmentioning

confidence: 99%

“…The number of particles was varied with the values of 40, 70, and 100, while the W and C1/C2 values were varied with the values of 0.2, 0.5, and 0.8. Table V shows that the best composition of variables was the composition of variables [2,3,4,6,7,9,10,11,12,13, www.ijacsa.thesai.org 14,15,16,17,18]. The variables eliminated from the selected variables were TX-RX distance, RX vertical angle to mainbeam, and building height.…”

Section: ) Particle Swarm Optimization (Pso) Feature Selectionmentioning

confidence: 99%

See 2 more Smart Citations

Development of Path Loss Prediction Model using Feature Selection-Machine Learning Approach

Alfaresi¹,

Nawawi²,

Suprapto³

2022

IJACSA

View full text Add to dashboard Cite

Wireless network planning requires accurate coverage predictions to get good quality. The path loss accurate model requires a flexible model for each area including land and water. The purpose of this research is to develop a Cost-Hatta model that can be applied to the mixed land-water area. The approach used of this research is the three methods of feature selection of machine learning. The first stage of the research was the collection of field data. The measurement data included system, weather, and geographical parameters. The next stage was feature selection to obtain the best composition of features for the development of the model. The feature selection methods used were Univariate FS, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). After obtaining the best features from each method, the next stage was to form a model using four machine learning algorithms, namely Random Forest Regression (RF), Deep Neural Network (DNN), K-Nearest Neighbor Regression (KNN), and Support Vector Regression (SVR). The results of the improvements to the path loss prediction model were tested using the evaluation parameters of Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Percentage Error (MAPE). The results of the testing showed that the improved Cost-Hatta model using the proposed Univariate-RF combination produced a very small RMSE value of 1.52. This indicates that the proposed model framework is highly suitable to be used in a mixed land-water area.

show abstract

Section: B Results Of Feature Selection Processmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: ) Particle Swarm Optimization (Pso) Feature Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Development of Path Loss Prediction Model using Feature Selection-Machine Learning Approach

Alfaresi¹,

Nawawi²,

Suprapto³

2022

IJACSA

View full text Add to dashboard Cite

show abstract

“…RT is a decision tree-based method that uses a tree-like structure in making predictions based on the rules set at each node [23], [41]. Thus, RT performance is highly influenced by the number of nodes from the root to the leaf [42]. Data processing and analysis in RT are easy to interpret.…”

Section: Regression Trees (Rt)mentioning

confidence: 99%

Mobile Network Coverage Prediction Based on Supervised Machine Learning Algorithms

et al. 2022

View full text Add to dashboard Cite

The need for wider coverage and high-performance quality of mobile networks is critical due to the maturity of Internet penetration in today's society. One of the primary drivers of this demand is the dramatic shift toward digitalization due to the Covid-19 pandemic impact. Meanwhile, the emergence of the 5G wireless standard and the increasingly complex actual operating environment of mobile networks make the traditional prediction model less reliable. With the recent advancements and promising capabilities of machine learning (ML), it is seen as an alternative to the traditional approaches for ground to ground (G2G) mobile communication coverage prediction. In this study, various ML models have been tested and evaluated to develop an ML-based received signal strength prediction model for mobile networks. However, the challenge is to identify a practical ML model that can fulfill the computing speed criteria while still meeting the prediction accuracy. A total of six categories of ML models, namely Linear Regression (LR), Artificial Neural Network (ANN), Support Vector Machine (SVM), Regression Trees (RT), Ensembles of Trees (ET), and Gaussian Process Regression (GPR) that consists of more than 20 types of established algorithms/kernels have been tested and evaluated in this paper to identify the best contender among them, in terms of speed and accuracy. Findings from the evaluation showed that the GPR model is the most accurate model for Reference Signal Received Power (RSRP) prediction in terms of RMSE and R 2 , followed by ET, RT, SVM, ANN and LR. Nevertheless, prediction speed and model training times are also important factors in determining the most practical model for RSRP prediction for several real-world mobile network planning applications. Finally, the ET model with Random Forest (RF) algorithm has been selected and highly recommended as the most practically employed ML model for developing rigorous RSRP predictions model in multi-frequency bands and multi-environment. The developed prediction model is capable of being utilized for the network analysis and optimization.

show abstract

“…Although the results were satisfied by using a random forest algorithm, there is no consideration under the realistic environments of UAV communication channels. Then, the path loss prediction model under the realistic environments was presented by using kNN and random forest algorithm for A2G-CM [24]. The results indicate that the random forest algorithm outperformed the kNN for channel prediction.…”

Section: Introductionmentioning

confidence: 99%

Empirical Path Loss Channel Characterization Based on Air‐to‐Air Ground Reflection Channel Modeling for UAV‐Enabled Wireless Communications

Supramongkonset

Duangsuwan

Maw

et al. 2021

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

The purpose of this work was to investigate the air-to-air channel model (A2A-CM) for unmanned aerial vehicle- (UAV-) enabled wireless communications. Specifically, a low-altitude small UAV needs to characterize the propagation mechanisms from ground reflection. In this paper, the empirical path loss channel characterizations of A2A ground reflection CM based on different scenarios were presented by comparing the wireless communication modules for UAVs. Two types of wireless communication modules both WiFi 2.4 GHz and LoRa 868 MHz frequency were deployed to study the path loss channel characterization between Tx-UAV and Rx-UAV. To investigate the path loss, three types of experimental channel models, such as CM1 grass floor, CM2 soil floor, and CM3 rubber floor, were considered under the ground reflection condition. The analytical A2A Two-Ray (A2AT-R) model and the modified Log-Distance model were simulated to compare the correlation with the measurement data. The measurement results in the CM3 rubber floor scenario showed the impact from the ground reflection at 1 m to 3 m Rx-UAV altitudes both 2.4 GHz and 868 MHz which was converged to the A2AT-R model and related to the modified Log-Distance model above 3 m. It clear that there is no ground reflection effect from the CM1 grass floor and CM2 soil floor. This work showed that the analytical A2AT-R model and the modified Log-Distance model can deploy to model the path loss of A2A-CM by using WiFi and LoRa wireless modules.

show abstract

Comparison of Path Loss Prediction Models for UAV and IoT Air-to-Ground Communication System in Rural Precision Farming Environment

Cited by 30 publications

References 21 publications

Development of Path Loss Prediction Model using Feature Selection-Machine Learning Approach

Development of Path Loss Prediction Model using Feature Selection-Machine Learning Approach

Mobile Network Coverage Prediction Based on Supervised Machine Learning Algorithms

Empirical Path Loss Channel Characterization Based on Air‐to‐Air Ground Reflection Channel Modeling for UAV‐Enabled Wireless Communications

Contact Info

Product

Resources

About