Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

Aldossari, Saud Alhajaj

doi:10.3390/electronics12030497

Cited by 9 publications

(4 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, they did not provide details related to the time required to perform calculations. In [21], the authors presented a methodology of data-driven techniques applied to predict path loss in 28 GHz using ML algorithms (random forest, decision tree, lasso regression, gradient boosting, and neural network-deep learning). The data for building the dataset was described in [22] and updated in this research to reflect an indoor environment.…”

Section: Related Work a Path Loss Estimation And Machine Learning (Ml)mentioning

confidence: 99%

5G mmWave Network Planning Using Machine Learning for Path Loss Estimation

Santana,

Martinez Alonso,

Guillen Nieto

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

New frequency bands, such as the mmWave at 28 GHz for fifth Generation networks in Frequency Range 2, are being introduced to accomplish the required throughput for new services such as remote surveillance, object tracking, and factory automation. These high-frequency bands are sensible to reflections and diffraction. Therefore, accurate path loss calculation relies on advanced models and ray tracing. However, this is time-consuming, and evaluating a large set of candidate solutions is no longer possible when planning the optimal number and location of base stations in the network planning process. This paper investigates the use of machine learning to approximate a complex mmWave ray-tracingbased path loss model in indoor scenarios. The much lower calculation time allows us to approximate the ray-tracer path loss estimation well and to apply a genetic algorithm for realizing network planning. The machine learning model is trained and validated for two buildings and tested with another, with an average of the Mean Absolute Error of 2.8 dB over all cases. It is shown that the combination of Machine Learning and Genetic Algorithm is able to find a network deployment in the FR2 band accounting for the minimum number of access points and minimum electromagnetic exposure, while still providing a predefined coverage percentage inside the building.

show abstract

Section: Related Work a Path Loss Estimation And Machine Learning (Ml)mentioning

confidence: 99%

5G mmWave Network Planning Using Machine Learning for Path Loss Estimation

Santana,

Martinez Alonso,

Guillen Nieto

et al. 2024

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…The proximity to 1 indicates a stronger fit in the regression [57]. The mathematical expression to calculate the R2 score is presented in (26) and (27) as follows [58,59]:…”

Section: R2 Scorementioning

confidence: 99%

Performance of Path Loss Models over Mid-Band and High-Band Channels for 5G Communication Networks: A Review

Shaibu,

Onwuka,

Salawu

et al. 2023

Future Internet

View full text Add to dashboard Cite

The rapid development of 5G communication networks has ushered in a new era of high-speed, low-latency wireless connectivity, as well as the enabling of transformative technologies. However, a crucial aspect of ensuring reliable communication is the accurate modeling of path loss, as it directly impacts signal coverage, interference, and overall network efficiency. This review paper critically assesses the performance of path loss models in mid-band and high-band frequencies and examines their effectiveness in addressing the challenges of 5G deployment. In this paper, we first present the summary of the background, highlighting the increasing demand for high-quality wireless connectivity and the unique characteristics of mid-band (1–6 GHz) and high-band (>6 GHz) frequencies in the 5G spectrum. The methodology comprehensively reviews some of the existing path loss models, considering both empirical and machine learning approaches. We analyze the strengths and weaknesses of these models, considering factors such as urban and suburban environments and indoor scenarios. The results highlight the significant advancements in path loss modeling for mid-band and high-band 5G channels. In terms of prediction accuracy and computing effectiveness, machine learning models performed better than empirical models in both mid-band and high-band frequency spectra. As a result, they might be suggested as an alternative yet promising approach to predicting path loss in these bands. We consider the results of this review to be promising, as they provide network operators and researchers with valuable insights into the state-of-the-art path loss models for mid-band and high-band 5G channels. Future work suggests tuning an ensemble machine learning model to enhance a stable empirical model with multiple parameters to develop a hybrid path loss model for the mid-band frequency spectrum.

show abstract

“…Jo et al [15] further advanced this by synergizing three pivotal techniques, ANN, Gaussian process, and PCA, for feature selection, presenting a holistic machine-learning framework for path loss modeling. Aldossari [16] explored the challenges of signal propagation in indoor environments, especially within the realm of 5G, proposing a data-driven approach leveraging artificial intelligence.…”

Section: Related Workmentioning

confidence: 99%

“…Focus Area Methodology Applicability to Urban VANETs [11] Channel Estimation Digital Twin with Deep Learning Dynamic urban vehicular environments [12] Channel Estimation LSTM networks and MLPs V2X communications [13] Physical-Layer Network Coding DNN-PNC Implementation Vehicular Ad-Hoc Networks [14] Path Loss Prediction Machine-Learning Models 5G mobile communication systems [15] Path Loss Prediction ANN, Gaussian Process, PCA Wireless sensor networks [16] Path Loss Prediction AI Indoor environments at 28 GHz [17] Congestion Control in VANETs Reinforcement Learning Vehicular ad hoc networks [18] Channel Modeling for VVLC Machine-Learning Framework V2X communication…”

Section: Referencementioning

confidence: 99%

Predictive Modeling of Signal Degradation in Urban VANETs Using Artificial Neural Networks

Muktar,

Fono,

Zongo

2023

Electronics

View full text Add to dashboard Cite

In urban Vehicular Ad Hoc Network (VANET) environments, buildings play a crucial role as they can act as obstacles that attenuate the transmission signal between vehicles. Such obstacles lead to multipath effects, which could substantially impact data transmission due to fading. Therefore, quantifying the impact of buildings on transmission quality is a key parameter of the propagation model, especially in critical scenarios involving emergency vehicles where reliable communication is of utmost importance. In this research, we propose a supervised learning approach based on Artificial Neural Networks (ANNs) to develop a predictive model capable of estimating the level of signal degradation, represented by the Bit Error Rate (BER), based on the obstacles perceived by moving emergency vehicles. By establishing a relationship between the level of signal degradation and the encountered obstacles, our proposed mechanism enables efficient routing decisions being made prior to the transmission process. Consequently, data packets are routed through paths that exhibit the lowest BER. To collect the training data, we employed Network Simulator 3 (NS-3) in conjunction with the Simulation of Urban MObility (SUMO) simulator, leveraging real-world data sourced from the OpenStreetMap (OSM) geographic database. OSM enabled us to gather geospatial data related to the Two-Dimensional (2D) geometric structure of buildings, which served as input for our Artificial Neural Network (ANN). To determine the most suitable algorithm for our ANN, we assessed the accuracy of ten learning algorithms in MATLAB, utilizing five key metrics: Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Correlation Coefficient (R), and Maximum Prediction Error (MaxPE). For each algorithm, we conducted fifteen iterations based on ten hidden neurons and gauged its accuracy against the aforementioned metrics. Our analysis highlighted that the ANN underpinned by the Conjugate Gradient With Powell/Beale Restarts (CGB) learning algorithm exhibited superior performance in terms of MSE, RMSE, MAE, R, and MaxPE compared to other algorithms such as Levenberg–Marquardt (LM), Bayesian Regularization (BR), BFGS Quasi-Newton (BFG), Resilient Backpropagation (RP), Scaled Conjugate Gradient (SCG), Fletcher–Powell Conjugate Gradient (CGF), Polak–Ribiére Conjugate Gradient (CGP), One-Step Secant (OSS), and Variable Learning Rate Backpropagation (GDX). The BER prediction by our ANN incorporates the TWO-RAY Ground (TRG) propagation model, an adjustable parameter within NS-3. When subjected to 300 new samples, the trained ANN’s simulation outcomes illustrated its capability to learn, generalize, and successfully predict the BER for a new data instance. Overall, our research contributes to enhancing the performance and reliability of communication in urban VANET environments, especially in critical scenarios involving emergency vehicles, by leveraging supervised learning and artificial neural networks to predict signal degradation levels and optimize routing decisions accordingly.

show abstract

Predicting Path Loss of an Indoor Environment Using Artificial Intelligence in the 28-GHz Band

Cited by 9 publications

References 36 publications

5G mmWave Network Planning Using Machine Learning for Path Loss Estimation

5G mmWave Network Planning Using Machine Learning for Path Loss Estimation

Performance of Path Loss Models over Mid-Band and High-Band Channels for 5G Communication Networks: A Review

Predictive Modeling of Signal Degradation in Urban VANETs Using Artificial Neural Networks

Contact Info

Product

Resources

About