Effect of Learning Rate on GRNN and MLP for the Prediction of Signal Power Loss in Microcell Sub-Urban Environment

Ebhota, Virginia C.; Isabona, Joseph; Srivastava, Viranjay M.

doi:10.15866/irecap.v9i1.15329

Cited by 5 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [14,15,23,24], the authors explored the long short-term memory model (LSMM) to tackle the non-stationary long-term data with time series analysis. But the LSMM only predicts well when the data is large [25][26][27][28].…”

Section: Literature Reviewmentioning

confidence: 95%

“…There exist many linear or nonlinear disease extrapolative models and methods in literature and among they key ones are autoregressive integrated moving average (ARIMA) [5] [6], Neural Networks (NN) [7]- [20] and nonlinear autoregressive neural networks (NAR) [21]. However, ARIMA, NN and NAR models, including other similar ones usually performed poorly on non-stationary long-term data and noisy data sets [22][23][24][25][26][27][28].…”

Section: Literature Reviewmentioning

confidence: 99%

“…MLP is a special popular feedforward artificial neural network (ANN) model with at least three layered nodes. Its input-output prediction function can be expressed as [18,20]:…”

Section: Six Alternative Regression Models For Comparisonmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates

Isabona¹,

Ojuh²

2021

IJMSC

Self Cite

View full text Add to dashboard Cite

Precise extrapolative mining and analysis of relevant dataset during or after any disease outbreak can assist the government, stake holders and relevant agencies in the health sector to make important decisions with respect to the disease outbreak control and management. While prior works has concentrated on non-stationary long term data, this work focuses on a short term non-stationary and relatively noisy data. Particularly, a distinctive nonparametric machine learning method based kernel-controlled probabilistic Gaussian process regression model has been proposed and employed to model and analyze Covid-19 pandemic data acquired over a period of approximately six weeks. To accomplish the aim, the MATLAB 2018a computational and machine learning environment was engaged to develop and perform the Gaussian process extrapolative analysis. The results displayed high scalability and optimal performance over the commonly used machine learning methods such as the Neural networks, Neural-Fuzzy networks, Random forest, Regression tree, Support Vector machines, K-nearest neighbor and Discriminant linear regression models. These results offer a solid foundation for conducting research on reliable prognostic estimations and analysis of contagious disease emergence intensity and spread.

show abstract

Section: Literature Reviewmentioning

confidence: 95%

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates

Isabona¹,

Ojuh²

2021

IJMSC

Self Cite

View full text Add to dashboard Cite

show abstract

“…In wireless radio communication system networks, signal power loss prediction models are unique mathematical models which are utilized by telecommunication network engineers in signal coverage appraisal of the radio signal path attenuation loss and coverage area of Base Station (BS) transmitter of areas served by a given transmitter in the course of network planning and management [1], [2]. Nonetheless, it is always a complex task in the planning of telecommunication networks to develop these signal power loss prediction models with optimal accuracy.…”

Section: Introductionmentioning

confidence: 99%

Designing and Investigating the Effect of Single-Intermediate and 2-Intermediate Layers of Vanilla Neural Networks in Electromagnetic Path Loss Prediction

Ebhota,

Shongwe

2023

IRECAP

View full text Add to dashboard Cite

Impact of two designed architectural compositions of Vanilla Neural Networks (VNNs): the single-intermediate layer of VNN and two (2)-intermediate layers of VNN, in the prediction of signal power loss were examined in this work using measured data from a Long Term Evolution (LTE) network collected from a micro-cell built up environment. The effect of different values of learning rate hyper-parameter were also examined on the VNN architectural models. Early stopping method at the ratio of 75%:15%:15% was adopted during the network training process to avoid over-fitting and Bayesian Regularization (BR) mathematical training algorithm was employed for the training process to ensure good network generalization. Both the intermediate layer neurons for the single-intermediate layer of the VNN and 2-intermediate layers of the VNN were carefully selected to ensure adequate and robust training with excellent predictive performance. Statistical performance metrics, the Correlation Coefficient (R), the Standard Deviation (SD) and Root Mean Squared Error (RMSE) were employed for result analysis of the performances of the two VNN architectural structures while the Mean Squared Error (MSE) and Coefficient of Regression (R) were employed for examining the effect of the various selected values of learning rates on the prediction performances of the two VNN models.The overall experimental results under similar circumstances for training both the VNN models while considering their architectural structures and the effect of learning rates show that for an efficient neural network training and prediction of signal power loss, a well-trained singleintermediate layer of VNN architectural structure with an appropriate neuron numbers gives more efficient and optimal prediction results as the results of the actual output is closest to the desired output showing optimal prediction in comparison with training using 2-intermediate layers of VNN model. The best neural networks training result outputs of a single intermediate layer VNN with 52neurons in the intermediate layer gives R of 0.9728, SD of 1.2758 and RMSE of 1.7435 while best training result of the 2-intermediate layers gives R of 0.9531, SD of 1.5407 and RMSE of 2.2754 on application of [16, 20] neurons which gives the highest prediction results of the considered neuron numbers. Training the single-intermediate layer VNN with small learning rate of 0.002 shows very high R of 0.9903 while with 2-intermediate layers VNN gives R of 0.8810 The training time required for training the single-intermediate layer VNN is considerable low in comparison to training time required to train 2-intermediate layers VNN for best prediction results. These prediction results are of utmost importance in the planning, design and upgrading of wireless network for optimal performance especially when applied in similar environment to the environment of data collection as VNNs results show adaptability and robustness.

show abstract

“…ML models rival deterministic models, having a faster prediction, with high accuracy [12]. Machine Learning algorithms such as K Nearest Neighbor (KNN) [13], Multiple Layer Perceptron (MLP) [8], Support Vector Regression (SVR) [14], Generalized Regression Neural Network (GRNN) [15], Radial Basis Function Neural Network (RBFNN) [16], and Random Forest (RF) [17] have been used in developing path loss models. However, such models were developed for specific environments, with fixed frequencies and antenna heights.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Regressor/Ensemble Selection for a Multi-Frequency and Multi-Environment Path Loss Prediction

2022

View full text Add to dashboard Cite

Wireless network parameters such as transmitting power, antenna height, and cell radius are determined based on predicted path loss. The prediction is carried out using empirical or deterministic models. Deterministic models provide accurate predictions but are slow due to their computational complexity, and they require detailed environmental descriptions. While empirical models are less accurate, Machine Learning (ML) models provide fast predictions with accuracies comparable to that of deterministic models. Most Empirical models are versatile as they are valid for various values of frequencies, antenna heights, and sometimes environments, whereas most ML models are not. Therefore, developing a versatile ML model that will surpass empirical model accuracy entails collecting data from various scenarios with different environments and network parameters and using the data to develop the model. Combining datasets of different sizes could lead to lopsidedness in accuracy such that the model accuracy for a particular scenario is low due to data imbalance. This is because model accuracy varies at certain regions of the dataset and such variations are more intense when the dataset is generated from a fusion of datasets of different sizes. A Dynamic Regressor/Ensemble selection technique is proposed to address this problem. In the proposed method, a regressor/ensemble is selected to predict a sample point based on the sample’s proximity to a cluster assigned to the regressor/ensemble. K Means Clustering was used to form the clusters and the regressors considered are K Nearest Neighbor (KNN), Extreme Learning Trees (ET), Random Forest (RF), Gradient Boosting (GB), and Extreme Gradient Boosting (XGBoost). The ensembles are any combinations of two, three or four of the regressors. The sample points belonging to each cluster were selected from a validation set based on the regressor that made prediction with lowest absolute error per individual sample point. Implementation of the proposed technique resulted in accuracy improvements in a scenario described by a few sample points in the training data. Improvements in accuracy were also observed on datasets in other works compared to the accuracy reported in the works. The study also shows that using features extracted from satellite images to describe the environment was more appropriate than using a categorical clutter height value.

show abstract

Effect of Learning Rate on GRNN and MLP for the Prediction of Signal Power Loss in Microcell Sub-Urban Environment

Cited by 5 publications

References 0 publications

Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates

Machine Learning Based on Kernel Function Controlled Gaussian Process Regression Method for In-depth Extrapolative Analysis of Covid-19 Daily Cases Drift Rates

Designing and Investigating the Effect of Single-Intermediate and 2-Intermediate Layers of Vanilla Neural Networks in Electromagnetic Path Loss Prediction

Dynamic Regressor/Ensemble Selection for a Multi-Frequency and Multi-Environment Path Loss Prediction

Contact Info

Product

Resources

About