Ikechi Risi

Work place: Department of Physics, River State University Port Harcourt, Nigeria

E-mail: ikechi.risi@ust.edu.ng

Website: https://orcid.org/0000-0001-83316550

Research Interests: Embedded System


Ikechi Risi is lecturer at Rivers State University, Nigeria in Physics Department where he lectures physics. He obtained his B.Sc and M.Sc in Solid State Physics at the university in 2013 and 2019 respectively and currently pursuing his Ph.D at Ignatius Ajuru University of Education, Port-Harcourt. His interest areas are electronic circuit design/construction, embedded system, and radio signal propagation engineering. He can be contacted through ikechi.risi@ust.edu.ng

Author Articles
An Adaptive Hybrid Outdoor Propagation Loss Prediction Modelling for Effective Cellular Systems Network Planning and Optimization

By Ikechi Risi Clement Ogbonda Friday Barikpe Sigalo Isabona Joseph

DOI: https://doi.org/10.5815/ijisa.2023.04.02, Pub. Date: 8 Aug. 2023

The frequent poor service network experienced by some mobile phone users within some deadlock areas in Nigeria is an issue which has been identified by different researchers due to wrong positioning and planning of the evolved NodeB (eNodeB) transmitter using existing propagation loss models. To effectively contribute towards this potential issue constantly experienced in some part of Nigeria, an adaptive hybrid propagation loss model that is based on wavelet transform and genetic algorithm methods has been developed for cellular network planning and optimization, with the capacity to resolve the problems absolutely. First, the signal strengths were measured within four selected eNodeB cell sites in long term evolution (LTE) at 2600MHz using drive-test method. Secondly, the measured data were denoised through wavelet tools. Thirdly, COST231 model was optimize and deduced to generic model with parameters. Fourthly, genetic optimization algorithm automatically developed the propagation loss models for denoised signal data (designated as wavelet-GA model) and unprocessed signal data (designated as GA model). The hybrid wavelet-GA propagation loss model, GA propagation loss model, and COST231 propagation loss model were compared based on three error metrics such as root mean square error (RMSE), mean absolute error (MAE) and correlation coefficient (R). The developed hybrid wavelet-GA model estimated the lowest RMSEs of 2.8813 dB, 3.9381 dB, 4.7643 dB, 6.9366 dB, whereas, COST231 model gave highest value of RMSE. The developed hybrid wavelet-GA model also derived the least value of MAE as compared with COST231 and the GA models, such as, 2.2016 dB, 2.8672 dB, 3.4766 dB, 5.8235 dB. The correlation coefficients were also compared, and it showed that the developed hybrid wavelet-GA model were 90.04%, 78.61%, 92.21% and 91.23% for the four cell sites. The developed hybrid wavelet-GA model was also validated to account for the performance level by checking for the correlation coefficient using another measured signal data from different eNodeB cell sites other than the once used for the developed of the hybrid wavelet-GA model. It was noticed that the developed hybrid wavelet-GA propagation loss model is 97.41% valid. Existing standard COST231 model are not able to predict propagation loss with high level of accuracy, as such not efficient to be applied within part of Port Harcourt, Nigeria. The proposed hybrid wavelet-GA model has proven to achieve high performance level and it is relevant to be utilized for cellular network planning and optimization. In future purposes, more regions and locations should be considered to form a broader view in the development of more robust propagation loss models.

[...] Read more.
A Gaussian Process Regression Model to Predict Path Loss for an Urban Environment

By Seyi E. Olukanni Ikechi Risi Salifu. F. U. Johnson Oladipupo S.

DOI: https://doi.org/10.5815/ijmsc.2023.02.02, Pub. Date: 8 May 2023

This research paper presents a Gaussian process regression (GPR) model for predicting path loss signal in an urban environment. The Gaussian process regression model was developed using a dataset of path loss signal measurements acquired in two urban environments in Nigeria. Three different kernel functions were selected and compared for their performance in the Gaussian process regression model, including the squared exponential kernel, the Matern kernel, and the rotational quadratic kernel. The GPR model was validated and evaluated using various performance metrics and compared with different regression models. The results show that the Gaussian process regression model with the Matern kernel outperforms the linear regression and the support vector regression, but the decision tree and the random forest regression did better than the GPR in both cities. In the city of Port Harcourt, the GPR has a RMSE value of 3.0776 dB, the DTR has 2.0005 dB, the SVR has 3.6047 dB, the RFR has 1.0459 dB, and the LR 3.5947dB. The proposed GPR model provides more accurate and efficient approach to predict path loss compared to traditional methods. The extensive data collection and analysis conducted has resulted in a well-developed and accurate model.

[...] Read more.
Optimal Call Failure Rates Modelling with Joint Support Vector Machine and Discrete Wavelet Transform

By Isabona Joseph Agbotiname Lucky Imoize Stephen Ojo Ikechi Risi

DOI: https://doi.org/10.5815/ijigsp.2022.04.04, Pub. Date: 8 Aug. 2022

Failure modeling is an essential component of reliability engineering. Enhanced failure rate modeling techniques are vital to the effective development of predictive and analytical methodologies, demonstration of the engineering procedure, allocation of procedures, design, and control of procedures. However, failure rate modeling has not been given adequate treatment in the literature. The need to investigate failure rate modeling leveraging cutting-edge techniques cannot be overemphasized. This paper proposed and applied a joint support vector regression (SVR) and wavelet transform (WT) approach termed (WT-SVR) to training and learning the call failures rate in wireless system networks. The wavelet transform has been accomplished using the wavelet compression sensing technique. In this technique, the standardized call failure rate data first go through a wavelet filtering transformation matrix. This is followed by separating and outputting the transformed filtered components in the compression phase. Finally, the transformed filtered output components were trained and evaluated using the SVR based on statistical learning theory. The resultant outcome revealed that the proposed WT-SVR learning method is by far better than using only the SVR method for call rate prognostic analysis. As a case in point, the WT-SVR attained STD values of 0.12, 0.21, 2.32, 0.22, 0.90, 0.81 and 0.34 on call failure data estimation compared to the basic SVR that attained higher STD values of 0.45, 0.98, 0.99, 0.46, 1.44, 2.32 and 3.22, respectively.

[...] Read more.
Cascade Forward Neural Networks-based Adaptive Model for Real-time Adaptive Learning of Stochastic Signal Power Datasets

By Odesanya Ituabhor Joseph Isabona Jangfa T. zhimwang Ikechi Risi

DOI: https://doi.org/10.5815/ijcnis.2022.03.05, Pub. Date: 8 Jun. 2022

In this work, adaptive learning of a monitored real-time stochastic phenomenon over an operational LTE broadband radio network interface is proposed using cascade forward neural network (CFNN) model. The optimal architecture of the model has been implemented computationally in the input and hidden units by means of incremental search process. Particularly, we have applied the proposed adaptive-based cascaded forward neural network model for realistic learning of practical signal data taken from an operational LTE cellular network. The performance of the adaptive learning model is compared with a benchmark feedforward neural network model (FFNN) using a number of measured stochastic SINR datasets obtained over a period of three months at two indoors and outdoors locations of the LTE network. The results showed that proposed CFNN model provided the best adaptive learning performance (0.9310 RMSE; 0.8669 MSE; 0.5210 MAE; 0.9311 R), compared to the benchmark FFNN model (1.0566 RMSE; 1.1164 MSE; 0.5568 MAE; 0.9131 R) in the first studied outdoor location. Similar robust performances were attained for the proposed CFNN model in other locations, thus indicating that it is superior to FFNN model for adaptive learning of real-time stochastic phenomenon.

[...] Read more.
Other Articles