A Generalized Regression Neural Network Approach to Wireless Signal Strength Prediction
Journal: International Journal of Trend in Scientific Research and Development (Vol.4, No. 3)Publication Date: 2020-06-09
Authors : Finangwai D. Jacob Deme C. Abraham Gurumdimma Y. Nentawe;
Page : 467-471
Keywords : Artificial Intelligence; Field Strength; Generalized Regression Neural Network; Okumura Model; COST 231 Hata Model;
Abstract
This study presents a Generalized Regression Neural network GRNN based approach to wireless communication network field strength prediction. As case study, the rural area between the cities of Bauchi and Gombe, Nigeria, was considered. The GRNN based predictor was created, validated and tested with field strength data recorded from multiple Base Transceiver Stations at a frequency of 1800MHz. Results indicate that the GRNN based model with Root Mean Squared Error RMSE value of 5.8dBm offers significant improvements over the empirical Okumura and COST 231 Hata models. While the Okumura model overestimates the field strength, the COST 231 Hata significantly underestimates it. Finangwai D. Jacob | Deme C. Abraham | Gurumdimma Y. Nentawe "A Generalized Regression Neural Network Approach to Wireless Signal Strength Prediction" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-3 , April 2020, URL: https://www.ijtsrd.com/papers/ijtsrd30501.pdf
Other Latest Articles
- Adhimantha Glaucoma A Review Based on Ayurveda and Modern Perspective
- Importance of Solar Energy in Day to Day Life
- Job Burnout and Personality as Predictors of Workplace Deviance
- Strength Analysis of Aluminium Composite Reinforced with Coconut Ash Powder A Review
- Power Quality Improvement using Shunt Active Power Filter
Last modified: 2020-06-09 14:57:09