Skripsi
PREDIKSI PATHLOSS PADA KOMUNIKASI 4G LTE MENGGUNAKAN METODE SUPORT VECTOR REGRESSION DI KOTA PALEMBANG
Pathloss is a reduction on a energy level in wireless telecommunications that is caused by refractions, diffractions, reflections, disseminations and absorption and also caused by interferences from the environment conditions which includes the contour of the propagation medium terrain, distance between transmitter and receiver, and the height and location of the antenna. Therefore, an accurate calculation is required to achieve maximum efficiency in telecommunication planning and optimal performance in wireless network. In this research, the prediction of pathloss is executed using the machine learning method Support Vector Regression (SVR) where a comparison and an analysis is will be done. The result of the acquired data is from the Drive Test that is done in 4G LTE Networks a particular area in Palembang City. The result of the data is continued with a comparison using different kernels on each tests which are linear kernel, radial basis function (RBF) and polynomial kernel. Those three kernels are to be re-compared to the same kernels but with the addition of the gridsearch algorithms to achieve optimal results. From the results that are obtained the best pathloss value is with the polynomial kernel using the root mean squred error (RMSE) validation parameter with the result of error of 4,4617 dan RBF kernel using the mean absolute error validation parameter with an error of 3.1885.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107002701 | T59606 | T596062021 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available