Analisis Dan Perbandingan Akurasi Model Prediksi Rentet Waktu Support Vector Machines Dengan Support Vector Machines Particle Swarm Optimization Untuk Arus Lalu Lintas Jangka Pendek

Haldi Budiman (Universitas Pendidikan Sultan Idris)

Systemic: Information System and Informatics Journal
Vol. 2 No. 1 (2016): Agustus

Many algorithms that can be used to predict the traffic flow, there are some who are known algorithms which have a more accurate performance and some are off in the performance test the accuracy of the algorithm. For this algorithm needs to be tested to find out. The proposed method is SVM, SVM-PSO. Compared this method in neural network-based algorithm that has been in curatorial commentary for UJIA rentettime prediction data. Algorithms to be tested is SVM, SVM-PSO and Neural Network, which used the data to predict short-term traffic flow. Each of these algorithms will be implemented by using RapidMiner5.1.Performance measurement is doneby calculating the average amount of error that occurs through Root Mean Square Error(RMSE). The smaller the valueof each of the stated performance parameters predicted value closer to the true value. Thus it can be seen that the algorithm is more accurate.