Text
PERBANDINGAN METODE ARTIFICIAL NEURAL NETWORK YANG DI OPTIMASI DENGAN GENETIC ALGORITHM DAN BAYESIAN OPTIMIZATION UNTUK PREDIKSI JALUR TERBAIK PADA SISTEM TRANSPORTASI PINTAR DI KOTA PINTAR
The development of technology is very rapid so that many applications have emerged, such as smart transportation applications. Smart transport is considered as an umbrella term that includes route optimization, parking, accident detection, road anomalies and infrastructure applications. The problem that is often encountered while on the highway is congestion caused by congested roads and poor road conditions and not wide enough so that many drivers experience delays in arriving at their destination. The purpose of this final project is to compare artificial neural network methods optimized with genetic algorithms and optimized with Bayesian optimization for the best path prediction using the best first search algorithm. The results of predicting road conditions using artificial neural networks obtained a model accuracy of 84.38% and a reading accuracy of 98.67%. After being optimized with a genetic algorithm, the model accuracy and reading accuracy increased to 91% and 100%. The best path chosen is line 5 because it has the smallest total weight, namely 16.7 with road conditions every 5 intersections, namely 3 moderate and 2 smooth. Meanwhile, when optimized with Bayesian optimization, the accuracy and readability of the model decreased to 82.81% and 92.28%. The best path chosen is path 2 because it has the smallest total weight, namely 16.4 with road conditions every 5 intersections, namely 5 moderate.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307002988 | T123037 | T1230372023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available