Skripsi
PENERAPAN SMART TRANSPORTATION PADA SMART CITY UNTUK MENENTUKAN RUTE TERBAIK MENGGUNAKAN METODE ONE DIMENSIONAL CONVOLUTIONAL NEURAL NETWORK YANG DI OPTIMASIKAN DENGAN GENETIC ALGORITHM (1D CNN-GA)
Congestion is one of the main causes of road users experiencing delays in arriving at their destination. In this study the authors wanted to overcome this problem with the best route determination system. This best route determination system applies the concept of Smart Transportation to Smart City. This study uses the You Only Look Once version 8 (YOLOv8) algorithm to detect and calculate the number of vehicles based on CCTV recordings, One Dimensional Convolutional Neural Network optimized with Genetic Algorithm (1D CNN-GA) to predict road conditions based on reference tables and the Best First Search Algorithm to determine the best route based on mileage and road conditions. The dataset used is vehicle images totaling 4224 images and a reference table containing 5 columns 320 rows in csv form. YOLOv8 produces a model with a mAP of 85.4% and test accuracy with an accuracy of 78.61%. Then 1D CNN produces a model accuracy of 89.0625% and a prediction accuracy of 100%. Followed by optimizing the 1D CNN model using the Genetic Algorithm to produce a model accuracy of 93.75% and 100% prediction accuracy. In optimization there is an increase of 4.6875% and the prediction results are still the same at 100%. And finally using the Best First Search Algorithm to determine the best route with parameters of mileage and road conditions. The best route results were chosen for route 4 because it has the lowest weight in all conditions.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307005152 | T121793 | T1217932023 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available