Skripsi
PENENTUAN JALUR TERBAIK PADA SMART TRANSPORTATION DALAM SMART CITY MENGGUNAKAN METODE ONE DIMENSIONAL CONVOLUTIONAL NEURAL NETWORK YANG DIOPTIMASI DENGAN BAYESIAN OPTIMIZATION (1DCNN-BO)
The system for determining the best path is included in the concept of Smart Transportation where the city that applies the concept is called a Smart City. This study uses the You Only Look Once version 8 (YOLOv8) algorithm to calculate the number of vehicles based on CCTV footage, One Dimensional Convolutional Neural Network optimized with Bayesian Optimization (1DCNN-BO) to predict road density conditions based on reference tables and the A-Star algorithm. to determine the best path. The dataset used is a dataset of vehicle images totaling 4224 images and a reference table of 5 columns and 320 rows of road conditions in .csv form. YOLOv8 produces a model with a mAP of 85.4% and a test accuracy of 78.61%. Then 1DCNN produces a model accuracy of 93.75% and 100% prediction accuracy. Followed by optimizing the 1DCNN model using Bayesian Optimization resulting in a model accuracy of 96.88%, an increase of 3.13% and the prediction results are maintained at 100%. And finally the A-Star algorithm to determine the best path with the parameters of road conditions and distance traveled gets the results of line 4 as the smallest weight in all conditions, namely morning at 08.00 am and 09.00 am, noon at 01.00 pm and 02.00 pm, afternoon at 04.00 pm and 05.00 pm.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2307005147 | T121424 | T1214242023 | Central Library (Reference) | Available but not for loan - Not for Loan |
No other version available