Skripsi
AKURASI SISTEM DETEKSI KEPADATAN KENDARAAN DI JALAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN FUZZY LOGIC
In Indonesia, especially in big cities, the number of motorized vehicles is increasing. The increase in the number of vehicles, especially in big cities, makes congestion an important problem that must be solved. One of the roads that often experience congestion is at the intersection. This final project will detect the problem of vehicle density in road traffic using fuzzy logic and image processing methods aimed at finding the accuracy of the density of road conditions. The results of the recognition of object detection patterns of cars and motorcycles using the Convolution Neural Network obtained the level of model accuracy obtained from the results of detecting cars and motorcycles ranging from 50% - 99% for detecting motorbikes and 51% - 98% for detecting cars. While the results of the accuracy of detecting road conditions using Fuzzy Mamdani were obtained on the 1st data in moderate condition (10.98), 2nd data in moderate condition (10.98), and the 3rd data in smooth condition (7.17). From the training data process, the results of the confusion matrix are obtained, namely, Precision Value of (0.93), Recall Value of (0.98), F-Score Value of (0.95), Accuracy Value of (97.5%). Keywords : Vehicle Detection, Convolution Neural Network, Confusion Matrix, Fuzzy Logic
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107004723 | T60616 | T606162021 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available