IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - Vocational School
      • UF - Software Engineering Technology
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - Vocational School
      • UF - Software Engineering Technology
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Implementasi Algoritma YOLOv12 dalam Sistem Analisis Lalu Lintas untuk Monitoring dan Prediksi Kemacetan

      Thumbnail
      View/Open
      Cover (511.4Kb)
      Fulltext (1.960Mb)
      Lampiran (156.7Kb)
      Date
      2026
      Jenis/Type
      Tugas Akhir
      Subtype
      Undergraduate Theses
      Author
      RAMADHANI, KAYLA ATTYA
      Indriasari, Sofiyanti
      Metadata
      Show full item record
      Abstract
      Kemacetan lalu lintas merupakan permasalahan di wilayah perkotaan yang memerlukan sistem pemantauan secara real-time. Penelitian ini bertujuan untuk mengimplementasikan algoritma YOLOv12 untuk mendeteksi kendaraan, memprediksi tingkat kepadatan lalu lintas, serta memberikan rekomendasi pengelolaan arus kendaraan. Metode penelitian menggunakan Cross Industry Standard Process for Data Mining (CRISP-DM). Model YOLOv12n diintegrasikan dengan DeepSORT untuk pelacakan kendaraan, algoritma K-Nearest Neighbor (KNN) dan linear regression untuk prediksi kepadatan, serta rule-based recommendation untuk menghasilkan rekomendasi. Hasil penelitian menunjukkan bahwa model YOLOv12n memperoleh akurasi 91,50% pada data testing dengan nilai precision 0,885, recall 0,915, dan mAP50 0,933. Sistem yang dikembangkan mampu melakukan monitoring kendaraan, memprediksi kepadatan lalu lintas, dan mendukung pengambilan keputusan pengelolaan lalu lintas secara real-time.
       
      Traffic congestion is a major issue in urban areas that requires a real-time traffic monitoring system. This study aims to implement the YOLOv12 algorithm for vehicle detection, traffic density prediction, and traffic management recommendation. The research adopted the Cross Industry Standard Process for Data Mining (CRISP-DM) methodology. The YOLOv12n model was integrated with DeepSORT for vehicle tracking, K-Nearest Neighbor (KNN) and linear regression algorithms for traffic density prediction, and a rule-based recommendation approach to generate traffic management recommendations. The results showed that the YOLOv12n model achieved an accuracy of 91,50% on the testing dataset, with a precision of 0,885, a recall of 0,915, and an mAP@50 of 0,933. The developed system is capable of monitoring vehicles, predicting traffic density, and supporting real-time decision-making for traffic management
       
      URI
      http://repository.ipb.ac.id/handle/123456789/178284
      Collections
      • UF - Software Engineering Technology [307]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository