Saputra, Dimas Bagus (2024) ANALISIS DATA SISTEM AUTOGATE MONITORING TRUK CONTAINER TERMINAL PETIKEMAS MENGGUNAKAN METODE KLASIFIKASI NAÏVE BAYES DAN K-NEAREST NEIGHBOR (K-NN). S1 thesis, Universitas Mercu Buana - Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (COVER)
41520110037-DIMAS BAGUS SAPUTRA-01 Cover - DIMAS BAGUS SAPUTRA.pdf Download (6MB) |
|
Text (BAB I)
_41520110037-DIMAS BAGUS SAPUTRA-02 Bab 1 - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (118kB) |
|
Text (BAB II)
41520110037-DIMAS BAGUS SAPUTRA-03 Bab 2 - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (264kB) |
|
Text (BAB III)
41520110037-DIMAS BAGUS SAPUTRA-04 Bab 3 - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (281kB) |
|
Text (BAB IV)
41520110037-DIMAS BAGUS SAPUTRA-05 Bab 4 - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (757kB) |
|
Text (BAB V)
41520110037-DIMAS BAGUS SAPUTRA-06 Bab 5 - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (121kB) |
|
Text (DAFTAR PUSTAKA)
41520110037-DIMAS BAGUS SAPUTRA-08 Daftar Pustaka - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (172kB) |
|
Text (LAMPIRAN)
41520110037-DIMAS BAGUS SAPUTRA-09 Lampiran - DIMAS BAGUS SAPUTRA.pdf Restricted to Registered users only Download (1MB) |
Abstract
Sistem autogate monitoring di terminal operasi 3 dirancang dan dievaluasi dalam penelitian ini. Teknologi RFID, sensor berat, dan kamera pengenal plat nomor digunakan untuk mengoptimalkan operasi logistik. Studi ini menggunakan data yang dikumpulkan dari sistem autogate terminal, yang mencatat lebih dari 250.000 entri tentang waktu masuk dan keluar truk, jenis barang yang dibawa, dan status operasional. Data dibagi untuk pelatihan dan pengujian menggunakan algoritma Naive Bayes dan K-Nearest Neighbor (KNN) setelah proses pembersihan dan transformasi untuk memastikan konsistensi. Akurasi Naive Bayes sebesar 98,71% pada pembagian data 80%-20%, sementara KNN mencapai akurasi hingga 99,95% dengan variasi nilai K. Model diuji berdasarkan metrik akurasi, presisi, recall, F1- Score, dan AUC. Hasil menunjukkan bahwa Naive Bayes diklasifikasikan sebagai sempurna dengan AUC 1,0, sementara KNN juga hampir sempurna dengan AUC 0,99. Pengujian tambahan dengan kurva ROC dan nilai AUC menunjukkan bahwa kedua metode ini memiliki kinerja klasifikasi yang sangat baik. Hasil ini menunjukkan bahwa penggunaan teknik pembelajaran mesin dalam sistem logistik dapat meningkatkan efisiensi dan keakuratan pengelolaan data lalu lintas kontainer. Dan hasil ini juga menunjukkan betapa pentingnya teknologi canggih dan manajemen data efisien untuk meningkatkan efisiensi dan keamanan operasi terminal operasi 3. The autogate monitoring system at operation terminal 3 was designed and evaluated in this study. RFID technology, weight sensors, and license plate recognition cameras were used to optimize logistics operations. The study utilized data collected from the terminal's autogate system, which recorded more than 250,000 entries about truck entry and exit times, types of goods carried, and operational status. The data was divided for training and testing using Naive Bayes and K-Nearest Neighbor (KNN) algorithms after cleaning and transformation processes to ensure consistency. Naive Bayes accuracy was 98.71% at 80%-20% data split, while KNN achieved accuracy up to 99.95% with varying K values. The models were tested based on accuracy, precision, recall, F1-Score, and AUC metrics. Results show that Naive Bayes is classified as perfect with an AUC of 1.0, while KNN is also almost perfect with an AUC of 0.99. Additional testing with ROC curves and AUC values showed that both methods had excellent classification performance. These results show that the use of machine learning techniques in logistics systems can improve the efficiency and accuracy of container traffic data management. And these results also show how important advanced technology and efficient data management are to improve the efficiency and safety of terminal operation 3 operations.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41520110037 |
| Uncontrolled Keywords: | Terminal Operasi 3, K-Nearest Neighbor (KNN), Naive Bayes, Klasifikasi, Sistem autogate monitoring Terminal Operation 3, K-Nearest Neighbor (KNN), Naive Bayes, Classification, Autogate monitoring system |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | SILMI KAFFA MARISKA |
| Date Deposited: | 27 Aug 2024 02:56 |
| Last Modified: | 30 Aug 2024 02:53 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/90760 |
Actions (login required)
 |
View Item |
