Prasetyo, Fauzi Budi (2025) Seleksi Fitur Deteksi Serangan Distributed Denial of Service pada Jaringan Internet of Things menggunakan Algoritma Chicken Swarm Optimization (CSO). S2 thesis, Universitas Mercu Buana Jakarta - Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (Cover)
55422120005-Fauzi Budi Prasetyo-01 COVER - fauzi budi Prasetyo.pdf Download (408kB) |
|
Text (BAB I)
55422120005-Fauzi Budi Prasetyo-02 BAB 1 - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (153kB) |
|
Text (BAB II)
55422120005-Fauzi Budi Prasetyo-03 BAB II - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (280kB) |
|
Text (BAB III)
55422120005-Fauzi Budi Prasetyo-04 BAB III - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (472kB) |
|
Text (BAB IV)
55422120005-Fauzi Budi Prasetyo-05 BAB IV - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (603kB) |
|
Text (BAB V)
55422120005-Fauzi Budi Prasetyo-06 BAB V - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (111kB) |
|
Text (Daftar Pustaka)
55422120005-Fauzi Budi Prasetyo-08 DAFTAR PUSTAKA - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (255kB) |
|
Text (Lampiran)
55422120005-Fauzi Budi Prasetyo-09 LAMPIRAN - fauzi budi Prasetyo.pdf Restricted to Registered users only Download (772kB) |
Abstract
Pertumbuhan pesat perangkat Internet of Things (IoT), yang diperkirakan mencapai 20,1 miliar pada tahun 2025, telah meningkatkan kerentanan terhadap serangan Distributed Denial of Service (DDoS), yang menyebabkan kerugian finansial signifikan hingga $10 juta per insiden. Studi ini mengusulkan metode seleksi fitur menggunakan algoritma Chicken Swarm Optimization (CSO) untuk meningkatkan efisiensi deteksi DDoS pada jaringan IoT. Menggunakan dataset CIC-IDS2017 dengan 79 fitur dan 225.745 catatan, dataset dibagi menjadi 70% pelatihan (180.596 catatan) dan 30% pengujian (45.149 catatan). CSO, yang terinspirasi oleh hierarki kawanan ayam, mengoptimalkan subset fitur, menghasilkan 17 fitur optimal dengan ambang batas 0,02381. Terintegrasi dengan Random Forest, model ini mencapai akurasi 99,99%, dikonfirmasi oleh matriks kebingungan yang menunjukkan 1 positif palsu dan 2 negatif palsu. Validasi silang 5-fold menghasilkan akurasi rata-rata 99,98% dengan simpangan baku 0,0079%. Pendekatan ini mengurangi beban komputasi dan meningkatkan akurasi deteksi, berkontribusi pada sistem keamanan IoT adaptif di tengah ancaman siber yang meningkat. The rapid growth of Internet of Things (IoT) devices, projected to reach 20.1 billion by 2025, has increased vulnerability to Distributed Denial of Service (DDoS) attacks, causing significant financial losses up to $10 million per incident. This study proposes a feature selection method using the Chicken Swarm Optimization (CSO) algorithm to enhance DDoS detection efficiency on IoT networks. Utilizing the CIC-IDS2017 dataset with 79 features and 225,745 records, the dataset was split into 70% training (180,596 records) and 30% testing (45,149 records). CSO, inspired by chicken flock hierarchy, optimized feature subsets, resulting in 17 optimal features with a threshold of 0.02381. Integrated with Random Forest, the model achieved 99.99% accuracy, confirmed by a confusion matrix showing 1 false positive and 2 false negatives. 5-fold cross-validation yielded an average accuracy of 99.98% with a standard deviation of 0.0079%. This approach reduces computational overhead and improves detection accuracy, contributing to adaptive IoT security systems amid rising cyber threats.
| Item Type: | Thesis (S2) |
|---|---|
| NIM/NIDN Creators: | 55422120005 |
| Uncontrolled Keywords: | Algoritma, Bnign, CIC-IDS2017, Cross-Validation, CSO, Dataset, DdoS, Fitur, IoT, Psuedocode, Python, Mechine Learning, Threshold, Ubuntu. Algoritma, Bnign, CIC-IDS2017, Cross-Validation, CSO, Dataset, DdoS, Fitur, IoT, Psuedocode, Python, Mechine Learning, Threshold, Ubuntu. |
| Subjects: | 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn |
| Divisions: | Pascasarjana > Magister Teknik Elektro |
| Depositing User: | ZAIRA ELVISIA |
| Date Deposited: | 18 Oct 2025 06:44 |
| Last Modified: | 18 Oct 2025 06:44 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/99449 |
Actions (login required)
 |
View Item |
