Rahman Ilyas Al Kahfi, . (2026) IMPLEMENTASI MACHINE LEARNING UNTUK DETEKSI SERANGAN DDOS PADA ARSITEKTUR KOMUNIKASI SISTEM SMART HYDROPONIC FIK UPNVJ. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (212kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (263kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (776kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (715kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB V.pdf Download (280kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (225kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (123kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (21MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (736kB) |
Abstract
The integration of Internet of Things (IoT) technology into modern agricultural systems delivers high efficiency, as demonstrated by the IoT Smart Hydroponic system at FIK UPNVJ. However, a heavy reliance on network connectivity exposes vulnerabilities to Distributed Denial of Service (DDoS) attacks, which can paralyze servers and disrupt data transmission between sensors and actuators. This study aims to implement a supervised learning approach using three machine learning algorithms and analyze their detection effectiveness in mitigating DDoS attacks across WebSocket and REST API communication architectures. The methodology encompasses raw network traffic recording via Tshark, pre-filtering packets on port 8000, and flow feature extraction using CICFlowMeter into four target classes (BENIGN, HTTP_FLOOD, TCP_SYN_FLOOD, and WS_FLOOD). The results indicate that the Support Vector Machine (SVM) and Random Forest algorithms achieved optimal performance. SVM demonstrated the highest performance, with Accuracy of 98.56%, Precision of 98.67%, Recall of 98.48%, and F1-Score of 98.57%, closely followed by Random Forest with Accuracy of 98.29%, Precision of 98.48%, Recall of 98.09%, and F1-Score of 98.25%. Conversely, the Decision Tree algorithm recorded the lowest performance, achieving Accuracy of 96.50%, Precision of 96.97%, Recall of 95.88%, and F1-Score of 96.31%. Notably, all three models achieved a perfect 100% classification performance for the TCP_SYN_FLOOD attack class.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511044] [Pembimbing 1: Supriyanto] [Pembimbing 2: Nurhuda Maulana] [Penguji 1: Widya Cholil] [Penguji 2: Hamonangan Kinantan Prabu] |
| Uncontrolled Keywords: | DDoS, IoT, Machine Learning, Smart Hydroponic, Supervised Learning |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | RAHMAN ILYAS AL KAHFI |
| Date Deposited: | 28 Aug 2026 08:00 |
| Last Modified: | 28 Aug 2026 08:00 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51950 |
Actions (login required)
 |
View Item |