Yusril, Ahmad (2026) Deteksi Tipe Perangkat Internet of Things Smart Home Menggunakan Machine Learning. Bachelor thesis, Institut Teknologi Kalimantan.
|
Text
04191007_cover.pdf Restricted to Repository staff only until 4 October 2028. Download (270kB) | Request a copy |
|
|
Text
04191007_statement_of_authenticity.pdf Restricted to Repository staff only until 4 October 2028. Download (457kB) | Request a copy |
|
|
Text
04191007_publishing_agreement.pdf Restricted to Repository staff only until 4 October 2028. Download (325kB) | Request a copy |
|
|
Text
04191007_approval_sheet.pdf Restricted to Repository staff only until 4 October 2028. Download (393kB) | Request a copy |
|
|
Text
04191007_preface.pdf Restricted to Repository staff only until 4 October 2028. Download (357kB) | Request a copy |
|
|
Text
04191007_abstract_id.pdf Restricted to Repository staff only until 4 October 2028. Download (473kB) | Request a copy |
|
|
Text
04191007_abstract_en.pdf Restricted to Repository staff only until 4 October 2028. Download (442kB) | Request a copy |
|
|
Text
04191007_table_of_content.pdf Restricted to Repository staff only until 4 October 2028. Download (435kB) | Request a copy |
|
|
Text
04191007_illustrations.pdf Restricted to Repository staff only until 4 October 2028. Download (226kB) | Request a copy |
|
|
Text
04191007_tables.pdf Restricted to Repository staff only until 4 October 2028. Download (129kB) | Request a copy |
|
|
Text
04191007_notations.pdf Restricted to Repository staff only until 4 October 2028. Download (97kB) | Request a copy |
|
|
Text
04191007_chapter_1.pdf Restricted to Repository staff only until 4 October 2028. Download (2MB) | Request a copy |
|
|
Text
04191007_chapter_2.pdf Restricted to Repository staff only until 4 October 2028. Download (1MB) | Request a copy |
|
|
Text
04191007_chapter_3.pdf Restricted to Repository staff only until 4 October 2028. Download (4MB) | Request a copy |
|
|
Text
04191007_chapter_4.pdf Restricted to Repository staff only until 4 October 2028. Download (5MB) | Request a copy |
|
|
Text
04191007_conclusions.pdf Restricted to Repository staff only until 4 October 2028. Download (454kB) | Request a copy |
|
|
Text
04191007_bibliography.pdf Restricted to Repository staff only until 4 October 2028. Download (540kB) | Request a copy |
|
|
Text
04191007_enclosure.pdf Restricted to Repository staff only until 4 October 2028. Download (355kB) | Request a copy |
|
|
Text
04191007_paper.pdf Restricted to Repository staff only until 4 October 2028. Download (285kB) | Request a copy |
|
|
Text
04191007_presentation.pdf Restricted to Repository staff only until 4 October 2028. Download (484kB) | Request a copy |
|
|
Text
04191007_Form. TA-020.pdf Restricted to Repository staff only until 4 October 2028. Download (388kB) | Request a copy |
Abstract
Perkembangan Internet of Things (IoT) menyebabkan meningkatnya jumlah dan keberagaman perangkat yang terhubung ke jaringan. Kondisi tersebut menimbulkan tantangan dalam pengelolaan dan keamanan jaringan, terutama dalam mengidentifikasi tipe perangkat IoT yang beroperasi secara bersamaan. Identifikasi perangkat IoT secara konvensional melalui alamat IP atau MAC address dinilai kurang andal karena bersifat dinamis dan mudah dimanipulasi. Oleh karena itu, diperlukan metode identifikasi yang lebih akurat dan adaptif berbasis karakteristik trafik jaringan. Penelitian ini bertujuan untuk mendeteksi tipe perangkat IoT menggunakan teknik machine learning berdasarkan analisis trafik jaringan. Data penelitian berupa file packet capture (PCAP) yang diperoleh dari aktivitas komunikasi perangkat IoT pada jaringan. Data tersebut diproses melalui tahapan preprocessing untuk menghilangkan noise dan paket yang tidak relevan, kemudian dilakukan ekstraksi fitur berbasis flow dan statistik paket jaringan. Fitur yang dihasilkan selanjutnya dibentuk menjadi dataset numerik untuk proses klasifikasi. Metode klasifikasi yang digunakan dalam penelitian ini meliputi algoritma K-Nearest Neighbors (KNN), Support Vector Machine (SVM), dan Random Forest. Evaluasi performa model dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa pendekatan machine learning berbasis fitur trafik jaringan mampu mengidentifikasi tipe perangkat IoT dengan tingkat akurasi yang baik. Model Random Forest memberikan performa terbaik dibandingkan dengan algoritma lainnya. Penelitian ini diharapkan dapat menjadi dasar pengembangan sistem monitoring dan keamanan jaringan IoT yang lebih efektif. Kata kunci: SVM, LSTM, XGBoost. Internet of Things, deteksi perangkat IoT, machine learning, klasifikasi, trafik jaringan.
| Item Type: | Thesis (Bachelor) |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Jurusan Teknologi Industri dan Proses > Teknik Elektro |
| Depositing User: | Ahmad Ahmad Yusril |
| Date Deposited: | 17 Jul 2026 02:13 |
| Last Modified: | 17 Jul 2026 02:13 |
| URI: | http://repository.itk.ac.id/id/eprint/27334 |
Actions (login required)
![]() |
View Item |
