IMPLEMENTASI ALGORITMA RANDOM FOREST DAN SELEKSI FITUR CHI-SQUARE PADA KLASIFIKASI SERANGAN BOTNET DI JARINGAN INTERNET OF THINGS (IoT)

NUGRAHA, MUHAMMAD ARUN and Stiawan, Deris (2022) IMPLEMENTASI ALGORITMA RANDOM FOREST DAN SELEKSI FITUR CHI-SQUARE PADA KLASIFIKASI SERANGAN BOTNET DI JARINGAN INTERNET OF THINGS (IoT). Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_56201_09011181823003.pdf] Text
RAMA_56201_09011181823003.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_TURNITIN.pdf] Text
RAMA_56201_09011181823003_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_0003047905_01_front_ref.pdf]
Preview
Text
RAMA_56201_09011181823003_0003047905_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[thumbnail of RAMA_56201_09011181823003_0003047905_02.pdf] Text
RAMA_56201_09011181823003_0003047905_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (279kB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_0003047905_03.pdf] Text
RAMA_56201_09011181823003_0003047905_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (254kB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_0003047905_04.pdf] Text
RAMA_56201_09011181823003_0003047905_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (524kB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_0003047905_05.pdf] Text
RAMA_56201_09011181823003_0003047905_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (112kB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_0003047905_06_ref.pdf] Text
RAMA_56201_09011181823003_0003047905_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (103kB) | Request a copy
[thumbnail of RAMA_56201_09011181823003_0003047905_07_lamp.pdf] Text
RAMA_56201_09011181823003_0003047905_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy

Abstract

Along with the development of the term Internet of Things (IoT) in the present day, more and more hardware or electronics are connected to the internet. This allows many devices to be potentially affected by botnet attacks. Botnets are one of the most common threats to systems and the security of IoT devices or networks in the era of cloud-based computing in modern times. Therefore, it is very important to understand the anatomy of botnets, classify botnet attacks, and what mechanisms can be used to deal with botnet-based attacks that occur on IoT devices and networks. Machine Learning (ML) has been used in research as one of the potential solutions in facing the threat of botnet attacks on IoT. Machine Learning also requires feature selection that can help reduce the number of features present in the dataset and choose the most suitable features for classification. This research uses Network Dataset on ToN-IoT Dataset developed by cyber Range Laboratory at University of New South Wales, Canberra. Chi-Square feature selection is applied to select the best features, and Random Forest algorithm is used in the classification process. The results of the classification using Chi-Square feature selection were able to obtain the level of accuracy, precision, recall, specificity, F1-Score, and error values well and with a relatively low classification error rate compared to classification results without feature selection, where the best results have an accuracy value of 99.83%, precision of 99.94%, Recall of 99.57%, specificity of 99.97%, F1-Score of 99.75%, and a low error value of 0.17%.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Internet of Things, Botnet Attack Classification, Chi-Square, Random Forest, Machine Learning
Subjects: Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA75.5.A142 Computer science. Information society. Information technology.
Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.A25 Computer security. Systems and Data Security.
Q Science > QA Mathematics > QA8.9-QA10.3 Computer science. Artificial intelligence. Computational complexity. Data structures (Computer scienc. Mathematical Logic and Formal Languages
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication Including telegraphy, telephone, radio, radar, television > TK5105.5.S72 Computer networks
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication Including telegraphy, telephone, radio, radar, television > TK5105.585.S724 Computer networks Internet (Computer network) Computer networks--Standards Quality control
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150-4380 Computer network resources
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Mr Muhammad Arun Nugraha
Date Deposited: 18 Aug 2022 04:25
Last Modified: 18 Aug 2022 04:25
URI: http://repository.unsri.ac.id/id/eprint/77406

Actions (login required)

View Item View Item