www.icact.org

Now 4754 visitors
Today:0 Yesterday:0
Total: 145183 215S 51P 5R
2026-10-21, Week 43

Member Login

TACT Journal Homepage

Call for Paper

Committee

Find My Paper

Author Homepage

Statistics & History

Welcome Message

Paper Procedure

FAQ

Paper Archives

Outstanding Papers

Program & Proceedings

Presentation Platform

Hotel & Travel Info

Photo Gallery

Scheduler Login

Seminar

Archives Login

Sponsors

Online Q&A Session


Paper Number	Author:
Paper Title
Keyword
Q&A Number	**Select your question number !!
Questioner eMail:
Question	How can dimensional feature reduction techniques, such as feature selection and feature extraction, be used to improve the accuracy and efficiency of botnet activity detection?
Answer by Author	Based on our research, the effectiveness of a machine learning model depends on many factors, one of which is the features involved in the modeling. Our research also proves that dimensional reduction affects the accuracy and efficiency of the detection model. Even so, each machine learning algorithm has other factors that affect the model's effectiveness, so different feature selection and feature extraction approaches are needed. If we look at the experimental results table, KNN and DT have different impacts even though they use the same dimensional reduction approach. In the DT, models without dimensional reduction tend to perform better than models that go through feature extraction with the concept of dimensional reduction. In contrast, the model with the KNN algorithm produces better performance when passing feature extraction with dimensional reduction. The low performance of the decision tree while combined with dimensional reduction because a single extracted feature forms a model with less complex rules and has an impact on decreasing the detection performance. Thus, feature selection and feature extraction, especially dimensional reduction, can be used to select features, generate new features or find the most relevant feature combinations to be compatible with the algorithms used in machine learning models to increase their accuracy and efficiency.

Save Q&A
* Edit or answer any Q&A by selecting Q&A number Hyper Link below + Write button (Save)

ICACT20230225 Question.1 Questioner: haodp@dau.edu.vn 2023-02-20 오후 7:53:33	ICACT20230225 Answer.1 Answer by Auhor 6025211020@mhs.its.ac.id 2023-02-20 오후 7:53:33 Chrome Click!!
How can dimensional feature reduction techniques, such as feature selection and feature extraction, be used to improve the accuracy and efficiency of botnet activity detection?	Based on our research, the effectiveness of a machine learning model depends on many factors, one of which is the features involved in the modeling. Our research also proves that dimensional reduction affects the accuracy and efficiency of the detection model. Even so, each machine learning algorithm has other factors that affect the model's effectiveness, so different feature selection and feature extraction approaches are needed. If we look at the experimental results table, KNN and DT have different impacts even though they use the same dimensional reduction approach. In the DT, models without dimensional reduction tend to perform better than models that go through feature extraction with the concept of dimensional reduction. In contrast, the model with the KNN algorithm produces better performance when passing feature extraction with dimensional reduction. The low performance of the decision tree while combined with dimensional reduction because a single extracted feature forms a model with less complex rules and has an impact on decreasing the detection performance. Thus, feature selection and feature extraction, especially dimensional reduction, can be used to select features, generate new features or find the most relevant feature combinations to be compatible with the algorithms used in machine learning models to increase their accuracy and efficiency.
ICACT20230225 Question.2 Questioner: haodp@dau.edu.vn 2023-02-20 오후 8:18:43	ICACT20230225 Answer.2 Answer by Auhor 6025211020@mhs.its.ac.id 2023-02-20 오후 8:18:43 Chrome Click!!
What are the most effective feature reduction techniques for botnet activity detection in different types of network traffic, such as network flow data and system log data?	From the experimental results, reducing the feature dimensions into one feature using network flow data can conclude that Fast ICA proved to be the most effective for classifying botnet traffic and normal traffic. But other dimensional reduction techniques are still effective. Because the effectiveness of dimensional reduction techniques depends on many factors, including the relevance of the extracted features, the number of features included, and reduced to how many features. So analyzing these factors is needed to increase the effectiveness and efficiency of the dimensional reduction technique. Unfortunately, the experiment only uses network flow data, so it is not easy to provide an analysis related to the log data system because these two data have different characteristics. Analyzing the impact of the dimensional reduction technique on the log data system is also a good idea to do in the future. Thanks for the inspiring question.
ICACT20230225 Question.3 Questioner: hbw017@mail.sdu.edu.cn 2023-02-24 오후 12:19:40	ICACT20230225 Answer.3 Answer by Auhor 6025211020@mhs.its.ac.id 2023-02-24 오후 12:19:40 Chrome Click!!
Thank you for your speech. What I want to ask is, do you have any follow-up plans and future prospects for your research?	Thank you for the question, we do have future prospect from this research. For example, analyzing the most effective number of extracted features suitable for the detection model and the best feature combinations brought to the extraction process. In addition, future research will be carried out by adding sample datasets to assist in a more profound analysis.

Now 4754 visitors Today:0 Yesterday:0 Total: 145183 215S 51P 5R 2026-10-21, Week 43

Now 4754 visitors
Today:0 Yesterday:0
Total: 145183 215S 51P 5R
2026-10-21, Week 43