Saldırı Tespit Sistemlerinde Genetik Algoritma Kullanarak Nitelik Seçimi ve Çoklu Sınıflandırıcı Füzyonu

Özgür, Atilla; Erdem, Hamıt

doi:10.17341/gazimmfd.406781

Cited by 4 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The training speed has been improved by adapting the parallel computing to the DBN training process in order to achieve global optimization with the genetic algorithm and to achieve more successful results in diagnosis accuracy. Özgür and Erdem [24] have used genetic algorithm in intrusion detection systems. In this study, it is suggested that feature selection and classifier fusion weight determination in intrusion detection classification applications need to be performed by using genetic algorithm (GA).…”

Section: Literature Reviewmentioning

confidence: 99%

Route Optimization for Medication Delivery of Covid-19 Patients with Drones

Kaya

Akdağ

2021

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

With the developments in information technologies and the intense use of online commerce, the use of drones in distribution process has gained importance. In order to transport products to more than one location, drones can perform the distribution by following a specific route, as in the traveling salesman problem. Drones provide advantages over land transportation since they are not affected by the traffic congestion and can be used autonomously. However, the limited battery durations increase the importance of using the optimum route in distribution processes. In this study, it is aimed to use drones in drug distribution. Nowadays, due to the Covid-19 pandemic, it is aimed to distribute the drugs for the patients in an optimum way with drones. In this study, it is aimed to find the optimized routes for drones in drug distribution since Covid-19 medicine distribution is a time-critic mission. Since the number of patients in a certain area may increase very quickly, it is ensured that the patients are divided into clusters and the optimum route is determined for each cluster. We propose a hybrid model consisting of a combination of K-means clustering and Ant Colony algorithms. In particular, Covid-19 patients use the mobile part of the developed application on their smartphones and transmit their medication requests to our central server. We have compared the performance of Ant Colony, Artificial Bee and Genetic algorithm metaheuristics at the stage of determining the most suitable route according to the demands collected dynamically on the central server. In the process of determining the most suitable route, Ant Colony algorithm yields the closest to optimum results for different location groups. We have developed the mobile and web site of the application to validate the proposed drug delivery model.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Route Optimization for Medication Delivery of Covid-19 Patients with Drones

Kaya

Akdağ

2021

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

show abstract

Veri setine uygulanan ön işlemler ile makine öğrenimi yöntemi kullanılarak geliştirilen saldırı tespit modellerinin performanslarının arttırılması

İLGÜN,

SAMET

2023

Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi

View full text Add to dashboard Cite

Son yıllarda yapay zekâ teknikleri kullanılarak geliştirilen siber saldırılar sızdıkları sistemin kullanıcı davranışlarını öğrenerek sisteme başarılı bir şekilde entegre olabilmekte ve bu sayede geleneksel güvenlik yazılımları tarafından tespit edilememektedir. Çeşidi ve sayısı hızla artan bu tür siber saldırılar anomali tabanlı Saldırı Tespit Sistemleri (STS) tarafından tespit edilebilmektedir. Ancak bu tür STS’lerin performansları yeterli olmadığı için STS’lerin performanslarının iyileştirilmesi ile ilgili yapılan araştırmaların önemi de artmaktadır. Bu çalışmada, anomali tabanlı saldırı tespit modellerinin tespit hızını ve doğruluğunu arttırmak için dört aşamalı bir metodoloji önerilmiştir. Bu metodoloji kapsamında kullanılan NSL-KDD veri setine ilk önce ön işlem uygulanmadan, daha sonra sırasıyla kategorik veri kodlama, ölçeklendirme, hibrit öznitelik seçimi ön işlemleri ayrı ayrı ve birlikte uygulanarak farklı veri setleri elde edilmiştir. Elde edilen veri setleri ve K-Nearest Neighbor (KNN), Multi Layer Perceptron (MLP), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) makine öğrenimi algoritmaları kullanılarak çok sayıda saldırı tespit modeli oluşturulmuştur. Son olarak en başarılı sonuçların elde edildiği modellerde hiper-parametre optimizasyonu yapılarak modellerin performansları iyileştirilmiştir. Çalışmanın sonunda eğitim veri seti üzerinde 0,373 s sürede %96,1 saldırı tespit başarısına, test veri seti üzerinde ise 0,005 s sürede %100 saldırı tespit başarısına ulaşılmıştır.

show abstract

Application of Explainable Artificial Intelligence in Intrusion Detection System Classification Using Boosting Algorithms

Atagün,

Temür,

Biroğul

2024

Mugla Journal of Science and Technology

View full text Add to dashboard Cite

The increased speed rates and ease of access to the Internet increase the availability of devices with Internet connections. Internet users can access many devices that they are authorized or not authorized. These systems, which detect whether users have unauthorized access or not, are called Intrusion Detection Systems. With intrusion detection systems, users' access is classified and it is determined whether it is a normal login or an anomaly. Machine learning methods undertake this classification task. In particular, Boosting algorithms stand out with their high classification performance. It has been observed that the Gradient Boosting algorithm provides remarkable classification performance when compared to other methods proposed for the Intrusion Detection Systems problem. Using the Python programming language, estimation was made with the Gradient Boost, Adaboost algorithms, Catboost, and Decision Tree and then the model was explained with SHAPASH. The goal of SHAPASH is to enable universal interpretation and comprehension of machine learning models. Providing an interpretable and explainable approach to Intrusion Detection Systems contributes to taking important precautions in the field of cyber security. In this study, classification was made using Boosting algorithms, and the estimation model created with SHAPASH, which is one of the Explainable Artificial Intelligence approaches, is explained.

show abstract

Saldırı Tespit Sistemlerinde Genetik Algoritma Kullanarak Nitelik Seçimi ve Çoklu Sınıflandırıcı Füzyonu

Abstract: Sınıflandırıcı füzyonu ile birlikte nitelik seçme yapılmıştır  Nitelik seçme ve sınıflandırıcı füzyonu için genetik algoritmalar kullanılmıştır

Cited by 4 publications

References 29 publications

Route Optimization for Medication Delivery of Covid-19 Patients with Drones

Route Optimization for Medication Delivery of Covid-19 Patients with Drones

Veri setine uygulanan ön işlemler ile makine öğrenimi yöntemi kullanılarak geliştirilen saldırı tespit modellerinin performanslarının arttırılması

Application of Explainable Artificial Intelligence in Intrusion Detection System Classification Using Boosting Algorithms

Contact Info

Product

Resources

About