WoS İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/6

Browse

Filters

2021 - 20242

Settings

Subject: search.filters.subject.Data Mining

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - WoS: 16
    Citation - Scopus: 20
    A Fast Intrusion Detection System Based on Swift Wrapper Feature Selection and Speedy Ensemble Classifier
    (Pergamon-elsevier Science Ltd, 2024) Zorarpaci, Ezgi
    Due to the widespread use of the internet, computer network systems may be exposed to different types of attacks. For this reason, the intrusion detection systems (IDSs) are often used to protect the network systems. Network traffic data (i.e., network packets) includes many features. However, most of them are irrelevant and can lead to a decrease in the runtime and/or the detection performance of the IDS. Although various data mining methods have been applied to improve the effectiveness of IDS, research regarding IDSs having high detection rates and better runtime performance (i.e., lower computational cost) is ongoing. On the other hand, the dimensionality reduction techniques help to eliminate unnecessary features and reduce the computation time of a classification algorithm. In the literature, the feature selection methods (i.e., filter and wrapper) have been widely used for the dimensionality reduction in IDSs. Although the wrapper feature selection techniques outperform the filters, they are time-consuming. Again, the ensemble classifiers can achieve higher detection rates for IDSs compared to the stand-alone classifiers, but they require more computation time to build the model. In order to improve the runtime performance and the detection rate of IDS, a swift wrapper feature selection and a speedy ensemble classifier are proposed in this study. For the dimensionality reduction, the swift wrapper feature selection (i.e., DBDE-QDA) is used, which consists of dichotomous binary differential evolution (DBDE) and quadratic discriminant analysis (QDA). For attack detection, the speedy ensemble classifier is used, which combines Holte's 1R, random tree, and reduced error pruning tree. In the experiments, the NSL-KDD, UNSW-NB15, and CICDDoS2019 datasets are used. According to the experimental results, the proposed IDS reaches 95%-97.4%, 82.7%, and 99.5%-99.9% detection rates for the NSL-KDD, UNSW-NB15, and CICDDoS2019 datasets. In this way, the proposed IDS competes with the state-of-the-art methods in terms of detection rate and false alarm rate. In addition, the proposed IDS has a lower computational cost than the state-of-the-art methods. Moreover, DBDE-QDA reduces the dimension by 60.97%-82.92%, 73.46%, and 96.55%-98.85% for the NSL-KDD, UNSW-NB15, and CICDoS2019 datasets.
  • Article
    Citation - WoS: 3
    Data Mining the City: User Demands Through Social Media
    (Konya Technical Univ, Fac Architecture & design, 2021) Cakir, Hulya Soydas; Levent, Vecdi Emre
    Purpose Information technologies are commonly used in architectural and urban design. The use of these technologies providing support at every stage of the design opens up different perspectives for designers and users. The aim of the study is to obtain user demands for green spaces of a specific district by mining data through social media and to detect the actual green spaces of the same district using applications developed for this purpose. User demands for design decisions and applications of green spaces and the current situation of the study area are evaluated. Design/Methodology/Approach The research is firstly realized through social media, and data obtained from Twitter is analysed in order to evaluate user demands for parks and green spaces of Atasehir district in Istanbul City. Secondly, all green areas in the same district are detected by using digital maps. Two applications are specifically designed for this research; Tweet Grabber is used for user sentiment analysis on social media and Map Grabber is processed for extraction of green spaces via maps. The total area of the green spaces is compared with the desired area of open and green spaces per user. Findings The user demands and thoughts obtained in the study about the green spaces of the district are compatible with the actual situation of green spaces. It is observed that the users are mostly dissatisfied with the adequacy of green spaces. Designers, politicians, municipalities and all stakeholders can benefit from the obtained user expectations and feedback. Interpreting user demands by mining data through social media enables user participation in design decisions. This research method can be supportive and adaptive in related issues of design for the cities, enabling user participation in architectural and urban design. Research Limitations/Implications Parks and green spaces of Atasehir district of Istanbul are taken as a case study. Twitter is chosen for mining of data in social media based on parameters such as keywords and location. Social/Practical Implications The impact and support of users in design decisions can be clearly demonstrated by advanced information technologies. Mining data through social media and developed applications will contribute to design decisions and policies for architectural and urban spaces. Originality/Value Tweet Grabber and Map Grabber applications are developed for this research in order to get text based and image based data. The research includes a unique case study for mining data through social media on a specific design issue and target location.