Yazar "Karaduman, Mucahit" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    CLASSIFICATION OF MALICIOUS NETWORK DATASET WITH RESIDUAL CNN
    (2025) Karaduman, Mucahit; YALÇIN, Sercan; YILDIRIM, Muhammed
    This paper proposes a Residual Convolutional Neural Network (CNN) based model for malicious traffic detection. Network security is becoming increasingly important every day as the digital world develops. It aims to classify the data labeled as benign and malicious in the ready dataset. In the proposed model, first of all, all the information in the dataset is digitized. Then, it is normalized to the range of 0-1 and made ready as an input to the proposed architecture. It is aimed to classify the information in this two-class dataset with the proposed Residual Convolutional Neural Network (CNN) architecture. The accuracy rate obtained after the training and testing stages of the model is 94.9%. This accuracy rate shows that the proposed model successfully results in the detection of malicious packets in network attacks and can be used for network security.
  • Küçük Resim Yok
    Öğe
    Determining the Demands of Disabled People by Artificial Intelligence Methods
    (Ali KARCI, 2021) Karaduman, Mucahit; Karci, Ali
    Analysis of brain activities and remote control are among the current issues that are being studied. Analysis of signals arising during brain functions is electroencephalography (EEG). EEG signals have intellectual, visual stimulation, and motion resultant forms. Especially, EEG signals generated by visual stimulus are within the scope of this study. In this study, research was carried out on the classification of EEG signals formed in a person looking at visual figures. For these studies, first of all, EEG signals from the brain were recorded with images and filtered to remove noise. Then, the features were extracted from the signals. In this study, Moment 5 feature was also used in addition to the features used in many studies such as mean, median, standard deviation and entropy. Then, classification was made using Support Vector Machine (SVM), k Nearest Neighbor (KNN), and Decision Tree (DT) algorithms. Classification was made for 4 different visual shapes used, since these shapes are square, circle, triangle, and star, and the same categorical names were used in the classification stage. As a result of the classification of EEG signals; SVM and KNN algorithms have determined which shape is viewed with 99.99% accuracy. These results show that different signals are produced in the brain according to the structure of the shape viewed. This situation shows that it can be used as a method to give patients the opportunity to express their requests just by looking or thinking.
  • Küçük Resim Yok
    Öğe
    Performance of Transformer-Based Methods on Restaurant Reviews Analysis
    (2025) Karaduman, Mucahit; BAYDEMİR, Muhammed Bedir; YILDIRIM, Muhammed
    Sentiment analysis provides important data in various areas, from customer feedback to social media posts, by determining the text's emotional tones. In this study, sentiment analysis was performed using restaurant reviews with a transformer-based model. The attention mechanism underlying these models dynamically learns the contextual relationships of words in the text and better captures the meaning of the language. The model was trained and tested using a dataset from a vast information source. First, tokenization and padding operations of the dataset were performed; then, the model was trained, and test results were obtained. The training accuracy of the model was calculated as 90.81% and the test accuracy as 85.79%. When other performance metrics were also considered, the model, which achieved high success for negative and positive classes, showed lower success for the neutral class. In terms of general evaluation, it is seen that the model exhibited good performance when the accuracy rate was taken into account. This shows that transformer-based approaches are suitable for natural language processing and usability in this area.