2
Archived Theses
0
DOIs Assigned
0%
DOI Rate
Discipline
Yeni bir saldırı tespit sistemi geliştirmek için yeni bir yöntem
After the increased use of digital devices connected to the Internet, which in turn leads to users sharing their personal information, the adoption of intergovernmental institutions, including civil ones, in their work of archiving, management, marketing, etc. . On networked distributed systems, security experts have made the focus of their efforts to provide the necessary cybersecurity, which is to prevent interference by unauthorized persons from gaining access to databases and to protect networks from malicious attacks that cause losses of funds or assets connected to digital networks. Network and in our research, we tried to address the problem of (DDoS) through machine learning technology, where the (Extra Trees Classifier) algorithm was used, which reduces the size of the input data with a low computational cost and low variance, and the Random Forest algorithm with a low bias to choose the best available results from the ExtraTreesClassifier and train The model using the (Dense Neural Network) for learning and testing (IDS) model achieved an accuracy of 99.85%.
Makine öğrenmeyi kullanarak ince iğne aspirasyon görüntülerinde meme kanseri tahmini
Breast cancer, with an estimated 1.5 million new cases per year, is a critical worldwide health problem owing to the disease's high fatality rate. It is also the most common cancer among women, accounting for 16% of all cancer cases in this demographic globally. Mammography is the most successful way for detecting breast cancer in its early stages, allowing for early intervention. Breast cancer may be detected in its early stages using ultrasound, magnetic resonance imaging, and computational tomography, albeit these methods are not as good in investigating and diagnosing these abnormalities as other ways This work aims to develop a methodology that is capable of identifying and classifying cancerous tumors using digital mammography images. In this way, the diagnostic work of these images, carried out by radiologist specialists, will be supported by the system to be developed through the methodology presented in this work. Therefore, with the proposed methodology, it was expected an increase in the agility and effectiveness of the diagnosis and, thus, to increase the chances of cure of the patients, since a rapid and effective diagnosis is of fundamental importance for the treatment of the disease.