Yazar "Candan, Hasibe" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Breast Cancer Prediction with Artificial Intelligence Based Clinical Decision Support System
    (Fevzullah TEMURTAŞ, 2023) Candan, Hasibe; Şahin, Hasan
    Breast cancer is caused by uncontrolled cell growth and early detection is crucial for successful treatment. Diagnostic methods such as MRI, mammography, ultrasound and biopsy are used in the diagnosis of cancer. AI-based clinical decision support systems can predict treatment outcomes. A study was conducted to diagnose breast cancer using blood values and to increase performance metrics by applying discretization preprocessing. Machine learning methods were compared with 10-fold cross-validation and discretization applied and unapplied data, and the model with the best results was created. It gave the highest classification performance in breast cancer outcome prediction, with a sensitivity value of 0.828 for the Multi-Layer Sensor. In the model created by applying discretization, the Support Vector Machines increased from 55% to 72%.
  • Küçük Resim Yok
    Öğe
    Hybrid Deep Neural Network for Electric Vehicle State of Charge Estimation
    (Institute of Electrical and Electronics Engineers Inc., 2024) Kadem, Onur; Candan, Hasibe; Kim, Jongrae H.
    In electric vehicles (EVs), a battery management system plays a critical role in ensuring the reliable and safe operation of batteries. One of its main tasks is to display the battery state of charge (SoC), reflecting the battery's current available charge level. However, the accuracy of SoC estimation is a formidable challenge due to the intricate nature of battery modelling. To overcome this challenge, data-driven methods have recently emerged as the dominant approach for SoC estimation. Considering the SoC estimation problem as a time series problem, we propose a hybrid deep neural network (DNN) that eliminates the need for feature engineering or adaptive filtering. The proposed DNN incorporates a convolutional layer, a long short-term memory layer, and a dense layer. The DNN was trained using data collected from benchmark EV driving cycles (DST, BJDST, and FUDS drive cycles) within a temperature range of 0 °C to 50 °C. The performance evaluation of the trained DNN has been carried out using another standard EV driving cycle (US06 drive cycle) at various operating temperatures. The results demonstrate that the trained DNN effectively captures the dynamic behaviour of the battery under various operational conditions, yielding a maximum percentage SoC estimation error of approximately 3%. Furthermore, the results indicate that the proposed DNN technique is capable of generalising the battery's dynamic response to unseen data. Overall, our findings show that the proposed technique is promising for EV applications in which battery operating conditions exhibit significant variability. © 2024 IEEE.
  • Küçük Resim Yok
    Öğe
    Siber Güvenlikte Yapay Zekanın Rolü ve Önemi: Bir Derleme
    (Murat GÖK, 2022) Mıjwıl, Maad M.; Sadıkoğlu, Emre; Cengiz, Emine; Candan, Hasibe
    Yapay zeka teknolojileri, siber güvenlik de dahil olmak üzere birçok alanı kapsamaktadır. Siber güvenliğin temel amacı; bilişim sistemlerini bilgisayar korsanları tarafından gerçekleştirilebilecek yetkisiz erişim, verilerin silinmesi/değiştirilmesi gibi şantajlara karşı korumak ve siber saldırıları önlemektir. Bu çalışma da, yapay zeka teknolojilerinin temel çerçevesi ve kavramları vurgulanarak dijital ortamda siber güvenliğin sağlanması konusunda yapay zekanın rolü ve önemi anlatılmıştır. Sanal dünyada her geçen gün daha da karmaşıklaşan siber tehditler karşısında kullanıcıların mahremiyetini ve verilerini koruyabilmek için yapay zeka yöntemlerini kullanmanın gerekli olduğu sonucuna varılmıştır.