Browsing by Author "Dedeturk, Bilge Kagan"

Now showing 1 - 6 of 6

Can artificial intelligence algorithms recognize knee arthroplasty implants from X-ray radiographs?
(MediHealth Academy, 2023) Gölgelioğlu, Fatih; Aşkın, Aydoğan; Gündoğdu, Mehmet Cihat; Uzun, Mehmet Fatih; Dedeturk, Bilge Kagan; Yalın, Mustafa; 0000-0002-8026-5003; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Dedetürk, Bilge Kağan
Aims: This study aimed to investigate the use of a convolutional neural network (CNN) deep learning approach to accurately identify total knee arthroplasty (TKA) implants from X-ray radiographs. Methods: This retrospective study employed a deep learning CNN system to analyze pre-revision and post-operative knee X-rays from TKA patients. We excluded cases involving unicondylar and revision knee replacements, as well as low-quality or unavailable X-ray images and those with other implants. Ten cruciate-retaining TKA replacement models were assessed from various manufacturers. The training set comprised 69% of the data, with the remaining 31% in the test set, augmented due to limited images. Evaluation metrics included accuracy and F1 score, and we developed the software in Python using the TensorFlow library for the CNN method. A computer scientist with AI expertise managed data processing and testing, calculating specificity, sensitivity, and accuracy to assess CNN performance. Results: In this study, a total of 282 AP and lateral X-rays from 141 patients were examined, encompassing 10 distinct knee prosthesis models from various manufacturers, each with varying X-ray counts. The CNN technique exhibited flawless accuracy, achieving a 100% identification rate for both the manufacturer and model of TKA across all 10 different models. Furthermore, the CNN method demonstrated exceptional specificity and sensitivity, consistently reaching 100% for each individual implant model. Conclusion: This study underscores the impressive capacity of deep learning AI algorithms to precisely identify knee arthroplasty implants from X-ray radiographs. It highlights AI’s ability to detect subtle changes imperceptible to humans, execute precise computations, and handle extensive data. The accurate recognition of knee replacement implants using AI algorithms prior to revision surgeries promises to enhance procedure efficiency and outcomes.
A Comparative Analysis on Medical Article Classification Using Text Mining & Machine Learning Algorithms
(Institute of Electrical and Electronics Engineers Inc., 2021) Kolukisa, Burak; Dedeturk, Bilge Kagan; Dedeturk, Beyhan Adanur; Gulşen, Abdulkadir; Bakal, Gokhan; 0000-0003-0423-4595; 0000-0002-4250-2880; 0000-0003-2897-3894; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Kolukisa, Burak; Gulşen, Abdulkadir; Bakal, Gokhan; Dedeturk, Beyhan Adanur
The document classification task is one of the widely studied research fields on multiple domains. The core motivation of the classification task is that the manual classification efforts are impractical due to the exponentially growing document volumes. Thus, we densely need to exploit automated computational approaches, such as machine learning models along with data & text mining techniques. In this study, we concentrated on the classification of medical articles specifically on common cancer types, due to the significance of the field and the decent number of available documents of interest. We deliberately targeted MEDLINE articles about common cancer types because most cancer types share a similar literature composition. Therefore, this situation makes the classification effort relatively more complicated. To this end, we built multiple machine learning models, including both traditional and deep learning architectures. We achieved the best performance (R¿82% F score) by the LSTM model. Overall, our results demonstrate a strong effect of exploiting both text mining and machine learning methods to distinguish medical articles on common cancer types.
CSA-DE-LR: enhancing cardiovascular disease diagnosis with a novel hybrid machine learning approach
(PEERJ INC, 2024) Dedeturk, Beyhan Adanur; Dedeturk, Bilge Kagan; Bakir-Gungor, Burcu; 0000-0003-4983-2417; 0000-0002-8026-5003; 0000-0002-2272-6270; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Beyhan Adanur, Dedeturk; Bakir-Gungor, Burcu
Cardiovascular diseases (CVD) are a leading cause of mortality globally, necessitating the development of efficient diagnostic tools. Machine learning (ML) and metaheuristic algorithms have become prevalent in addressing these challenges, providing promising solutions in medical diagnostics. However, traditional ML approaches often need to be improved in feature selection and optimization, leading to suboptimal performance in complex diagnostic tasks. To overcome these limitations, this study introduces a new hybrid method called CSA-DE-LR, which combines the clonal selection algorithm (CSA) and differential evolution (DE) with logistic regression. This integration is designed to optimize logistic regression weights efficiently for the accurate classification of CVD. The methodology employs three optimization strategies based on the F1 score, the Matthews correlation coefficient (MCC), and the mean absolute error (MAE). Extensive evaluations on benchmark datasets, namely Cleveland and Statlog, reveal that CSA-DELR outperforms state-of-the-art ML methods. In addition, generalization is evaluated using the Breast Cancer Wisconsin Original (WBCO) and Breast Cancer Wisconsin Diagnostic (WBCD) datasets. Significantly, the proposed model demonstrates superior efficacy compared to previous research studies in this domain. This study's findings highlight the potential of hybrid machine learning approaches for improving diagnostic accuracy, offering a significant advancement in the fields of medical data analysis and CVD diagnosis.
An efficient network intrusion detection approach based on logistic regression model and parallel artificial bee colony algorithm
(ELSEVIER, 2024) Kolukısa, Burak; Dedeturk, Bilge Kagan; Hacilar, Hilal; Gungor, Vehbi Cagri; 0000-0003-0423-4595; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Kolukısa, Burak; Hacilar, Hilal; Gungor, Vehbi Cagri
In recent years, the widespread use of the Internet has created many issues, especially in the area of cybersecurity. It is critical to detect intrusions in network traffic, and researchers have developed network intrusion and anomaly detection systems to cope with high numbers of attacks and attack variations. In particular, machine learning and meta-heuristic methods have been widely used for network intrusion detection systems (NIDS). However, existing studies on these systems usually suffer from low performance results such as accuracy, F1-measure, false positive rate, and false negative rate, and generally do not use automatic parameter tuning techniques. To address these challenges, this study proposes a novel approach based on a logistic regression model trained using a parallel artificial bee colony (LR-ABC) algorithm with a hyper-parameter optimization technique. The performance of the proposed model is evaluated against state -of-the-art machine learning and deep learning models on two publicly available NIDS datasets. Comparative performance evaluations show that the proposed method achieved satisfactory results with accuracy of 88.25% on the UNSW-NB15 dataset and 90.11% on the NSL-KDD dataset, and F1-measures of 88.26% and 90.15%, respectively. These findings demonstrate the efficacy of the proposed LR-ABC model in enhancing the accuracy and reliability, while providing a scalable solution to adapt to the dynamic and evolving landscape of cybersecurity threats.
Lifetime maximization of IoT-enabled smart grid applications using error control strategies
(ELSEVIER, 2024) Tekin, Nazli; Dedeturk, Bilge Kagan; Gungor, Vehbi Cagri; 0000-0003-0803-8372; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Gungor, Vehbi Cagri
Recently, with the advancement of Internet of Things (IoT) technology, IoT-enabled Smart Grid (SG) applications have gained tremendous popularity. Ensuring reliable communication in IoT-based SG applications is challenging due to the harsh channel environment often encountered in the power grid. Error Control (EC) techniques have emerged as a promising solution to enhance reliability. Nevertheless, ensuring network reliability requires a substantial amount of energy consumption. In this paper, we formulate a Mixed Integer Programming (MIP) model which considers the energy dissipation of EC techniques to maximize IoT network lifetime while ensuring the desired level of IoT network reliability. We develop meta-heuristic approaches such as Artificial Bee Colony (ABC) and Particle Swarm Optimization (PSO) to address the high computation complexity of large-scale IoT networks. Performance evaluations indicate that the EC-Node strategy, where each IoT node employs the most energy-efficient EC technique, yields a minimum of 8.9% extended lifetimes compared to the EC-Net strategies, where all IoT nodes employ the same EC method for a communication. Moreover, the PSO algorithm reduces the computational time by 77% while exhibiting a 2.69% network lifetime decrease compared to the optimal solution.
Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network
(PEERJ INC, 2024) Hacilar, Hilal; Dedeturk, Bilge Kagan; Bakir-Gungor, Burcu; Gungor, Vehbi Cagr; 0000-0002-5811-6722; 0000-0002-2272-6270; AGÜ, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü; Hacilar, Hilal; Bakir-Gungor, Burcu
Cyberattacks are increasingly becoming more complex, which makes intrusion detection extremely difficult. Several intrusion detection approaches have been developed in the literature and utilized to tackle computer security intrusions. Implementing machine learning and deep learning models for network intrusion detection has been a topic of active research in cybersecurity. In this study, artificial neural networks (ANNs), a type of machine learning algorithm, are employed to determine optimal network weight sets during the training phase. Conventional training algorithms, such as back- propagation, may encounter challenges in optimization due to being entrapped within local minima during the iterative optimization process; global search strategies can be slow at locating global minima, and they may suffer from a low detection rate. In the ANN training, the Artificial Bee Colony (ABC) algorithm enables the avoidance of local minimum solutions by conducting a high-performance search in the solution space but it needs some modifications. To address these challenges, this work suggests a Deep Autoencoder (DAE)-based, vectorized, and parallelized ABC algorithm for training feed-forward artificial neural networks, which is tested on the UNSW-NB15 and NF-UNSW-NB15-v2 datasets. Our experimental results demonstrate that the proposed DAE-based parallel ABC-ANN outperforms existing metaheuristics, showing notable improvements in network intrusion detection. The experimental results reveal a notable improvement in network intrusion detection through this proposed approach, exhibiting an increase in detection rate (DR) by 0.76 to 0.81 and a reduction in false alarm rate (FAR) by 0.016 to 0.005 compared to the ANN-BP algorithm on the UNSWNB15 dataset. Furthermore, there is a reduction in FAR by 0.006 to 0.0003 compared to the ANN-BP algorithm on the NF-UNSW-NB15-v2 dataset. These findings underscore the effectiveness of our proposed approach in enhancing network security against network intrusions.