Muhammed Emre Colak

Muhammed Emre Colak

Auto-generated profile, based on publicly available information

Muhammed Emre Colak

Firat Universitesi

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 April 2024
Verified
Conference Paper
Closed access
ÖKÖmer Miraç Kökçam
Ömer Miraç Kökçam
ABAytuğ BOYACI
Aytuğ BOYACI
MÇMuhammed Emre Çolak
Muhammed Emre Çolak
Brain tumors are abnormal cell growths that occur in various parts of the brain, and the accurate classification of these tumors plays a critical role in determining treatment methods. Classification and diagnosis of brain tumors based on artificial intelligence and deep learning models have been made possible due to advances in medical image processing technologies. For instance, such technologies facilitate quick detection of tumors by health experts thereby improving early diagnosis rate and hence enhancing treatment outcomes. Importantly, however, one considers improvement or breakthroughs in artificial intelligence-based classification systems as a crucial step forward towards brain tumor diagnosis as well as its treatment strategy. In this study we use Google Research's ImageNet-21k pre-trained ResNet50 model for classifying brain tumor cases. This model is a deep learning-based image classification tool and is capable of learning from large data sets. The model is specifically trained for high-resolution image recognition and is designed to achieve high accuracy rates. The results showed a classification accuracy of 99.9 percent, which is an exceptional accuracy rate for this model. This accuracy rate indicates that the model is highly effective in detecting and classifying brain tumors. High accuracy rates allow for early diagnosis of patients' diseases and, as it is often said in medicine, “Early Diagnosis Saves Lives”. This result is one of the many proofs of how effective artificial intelligence and deep learning are in medical image analysis.

31 July 2018 in PeerJ
Verified
Journal Article
Open access
PDF file
KYKadir Yildirim
Kadir Yildirim
MOMahmut Taha Olcucu
Mahmut Taha Olcucu
MCMuhammed Emre Colak
Muhammed Emre Colak
Introduction: In this study, a survey was prepared for urologists that asked about their primary choice of treatment for urolithiasis in daily practice and their answers were evaluated. Methods: The survey was prepared on the Google Docs website and it was sent to 1,016 urologists via email with 752 confirmed deliveries. In addition to the demographic questions about each participant’s age, gender, and institution, the survey presented case scenarios focusing on their preferred treatment modalities for distal ureteric, proximal ureteric, and renal calculi. The participating urologists were divided into two groups according to the frequency that they treat urolithiasis patients. Results: Of the 752 surveys delivered, 211 urologists (28.05%) responded and 204 answered all questions. According to the results, there were no significant differences between the treatment approaches and the other localizations, but there was a statistically significant difference for treatment approaches to lower pole stones between two groups. In response to the question of which stone treatment method was used less frequently, 124 (60.7%) participants answered that they used shock wave lithotripsy less in the last 10 years. Conclusion: The present study has shown that while the management of renal and ureteric calculi by Turkish urologists is highly varied, the overall treatment patterns are in accordance with the European Association of Urology guidelines. However, similar to the global trend extracorporeal shock wave lithotripsy is less preferred by Turkish urologists.

12 October 2015 in Elektronika ir Elektrotechnika
Verified
Journal Article
Open access
PDF file
MCMuhammed Emre Colak
Muhammed Emre Colak
AVAsaf Varol
Asaf Varol
A Novel Intelligent Optimization Algorithm Inspired from Circular Water Waves

2 October 2015 in Elektronika ir Elektrotechnika
Verified
Journal Article
Open access
PDF file
MCMuhammed Emre Colak
Muhammed Emre Colak
AVAsaf Varol
Asaf Varol
In this paper, a novel nature inspired algorithm for continuous optimization of numerical functions has been proposed. The algorithm is inspired from the circular wave created from a water drop when it falls to a still water. Algorithm itself has been developed with the purpose of distributed working thus kept as embarrassingly parallel as possible. Proposed algorithm is tested with eight different benchmark functions and up to thirty dimensions. The experimental results are promising and encouraging for further research studies.DOI: http://dx.doi.org/10.5755/j01.eee.21.5.13316

1 November 2019
Verified
Conference Paper
Closed access
MCMuhammed Emre Colak
Muhammed Emre Colak
AVAsaf Varol
Asaf Varol
In this paper, a novel approach to detect iris from images which contains frontal faces is proposed. The approach can be used for real time eye detection from cheap web cameras or other kind of cameras. First face region is detected by using haar cascades for frontal faces than possible eye region chosen from the face region. The eye regions reduced with the foreknowledge which is eyes are darker. Reduced image used with a tailored template matching algorithm to determine where eye really is.

1 January 2020 in Tehnicki vjesnik - Technical Gazette
Verified
Journal Article
Open access
PDF file
MCMuhammed Emre Colak
Muhammed Emre Colak
AVAsaf Varol
Asaf Varol
Eye detection algorithms are being used in many fields such as camera applications for entertainment and commercial purposes, gaze detection applications, computer-human interaction applications, and eye recognition applications for security, etc. Successful and fast eye detection is an essential step for all these applications in order to achieve good results. There are many eye detection methods in the literature, and most of them rely on the Viola-Jones method to detect the face before localizing eyes. In this paper, a straightforward approach to detect eyes from images which contain a frontal face is proposed. The approach can be used for real-time eye detection using cheap web cameras or other cameras. First, face landmarks are detected from the image, and by utilizing these landmarks; the eye region is determined. The eye radius is estimated by utilizing eye corners. Then, reduced input images are tested with a tailored matching algorithm which does not need image reduction to determine where the eye is.