13 results for “Batch Normalization”
Research Article
Open Access A New Convolutional Neural Network Model for Skin Cancer Detection in Dermatoscopic Images
Mustafa Furkan Keskenler, Keskenler M, Deniz Dal, Dal D
Cognitive Models and Artificial Intelligence Conference 2023 https://doi.org/10.36287/setsci.6.1.006
Skin cancer is the abnormal growth of skin cells and one of the most common cancers of all. There are several types of skin cancer. Melanoma, a form of skin cancer, has increased 237% in Turkey in the last 30 years. While the U.S. adds about one million new ca…
Research Article
Open Access El Yazısı Karakterlerin Tanınmasında Derin Sinir Ağlarının Etkinliği Kısıtlı ve Geniş Sınıf Yapılarının Performans Analizi
Erdin Fidan, Fidan E, Mahir Kaya, Kaya M
International Symposium on AI-Driven Engineering Systems 2025 https://doi.org/10.36287/setsci.22.65.001
Bu çalışmada, el yazısı karakterlerin tanınmasına yönelik derin öğrenme tabanlı bir model geliştirilmiştir. Model, farklı sayıda çıkış sınıfı (karakter) için test edilmiş; yalnızca 10 karakterin sınıflandırıldığı senaryoda %96 doğruluk oranı elde edilirken, sı…
Research Article
Open Access Akut Lenfoblastik Löseminin Makine Öğrenimi ile Sınıflandırılması
Ayşe Berika Varol Malkoçoğlu , Varol Malkoçoğlu A, İsmail İşeri, İşeri İ
4th International Symposium on Innovative Approaches in Engineering and Natural Sciences 2019 https://doi.org/10.36287/setsci.4.6.139
Akut Lenfoblastik Lösemi (ALL) genellikle 2-5 yaş arasındaki çocuklarda görülen, kemik iliğindeki beyaz kan hücrelerinin hızlı artışından ve şekilsel bozukluklarından kaynaklanan bir kanser türüdür. Tespit edilip tedavi sürecinin başlatılmadığı takdirde ölümle…
Research Article
Open Access Execution Certificates for Open Finance: Auditable Data Availability, Latency, and Cost in Learned Lead–Lag Trading
Eric Benhamou, Benhamou E, Jean-Jacques Ohana, Ohana J, Beatrice Guez, Guez B, Thomas Jacquot, Jacquot T, Ethan Setrouk, Setrouk E, Chamyl Saadi, Saadi C
Proceedings of the International Conference on Open Finance (ICOF 2026) 2026 https://doi.org/10.36287/setsci.25.2.001
Open-finance interfaces make market data and trading services programmable, but an API response is not an executable signal. Economic information depends on data receipt, inference completion, and feasible order arrival. We propose an execution certificate: a …
Research Article
Open Access A Deep Learning Framework for the Identification of Distinct Stages in Diabetic Retinopathy through Retinal Image Analysis
A.D.P. Rupasinghe, Rupasinghe A, K.G. Samarawickrama, Samarawickrama K
International Symposium on AI-Driven Engineering Systems 2025 https://doi.org/10.36287/setsci.22.3.001
Diabetic retinopathy is the leading cause of blindness among diabetic patients. It occurs when the light-sensitive tissue in the retina is damaged. According to WHO statistics, the current global prevalence of diabetic retinopathy is approximately 103 million …
Research Article
Open Access Meme Histopatoloji Görüntülerinin Derin Öğrenme Yöntemleri İle Sınıflandırılması
Meral Karakurt, Karakurt M, İsmail İşeri, İşeri İ
International Congress on Human-Computer Interaction, Optimization and Robotic Applications 2019 https://doi.org/10.36287/setsci.4.5.019
Kanser, insan ölümlerine sebep olan hastalıklar arasında ikinci sırada gelmektedir. Günümüzde insanların kansere yakalanma oranları giderek artmaktadır. Kanser; kötü beslenme, sigara ve alkol kullanımı, uzun süre güneş ışığına maruz kalma gibi birçok nedenle o…
Research Article
Open Access Accurate and Scalable Object Detection for Smart Warehousing Using YOLOv8 and Residual CNNs
Iman Elawady, Elawady I, Abdulrahman Al Homsi, Homsi A, Omer Ahmed Mohamed Ahmed, Ahmed O
International Symposium on AI-Driven Engineering Systems 2025 https://doi.org/10.36287/setsci.22.51.001
Robust object detection and classification in dynamic industrial scenarios is still a challenge, in particular if the system has to work in real-time on mid-ranged hardware. Classical vision-based methods have difficulties to cope with low/weak illumination, r…
Research Article
Open Access The Random Forest with Hybrid Principal Component Analysis for detecting Healthy and Insomnia individuals in three subtypes of Cyclic Alternating Pattern Sleep Study
Nadhim Azeez Sayel, Sayel N, Mohammad Fayaz, Fayaz M
Proceeding of the Cognitive Models and Artificial Intelligence Conference 2024 https://doi.org/10.36287/setsci.17.1.001
Sleep disorders such as insomnia, sleep bruxism, narcolepsy, and sleep-disordered breathing have different sleep quality parameters such as cyclic alternating pattern phases and A subtype phases. This study aims to analyze and predict the A phase subtypes from…
Research Article
Open Access The New Activation Function for Complex Valued Neural Networks: Complex Swish Function
Mehmet Çelebi, Çelebi M, Murat Ceylan, Ceylan M
4th International Symposium on Innovative Approaches in Engineering and Natural Sciences 2019 https://doi.org/10.36287/setsci.4.6.050
Complex-valued artificial neural network (CVANN) has been developed to process data with complex numbers directly. In a CVANN the weights, threshold, inputs and outputs are all complex numbers. The convergence of the CVANN back propagation algorithm depending …
Research Article
Open Access Recognition of Handwritten Source Code Characters With Deep Neural Networks
Barış Kılıçlar, Kılıçlar B, Metehan Makinacı, Makinacı M
4th International Symposium on Innovative Approaches in Engineering and Natural Sciences 2019 https://doi.org/10.36287/setsci.4.6.111
In this paper we presents an application of deep learning techniques to recognize handwritten source code characters. Although there are many works on the handwritten character recognition (HCR) problem, very few works have been done about the offline handwrit…
Research Article
Open Access GAUSS FONKSİYONLARI İLE PENCERELENMİŞ POLİNOM AKTİVASYON FONKSİYONU KULLANAN DALGACIK SİNİR AĞI İLE YAPAY SİNİR AĞLARININ, ÇOK KISA VADELİ RÜZGAR HIZI TAHMİNİNDE, TAHMİN BAŞARIMLARININ KARŞILAŞTIRILMASI
Serkan Şenkal, Şenkal S, Cem Emeksiz, Emeksiz C
3rd International Symposium on Innovative Approaches in Scientific Studies (Engineering and Natural Sciences) 2019
Fosil bazlı yakıtların giderek ömrünü tamamladığı dünyamızda alternatif enerji kaynaklarının önemi hızla artmaktadır. Bir alternatif enerji şekli olan rüzgar enerjisinde, rüzgar türbinleri kurulu olduğu alanın sadece %1’ini işgal etmesi ve kurulduğu kırsal ala…
Research Article
Open Access The Effect of Cutting Parameters on Surface Hardness Change in Turning of 16MnCr5 Steel
Ümmü Gamze Durutürk, Durutürk Ü, Kağan Telek, Telek K, Ahmet Özdemir, Özdemir A
Ist International Symposium on Innovative Approaches in Scientific Studies 2018
Cementation steels; surface hardness is high and abrasion resistant materials.Also, cementation steels are materials with the alloyed or non-alloyed structure which materials used in the manufacture of parts which are resistant to shock and variable loads.Addi…
Research Article
Open Access Non-Magnetic Materials Assignment based on Artificial Neural Network
Umut Özkaya, Özkaya U, Şaban Öztürk, Öztürk Ş, Levent Seyfi, Seyfi L, Bayram Akdemir, Akdemir B
Ist International Symposium on Innovative Approaches in Scientific Studies 2018
In this paper, signal recognition system is proposed for classification of soil types and buried object by using feature extraction and artificial neural networks. Using GprMax simulation program, 300 GPR A scan signals were obtained for different ground plane…
