İlhan Umut

Dr. İlhan Umut

Tekirdag Namik Kemal University, Tekirdağ, Turkey (Türkiye)
orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
28 December 2012 in International Journal of Green Energy
Verified
Journal Article
Closed access
BDBahtiyar Dursun
Bahtiyar Dursun
CGCihan Gokcol
Cihan Gokcol
İlhan Umutİlhan Umut
İlhan Umut
EUErdem Ucar
Erdem Ucar
SKSureyya Kocabey
Sureyya Kocabey
This article investigates the possibility of providing electricity from solar/wind hybrid systems for a remote location with no electricity connection in the city of Edirne in the westernmost province of Turkey in order to decrease the high cost of utilizing only stand-alone diesel system and to achieve considerable fuel savings. In this study, National Renewable Energy Laboratory's (NREL) HOMER (Hybrid Optimization Model for Electric Renewables) software is used to perform the techno-economic feasibility of such hybrid systems considering both solar data and wind data. Additionally, the contribution of solar and wind on energy production, cost of energy, and total operating hours of diesel generator is examined for the optimal hybrid configurations. Furthermore, fuel savings and reduction in carbon emissions of different hybrid systems are investigated. Finally, suitability of utilizing hybrid solar–wind energy system over stand-alone diesel system is discussed mainly based on different solar global irradiances, wind speed, and diesel price.

18 October 2016 in Behaviour & Information Technology
Verified
Journal Article
Closed access
EUErdem Ucar
Erdem Ucar
HÜHakan Üstünel
Hakan Üstünel
TCTurhan Civelek
Turhan Civelek
İlhan Umutİlhan Umut
İlhan Umut
The aim of this study is to identify the effects of force feedback haptic applications developed in virtual reality environments (VREs), which is an important field of study in computer science and engineering, on gifted students’ attitudes towards chemistry education in learning process. A 3D 6 DOF (Degree of Freedom) haptik device (Phantom Omni™) has been used to develop the algorithm in this study. It can be used to transmit force and motion using a haptic device. Visual C++ was choosen as the software development environment. OpenGL™ and Haptic Device Application Programming Interface have been used for rendering graphics. At the 3D image creation state Wrap 1200™, which is a kind of head-mounted display, has been chosen. The sample of this study consists of 52 students identified as gifted and are attending 6th and 7th grades at the Istanbul Science & Art Center in Istanbul. The experimental group studied chemical bonds using an application developed by using a force feedback haptic device in VRE and the control group studied it by traditional teaching methods. The study reveals that there is a relation between using force feedback haptic applications which are developed in VREs and gifted students’ attitudes towards educational programs.

16 July 2024 in Sensors
Verified
Journal Article
Open access
PDF file
İlhan Umutİlhan Umut
İlhan Umut
ÜKÜMİT CAN KUMDERELİ
ÜMİT CAN KUMDERELİ
The aim of this study is to develop a practical software solution for real-time recognition of sign language words using two arms. This will facilitate communication between hearing-impaired individuals and those who can hear. We are aware of several sign language recognition systems developed using different technologies, including cameras, armbands, and gloves. However, the system we propose in this study stands out for its practicality, utilizing surface electromyography (muscle activity) and inertial measurement unit (motion dynamics) data from both arms. We address the drawbacks of other methods, such as high costs, low accuracy due to ambient light and obstacles, and complex hardware requirements, which have limited their practical application. Our software can run on different operating systems using digital signal processing and machine learning methods specific to this study. For the test, we created a dataset of 80 words based on their frequency of use in daily life and performed a thorough feature extraction process. We tested the recognition performance using various classifiers and parameters and compared the results. The random forest algorithm emerged as the most successful, achieving a remarkable 99.875% accuracy, while the naïve Bayes algorithm had the lowest success rate with 87.625% accuracy. The new system promises to significantly improve communication for people with hearing disabilities and ensures seamless integration into daily life without compromising user comfort or lifestyle quality.

8 July 2015 in Journal of Human Sciences
Verified
Journal Article
Open access
PDF file
HÜHakan Üstünel
Hakan Üstünel
EUErdem Uçar
Erdem Uçar
TCTurhan Civelek
Turhan Civelek
İlhan Umutİlhan Umut
İlhan Umut
The research aims to investigate gifted students’ FD/FI cognitive styles and factors affecting them like preferring to take Information & Communication Technologies-based courses at gifted children’s school. The study was carried out on two groups. First group consisted of 52 students identified as gifted who are attending 6th and 7th grades at the Istanbul Science &Art Center in Istanbul, Turkey, the second group consisted of 38 students who are not identified as gifted and totally the study consists of 90 students. In order to collect data pertaining to this research, Group Embedded Figures Test (GEFT) was used to measure Field Dependence/Field Independence, (FD/FI). According to the findings of the research, it has been observed that there is a significant difference between favored gifted students’ cognitive style scores and other students’ who are not identified as gifted. There is also a significant difference between in favor of Information& Communication Technologies (ICT) based course taking gifted students’ cognitive style scores and other gifted students who are not taking ICT-based courses in Science and Art Center. In contrast to these, there is not a significant differences were found on cognitive styles in terms of gender and grade variants in both groups.

24 April 2016 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
İlhan Umutİlhan Umut
İlhan Umut
GÇGüven Çentik
Güven Çentik
The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, -nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while -nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present. The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, -nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while -nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present.

31 May 2022 in Tekirdağ Ziraat Fakültesi Dergisi
Verified
Journal Article
Closed access
DADinçer Akal
Dinçer Akal
İlhan Umutİlhan Umut
İlhan Umut
Fosil kaynakların sınırlı rezervleri, fiyatlarındaki dalgalanmalar ve çevreye verdikleri zarar, ülkeleri birincil enerji kaynaklarına alternatif arayışlarına yöneltmiştir. Sınırsız ve çevre dostu bir kaynak olan güneş enerjisi, diğer enerji kaynaklarına göre güçlü bir alternatiftir. Avrupa Birliği ülkelerinin büyük çoğunluğu güneş enerjisinden elektrik üretiminde tüketicilere birçok teşvik mekanizması ile çeşitli fırsatlar sunmakta ve yaygın olarak kullanılmasını sağlamaktadır. Dünyanın pek çok yerinde; güneş, rüzgâr, hidrojen ve jeotermal gibi yenilenebilir enerji kaynaklarına olan ilgi de artmaktadır. Tüm bunların yanında, alternatif enerji kaynaklarının kullanılması ve enerji eldesinin daha verimli hale getirilmesi için araştırmalar devam etmektedir. Güneş enerjisinden elektrik eldesi için gerekli olan ışınım değeri, gün içindeki hava durumuna ve mevsim özelliklerine göre değişmektedir. Güneş enerjisi santrallerinin kurulduğu bölgedeki iklim koşulları, fotovoltaik panellerden elde edilecek çıkış gücünü ve enerji maliyetini doğrudan etkiler. Çevresel şartlara göre fotovoltaik panellerden üretilen çıkış gücünün tahminlenmesi, güneş enerji sistemlerinin kurulumunda şirketlere rehberlik etmesi, maksimum enerji eldesi, enerjinin yönetimi ve sistemin verimli çalıştırılabilmesi için büyük önem arz etmektedir. Bu çalışmada, kurulumu yapılan fotovoltaik panellerden elde edilen veriler (Sıcaklık, Nem, Basınç, Işınım) kullanılarak güç değerlerinin tahminlenmesi için ileri beslemeli geriye yayılımlı yapay sinir ağları ve KNN (K-Nearest Neighbors) yöntemleri kullanılmıştır. Böylece gerçek saha şartlarında elde edilen panel değerleri her iki yöntemle de eğitilerek sonuçları karşılaştırılmıştır. Sonuç olarak panelin güç değerleri en yüksek %98.7945 doğrulukla geliştirilen yapay sinir ağı modeli kullanılarak sınıflandırılmıştır. Bu çalışma kapsamında geliştirilen güneş enerjisi tahmini için kullanılan makine öğrenmesi modellerinin yüksek performansa sahip olduğu ve gerçek değerlere çok yakın sonuçlar üretebildiği görülmüştür. Ayrıca belirlenen yük talebine göre farklı özelliklere sahip lokasyonlarda geliştirilen her iki yapay zekâ modelinin de kullanılabileceği sonucuna varılmıştır.