Nilüfer Yurtay

Dr. Nilüfer Yurtay

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
12 June 2023 in Engineering Science and Technology, an International Journal
Verified
Journal Article
Open access
Esin Ayşe ZAİMOĞLUEsin Ayşe ZAİMOĞLU
Esin Ayşe ZAİMOĞLU
NYNilüfer Yurtay
Nilüfer Yurtay
HDHüseyin Demirci
Hüseyin Demirci
YYYüksel Yurtay
Yüksel Yurtay

21 December 2022 in Arabian Journal for Science and Engineering
Verified
Journal Article
Closed access
PDF file
HDHüseyin Demirci
Hüseyin Demirci
NYNilüfer Yurtay
Nilüfer Yurtay
YYYüksel Yurtay
Yüksel Yurtay
Esin Ayşe ZAİMOĞLUEsin Ayşe ZAİMOĞLU
Esin Ayşe ZAİMOĞLU

4 March 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AYAli YILMAZ
Ali YILMAZ
YYYüksel Yurtay
Yüksel Yurtay
NYNilüfer Yurtay
Nilüfer Yurtay
AYOLO introduces a novel fusion architecture that integrates unsupervised learning techniques with Vision Transformers, leveraging the YOLO series models as its foundation. This innovation enables the effective utilization of rich, unlabeled data, establishing a new pretraining methodology tailored to YOLO architectures. On a custom dataset comprising 80 images of poppy plants, AYOLO achieved a remarkable Average Precision (AP) of 38.7% while maintaining a high rendering speed of 239 FPS (Frames Per Second) on a Tesla K80 GPU. Real-time performance is demonstrated by achieving 239 FPS, and feature fusion optimally combines spatial and semantic information across scales. This performance surpasses the previous state-of-the-art YOLO v6-3.0 by +2.2% AP while retaining comparable speed. AYOLO exemplifies the potential of integrating advanced information fusion techniques with supervised pretraining, significantly enhancing precision and efficiency for object detection models optimized for small, specialized datasets.

1 September 2023 in Turkish Journal of Civil Engineering
Verified
Journal Article
Open access
PDF file
ZKZeliha Cagla Kuyumcu
Zeliha Cagla Kuyumcu
HAHAKAN ASLAN
HAKAN ASLAN
NYNilüfer Yurtay
Nilüfer Yurtay
This study aims to investigate the possible relationships of risk factors related to traffic accidents playing important roles in increasing the likelihood of accidents. In the previous studies, parametric models are mostly used to investigate the causes of traffic accidents. As a non-parametric data mining model with its increasing usage in recent years; association rule mining was employed in this study to analyse the traffic accident data for the period of 2015 and 2020 in the city of Sakarya, Turkey. The analysis of the data studied revealed the relationships among the external/environmental, driver, road, vehicle and nature of accident factors. Some important rules regarding accidents occurring on daylight came into prominence within the scope of this study. In addition, the correlations between the driver casualties and their education level and ages are established to be related. The findings are beneficial for transportation authorities to apply effective operational strategies and campaigns to increase the road safety.

14 December 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ZKZeliha Cagla Kuyumcu
Zeliha Cagla Kuyumcu
HAHAKAN ASLAN
HAKAN ASLAN
NYNilüfer Yurtay
Nilüfer Yurtay
The number of traffic accidents in a region rises as the vehicle–km value in traffic increases. Furthermore, since automobiles make up the highest proportion of vehicles in traffic, they represent the greatest weight in traffic accidents. This study aims to establish a model to predict the driver’s status (survived–injured–dead) as a result of the fatal-injury type of accident. The size of the vehicles suppresses the direct factors related to drivers by having a significant and dominant effect on the analysis of the results of the accidents by concealing the other important factors which must be taken into consideration with regard to the casualty levels of the drivers. Consequently, this paper focuses on automobiles, which are the most frequently involved vehicle type in accidents. Furthermore, the dataset representing the accidents that occurred in Turkey between 2015 and 2021 was employed for the analysis of the effects of the attributes of the drivers on the outcome of casualties for automobile-related accidents alone. The uniqueness of this research stems from being the first study in Turkey to investigate the severity levels of the drivers involved in automobile-related accidents. In addition, this study highlights the preventable factors investigated relatively less than other factors in the literature in order to establish a successful model. The difference between the success of the models with regard to accuracy obtained through dominant and investigated factors is only 5.0%. Random Forests, Naïve Bayes, and CHAID (Chi-squared Automatic Interaction Detection) models were established and compared as decision tree algorithms. The results revealed the fact that the CHAID model produced the most successful outcomes among them. Driver fault, gender, education level, and age, along with alcohol usage and surface condition, were found to be significant influential factors for the severity of traffic accidents.

1 December 2021 in Interactive Learning Environments
Verified
Journal Article
Closed access
EBEsra Çoban Budak
Esra Çoban Budak
NYNilüfer Yurtay
Nilüfer Yurtay
YBYusuf Budak
Yusuf Budak
AGAynur Kolburan Geçer
Aynur Kolburan Geçer
In a world designed for non-disabled people, visually impaired students (VIS), have to overcome difficulties such as content and exam formats, in their education life. The aim of this study is to determine the usefulness level of the online voice-assisted exam system (OVAES), which was designed and developed by the researchers with reference to the Universal Design Model (UDM). A scanning model with a semi-structured interview form is applied to collect the visually impaired students’ views on the usefulness of this system. Fourteen visually impaired students regularly participated in the practice tests on a voluntary basis. While the frequency, percentage, mean and standard deviation values were used in the analysis of quantitative data, content analysis was performed on the qualitative data obtained with open-ended questions. According to the findings, it is determined that the voice-assisted exam system is suitable for usage habits. The contribution of system components such as audio support, keyboard support, screen reading to the comprehensibility of the content are significantly positive. The study validated the hypothesis that the participants can carry out online assessment and evaluation activities alone with the help of biometric data on customizable online pages, regardless of location, without the need for another person.