Halim Ferit Bayata

Dr. Halim Ferit Bayata

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
15 February 2024 in International Journal of Engineering and Geosciences
Verified
Journal Article
Open access
PDF file
ÖAÖzlem Akar
Özlem Akar
ESEkrem Saralioglu
Ekrem Saralioglu
OGOğuz Güngör
Oğuz Güngör
HBHalim Ferit Bayata
Halim Ferit Bayata
The Erzincan (Cimin) grape, which is an endemic product, plays a significant role in the economy of both the region it is cultivated in and the overall country. Therefore, it is crucial to closely monitor and promote this product. The objective of this study was to analyze the spatial distribution of vineyards by utilizing advanced machine learning and deep learning algorithms to classify high-resolution satellite images. A deep learning model based on a 3D Convolutional Neural Network (CNN) was developed for vineyard classification. The proposed model was compared with traditional machine learning algorithms, specifically Support Vector Machine (SVM), Random Forest (RF), and Rotation Forest (ROTF). The accuracy of the classifications was assessed through error matrices, kappa analysis, and McNemar tests. The best overall classification accuracies and kappa values were achieved by the 3D CNN and RF methods, with scores of 86.47% (0.8308) and 70.53% (0.6279) respectively. Notably, when Gabor texture features were incorporated, the accuracy of the RF method increased to 75.94% (0.6364). Nevertheless, the 3D CNN classifier outperformed all others, yielding the highest classification accuracy with an 11% advantage (86.47%). The statistical analysis using McNemar's test confirmed that the χ2 values for all classification outcomes exceeded 3.84 at the 95% confidence interval, indicating a significant enhancement in classification accuracy provided by the 3D CNN classifier. Additionally, the 3D CNN method demonstrated successful classification performance, as evidenced by the minimum-maximum F1-score (0.79-0.97), specificity (0.95-0.99), and accuracy (0.91-0.99) values.

1 October 2020 in Proceedings of the Institution of Civil Engineers - Transport
Verified
Journal Article
Closed access
OBOsman Ünsal BAYRAK
Osman Ünsal BAYRAK
HBHalim Ferit Bayata
Halim Ferit Bayata
The choice of intersection type in a road network is one of the most important decisions to be made in transportation engineering. Capacity and level of service are the two main factors considered in the type of intersection design, but safety and economy should also be taken into account when determining the intersection type since these are equally important. A number of parameters can be used to evaluate the performance of an intersection, including travel time, average delay, queue length, fuel consumption and vehicle exhaust emissions. Adding safety and construction costs to these parameters makes decision-making more difficult. In this study, the analytic hierarchy process (AHP) was used as a multi-criteria decision approach to overcome this problem. Three intersection types were modelled and tested using Vissim software in line with the above parameters. An AHP model was then generated using the Vissim results and the AHP results and applicability were analysed.

24 November 2022 in Coatings
Verified
Journal Article
Open access
PDF file
FBFatih İrfan BAŞ
Fatih İrfan BAŞ
OBOsman Ünsal BAYRAK
Osman Ünsal BAYRAK
HBHalim Ferit Bayata
Halim Ferit Bayata
This study aimed to determine the material properties and the thickness of the layers of an unbonded jointed plain concrete pavement design over a deteriorated flexible pavement that lost its service capability. Maximum principal stresses occurring under the concrete pavement should not exceed the modulus of rupture of the concrete. Three-dimensional finite element analyses using ANSYS (Release 18.1 SAS IP, Inc.) software were carried out with the Taguchi method. The most reliable solution for the pavement design was investigated with whole configuration axle loading that reflects the realistic traffic situation. The stress values under the concrete slab due to the positive temperature gradient neglected in the American Association of State Highway and Transportation Officials (AASHTO) method were also investigated. The concrete slabs are exposed to these stresses for longer than the axle loads. Temperature distributions throughout the thickness of the concrete slab were calculated with the bilinear formulas suggested in the study. Axle loadings were applied on both the pavement edge and corner to reflect the most critical loading condition in the pavement design. The critical axle type was found to be 1.2. It was observed that a 0.15 m concrete thickness was appropriate for the concrete class, joint spacing and hot mix asphalt (HMA) elasticity modulus levels used for the 1.22, 1.122, and 1.2 + 111 axle types, but it was not appropriate for the 1.2 axle types. The slab thicknesses calculated with the AASHTO method, and the finite element method were found to be close to each other. It was determined that the concrete thickness significantly affected the maximum principal stress, with a performance statistic (S/N) value of 1692 for the 1.2 axle type. This was followed by the modulus of elasticity of the concrete with an S/N value of 0.356, the modulus of elasticity of the existing flexible pavement with an S/N value of 0.244, and the concrete joint spacing with an S/N value of 0.105. A practical design guide was recommended to extend the service life of a highly deteriorated flexible pavement with the construction of unbonded jointed plain concrete.

4 December 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
OOOmer Faruk Oztürk
Omer Faruk Oztürk
Yusuf MazlumYusuf Mazlum
Yusuf Mazlum
Metin Mutlu AYDINMetin Mutlu AYDIN
Metin Mutlu AYDIN
Emine CoruhEmine Coruh
Emine Coruh
HBHalim Ferit Bayata
Halim Ferit Bayata
Recent advances in tunnel infrastructure have emphasized safety, operational efficiency and low operating costs. Modern tunnels are equipped with systems to improve both safety and operational performance. This study investigates the effect of tunnel lighting and vehicle breakdown scenarios on driver lane changing behaviour (LCB) using a driving simulator modelled on the third longest twin-tube tunnel. Data were collected from 125 drivers considering various driver characteristics with different lighting conditions and the presence of a stopped vehicle in a lane. The results show that drivers tend to slow down and change lanes more safely in response to red and flashing lights. In contrast, blue sky lights, which are designed to reduce stress and compare with other dangerous scenarios, had no significant effect on LCB. In addition, demographic factors such as gender and previous simulator experience played a role in influencing LCB tendencies. Female drivers and those familiar with simulators showed more cautious behaviour. The findings showed valuable insights into how tunnel lighting systems can improve safety. Results highlighted the potential for dynamic lighting and targeted driver training programs to improve tunnel safety. All these findings may contribute to ongoing efforts to improve traffic management and reduce accidents in tunnel environments.

2 February 2021 in Sādhanā
Verified
Journal Article
Closed access
PDF file
ADAhmet Oğuz Demiriz
Ahmet Oğuz Demiriz
OBOsman Ünsal BAYRAK
Osman Ünsal BAYRAK
HBHalim Ferit Bayata
Halim Ferit Bayata

29 June 2024 in Iranian Journal of Science and Technology, Transactions of Civil Engineering
Verified
Journal Article
Closed access
PDF file
HBHalim Ferit Bayata
Halim Ferit Bayata
FBFatih İrfan Baş
Fatih İrfan Baş
GMGamze Şeyda Mengi
Gamze Şeyda Mengi