Bulent Tugrul

Dr. Bulent Tugrul

Ankara University
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
10 August 2022 in Agriculture
Verified
Journal Article
Open access
PDF file
Bulent TugrulBulent Tugrul
Bulent Tugrul
El Houcine El FatimiEl Houcine El Fatimi
El Houcine El Fatimi
RERecep Eryigit
Recep Eryigit
Rapid improvements in deep learning (DL) techniques have made it possible to detect and recognize objects from images. DL approaches have recently entered various agricultural and farming applications after being successfully employed in various fields. Automatic identification of plant diseases can help farmers manage their crops more effectively, resulting in higher yields. Detecting plant disease in crops using images is an intrinsically difficult task. In addition to their detection, individual species identification is necessary for applying tailored control methods. A survey of research initiatives that use convolutional neural networks (CNN), a type of DL, to address various plant disease detection concerns was undertaken in the current publication. In this work, we have reviewed 100 of the most relevant CNN articles on detecting various plant leaf diseases over the last five years. In addition, we identified and summarized several problems and solutions corresponding to the CNN used in plant leaf disease detection. Moreover, Deep convolutional neural networks (DCNN) trained on image data were the most effective method for detecting early disease detection. We expressed the benefits and drawbacks of utilizing CNN in agriculture, and we discussed the direction of future developments in plant disease detection.

23 October 2023 in IEEE Access
Verified
Journal Article
Open access
ADAssad Souleyman Doutoum
Assad Souleyman Doutoum
Bulent TugrulBulent Tugrul
Bulent Tugrul
Leaf’s primary function is to produce nutrients through photosynthesis and support the plant’s growth. Leaf diseases caused by bacteria or other pathogens can negatively impact agricultural yields. Immediate and early diagnosis of diseases is vital for plant health. The significant development of deep learning algorithms for leaf diseases classification and detection contributed to a solid tool with a robust and reliable accuracy rate. This study presents a comprehensive review of leaf diseases research in the literature. It also highlights the gaps that need to be filled as well as the obstacles and problems facing research projects. The total number of papers retrieved from five electronic databases is 256. We analyzed and classified them into seven research questions. The results demonstrate that 63% of the papers are journal articles, 35% are conference papers, and 2% are workshop papers.

1 November 2020 in IEEE Transactions on Engineering Management
Verified
Journal Article
Closed access
MOMurat Osmanoglu
Murat Osmanoglu
Bulent TugrulBulent Tugrul
Bulent Tugrul
TDTuncay Dogantuna
Tuncay Dogantuna
Erkan BostanciErkan Bostanci
Erkan Bostanci
Price fluctuation in agricultural products that adversely affects the actors of the market is a serious issue influenced by many factors. Uncertainty in yield estimation of the products can be counted as one of the major factors. It is a fact that an effective yield estimation method may help decision-making actors to develop effective and stable production and price policies. There are traditional and remote sensing methods aimed at calculating the correct yield estimate. However, these methods produce outputs only after the sowing season of the products. In this case, decision makers do not have enough instruments in hand to ensure price stability. Generally, the existing yield estimation systems are designed in a centralized setting. However, effective tracking may not be possible due to problems in the data flow. In this article, we will propose a blockchain-based solution that carries out yield estimation of agricultural products. Our solution brings all participants interested in agriculture together and produces an early yield estimation. Thus, the necessary precautions for the excessive imbalances that may arise in agricultural products will be planned in advance.

31 January 2025 in PeerJ Computer Science
Verified
Journal Article
Open access
PDF file
ADAssad Souleyman Doutoum
Assad Souleyman Doutoum
Bulent TugrulBulent Tugrul
Bulent Tugrul
Agriculture sustains populations and provides livelihoods, contributing to socioeconomic growth. Apples are one of the most popular fruits and contains various antioxidants that reduce the risk of chronic diseases. Additionally, they are low in calories, making them a healthy snack option for all ages. However, several factors can adversely affect apple production. These issues include diseases that drastically lower yield and quality and cause farmers to lose millions of dollars. To minimize yield loss and economic effects, it is essential to diagnose apple leaf diseases accurately and promptly. This allows targeted pesticide and insecticide use. However, farmers find it difficult to distinguish between different apple leaf diseases since their symptoms are quite similar. Computer vision applications have become an effective tool in recent years for handling these issues. They can provide accurate disease detection and classification through massive image datasets. This research analyzes and evaluates datasets, deep learning methods and frameworks built for apple leaf disease detection and classification. A systematic analysis of 45 articles published between 2016 and 2024 was conducted to evaluate the latest developments, approaches, and research needs in this area.

1 October 2019
Verified
Conference Paper
Closed access
ZÖZeynep Özdemi̇r
Zeynep Özdemi̇r
Bulent TugrulBulent Tugrul
Bulent Tugrul
People throughout history have wondered their position on the world. This led to the development of Global Navigation Satellite Systems (GNSS). The most widely used is the GPS (Global Positioning System) technology. Signals emitted from GPS satellites. Calculates your own location by detecting GPS receivers on earth. The GPS data obtained in this study was sent to a remote server via GSM and GPRS and turned into a real-time tracking system. The location of the GPS device can be monitored instantly by observing the application map screen from devices such as computer and phone. This monitored location has a certain delay considering the factors such as the arrival time of the GPS data to the device and the time the device connects to the internet. The system operates with a delay of 4 - 5 seconds. In addition, the Geofence field is used to alert the device when it moves away from a specified location. As the Geofence area, a predetermined polygon on the map can be used or the polygon area drawn during the application can be used as Geofence. On the application screen, an audible warning is given when leaving the Geofence area. GPS does not always show the exact correct position; it has a certain margin of error. Many factors affect this margin of error. This causes the application to give false alarms and operate with the wrong location. In order to reduce this error, the error rate was tried to be reduced by using Kalman filter, logistic regression analysis and moving average filter. Normally the error margin of up to 15 meters is considerably reduced by these filters.

7 October 2021 in Symmetry
Verified
Journal Article
Open access
PDF file
RERecep Eryigit
Recep Eryigit
Bulent TugrulBulent Tugrul
Bulent Tugrul
We report the results of an in-depth study of 15 variants of five different Convolutional Neural Network (CNN) architectures for the classification of seeds of seven different grass species that possess symmetry properties. The performance metrics of the nets are investigated in relation to the computational load and the number of parameters. The results indicate that the relation between the accuracy performance and operation count or number of parameters is linear in the same family of nets but that there is no relation between the two when comparing different CNN architectures. Using default pre-trained weights of the CNNs was found to increase the classification accuracy by ≈3% compared with training from scratch. The best performing CNN was found to be DenseNet201 with a 99.42% test accuracy for the highest resolution image set.