Batuhan Asiroglu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Batuhan Asiroglu has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Tolga Ensari
Arkansas Tech University, Russellville, USA
4 shared publications - Mustafa Dagtekin
İSTANBUL ÜNİVERSİTESİ-CERRAHPAŞA, MÜHENDİSLİK FAKÜLTESİ
3 shared publications Eyyup Yildiz
Computer Engineering Department, Erzincan Binali Yildı rı m University, Erzincan, Turkey
2 shared publications- Sibel Senan
İstanbul Üniversitesi-Cerrahpaşa
2 shared publications - Yagiz Nalcakan
School of Integrated Technology, Yonsei University, Incheon 21983, Republic of Korea
2 shared publications Ahmet Zencirli
Computer Engineering, Istanbul University-Cerrahpasa, Istanbul, Turkey
1 shared publication
Latest Publications
- Open Access
- 12 October 2026
- Published by Ankara University Faculty of Agriculture in Tarım Bilimleri Dergisi
- Vol. 32 (4) , 1030-1050
Early Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery
Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.
- 12 October 2026
- Published by Ankara University Faculty of Agriculture in Tarım Bilimleri Dergisi
- Vol. 32 (4) , 1030-1050
Open AccessEarly Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery
Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A Deep Learning Based Object Detection System for User Interface Code Generation
The Graphical User Interfaces (GUIs) of web applications include visuals and designs that allow users to interact with machines. Once the GUI design is done, it is necessary to generate its GUI code. However, the GUI code generation process is highly time consuming as well as highly dependent on software developers. Therefore, the development of automatic GUI code generating systems is of great importance recently. In this study, a GUI code generating system for web sites is designed using the Deep Learning (DL) approach. The dataset including “coordinate, width, height and type” of GUI objects is created using 7500 webpages. The created dataset is applied to the proposed system in order to detect objects in the GUI image and generate DSL mark-up code. Experiments were carried out to analyze the effectiveness of the proposed system and the performance evaluations were made.
- 9 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A Deep Learning Based Object Detection System for User Interface Code Generation
The Graphical User Interfaces (GUIs) of web applications include visuals and designs that allow users to interact with machines. Once the GUI design is done, it is necessary to generate its GUI code. However, the GUI code generation process is highly time consuming as well as highly dependent on software developers. Therefore, the development of automatic GUI code generating systems is of great importance recently. In this study, a GUI code generating system for web sites is designed using the Deep Learning (DL) approach. The dataset including “coordinate, width, height and type” of GUI objects is created using 7500 webpages. The created dataset is applied to the proposed system in order to detect objects in the GUI image and generate DSL mark-up code. Experiments were carried out to analyze the effectiveness of the proposed system and the performance evaluations were made.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Smart Clothing Recommendation System with Deep Learning
Recommendation systems based on machine learning are very important both customers and sellers in our daily life. Many recommendation systems need user’s previous shopping activities and digital footprints to make best recommendation purpose for next item shopping. In this study, we develop a cloth recommendation system with using only single photo of user with scalable embedded system. This study lead to important results and give new opportunities for clothing companies and advertisements. In this study, we show that how our system recommends a cloth options without user’s previous shopping act data with embedded system and machine learning. In order to recommend a cloth, we develop two inception based convolutional neural networks as prediction part and one feed forward neural network as recommender. In this study, we reach to 98% accuracy on color prediction, 86% accuracy on gender and cloth’s pattern predictions and 75% accuracy on clothing recommendation.
- 1 October 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Smart Clothing Recommendation System with Deep Learning
Recommendation systems based on machine learning are very important both customers and sellers in our daily life. Many recommendation systems need user’s previous shopping activities and digital footprints to make best recommendation purpose for next item shopping. In this study, we develop a cloth recommendation system with using only single photo of user with scalable embedded system. This study lead to important results and give new opportunities for clothing companies and advertisements. In this study, we show that how our system recommends a cloth options without user’s previous shopping act data with embedded system and machine learning. In order to recommend a cloth, we develop two inception based convolutional neural networks as prediction part and one feed forward neural network as recommender. In this study, we reach to 98% accuracy on color prediction, 86% accuracy on gender and cloth’s pattern predictions and 75% accuracy on clothing recommendation.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Scotto: Real-Time Driver Behavior Scoring Using In-Vehicle Data
This paper explores the minimal dataset to be collected from vehicles, to efficiently score drivers, using common vehicle sensors. This can lead to important results for insurance companies, advertisements and personalization. Existing work relies on several sensor information that are collected over a drive including acceleration/deceleration patterns or average trip duration. Vehicular companies make vehicular sensor information available to many external services. To explore how to score driving behaviors from such a data, we consider a system that interfaces to vehicle bus and executes supervised learning methods on this data. To facilitate this analysis, we collect invehicle data from 20 drivers on a test route and have less than %10 error in our scoring algorithm.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Scotto: Real-Time Driver Behavior Scoring Using In-Vehicle Data
This paper explores the minimal dataset to be collected from vehicles, to efficiently score drivers, using common vehicle sensors. This can lead to important results for insurance companies, advertisements and personalization. Existing work relies on several sensor information that are collected over a drive including acceleration/deceleration patterns or average trip duration. Vehicular companies make vehicular sensor information available to many external services. To explore how to score driving behaviors from such a data, we consider a system that interfaces to vehicle bus and executes supervised learning methods on this data. To facilitate this analysis, we collect invehicle data from 20 drivers on a test route and have less than %10 error in our scoring algorithm.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Automatic HTML Code Generation from Mock-Up Images Using Machine Learning Techniques
The design cycle for a web site starts with creating mock-ups for individual web pages either by hand or using graphic design and specialized mock-up creation tools. The mockup is then converted into structured HTML or similar markup code by software engineers. This process is usually repeated many more times until the desired template is created. In this study, our aim is to automate the code generation process from hand-drawn mock-ups. Hand drawn mock-ups are processed using computer vision techniques and subsequently some deep learning methods are used to implement the proposed system. Our system achieves 96% method accuracy and 73% validation accuracy.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Automatic HTML Code Generation from Mock-Up Images Using Machine Learning Techniques
The design cycle for a web site starts with creating mock-ups for individual web pages either by hand or using graphic design and specialized mock-up creation tools. The mockup is then converted into structured HTML or similar markup code by software engineers. This process is usually repeated many more times until the desired template is created. In this study, our aim is to automate the code generation process from hand-drawn mock-ups. Hand drawn mock-ups are processed using computer vision techniques and subsequently some deep learning methods are used to implement the proposed system. Our system achieves 96% method accuracy and 73% validation accuracy.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Digital Data Forgetting: A Machine Learning Approach
Digital transformation of the world goes very fast during last two decades. Today, data is power and very important. Firstly, magnetic tapes and then digital data storages have been used to collect all data. After this process, big data and its tool machine learning became very popular in both literature and industry. People use machine learning in order to obtain meaningful information from the big data. It brings valuable planning results. However, nowadays it is quite hard to collect and store all digital data to computers. This process is expensive and we will not have enough space to store data in the future. Therefore, we need and propose “Digital Data Forgetting” phrase with machine learning approach. With this digital/software solution, we will have more valuable data and will be able to erase the rest of them. We called this operation “Big Cleaning”. In this article, we use a data set to get and extract more valuable data with principal component analysis (PCA), deep autoencoder and k-nearest neighbor machine learning methods in the experimental analysis section.
- 1 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Digital Data Forgetting: A Machine Learning Approach
Digital transformation of the world goes very fast during last two decades. Today, data is power and very important. Firstly, magnetic tapes and then digital data storages have been used to collect all data. After this process, big data and its tool machine learning became very popular in both literature and industry. People use machine learning in order to obtain meaningful information from the big data. It brings valuable planning results. However, nowadays it is quite hard to collect and store all digital data to computers. This process is expensive and we will not have enough space to store data in the future. Therefore, we need and propose “Digital Data Forgetting” phrase with machine learning approach. With this digital/software solution, we will have more valuable data and will be able to erase the rest of them. We called this operation “Big Cleaning”. In this article, we use a data set to get and extract more valuable data with principal component analysis (PCA), deep autoencoder and k-nearest neighbor machine learning methods in the experimental analysis section.