Ünlü, Mehmet Zübeyir
Loading...
Profile URL
Name Variants
Unlu, M. Z.
Unlu, M.
Unlu, M
Ünlü, M
Unlu, Mehmet Zubeyir
Ünlü, MZ
Ünlü, M. Z.
Unlu, MZ
Ünlü, M.
Unlu, Mehmet
Ünlü, Mehmet
Unlu, Mehmet Z.
Ünlü, Mehmet Z.
Unlu, M.
Unlu, M
Ünlü, M
Unlu, Mehmet Zubeyir
Ünlü, MZ
Ünlü, M. Z.
Unlu, MZ
Ünlü, M.
Unlu, Mehmet
Ünlü, Mehmet
Unlu, Mehmet Z.
Ünlü, Mehmet Z.
Job Title
Email Address
zubeyirunlu@iyte.edu.tr
Main Affiliation
03.05. Department of Electrical and Electronics Engineering
Status
Current Staff
Website
ORCID ID
Scopus Author ID
Turkish CoHE Profile ID
Google Scholar ID
WoS Researcher ID
Sustainable Development Goals
1NO POVERTY
0
Research Products
2ZERO HUNGER
0
Research Products
3GOOD HEALTH AND WELL-BEING
1
Research Products
4QUALITY EDUCATION
0
Research Products
5GENDER EQUALITY
0
Research Products
6CLEAN WATER AND SANITATION
0
Research Products
7AFFORDABLE AND CLEAN ENERGY
0
Research Products
8DECENT WORK AND ECONOMIC GROWTH
1
Research Products
9INDUSTRY, INNOVATION AND INFRASTRUCTURE
0
Research Products
10REDUCED INEQUALITIES
0
Research Products
11SUSTAINABLE CITIES AND COMMUNITIES
0
Research Products
12RESPONSIBLE CONSUMPTION AND PRODUCTION
0
Research Products
13CLIMATE ACTION
0
Research Products
14LIFE BELOW WATER
0
Research Products
15LIFE ON LAND
0
Research Products
16PEACE, JUSTICE AND STRONG INSTITUTIONS
0
Research Products
17PARTNERSHIPS FOR THE GOALS
0
Research Products
Documents
21
Citations
184
h-index
6
Documents
1
Citations
0
Scholarly Output
17
Articles
8
Views / Downloads
26378/7783
Supervised MSc Theses
3
Supervised PhD Theses
0
WoS Citation Count
116
Scopus Citation Count
127
Patents
0
Projects
1
WoS Citations per Publication
6.82
Scopus Citations per Publication
7.47
Open Access Source
10
Supervised Theses
3
| Journal | Count |
|---|---|
| 2017 25th Signal Processing and Communications Applications Conference, SIU 2017 | 1 |
| 2024 IEEE International Conference on Cognitive Computing and Complex Data -- SEP 28-30, 2024 -- Qinzhou, PEOPLES R CHINA | 1 |
| 24th Signal Processing and Communication Application Conference, SIU 2016 | 1 |
| 25th Signal Processing and Communications Applications Conference, SIU 2017 | 1 |
| 25th Signal Processing and Communications Applications Conference (SIU) -- MAY 15-18, 2017 -- Antalya, TURKEY | 1 |
Current Page: 1 / 3
Scopus Quartile Distribution
Competency Cloud
17 results
Scholarly Output Search Results
Now showing 1 - 10 of 17
Article Citation - WoS: 2Citation - Scopus: 3Handwriting Recognition by Derivative Dynamic Time Warping Methodology Via Sensor-Based Gesture Recognition(Maejo University, 2022) Tunçer, Esra; Ünlü, Mehmet ZübeyirA handwritten character recognition methodology based on signals of acceleration obtained from gesture sensors with dynamic time warping (DTW) is presented. After applying the preprocessing steps of filtering, character separation and normalisation, similarities are detected by DTW and each signal component corresponding to a character is classified. However, the nature of the writing process may induce additional time-shifting problems among repetitions of characters since DTW uses only the amplitude values of signals to calculate the distance between them. Accordingly, when signals have different acceleration and deceleration values, irrelevant points of the signals may match each other just because their amplitude values are close. To overcome this problem, derivative dynamic time warping (DDTW) methodology is also implemented. The methodologies mentioned as well as the linear alignment approach were tested with Euclidean, Manhattan and Chessboard distance metrics to detect user-dependent/independent acceleration signals of lower-case characters of the English alphabets and digits. Recognition accuracy rates of Euclidean and Chessboard metrics with DDTW are 98.65%, which is the highest value among all methods applied and metrics. The comparison of Euclidean and Chessboard durations shows that Chessboard with DDTW is the most efficient method in terms of time.Article An AI-Based Solution for Warehouse Safety: Video Surveillance System Based Anomaly Detection in Equipment-Human Interactions with Vanilla Autoencoder(Elsevier Ltd, 2025) Elçi, T.; Unlu, M.The significant growth of the logistics sector in recent years has resulted in the expansion of warehouse operations and an increased use of equipment, leading to a rise in workplace accidents. These incidents are predominantly attributed to factors such as carelessness, fatigue, high work intensity, individual behaviors, lack of experience, insufficient training, and employee negligence. To enhance warehouse safety, it is essential to implement a system capable of real-time prediction of human-equipment interactions. This study proposes a comprehensive video surveillance framework designed to improve occupational safety in warehouse environments. The system integrates key components, including object detection, object tracking, action recognition, and alarm classification, to effectively reduce risks and prevent accidents.The system employs YOLOv7, a deep learning model with the ability to quickly and accurately detect objects in a single network pass, as the object detection methodology, and DeepSORT, an algorithm for object tracking that assigns unique identifiers to each object and utilizes deep learning techniques to improve tracking performance. The action detection component of the system introduces a novel approach by analyzing and identifying actions and movements while detecting anomalies and potential risks. By leveraging features such as the speed, tags, movement direction, and coordinate data of individuals and equipment, the system estimates alarm levels and generates corresponding alarms, providing an innovative and dynamic solution for real-time risk assessment. The system, tested to demonstrate technological capabilities such as real-time responsiveness and high operational success rates, is designed to predict accidents in warehouse environments, generate alarms, and significantly reduce the risk of occupational accidents. © 2025 The Franklin Institute. Published by Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.Master Thesis Video Surveillance System Based on Action and Event Recognition With Moving Object Detection and Tracking(01. Izmir Institute of Technology, 2024) Elçi, Tuğçe; Ünlü, Mehmet ZübeyirLojistik sektörünün son yıllarda hızla büyümesi, depo alanlarının genişlemesine ve kullanılan ekipman sayısının artmasına neden olarak iş kazalarının artmasına neden olmuştur. Depolarda meydana gelen iş kazaları çoğunlukla dikkatsizlik, yorgunluk, yoğun iş temposu, bireysel davranışlar, deneyim eksikliği, yetersiz eğitim ve çalışanların ihmalinden kaynaklanmaktadır. Bu nedenle depo içi emniyetin sağlanması için insan ve ekipman etkileşimini gerçek zamanlı olarak tahmin eden bir sisteme ihtiyaç vardır. Tez kapsamında depo ortamlarında iş güvenliğini artıracak nesne algılama, nesne izleme, eylem algılama ve alarm sınıflandırma bileşenlerinden oluşan kapsamlı bir video gözetim sistemi önerilmektedir. Bu sistemde nesne tespit metodolojisi olarak kullanılan YOLOv7, nesneleri tek bir ağ geçişinde hızlı ve doğru bir şekilde tespit eden bir derin öğrenme modelidir. Deep SORT ise izlenen her nesneye benzersiz bir tanımlayıcı atayan ve izleme sırasında derin öğrenmeyi kullanan bir bilgisayarlı görme izleme teknolojisidir. Sistemin eylem algılama kısmı, anormallikleri ve potansiyel riskleri tanıyarak eylemleri ve hareketleri tanımlamak ve analiz etmek için tasarlanmıştır. Bu bölümde insan ve ekipmanların hız, etiket, hareket yönü ve koordinat bilgileri kullanılarak çeşitli alarm seviyeleri tahmin edilmekte ve bu tahmini alarm seviyelerine bağlı olarak da farklı alarm seviyeleri üretilmektedir. Gerçek zamanlı müdahale ve yüksek başarı oranıyla çalışabilme gibi teknolojik yeterlilikleri sağlaması test edilen bu sistem sayesinde depolardaki kazalar tahmin edilecek, alarmlar üretilecek ve olası iş kazaları büyük ölçüde önlenebilecektir.Article Citation - WoS: 1Citation - Scopus: 2Dinamik Zaman Bükme Metodu Kullanarak İvmeölçer Tabanlı El Yazısı Karakter Tanıma(Institute of Electrical and Electronics Engineers Inc., 2016) Tunçer, Esra; Ünlü, Mehmet ZübeyirBu çalışmada, ivmeölçer kullanılarak el yazısı ile yazılan karakterlerin tanınması yapılmıştır. Karakter tanıma çalışmalarında genellikle kullanılan görüntü işleme teknikleri yerine, bu projede yazıyı yazan kişinin yazma hareketlerinden elde edilen veriler kullanılmıştır. Kişinin yazıyı yazma hareketlerini elde edebilmek için 3 eksenli ivmeölçer kullanılmış ve buradan elde edilen verilerle karakterler Dinamik Zaman Bükme yöntemiyle tanınmıştır. İvmeölçer ile elde edilen veriler genellikle gürültülü veriler olduğundan verilere tanıma işleminden önce filtreleme, bölütleme ve normalizasyon gibi ön işleme teknikleri uygulanmıştır. Yapılan deneysel çalışmalarda %98,08’lik doğru tanıma oranına ulaşılmıştır.Conference Object İskelet Dal Noktaları Kullanan Entropik Çizgelerde Çakıştırma ve Optimizasyon(Institute of Electrical and Electronics Engineers Inc., 2017) Ergün, Aslı; Ergün, Serkan; Ünlü, Mehmet Zübeyir; Güngör, CengizGörüntü çakıştırma işleminde görüntülerin ne kadar benzediklerinin ve iki görüntü arasındaki benzerliği maksimuma getiren kayma, dönme ve ölçeklendirme dönüşüm parametre değerlerinin bulunması gerekmektedir. Benzerlik ölçütü ve buna bağlı parametreler hesaplanırken entropik çizge diye adlandırılan, bilgi teorisi tabanlı ölçütlerin çizge üzerinde yakınsama yöntemleri kullanılabilir. Bu çalışmada, farklı entropik çizgeler üzerinde benzerlik ve optimizasyon ölçütleri karşılaştırılmış ve çizge oluşturmak için iskelet dal öznitelik noktalarının kullanılmasının başarılı sonuçlar verdiği görülmüütür.Article Citation - WoS: 21Citation - Scopus: 26Computerized Method for Nonrigid Mr-To Breast-Image Registration(Elsevier Ltd., 2010) Ünlü, Mehmet Zübeyir; Krol, A.; Magri, A.; Mandel, J. A.; Lee, W.; Baum, K. G.; Lipson, E. D.; Coman, I. L.; Feiglin, D. H.We have developed and tested a new simple computerized finite element method (FEM) approach to MR-to-PET nonrigid breast-image registration. The method requires five-nine fiducial skin markers (FSMs) visible in MRI and PET that need to be located in the same spots on the breast and two on the flanks during both scans. Patients need to be similarly positioned prone during MRI and PET scans. This is accomplished by means of a low gamma-ray attenuation breast coil replica used as the breast support during the PET scan. We demonstrate that, under such conditions, the observed FSM displacement vectors between MR and PET images, distributed piecewise linearly over the breast volume, produce a deformed FEM mesh that reasonably approximates nonrigid deformation of the breast tissue between the MRI and PET scans. This method, which does not require a biomechanical breast tissue model, is robust and fast. Contrary to other approaches utilizing voxel intensity-based similarity measures or surface matching, our method works for matching MR with pure molecular images (i.e. PET or SPECT only). Our method does not require a good initialization and would not be trapped by local minima during registration process. All processing including FSMs detection and matching, and mesh generation can be fully automated. We tested our method on MR and PET breast images acquired for 15 subjects. The procedure yielded good quality images with an average target registration error below 4 mm (i.e. well below PET spatial resolution of 6-7 mm). Based on the results obtained for 15 subjects studied to date, we conclude that this is a very fast and a well-performing method for MR-to-PET breast-image nonrigid registration. Therefore, it is a promising approach in clinical practice. This method can be easily applied to nonrigid registration of MRI or CT of any type of soft-tissue images to their molecular counterparts such as obtained using PET and SPECT. © 2009 Elsevier Ltd. All rights reserved.Master Thesis Design of an Offline Ottoman Character Recognition System for Translating Printed Documents To Modern Turkish(Izmir Institute of Technology, 2019) Küçükşahin, Naz; Ünlü, Mehmet ZübeyirOptical character recognition (OCR) is one of the most studied topics for many years. As a result of these studies, systems developed especially for the Latin alphabet have become more accurate even for handwritten texts. However, there are very limited studies on Ottoman OCR systems in the literature and it is still a subject of interest due to the complexity of the language in grammar, writing and spelling. In this thesis, it is aimed to design an offline OCR system that recognizes Ottoman characters using deep convolutional neural networks. The proposed work consists of several steps such as image processing, image digitization and character segmentation, adaptation of inputs to the network, training of the network, recognition and evaluation of results. Firstly, a character dataset was created by segmenting text images of different lengths that was selected among scanned samples of various Ottoman literature from the digital database of Turkish National Library. Two convolutional neural networks of different complexity were trained with the created character dataset and the relationship between recognition rates and network complexity was evaluated. Secondly, using the Histogram of Oriented Gradients and Principal Component Analysis, the features of the created dataset were extracted and the Ottoman characters were classified with k-Nearest Neighbor Algorithm and Support Vector Machines which are widely used classification methods in the literature. The performed analyzes have shown that both networks provide acceptable recognition rates compared to the conventional classifiers, however complex deep neural network showed better accuracy and lower loss.Article Vision-Language Model Approach for Few-Shot Learning of Attention Deficit Hyperactivity Disorder Using EEG Connectivity-Based Featured Images(IOP Publishing Ltd, 2025) Catal, Mehmet Sergen; Gumus, Abdurrahman; Karabiber Cura, Ozlem; Aydin, Ocan; Zubeyir Unlu, MehmetTraditional medical diagnosis approaches have predominantly relied on single-modality analysis, limiting clinicians to interpreting isolated data streams such as images or time series. The integration of vision language models (VLMs) into neurophysiological analysis represents a paradigm shift toward multimodal diagnostic frameworks, enabling clinicians to interact with diagnosis models through diverse modalities including text, audio, visual inputs, etc. This multimodal interaction capability extends beyond conventional label-based classification, offering clinicians flexibility in diagnostic reasoning and decision-making processes. Building on this foundation, this study explores the application of VLMs to electroencephalography (EEG)-based attention deficit hyperactivity disorder (ADHD) classification, addressing a gap in neurophysiological diagnostics. The proposed framework applies VLM-based few-shot ADHD classification by converting raw EEG data into EEG connectivity-based featured images compatible with contrastive language-image pre-training's (CLIP) image encoder. The adaptor-based CLIP approach (Tip-Adapter and Tip-Adapter-F) for few-shot learning improves CLIP's zero-shot classification performance, achieving 78.73% accuracy with 1-shot and 98.30% accuracy with 128-shot using the RN50x16 backbone. Experiments investigate prompt engineering effects, backbone architectures of CLIP, patient-based classification, and combinations of EEG connectivity features. Comparative analysis is performed with two datasets to evaluate the approach between different data sources. Through the adaptation of pre-trained VLMs to neurophysiological data, this technique demonstrates the potential for multimodal diagnostic frameworks that enable flexible clinician-model interactions beyond conventional label-based classification systems. The approach achieves effective ADHD classification with minimal training data while establishing foundations for applying VLMs in clinical neuroscience, where diverse modality interactions through text, visual, and audio inputs can enhance diagnostic workflows. The code is publicly available on GitHub to facilitate further research in the field: https://github.com/miralab-ai/vlm-few-shot-eeg.Conference Object Registration and Optimization in Fintropic Graphs Using Branch Skeleton Features(Institute of Electrical and Electronics Engineers Inc., 2017) Ergün, Aslı; Ergün, Serkan; Ünlü, Mehmet Zübeyir; Güngör, CengizIn image registration process, it is necessary to find the similarity of the images and thetranslation, rotation and scaling transformation parameter values that maximize the similarity between the two images. When the similarity measure and related parameters are calculated, information theory based entropic graphs can be used. In this study, similarity and optimization measures are compared on different entropic graphs. It has been seen that skeleton branch feature points to build entropic graphs give successful results.Article A Saliency-Weighted Orthogonal Regression-Based Similarity Measure for Entropic Graphs(Springer, 2019) Ergün, Aslı; Ergün, Serkan; Ünlü, Mehmet Zübeyir; Güngör, CengizVarious measures are used to determine similarity ratios among images before and after image registration. Image registration methods are based on finding the translation, rotation, and scaling parameters that maximize the similarity between two images by taking advantage of the feature points and densities that are found. While the similarity criterion is calculated, it is possible and advantageous to use approximation methods on the graphs based on information theory. The current study proposes a new similarity measure based on saliency-weighted orthogonal regression derived from the weighted sums of the saliency map of the orthogonal regression residuals formed on the entropic graph. It is evaluated in terms of both quantitative and qualitative methods and compared with other graph-based similarity measures.