Researcher:
Can, Yekta Said

Profile Picture
ORCID

Job Title

Researcher

First Name

Yekta Said

Last Name

Can

Name

Name Variants

Can, Yekta Said

Email Address

Birth Date

Filters

2020 - 202218

Advanced Search

Filter by

Settings

Researcher Of Publications: search.filters.isAuthorOfPublication.cb5ab2a0-245b-4d38-bf86-e979c89e511f

Search Results

Now showing 1 - 10 of 18
  • Placeholder
    PublicationMetadata only
    End-to-end deep multi-modal physiological authentication with smartbands
    (IEEE-Inst Electrical Electronics Engineers Inc, 2021) Ekiz, Deniz; Dardağan, Yağmur Ceren; Aydar, Furkan; Köse, Rukiye Dilruba; Ersoy, Cem; N/A; Can, Yekta Said; Researcher; College of Social Sciences and Humanities; N/A
    The number of fitness tracker users increases every day. Most of the applications require authentication to protect privacy-preserving operations. Biometrics such as face images have been used widely as login tokens, but they have privacy issues. Moreover, occlusions like face masks used for COVID may reduce their effectiveness. Smartbands can track heart rate, movements, and electrodermal activities. They have been widely used for health-related applications. The use of smartbands for authentication is in the exploratory stage. Physiological signals gathered from smartbands may be used to create a multi-modal and multi-sensor authentication system. The popularity of smartbands enables us to deploy new applications without a need to buy additional hardware. In this study, we explore the multi-modal physiological biometrics with end-to-end deep learning and feature-based traditional systems. We collected multi-modal physiological data of 80 people for five days using modern smartbands. We applied a deep learning approach to the multi-modal physiological data and used feature-based traditional machine learning classifiers. The CNN-LSTM model achieved a 9.31% equal error rate and outperformed other models in terms of authentication performance.
  • Placeholder
    PublicationMetadata only
    Privacy-preserving federated deep learning for wearable IoT--based biomedical monitoring
    (Association for Computing Machinery (ACM), 2021) Ersoy, Cem; N/A; Can, Yekta Said; Researcher; College of Social Sciences and Humanities; N/A
    IoT devices generate massive amounts of biomedical data with increased digitalization and development of the state-of-the-art automated clinical data collection systems. When combined with advanced machine learning algorithms, the big data could be useful to improve the health systems for decision-making, diagnosis, and treatment. Mental healthcare is also attracting attention, since most medical problems can be associated with mental states. Affective computing is among the emerging biomedical informatics fields for automatically monitoring a person's mental state in ambulatory environments by using physiological and physical signals. However, although affective computing applications are promising to improve our daily lives, before analyzing physiological signals, privacy issues and concerns need to be dealt with. Federated learning is a promising candidate for developing high-performance models while preserving the privacy of individuals. It is a privacy protection solution that stores model parameters instead of the data itself and abides by the data protection laws such as EU General Data Protection Regulation (GDPR) and California Consumer Privacy Act (CCPA). We applied federated learning to heart activity data collected with smart bands for stress-level monitoring in different events. We achieved encouraging results for using federated learning in IoT-based wearable biomedical monitoring systems by preserving the privacy of the data.
  • Placeholder
    PublicationMetadata only
    Automatic detection of road types from the third military mapping survey of Austria-Hungary historical map series with deep convolutional neural networks
    (IEEE-inst Electrical Electronics Engineers inc, 2021) N/A; N/A; Department of History; Can, Yekta Said; Gerrits, Petrus Johannes; Kabadayı, Mustafa Erdem; Resercher; Master Student; Faculty Member; Department of History; College of Social Sciences and Humanities; Graduate School of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; N/A; 33267
    With the increased amount of digitized historical documents, information extraction from them gains pace. Historical maps contain valuable information about historical, geographical and economic aspects of an era. Retrieving information from historical maps is more challenging than processing modern maps due to lower image quality, degradation of documents and the massive amount of non-annotated digital map archives. Convolutional Neural Networks (CNN) solved many image processing challenges with great success, but they require a vast amount of annotated data. for historical maps, this means an unprecedented scale of manual data entry and annotation. in this study, we first manually annotated the Third Military Mapping Survey of austria-Hungary historical map series conducted between 1884 and 1918 and made them publicly accessible. We recognized different road types and their pixel-wise positions automatically by using a CNN architecture and achieved promising results.
  • Placeholder
    PublicationMetadata only
    Text detection and recognition by using CNNs in the Austro-Hungarian historical military mapping survey
    (Association for Computing Machinery, 2021) Department of History; N/A; Kabadayı, Mustafa Erdem; Can, Yekta Said; Faculty Member; Researcher; Department of History; College of Social Sciences and Humanities; College of Social Sciences and Humanities; 33267; N/A
    Historical maps include precious data about historical, geographical and economic perspectives of a period. However, several unique challenges and opportunities accompany historical maps compared to modern maps, such as low-quality images, degraded manuscripts and the huge quantity of non-annotated digital map collections. In the recent decade, Convolutional Neural Networks (CNNs) are applied to solve various image processing problems, but they need enormous annotated data to have accurate results. In this work, we annotated text regions of the Third Military Mapping Survey of Austria-Hungary historical map series conducted between 1884 and 1918 manually and made them accessible for researchers. Then, we detected the pixel-wise positions of text regions by employing the deep neural network architecture and recognized them with encouraging error rates.
  • Placeholder
    PublicationMetadata only
    CNN-based page segmentation and object classification for counting population in ottoman archival documentation
    (Multidisciplinary Digital Publishing Institute (MPDI), 2020) Department of History; N/A; Kabadayı, Mustafa Erdem; Can, Yekta Said; Faculty Member; Researcher; Department of History; College of Social Sciences and Humanities; College of Social Sciences and Humanities; 33267; N/A
    Historical document analysis systems gain importance with the increasing efforts in the digitalization of archives. Page segmentation and layout analysis are crucial steps for such systems. Errors in these steps will affect the outcome of handwritten text recognition and Optical Character Recognition (OCR) methods, which increase the importance of the page segmentation and layout analysis. Degradation of documents, digitization errors, and varying layout styles are the issues that complicate the segmentation of historical documents. The properties of Arabic scripts such as connected letters, ligatures, diacritics, and different writing styles make it even more challenging to process Arabic script historical documents. In this study, we developed an automatic system for counting registered individuals and assigning them to populated places by using a CNN-based architecture. To evaluate the performance of our system, we created a labeled dataset of registers obtained from the first wave of population registers of the Ottoman Empire held between the 1840s and 1860s. We achieved promising results for classifying different types of objects and counting the individuals and assigning them to populated places.
  • Placeholder
    PublicationMetadata only
    Developing an automatic layout analysis system for Ottoman population registers
    (IEEE, 2020) Can, Yekta Said; Kabadayı, Mustafa Erdem; Researcher; Faculty Member; College of Social Sciences and Humanities; N/A; 33267
    For extracting information from the historical documents, digitization efforts have increased dramatically in the recent decades. Accurate layout analysis will help researchers for developing more robust HTR and OCR techniques which will extract meaningful information from these documents. Variable layouts, low quality and distorted images of historical documents create different problems to deal with when compared to modern document processing. Arabic script features have even more problems for these automatic processing systems. In this study, we have developed a tool for automatically analyzing the layouts of the first Ottoman population registers which are written in Arabic script form. We built a dataset for testing the performance of our system which are chosen from the first population records of the Ottoman Empire between the 1840s and 1860s. We successfully classified two different object types in those documents.
  • Placeholder
    PublicationMetadata only
    Classification of original and counterfeit gold matters by applying deep neural networks and support vector machines
    (Uludağ Üniversitesi Mühendislik Fakültesi, 2022) N/A; Can, Yekta Said; Researcher; College of Social Sciences and Humanities; N/A
    Gold is one of the most counterfeited precious metals. The color of copper is like gold. For this reason, copper is one of the most used materials for color counterfeiting. When the chemical properties are concerned, wolfram is like gold (density of gold and tungsten are 19.30 g/ml and 19.25 g/ml, respectively), so it can be used as a chemical counterfeit. The purity of gold can be determined by X-ray, but this method is costly. The current low-cost methods of jewelers have been experimented with for counterfeit gold detection in this paper. When a gold matter is hit by a subject, the sound frequency is higher than the frequency of sound when the same experiment is done with copper. Furthermore, counterfeit gold color is brighter than real ones. The color of gold is unique, and it is called "gold yellow". In this research, by employing sound and image processing, counterfeit and original gold are differentiated. For the image processing part, first a Convolutional Neural Network (CNN)-based toolbox for segmenting the gold material is applied. Then, deep CNNs for differentiating the color of the gold and copper materials are employed. Promising results are achieved with both sound and image processing techniques. /Öz: Altın, en çok taklit edilen değerli metallerden biridir. Bakırın rengi altına benzer. Bu nedenle bakır, renk sahteciliği için en yaygın kullanılan malzemelerden biridir. Kimyasal özellikler söz konusu olduğunda, volfram altına benzer (altın ve tungstenin yoğunluğu sırasıyla 19.30 g/ml ve 19.25 g/ml'dir), bu nedenle kimyasal bir sahte olarak kullanılabilir. Altının saflığı X-ray ile belirlenebilir, ancak bu yöntem maliyetlidir. Bu yazıda, sahte altın tespiti için kuyumcuların mevcut düşük maliyetli yöntemleri ve sahte parayı tespit etmek için kullanılan düşük maliyetli yöntemler denenmiştir. Bir yüzeye altın bir madde çarptığında, ses frekansı aynı deney bakır ile yapıldığındaki sesin frekansından daha yüksektir. Ayrıca, sahte altın rengi gerçek olanlardan daha parlaktır. Altın rengi benzersizdir ve "altın sarısı" olarak adlandırılır. Bu araştırmada ses ve görüntü işleme yöntemleri kullanılarak sahte ve orijinal altın ayrımı yapılmıştır. Görüntü işleme kısmı için, önce görüntüden altını segmentlere ayırmak için CNN tabanlı bir araç kutusu uygulanır. Bundan sonra, altın ve bakır malzemelerin rengini ayırt etmek için derin Evrişimli Sinir Ağları kullanılır. Hem ses hem de görüntü işleme teknikleri ile umut verici sonuçlar elde edilmektedir.
  • Placeholder
    PublicationMetadata only
    Curation of historical Arabic handwritten digit datasets from Ottoman population registers: a deep transfer learning case study
    (IEEE, 2020) Can, Yekta Said; Kabadayı, Mustafa Erdem; Researcher; Faculty Member; College of Social Sciences and Humanities; N/A; 33267
    With the increasing number of digitization efforts of historical manuscripts and archives, automatical information retrieval systems need to extract meaning fast and reliably. Historical archives bring more challenges for these systems when compared to modern manuscripts. More advanced algorithms, archive specific methods, preprocessing techniques are needed to retrieve information. Cutting-edge machine learning algorithms should also be applied to retrieve meaning from these documents. One of the most important research issues of historical document analysis is the lack of public datasets. Although there are plenty of public datasets for modern document analysis, the number of public annotated historical archives is limited. Researchers can test novel algorithms on these modern datasets and infer some results, but their performance is unknown without testing them on historical datasets. In this study, we created a historical Arabic handwritten digit dataset by combining manual annotation and automatic document analysis techniques. The dataset is open for researchers and contained more than 6000 digits. We then tested deep transfer learning algorithms and various machine learning techniques to recognize these digits and achieved promising results.
  • Placeholder
    PublicationMetadata only
    Automatic CNN-based Arabic numeral spotting and handwritten digit recognition by using deep transfer learning in Ottoman population registers
    (Mdpi, 2020) N/A; Department of History; Can, Yekta Said; Kabadayı, Mustafa Erdem; Researcher; Faculty Member; Department of History; College of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; 33267
    Historical manuscripts and archival documentation are handwritten texts which are the backbone sources for historical inquiry. Recent developments in the digital humanities field and the need for extracting information from the historical documents have fastened the digitization processes. Cutting edge machine learning methods are applied to extract meaning from these documents. Page segmentation (layout analysis), keyword, number and symbol spotting, handwritten text recognition algorithms are tested on historical documents. For most of the languages, these techniques are widely studied and high performance techniques are developed. However, the properties of Arabic scripts (i.e., diacritics, varying script styles, diacritics, and ligatures) create additional problems for these algorithms and, therefore, the number of research is limited. In this research, we first automatically spotted the Arabic numerals from the very first series of population registers of the Ottoman Empire conducted in the mid-nineteenth century and recognized these numbers. They are important because they held information about the number of households, registered individuals and ages of individuals. We applied a red color filter to separate numerals from the document by taking advantage of the structure of the studied registers (numerals are written in red). We first used a CNN-based segmentation method for spotting these numerals. In the second part, we annotated a local Arabic handwritten digit dataset from the spotted numerals by selecting uni-digit ones and tested the Deep Transfer Learning method from large open Arabic handwritten digit datasets for digit recognition. We achieved promising results for recognizing digits in these historical documents.
  • Placeholder
    PublicationMetadata only
    Line segmentation of individual demographic data from Arabic handwritten population registers of Ottoman Empire
    (Springer International Publishing Ag, 2021) N/A; Department of History; Can, Yekta Said; Kabadayı, Mustafa Erdem; Researcher; Faculty Member; Department of History; College of Social Sciences and Humanities; College of Social Sciences and Humanities; N/A; 33267
    Recently, more and more studies have applied state-of-the-art algorithms for extracting information from handwritten historical documents. Line segmentation is a vital stage in the HTR systems; it directly affects the character segmentation stage, which affects the recognition success. In this study, we first applied deep learning-based layout analysis techniques to detect individuals in the first Ottoman population register series collected between the 1840s and 1860s. Then, we used a star path planning algorithm-based line segmentation to the demographic information of these detected individuals in these registers. We achieved encouraging results from the selected regions, which could be used to recognize the text in these registers.