Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940

Browse

Now showing 1 - 20 of 52

Comparing Humans and Deep Neural Networks on Face Recognition Under Various Distance and Rotation Viewing Conditions
(Journal of Vision, 2023) Fux, Michal; Arslan , Şuayb Şefik; Jang, Hojin; Boix, Xavier; Cooper, Avi; Groth, Matt J; Sinha, Pawan
Humans possess impressive skills for recognizing faces even when the viewing conditions are challenging, such as long ranges, non-frontal regard, variable lighting, and atmospheric turbulence. We sought to characterize the effects of such viewing conditions on the face recognition performance of humans, and compared the results to those of DNNs. In an online verification task study, we used a 100 identity face database, with images captured at five different distances (2m, 5m, 300m, 650m and 1000m) three pitch values (00 - straight ahead, +/- 30 degrees) and three levels of yaw (00, 45, and 90 degrees). Participants were presented with 175 trials (5 distances x 7 yaw and pitch combinations, with 5 repetitions). Each trial included a query image, from a certain combination of range x yaw x pitch, and five options, all frontal short range (2m) faces. One was of the same identity as the query, and the rest were the most similar identities, chosen according to a DNN-derived similarity matrix. Participants ranked the top three most similar target images to the query image. The collected data reveal the functional relationship between human performance and multiple viewing parameters. Nine state-of-the-art pre-trained DNNs were tested for their face recognition performance on precisely the same stimulus set. Strikingly, DNN performance was significantly diminished by variations in ranges and rotated viewpoints. Even the best-performing network reported below 65% accuracy at the closest distance with a profile view of faces, with results dropping to near chance for longer ranges. The confusion matrices of DNNs were generally consistent across the networks, indicating systematic errors induced by viewing parameters. Taken together, these data not only help characterize human performance as a function of key ecologically important viewing parameters, but also enable a direct comparison of humans and DNNs in this parameter regime
Yüz Tanıma
(Elektrik Mühendisleri Odası EMO), 2015) Muhittin, Gökmen
Görüntü işleme alanında çalışan 36 farklı üniversiteden 52 doktora ve yüksek lisans öğrencisinin katılımı ile başlayan akademik kampta, alanında uzmanlıkları ile tanınan 11 farklı üniversiteden 14 akademisyenin katılımıyla 17 farklı seminer ve ders gerçekleştirildi. 2. Akademik Kamp çalışmalarına, 16 Nisan 2015 tarihinde saat 09:00`da açılış töreni ile başladı. Açılışta ilk olarak konuşan EMO Müdürü Emre Metin, kamp çalışmalarına ilişkin temel bilgileri katılımcılara aktardı. Metin`in ardından kürsüye gelen EMO Yönetim Kurulu Başkanı Hüseyin Yeşil ise konuşmasına kamp çalışmalarına katkı veren EMO MİSEM Komisyonu Başkanı Orhan Örücü, Prof . Dr. Tayfun Akgül ve kampa ev sahipliği yapan Nesin Vakfı`na teşekkür ederek, başladı. EMO Akademiyle Bağını Güçlendiriyor EMO`nun akademi dünyası ile daha yakın ilişki kurmayı hedeflediğine dikkat çeken Yeşil, ikincisi yapılan akademik kampı tekrarlamak istediklerini kaydetti. EMO`nun kendi meslek alanlarına giren üniversitelerin ilgili bölümleri ile özel ilişkiler kurmaya çalıştığını ifade eden Yeşil, bu kapsamda 25 Ekim 2014 tarihinde 56 bölüm başkanı ile bir toplantı düzenlediklerini kaydetti. EMO ve üniversite çalışmalarının koordine edilebilmesi için 11 Nisan 2015 tarihinde bir toplantı daha gerçekleştirildiğini ifade eden Yeşil, bu kapsamda Elektrik-Elektronik-Kontrol-Biyomedikal Mühendisliği Bölüm Başkanları Konseyi`nin de kurulduğunu bildirdi. EMO tarafından yayımlanan EMO Bilimsel Dergi ile alandaki bilimsel dergi ihtiyacının giderilmeye çalışıldığını ifade eden Yeşil, derginin 8. sayının hazırlıklarının yapıldığını kaydetti. Genç akademisyenlerden EMO Bilimsel Dergisi için makale katkısı isteyen Yeşil, baş editör Prof. Dr. Hamit Serbest ve diğer dergi editörlerine katkıları dolayısıyla teşekkür etti. EMO`nun Meslek İçi Eğitim Merkezi (MİSEM) çalışmaları kapsamında yürüttüğü eğitim ve seminerlere de dikkat çeken Yeşil, mesleki ve teknik gelişmelerin bu eğitimlerle üyelere aktarılmaya çalışıldığını vurguladı. EMO`nun mesleki ve teknik gündemin yanında toplumsal yaşamda da katkılar sağlamaya çalıştığını ifade eden Yeşil, konuşmasını şöyle sürdürdü: "Yalnızca Soma`da yaşanan iş cinayeti hem de tüm Türkiye`yi karanlıkta bırakan elektrik kesintisi konularında bile kamuoyunu bilgilendirme çabalarımız bile EMO`nun varlığının önemli olduğunu ortaya koymaktadır. Gerçeklerin ortaya çıkması için yürütmeye çalıştığımız bu çalışmaların genç arkadaşlarımızın da katkılarıyla güçlenerek, süreceğine inanıyoruz." Yeni Kamplar Geliyor Yeşil`in ardından kürsüye gelen EMO MİSEM Komisyonu Başkanı Orhan Örücü ise konuşmasına daha önce düzenlenen akademik kampa ilişkin bilgi aktararak başladı. Örücü, Akademik Kampa 36 farklı üniversiteden toplam 52 öğrencinin katılım sağlamasının önemine işaret ederek, kampta yer alan genç 20 kadın akademisyeni de kutladı. Akademik kampların farklı konularda daha sık periyotlarda tekrarlanması için çalışmalar yürütüldüğünü ifade eden Örücü, ODTÜ`den Prof. Dr. Murat Eyüpoğlu ile birlikte "Manyetik Görüntüleme", yine ODTÜ`den Prof. Dr. Bülent Ertan ile "Elektrik Makineleri ve Güç Elektroniği" ve İTÜ`den Doç. Dr. Neslihan Şengür ile "Yapay Sinir Ağları" konularına ilişkin kamp düzenlenebilmesi için çalışmalar yürütüldüğünü bildirdi. Örücü, hazırlık çalışmaları kapsamında seminerlere katılacak deneyimli akademisyenlerin belirlenmesi için önümüzdeki dönemde genç akademisyenler arasından EMO tarafından anketler düzenleneceği ve öneriler alınacağını kaydetti. Örücü`nün ardından konuşan Prof. Dr. Tayfun Akgül ise bir önceki kamp çalışmalarına değinerek, "çok keyifli" bir çalışma sürecinin yaşandığını kaydetti. Akgül, akademik kampların daha sıcak ilişkiler yaratarak, çalışmaların ivmesini artırdığına dikkat çekti. Nesin Vakfı`na Matematik Köyü`nden yarattığı çalışma ortamı için teşekkür eden Akgül, tüm katılımcıların kamp çalışmalarında önemli katkılar sağlayacağına inandığını ifade etti. Akgül`ün konuşmasını tamamlamasının ardından, katılımcılar kendini tanıtarak yaptıkları çalışmalara ilişkin bilgi aktardı. Kampta daha sonra Prof. Dr. Muhittin Gökmen`in verdiği "Yüz Tanıma" başlıklı derse geçildi. Kampta ilk gün çalışmaları kapsamında Gökmen`in yanı sıra Prof. Dr. Tayfun Akgül "Bilim Etiği", Prof. Dr. Hamit Serbest "Bilim, Mühendislik ve Öğretim Kurumları", Prof. Dr. Tayfun Akgül "Yüzsüz Yüz Tanıma" ve Prof. Dr. Enis Çetin "Orman Yangını Bulma, Örüntü Tanıma, Mikroskop Görüntülerinin İşlenmesi" konu başlıklarında seminerler verdi. Kamp çalışmaları kapsamında 17 Mart 2015 Cuma günü ise ilk olarak EMO Bilimsel Dergi Yayın Kurulu Üyesi Prof. Dr. Altay Güvenir tarafından "EMO Bilimsel Dergi Tanıtımı" başlıklı oturum düzenlendi. Ardından Prof. Dr. Atilla Bir`in tarafından ise katılımcılara "Öklid`ten Nasreddin Tusi`ye, Tusi`den Uluğ Bey‘e Bilim" başlıklı sunum gerçekleştirildi. Kamp çalışmaları kapsamında öğlden sonra Prof. Dr. Ayşin Ertüzün tarafından "Doku Analizi ve Örüntü Tanıma", Yrd. Doç. Dr. Emre Sümer tarafından ise "Görüntü İşleme Teknikleri ile 3-B Bina Modelleme" dersleri verildi. Günün son dersinin ise Prof. Dr. Ali Nesin, "Mühendisler ve Matematik; Sayı Ne Demektir?" başlıklığı altında yaptı. Cumartesi günü ise ilk olarak Yrd. Doç. Dr. Berk Gökberk`ün "Biyometri", Prof. Dr. Arif Nacaroğlu`nun "Sıkıştırılmış Sinyallerin Algılanması", Yrd. Doç. Dr. Özlem Durmaz İncel`in "İnsan Eylemi ve Bağlam Tanıma" ve Prof. Dr. A. Aydın Alatan`ın "Ardışık Görüntülerden Sahne Derinliği Kestirimi" başlıklı dersleri gerçekleştirildi. Kampın son gününde ise Yrd. Doç. Dr. Alper Selver`in "Sıradüzenli Sistemlerin Günlük Yaşam Uygulamaları: Kalite Tespiti, Organ Görüntüleme ve Radarla Nesne Tespiti" ile Doç. Dr. Hazım Kemal Ekenel`in "İçerik Tabanlı İmge ve Video Çıkarımı" başlıklı dersleri yapıldı. Kamp çalışmaları Efes Harabeleri`ne ve Şirince Köyü`ne yapılan gezi ile tamamlandı.
Citation - WoS: 2
Citation - Scopus: 2
Implementation of Multi-Threaded Erasure Coding Under Multi-Processing Environments
(2016) Arslan, Şuayb Şefik
Galois alan aritmetiği depolama ve iletişim cihazlarını veri kayıplarına karşı korumak için Reed-Solomon silme kodlarının temelini oluşturmaktadır. Galois alan aritmeti^ginin en güncel uygulamaları hızlı Galois alan hesaplamaları yapmamıza imkan sağlayan Intel’in SIMD eklerinde olduğu gibi 128-bitlik işlemci vektör talimatlarına dayanmaktadır. Buna rağmen, bu uygulamalar çoklu–dizin ve çoklu–süreçli ortamlara göre optimize edilmemiştir. Diğer taraftan, sunucuların çoklu istekleri eş zamanlı olarak yerine getirmesi ve donanımın sağladığı tüm paralelliği kodlama yükünü etkili yürütmek için kullanması arzu edilmektedir. Bu makale silme kodlarının çoklu-dizin işlemcilerle çoklu–süreçli ortamlarda nasıl kullanılaca^gının detaylarını sunmakta ve tek dizinli uygulamalara göre emtia mikro işlemciler ve Jerasure 2.0 yazılım kütüphanesini kullanarak önemli ölçüde performans artışının olabileceğini göstermektedir.
Cooperative Network Coding for Distributed Storage Using Base Stations With Link Constraints
(arXiv, 2021) Arslan, Şuayb Şefik; Pourmandi, Massoud; Haytaoğlu, Elif
In this work, we consider a novel distributed data storage/caching scenario in a cellular setting where multiple nodes may fail/depart at the same time. In order to maintain the target reliability, we allow cooperative regeneration of lost nodes with the help of base stations allocated in a set of hierarchical layers. Due to this layered structure, a symbol download from each base station has a different cost, while the link capacities connecting the nodes of the cellular system and the base stations are also limited. In this more practical and general scenario, we present the fundamental trade-off between repair bandwidth cost and the storage space per node. Particularly interesting operating points are the minimum storage as well as bandwidth cost points in this trade-off curve. We provide closed-form expressions for the corresponding bandwidth (cost) and storage space per node for these operating points. Finally, we provide an explicit optimal code construction for the minimum storage regeneration point for a given set of system parameters.
Erasure Coding Magnetic Tapes for Minimum Latency and Adaptive Parity Protection Feedback
(Patent Ofisi : US, 2019) Goker, Turguy; Arslan, Şuayb Şefik; Le, Hoa; Peng, James; Prigge, Carsten
A magnetic tape device or system can store erasure encoded data that generates a multi-dimensional erasure code corresponding to an erasure encoded object comprising a code-word (CW). The multi-dimensional erasure code enables using a single magnetic tape in response to a random object/file request, and correct for an error within the single magnetic tape without using other tapes. Encoding logic can further utilize other magnetic tapes to generate additional parity tapes that recover data from an error of the single magnetic tape in response to the error satisfying a threshold severity for a reconstruction of the erasure coded object or chunk (s) of the CW. The encoding logic can be controlled, at least in part, by one or more iterative coding processes between multiple erasure code dimensions that are orthogonal to one another.
Citation - WoS: 27
Citation - Scopus: 30
Service-Aware Multi-Resource Allocation in Software-Defined Next Generation Cellular Networks
(2018) Arslan, Şuayb Şefik; Zeydan, Engin; Narmanloğlu, Ömer
Network slicing is one of the major solutions needed to meet the requirements of next generation cellular networks, under one common network infrastructure, in supporting multiple vertical services provided by mobile network operators. Network slicing makes one shared physical network infrastructure appear as multiple logically isolated virtual networks dedicated to different service types where each Network Slice (NS) benefits from on-demand allocated resources. Typically, the available resources distributed among NSs are correlated and one needs to allocate them judiciously in order to guarantee the service, MNO, and overall system qualities. In this paper, we consider a joint resource allocation strategy that weights the significance of the resources per a given NS by leveraging the correlation structure of different quality-of-service (QoS) requirements of the services. After defining the joint resource allocation problem including the correlation structure, we propose three novel scheduling mechanisms that allocate available network resources to the generated NSs based on different type of services with different QoS requirements. Performance of the proposed schedulers are then investigated through Monte-Carlo simulations and compared with each other as well as against a traditional max-min fairness algorithm benchmark. The results reveal that our schedulers, which have different complexities, outperform the benchmark traditional method in terms of service-based and overall satisfaction ratios, while achieving different fairness index levels.
Citation - WoS: 20
Citation - Scopus: 28
An Evaluation of Recent Neural Sequence Tagging Models in Turkish Named Entity Recognition
(Elsevier, 2021) Makaroğlu, Didem; Demir, Şeniz; Aras, Gizem; Çakır, Altan
Named entity recognition (NER) is an extensively studied task that extracts and classifies named entities in a text. NER is crucial not only in downstream language processing applications such as relation extraction and question answering but also in large scale big data operations such as real-time analysis of online digital media content. Recent research efforts on Turkish, a less studied language with morphologically rich nature, have demonstrated the effectiveness of neural architectures on well-formed texts and yielded state-of-the art results by formulating the task as a sequence tagging problem. In this work, we empirically investigate the use of recent neural architectures (Bidirectional long short-term memory (BiLSTM) and Transformer-based networks) proposed for Turkish NER tagging in the same setting. Our results demonstrate that transformer-based networks which can model long-range context overcome the limitations of BiLSTM networks where different input features at the character, subword, and word levels are utilized. We also propose a transformer-based network with a conditional random field (CRF) layer that leads to the state-of-the-art result (95.95% f-measure) on a common dataset. Our study contributes to the literature that quantifies the impact of transfer learning on processing morphologically rich languages.
Citation - WoS: 3
Citation - Scopus: 5
Unraveling Neural Pathways of Political Engagement: Bridging Neuromarketing and Political Science for Understanding Voter Behavior and Political Leader Perception
(2023) Çakar, Tuna; Filiz, Gözde
Political neuromarketing is an interdisciplinary field that combines marketing, neuroscience, and psychology to understand voter behavior and political leader perception. This interdisciplinary field offers novel techniques to understand complex phenomena such as voter engagement, political leadership, and party branding. This study aims to understand the neural activation patterns of voters when they are exposed to political leaders using functional near-infrared spectroscopy (fNIRS) and machine learning methods. We recruited participants and recorded their brain activity using fNIRS when they were exposed to images of different political leaders. This neuroimaging method (fNIRS) reveals brain regions central to brand perception, including the dorsolateral prefrontal cortex (dlPFC), the dorsomedial prefrontal cortex (dmPFC), and the ventromedial prefrontal cortex (vmPFC). Machine learning methods were used to predict the participants' perceptions of leaders based on their brain activity. The study has identified the brain regions that are involved in processing political stimuli and making judgments about political leaders. Within this study, the best-performing machine learning model, LightGBM, achieved a highest accuracy score of 0.78, underscoring its efficacy in predicting voters' perceptions of political leaders based on the brain activity of the former. The findings from this study provide new insights into the neural basis of political decision-making and the development of effective political marketing campaigns while bridging neuromarketing, political science and machine learning, in turn enabling predictive insights into voter preferences and behavior
Citation - Scopus: 7
The Use of Neurometric and Biometric Research Methods in Understanding the User Experience During Product Search of First-Time Buyers in E-Commerce - Conference Paper
(Springer, 2017) Rızvanoğlu, Kerem; Gürvardar, İrfan; Çakar, Tuna; Öztürk, Özgürol; Zengin Çelik, Deniz
Understanding user experience (UX) during e-commerce has been a relatively important research area especially in the last decade. The use of conventional methods in UX such as task-observation, in-depth interviews and questionnaires has already contributed for the measurement of the efficiency and effectiveness. This empirical study has aimed to make use of both conventional and neuroscientific methods simultaneously to provide a richer analysis framework for understanding the product search experience of the first-time buyers. The current work provides insights for the results from the combined use of conventional and neuroscientific-biometric methods in a UX study. Although this has been an exploratory study within a limited literature, the obtained results indicate a potential use of these methods for UX research, which may contribute to improve the relevant experience in various digital platforms.
Citation - WoS: 13
Citation - Scopus: 21
Advancements in Distributed Ledger Technology for Internet of Things
(Elsevier, 2020) Jurdak, Raja; Arslan, Şuayb Şefik; Krishnamachari, Bhaskar; Jelitto, Jens
Internet of Things (IoT) is paving the way for different kinds of devices to be connected and properly communicated at a mass scale. However, conventional mechanisms used to sustain security and privacy cannot be directly applied to IoT whose topology is increasingly becoming decentralized. Distributed Ledger Technologies (DLT) on the other hand comprise varying forms of decentralized data structures that provide immutability through cryptographically linking blocks of data. To be able to build reliable, autonomous and trusted IoT platforms, DLT has the potential to provide security, privacy and decentralized operation while adhering to the limitations of IoT devices. The marriage of IoT and DLT technology is not very recent. In fact many projects have been focusing on this interesting combination to address the challenges of smart cities, smart grids, internet of everything and other decentralized applications, most based on blockchain structures. In this special issue, the focus is on the new and broader technical problems associated with the DLT-based security and backend platform solutions for IoT devices and applications.
Citation - WoS: 4
Citation - Scopus: 5
Designing restorative landscapes for students: A Kansei engineering approach enhanced by VR and EEG technologies
(Elsevier, 2024) Karaca, Elif; Çakar, Tuna; Karaca, Mehmet; Gul, Hasan Huseyin Mirac
This study explores the alignment of specific landscape features within school environments with the core elements of Attention Restoration Theory (ART) that includes Coherence, Fascination, Compatibility, and Being Away. Utilizing Kansei Engineering, this research integrates emotional analysis into landscape design by employing Virtual Reality (VR) and Electroencephalogram (EEG) technologies to record students' responses to different landscape simulations. Analytical techniques, including the Taguchi Method and Analysis of Variance (ANOVA), were applied to evaluate the data. The findings have revealed that students associate a sense of enclosure with a coherent landscape and openness with a fascinating landscape, the lawn's significance was also highlighted for coherent landscape. However, limited insights were gained regarding Compatibility and Being Away. The study advocates for diverse cognitive zones within school landscapes to promote mental restoration, emphasizing the need for varied design elements that cater to the elevated experience of students.
Customer Segmentation and Churn Prediction via Customer Metrics
(IEEE, 2022) Bozkan, Tunahan; Cakar, Tuna; Sayar, Alperen; Ertugrul, Seyit
In this study, it is aimed to predict whether customers operating in the factoring sector will continue to trade in the next three months after the last transaction date, using data-driven machine learning models, based on their past transaction movements and their risk, limit and company data. As a result of the models established, Loss Analysis (Churn) of two different customer groups (Real and Legal factory) was carried out. It was estimated by the XGBoost model with an F1 Score of 74% and 77%. Thanks to this modeling, it was aimed to increase the retention rate of customers through special promotions and campaigns to be made to these customer groups, together with the prediction of the customers who will leave. Thanks to the increase in retention rates, a direct contribution to the transaction volume on a company basis was ensured.
Joint Multi-Nanopore Sequencing for Reliable Data Retrieval in Nucleic Acid Storage
(2023) Arslan , Şuayb Şefik; Göker, Turguy; Doerner, Don
A nucleic acid storage system (100) that uses nanopore sequencing to read data values chemically embedded in oligonucleotides includes a membrane (102), a voltage source (108), and a nucleic acid strand (110). The membrane (102) has a plurality of nanopores (104) that are stacked upon one another in a multi-nanopore arrangement. The voltage source (108) is configured to direct voltage across the plurality of nanopores (104). The nucleic acid strand (110) including the oligonucleotides is threaded through each of the plurality of nanopores (104) within the membrane (102). A separate base signal (118) is generated from the nucleic acid strand (110) being threaded through each of the plurality of nanopores (104), and Recursive Neural Networks can be used to estimate a signal shape for each oligonucleotide. Recurrent Convolutional Neural Networks and noise predictive data detection algorithms can be used based on the estimated signal shapes to sequence the oligonucleotides.
Citation - WoS: 9
Citation - Scopus: 11
An Efficient Multiscale Scheme Using Local Zernike Moments for Face Recognition
(MDPI, 2018) Gökmen, Muhittin; Başaran, Emrah; Kamasak, Mustafa E.
In this study, we propose a face recognition scheme using local Zernike moments (LZM), which can be used for both identification and verification. In this scheme, local patches around the landmarks are extracted from the complex components obtained by LZM transformation. Then, phase magnitude histograms are constructed within these patches to create descriptors for face images. An image pyramid is utilized to extract features at multiple scales, and the descriptors are constructed for each image in this pyramid. We used three different public datasets to examine the performance of the proposed method:Face Recognition Technology (FERET), Labeled Faces in the Wild (LFW), and Surveillance Cameras Face (SCface). The results revealed that the proposed method is robust against variations such as illumination, facial expression, and pose. Aside from this, it can be used for low-resolution face images acquired in uncontrolled environments or in the infrared spectrum. Experimental results show that our method outperforms state-of-the-art methods on FERET and SCface datasets.
Citation - WoS: 3
Citation - Scopus: 3
Asymptotically Mds Array Bp-Xor Codes
(2018) Arslan, Şuayb Şefik
Belief propagation (BP) on binary erasure channels (BEC) is a low complexity decoding algorithm that allows the recovery of message symbols based on bipartite graph pruning process. Recently, array XOR codes have attracted attention for storage systems due to their burst error recovery performance and easy arithmetic based on Exclusive OR (XOR)-only logic operations. Array BP-XOR codes are a subclass of array XOR codes that can be decoded using BP under BEC. Requiring the capability of BP-decodability in addition to Maximum Distance Separability (MDS) constraint on the code construction process is observed to put an upper bound on the achievable code block-length, which leads to the code construction process to become a hard problem. In this study, we introduce asymptotically MDS array BP-XOR codes that are alternative to exact MDS array BP-XOR codes to allow for easier code constructions while keeping the decoding complexity low with an asymptotically vanishing coding overhead. We finally provide a code construction method that is based on discrete geometry to fulfill the requirements of the class of asymptotically MDS array BP-XOR codes.
What Is the Effective Resolution of the Retinal Image of a Distant Face?
(Vision Sciences Society Annual Meeting Abstract, 2023) Arslan , Şuayb Şefik; Fux, Michal; Sinha, Pawan
We consider the following question: What is the effective resolution of a face image projected on the retina, when the face is at a specified distance from the eye? Though simple to state, this is a surprisingly challenging issue to resolve. The mapping between viewing distance and effective resolution cannot be readily derived based on the contrast sensitivity, Snellen acuity, or even the packing density of photoreceptors in the fovea. With initial guidelines derived from theoretical considerations, images of varying resolution were presented across a range of viewing distances. For each distance, participants were required to perform an ‘odd one out’ task. This involved detecting the one that was different from the rest in a 2x2 grid, with image resolution being the only dimension of variation. As the experiment progressed, the viewing distance decreased monotonically, and participants were able to detect increasingly subtle resolution differences between the three standard images and the outlier. The collected data have allowed us to establish the upper/lower bounds on the effective available resolution for typical human vision as a function of viewing distance. Interestingly, we find that humans perform significantly better, particularly at short ranges, than what a theoretical model predicts based on projected image size, cone density, and foveal extent. Accordingly, we suggest that the non-uniform in-fovea density, as well as less sharp fall-off in the acuity density function outside the fovea, need to be integrated into future theoretical models to translate viewing distance to perceived image characteristics. A pragmatic benefit of the mapping is that it enables a direct comparison of human face recognition performance as assessed across blur and viewing distance. Additionally, it allows us to systematically compare human performance on face recognition at varying distances with that of machine vision systems using the common axis of resolution.
Citation - WoS: 1
Citation - Scopus: 1
Understanding the Psychological and Financial Correlates for Consumer Credit Use;
(Sosyoekonomi Society, 2024) Ertuğrul, Seyit; Sayar, Alperen; Şahin, Türkay; Çakar,Tuna
This study investigated the behavioural and cognitive predictors of consumer credit usage to develop a behavioural credit risk assessment procedure for a factoring company. Participants completed surveys measuring personality traits, self-esteem, material and monetary values, compulsive and impulsive buying tendencies, self-control, and impulsiveness. Financial surveys also assessed financial literacy and knowledge of financial concepts. The results indicated that extraversion, conscientiousness, emotional stability, and experiential self-control were significant predictors of consumer credit usage. These findings suggest that a finance company can use these personality traits and financial characteristics to develop a more accurate and effective credit risk assessment procedure, such as psychometric tests. © 2024, Sosyoekonomi Society. All rights reserved.
Citation - Scopus: 4
Classification of Skin Lesion Images With Deep Learning Approaches
(University of Latvia, 2022) Kulavuz, Bahadır; Ertuğrul, Berkay; Bakırman, Tolga; Çakar, Tuna; Doğan, Metehan; Bayram, Bülent; Bayram, Buket
Skin cancer is one of the most dangerous cancer types in the world. Like any other cancer type, early detection is the key factor for the patient's recovery. Integration of artificial intelligence with medical image processing can aid to decrease misdiagnosis. The purpose of the article is to show that deep learning-based image classification can aid doctors in the healthcare field for better diagnosis of skin lesions. VGG16 and ResNet50 architectures were chosen to examine the effect of CNN networks on the classification of skin cancer types. For the implementation of these networks, the ISIC 2019 Challenge has been chosen due to the richness of data. As a result of the experiments, confusion matrices were obtained and it was observed that ResNet50 architecture achieved 91.23% accuracy and VGG16 architecture 83.89% accuracy. The study shows that deep learning methods can be sufficiently exploited for skin lesion image classification. © 2022 Baltic Journal of Modern Computing. All rights reserved.
Model for Estimating the Probability of a Customer To Have a Transaction
(IEEE, 2022) Sayar Alperen; Çakar Tuna; Ertugrul Seyit; Bozkan Tunahan
In this study, it is aimed to estimate the probability of a customer who comes to the institution for the first time to make a transaction in the next 3 months, using data-driven machine learning models, in order to provide financing to the seller company by assigning the receivables arising from the sale of goods and services in a company actively operating in the factoring sector. Accordingly, it was aimed to directly contribute to the transaction volume on a business basis by acting and taking action with more effective, efficient and correct approaches by finding high-potential and low-potential customers. In this context, provided by KKB (Credit Registration Bureau); The data set to he used in machine learning models was created with feature engineering and exploratory data analysis, using the Risk, Mersis, GIB information of the prospective customers and the historical information of the customers, check issuers, customer representatives and branches kept in the database. Since the leads coming to the institution are in two different types of organizations (Individual and Legal), two different forecasting models were applied. Multiple classification models were tried, and the highest F1-Score of 86% for private companies was obtained with the Random Forest model, and the highest F1- Score for commercial companies was obtained with the Random Forest model with 82%. © 2022 IEEE.
Citation - WoS: 4
Citation - Scopus: 5
Private Minutia-Based Fingerprint Matching
(2015) Sarıer, Neyire Deniz
In this paper, we propose an efficient biometric authentication protocol for fingerprints particularly suited for the minutia-based representation. The novelty of the protocol is that we integrate the most efficient (linear complexity) private set intersection cardinality protocol of Cristofaro et al. and a suitable helper data system for biometrics in order to improve the accuracy of the system. We analyze the security of our scheme in the standard model based on well-exploited assumptions, considering malicious parties, which is essential to eliminate specific attacks on biometric authentication schemes designed for semi-honest adversaries only. Finally, the complexity is compared to the existing provably secure schemes for fingerprint matching, which shows that the new proposal outperforms them both in semi-honest and malicious security models.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Access Right "info:eu-repo/semantics/openAccess"