Bilgisayar Mühendisliği Bölümü Koleksiyonu

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

Browse

Now showing 1 - 9 of 9

Citation - WoS: 1
Citation - Scopus: 1
A Novel Genetic Algorithm-Based Improvement Model for Online Communities and Trust Networks
(IOS Press, 2020) Bekmezci, ilker; Cimen, Egemen Berkic; Ermiş, Murat
Social network analysis offers an understanding of our modern world, and it affords the ability to represent, analyze and even simulate complex structures. While an unweighted model can be used for online communities, trust or friendship networks should be analyzed with weighted models. To analyze social networks, it is essential to produce realistic social models. However, there are serious differences between social network models and real-life data in terms of their fundamental statistical parameters. In this paper, a genetic algorithm (GA)-based social network improvement method is proposed to produce social networks more similar to real-life data sets. First, it creates a social model based on existing studies in the literature, and then it improves the model with the proposed GA-based approach based on the similarity of the average degree, the k-nearest neighbor, the clustering coefficient, degree distribution and link overlap. This study can be used to model the structural and statistical properties of large-scale societies more realistically. The performance results show that our approach can reduce the dissimilarity between the created social networks and the real-life data sets in terms of their primary statistical properties. It has been shown that the proposed GA-based approach can be used effectively not only in unweighted networks but also in weighted networks.
Base Station-Assisted Cooperative Network Coding for Cellular Systems With Link Constraints
(IEEE, 2022) Arslan, Suayb S.; Pourmandi, Massoud; Haytaoglu, Elif
We consider a novel distributed data storage/caching scenario in a cellular network, where multiple nodes may fail/depart simultaneously To meet reliability, we allow cooperative regeneration of lost nodes with the help of base stations allocated in a set of hierarchical layers1. Due to this layered structure, a symbol download from each base station has a different cost, while the link capacities between the nodes of the cellular system and the base stations are also constrained. Under such a setting, we formulate the fundamental trade-off with closed form expressions between repair bandwidth cost and the storage space per node. Particularly, the minimum storage as well as bandwidth cost points are formulated. Finally, we provide an explicit optimal code construction for the minimum storage regeneration point for a special set of system parameters.
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.
Citation - WoS: 4
Citation - Scopus: 4
Cost of Guessing: Applications To Data Repair
(Institute of Electrical and Electronics Engineers Inc., 2020) Arslan, Şuayb Şefik; Haytaoğlu, Elif
In this paper, we introduce the notion of cost of guessing and provide an optimal strategy for guessing a random variable taking values on a finite set whereby each choice may be associated with a positive finite cost value. Moreover, we drive asymptotically tight upper and lower bounds on the moments of cost of guessing problem. Similar to previous studies on the standard guesswork, established bounds on moments quantify the accumulated cost of guesses required for correctly identifying the unknown choice and are expressed in terms of the Rényi's entropy. A new random variable is introduced to bridge between cost of guessing and the standard guesswork and establish the guessing cost exponent on the moments of the optimal guessing. Furthermore, these bounds are shown to serve quite useful for finding repair latency cost for distributed data storage in which sparse graph codes may be utilized.
Citation - WoS: 2
Citation - Scopus: 2
Facial Expression Recognition From Still Images
(2017) Gökmen, Muhittin; Gazioglu, Bilge Suheyla Akkoca
With the development of technology, Facial Expression Recognition (FER) become one of the important research areas in Human Computer Interaction. Changes in the movement of some muscles in face create the facial expressions. By defining these changes, facial expressions can be recognized. In this study, a cascaded structure consists of Local Zernike Moments (LZM), Local XOR Patterns (LXP) and Global Zernike Moments (GZM) methods is proposed for the FER problem. The generally used database is the Extended Chon - Kanade (CK +) in FER problems. The database consists of image sequences of 327 expressions of 118 people. Most FER system includes recognition of 7 classes of emotions happiness, sadness, surprise, anger, disgust, fear and contempt, and we use Library of Support Vector Machines (LIBSVM) classifier for multi class classification with the leave one out cross-validation method. Our overall system performance is measured as 90.34% for FER.
Citation - Scopus: 1
Improved Bounds on the Moments of Guessing Cost
(IEEE, 2022) Arslan, Suayb S.; Haytaoglu, Elif
Guessing a random variable with finite or countably infinite support in which each selection leads to a positive cost value has recently been studied within the context of "guessing cost". In those studies, similar to standard guesswork, upper and lower bounds for the rho-th moment of guessing cost are described in terms of the known measure Renyi's entropy. In this study, we non-trivially improve the known bounds using previous techniques along with new notions such as balancing cost. We have demonstrated that the novel lower bound proposed in this work, achieves 5.84%, 18.47% higher values than that of the known lower bound for rho = 1 and rho = 5, respectively. As for the upper bound, the novel expression provides 10.93%, 5.54% lower values than that of the previously presented bounds for rho = 1 and rho = 5, respectively.
Mention Detection in Turkish Coreference Resolution
(Tubitak Scientific & Technological Research Council Turkey, 2024) Demir, Seniz; Akdag, Hanifi Ibrahim
A crucial step in understanding natural language is detecting mentions that refer to real-world entities in a text and correctly identifying their boundaries. Mention detection is commonly considered a preprocessing step in coreference resolution which is shown to be helpful in several language processing applications such as machine translation and text summarization. Despite recent efforts on Turkish coreference resolution, no standalone neural solution to mention detection has been proposed yet. In this article, we present two models designed for detecting Turkish mentions by using feed-forward neural networks. Both models extract all spans up to a fixed length from input text as candidates and classify them as mentions or not mentions. The models differ in terms of how candidate text spans are represented. The first model represents a span by focusing on its first and last words, whereas the representation also covers the preceding and proceeding words of a span in the second model. Mention span representations are formed by using contextual embeddings, part-of-speech embeddings, and named-entity embeddings of words in interest where contextual embeddings are obtained from pretrained Turkish language models. In our evaluation studies, we not only assess the impact of mention representation strategies on system performance but also demonstrate the usability of different pretrained language models in resolution task. We argue that our work provides useful insights to the existing literature and the first step in understanding the effectiveness of neural architectures in Turkish mention detection.
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.
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.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Scopus Q "Q3"