https://hdl.handle.net/20.500.12294/416 Bilgisayar Mühendisliği Bölümüne ait bildiri ve sunumlar bu koleksiyonda listelenir. Wed, 12 Aug 2026 03:00:54 GMT 2026-08-12T03:00:54Z https://hdl.handle.net/20.500.12294/4037 Adaptation of n-out-of-n secret sharing scheme into IoT network Kocatekin, Tugberk; Caliskan, Cafer Internet of Things (IoT) has become an established part of our daily lives by interconnecting billions of devices in diverse areas such as healthcare, smart home technologies, agriculture, etc. However, these devices are limited in memory, energy and computational capabilities. This creates a great potential for security issues to arise as being constrained prevents them from applying complex cryptographic algorithms. In this study, we propose a novel method to provide a low-cost and secure communication for constrained IoT devices. The proposed method is based on a n-out-of-n secret sharing scheme and mimicks the idea of visual cryptography in a digital set-up.Generally, when an IoT device communicates with an outer party, it establishes the communication by itself or through a mediary such as a central hub or gateway; which leads to single point of failure. Our proposed method aims for a distributed environment in which devices collaborate with each other and therefore divide the responsibility of sending a message into multiple devices, instead of just one device. Therefore, when a device plans on sending a message, all its neighbors send it on the behalf of this device. © 2023 IEEE. Sun, 01 Jan 2023 00:00:00 GMT https://hdl.handle.net/20.500.12294/4037 2023-01-01T00:00:00Z https://hdl.handle.net/20.500.12294/3271 2D Vector Representation of Binomial Hierarchical Tree Items Donmez, Ilknur; Karateke, Seda; Zontul, Metin Today Artificial Intelligence (AI) algorithms need to represent different kinds of input items in numeric or vector format. Some input data can easily be transformed to numeric or vector format but the structure of some special data prevents direct and easy transformation. For instance, we can represent air condition using humidity, pressure, and temperature values with a vector that has three features and we can understand the similarity of two different air measurements using cosine-similarity of two vectors. But if we are dealing with a general ontology tree, which has elements "entity"as the root element, its two children "living things"and "non-living things"as first- level elements repeatedly children of "living things"that are "Animals", "Plants"as second level elements, it is harder to represent this kind of data with numeric values. The ontology tree starts from the general items and goes to specific items. If we want to represent an element of this tree with a vector; how can it be possible? And if we want the measured similarity using some methods like cosine-similarity, which one similarity is higher, ("Animal"and "non-living thing") or ("Animal"and "Living thing")? How should we select the values of this vector for each item of the hierarchical tree? In this paper, we propose an original and basic idea to represent the hierarchical tree items with 2D vectors and in the proposed method the cosine-similarity metric works for measuring the semantic similarity of represented items at the same level as parent items. There are two important results related to our representation: (1) The "y"values of the items give the hierarchical level of the item. (2) For the same level items, the cosine similarities between the parent item and child items are higher if the child belongs to this parent compared to other childrens'. In other words, the cosine similarity between the parent item and child items is highest if the child belongs to this parent. © 2022 IEEE. Sat, 01 Jan 2022 00:00:00 GMT https://hdl.handle.net/20.500.12294/3271 2022-01-01T00:00:00Z https://hdl.handle.net/20.500.12294/3264 Object Detection in Shelf Images with YOLO Melek, Ceren Gulra; Sonmez, Elena Battini; Albayrak, Songul Object detection in shelf images can solve many problems in retails sales such as monitoring the number of products on the shelves, completing the missing products and matching the planogram continuously. This study aims to detect object in shelf images with deep learning algorithms. Firstly, object detection algorithms and datasets are examined in the literature. Then, experimental study is performed using Coca Cola images obtained from Imagenet and Grocery dataset with YOLO (You Only Look Once) algorithm. Results of the study are discussed from different sides such as number of classes, threshold values and numder of iteration. © 2019 IEEE. Tue, 01 Jan 2019 00:00:00 GMT https://hdl.handle.net/20.500.12294/3264 2019-01-01T00:00:00Z https://hdl.handle.net/20.500.12294/3260 A Joint Design of User Modeling and Resource Management in Cognitive Radio Networks Sadreddini, Zhaleh; Güler, Erkan The limited available spectrum and inefficient spectrum utilization make it necessary to employ dynamic spectrum access techniques. The key enabling technology for dynamic spectrum access is cognitive radio (CR), which exploits the existing wireless spectrum opportunistically and utilizes the licensed spectrum when primary users are passive. Thus, the activities of primary radio (PR) and cognitive radio (CR) users play a major role in the performance of cognitive radio networks. In this paper, a joint solution for user modeling and spectrum management is offered. The activities of PR and CR users are modeled through three-state Markov chain as the spectrum resource blocks are utilized with help of service-level overbooking strategy. Simulation results show the performance of the booking limit with respect to the channel release ratio of CR users and consequently the improved revenue of the network. © 2019 IEEE. Tue, 01 Jan 2019 00:00:00 GMT https://hdl.handle.net/20.500.12294/3260 2019-01-01T00:00:00Z