Erişim şekli için "info:eu-repo/semantics/closedAccess" MF - Makale Koleksiyonu | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering listeleme
Toplam kayıt 52, listelenen: 1-20
-
Adaptive convolution kernel for artificial neural networks
(Academic Press Inc., 2021-02)Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3 × 3) kernels. This paper describes a method for learning the size of convolutional kernels to provide varying size ... -
An adaptive locally connected neuron model: Focusing neuron
(Elsevier B.V., 2021-01-02)This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic ... -
Algebraic break of a cryptosystem based on discretized two-dimensional chaotic maps
(Elsevier Science BV, 2009-03-30)Recently, a cryptosystem based on two-dimensional discretized chaotic maps was proposed [T. Xiang, et al., Phys. Lett. A 364 (2007) 252]. In this Letter, we cryptanalyze the proposal using algebraic methods. We give three ... -
Algebraic break of image ciphers based on discretized chaotic map lattices
(Elsevier Science Inc, 2011-01-01)In this paper, we provide an algebraic cryptanalysis of a recently proposed chaotic image cipher. We show that the secret parameters of the algorithm can be revealed using chosen-plaintext attacks. Our attack uses the orbit ... -
Assessment of algorithms for mitosis detection in breast cancer histopathology images
(Elsevier Science BV, 2015-02)The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers. ... -
BinBRO: Binary Battle Royale Optimizer algorithm
(Elsevier Ltd, 2022-02-04)Stochastic methods attempt to solve problems that cannot be solved by deterministic methods with reasonable time complexity. Optimization algorithms benefit from stochastic methods; however, they do not guarantee to obtain ... -
Breaking an orbit-based symmetric cryptosystem
(Pergamon-Elsevier Science Ltd, 2011-09)We report a break for a recently proposed class of cryptosystems. The cryptosystem uses constant points of a periodic secret orbit to encrypt the plaintext. In order to break the system, it suffices to sort the constant ... -
Closeness and uncertainty aware adversarial examples detection in adversarial machine learning
(Elsevier Ltd, 2022-07)While deep learning models are thought to be resistant to random perturbations, it has been demonstrated that these architectures are vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These ... -
Colored simultaneous geometric embeddings and universal pointsets
(Springer, 2011-07)Universal pointsets can be used for visualizing multiple relationships on the same set of objects or for visualizing dynamic graph processes. In simultaneous geometric embeddings, the same point in the plane is used to ... -
Comment on "Modified Baptista type chaotic cryptosystem via matrix secret key" [Phys. Lett. A 372 (2008) 5427]
(Elsevier Science BV, 2009-09-07)In this comment, we analyze a recently proposed Baptista-like cryptosystem and show that it is not invertible. Others weaknesses are also reported. A modified version of this cryptosystem is proposed to show how to overcome ... -
ComStreamClust: a communicative multi-agent approach to text clustering in streaming data
(Springer Science and Business Media Deutschland GmbH, 2023-12)Topic detection is the task of determining and tracking hot topics in social media. Twitter is arguably the most popular platform for people to share their ideas with others about different issues. One such prevalent issue ... -
Constructing a WordNet for Turkish using manual and automatic annotation
(Assoc Computing Machinery, 2018-05)In this article, we summarize the methodology and the results of our 2-year-long efforts to construct a comprehensive WordNet for Turkish. In our approach, we mine a dictionary for synonym candidate pairs and manually mark ... -
Cost-conscious comparison of supervised learning algorithms over multiple data sets
(Elsevier Sci Ltd, 2012-04)In the literature, there exist statistical tests to compare supervised learning algorithms on multiple data sets in terms of accuracy but they do not always generate an ordering. We propose Multi(2)Test, a generalization ... -
Cryptanalysis of a chaos-based image encryption algorithm
(Elsevier Science BV, 2009-03-30)A chaos-based image encryption algorithm was proposed in [Z.-H. Guan, F. Huang, W. Guan, Phys. Lett. A 346 (2005) 153]. In this Letter, we analyze the security weaknesses of the proposal. By applying chosen-plaintext and ... -
Cryptanalysis of a cryptosystem based on discretized two-dimensional chaotic maps
(Elsevier Science BV, 2008-11-17)Recently, an encryption algorithm based on two-dimensional discretized chaotic maps was proposed [Xiang et al., Phys. Lett. A 364 (2007) 252]. In this Letter, we analyze the security weaknesses of the proposal. Using the ... -
Cryptanalysis of a multi-chaotic systems based image cryptosystem
(Elsevier Science BV, 2010-01-15)This paper is a cryptanalysis of a recently proposed multi-chaotic systems based image cryptosystem. The cryptosystem is composed of two shuffling stages parameterized by chaotically generated sequences. We propose and ... -
Cryptanalysis of a new substitution-diffusion based image cipher
(Elsevier Science BV, 2010-07)This paper introduces two different types of attacks on a recently proposed cryptosystem based on chaotic standard and logistic maps. In the two attacks, only a pair of (plaintext/ciphertext) was needed to totally break ... -
Cryptanalysis of Fridrich's chaotic image encryption
(World Scientific Publishing, 2010-05)We cryptanalyze Fridrich's chaotic image encryption algorithm. We show that the algebraic weaknesses of the algorithm make it vulnerable against chosen-ciphertext attacks. We propose an attack that reveals the secret ... -
Design and analysis of classifier learning experiments in bioinformatics: survey and case studies
(IEEE Computer Soc, 2012-12)In many bioinformatics applications, it is important to assess and compare the performances of algorithms trained from data, to be able to draw conclusions unaffected by chance and are therefore significant. Both the design ... -
Eigenclassifiers for combining correlated classifiers
(Elsevier Science Inc, 2012-03-15)In practice, classifiers in an ensemble are not independent. This paper is the continuation of our previous work on ensemble subset selection [A. Ulas, M. Semerci, O.T. Yildiz, E. Alpaydin, Incremental construction of ...