Ara
Toplam kayıt 143, listelenen: 91-100
A learning object harvesting model and a sample application
(Işık Üniversitesi, 2008-03-06)
The aim of this thesis is to enable harvesting of Learning Objects which are embedded in web pages. Two main challenges have been identified which are interoperability and semantics. For this purpose, several learning ...
Security of chaotic cryptosystems
(Işık Üniversitesi, 2008)
In this thesis, we tried to show the weaknesses of chaotic cryptosystems. We break four chaos-based cryptosystems and proved our attacks. In our first cryptanalysis, we broke a cryptosystem based on two dimensional chaotic ...
Semi-automatic customization for modeling human face
(Işık Üniversitesi, 2012-02-14)
Model-based vision has firmly established its roots as a robust approach in rec-ognizing and locating known traits in rigid objects even under the presence of noise, clutter and occlusion. However the application of such ...
Evolving strategies for web crawler
(Işık Üniversitesi, 2009-05-06)
With the rapid growth of Internet and Internet-based information, it becomes the largest and publicly accessible data source in the world. Every day millions of information available so to achieve information becomes harder. ...
Spline based neural networks
(Işık Üniversitesi, 2005-06)
In this thesis, we applied the Catmull-Rom splines and B-splines to the neural networks models, which are Multi Layer Perceptrons, Elman Networks, and Locally Recurrent Neural Networks, as adaptive activation functions. ...
Fingertip ECG signal based biometric recognition system
(Işık Üniversitesi, 2016-05-10)
The idea is the; realize biometric recognition system by using ECG signal which was began to use in the last 10 years. Until now, ECG based biometric systems have been developed by using the database which ECG signals are ...
Fabric defect detection in frequency domain using fourier analysis
(Işık Üniversitesi, 2016)
An overwhelming majority of image processing based defect detection approaches rely on machine learning methods to train a model for comparison of test examples. This requires a training phase for each item to be learned ...
Word sense disambiguation, named entity recognition, and shallow parsing tasks for Turkish
(Işık Üniversitesi, 2019-04-02)
People interactions are based on sentences. The process of understanding sentences is thru converging, parsing the words and making sense of words. The ultimate goal of Natural Language Processing is to understand the ...
Statistical analysis of bus transportation networks for four largest cities in Turkey
(Işık Üniversitesi, 2011-06-01)
Network properties for public bus transportation networks (BTNs) of four largest cities (İstanbul, İzmir, Ankara, Bursa) in Turkey have been analyzed under C-, L- and P-Space topologies. Node degree distributions are shown ...
Cost sensitive learning algorithms
(Işık Üniversitesi, 2008)
This thesis studies the cost sensitive learning algorithms that calculate the class learning algorithms errors and costs. Data mining is the automated extraction of hidden predictive information from databases that can be ...