Yazar "Kurnaz, Ismail" seçeneğine göre listele

Listeleniyor 1 - 6 / 6
  • Küçük Resim Yok
    Öğe
    Classification of ElectroCorticoGraphy Signals Reduced by Wavelet Transform
    (Ieee, 2016) Kurnaz, Ismail; ErdemErkan
    Studies to solve the mystery of how the human brain works is receiving considerable attention in recent years. Analysis of the signals produced in brain is also within the scope. In this study, classification of ECoG (Electrocorticography) signals which produced in brain is performed. The data used in this study were obtained from data set no 1 which had been used on BCI Competition III. The first part, to decrease the processing load, the number of channels are reduced by eliminating channels (electrodes) which have low separation success. Than it was obtained Wavelet coefficients by Discrete Wavelet Transform (DWT) and determined classification features from Wavelet Coefficents. These features are tested by KNN (K Nearest Neighbors), SVM (Support Vector Machine) and LDA (Linear Discriminate Analysis) classification methods. It's obtained that 94% success in classification by using KNN.
  • Küçük Resim Yok
    Öğe
    Developing a parameterized simulation platform with intelligent synthetic agents for training driver candidates
    (Elsevier Science Bv, 2011) Cavusoglu, Abdullah; Kurnaz, Ismail
    This study presents a driver Traffic Training Simulator (TTS) that utilizes intelligent synthetic actors. The movements of intelligent actors are realized using a network flow graph consisting of segment nodes. The intelligent actors in traffic are capable of such objectives as vehicles and lane following. In addition, they are capable of moving according to the traffic signs and lights. The duration of traffic lights can parametrically be determined by the simulator interface. Moreover, parametric values such as weather conditions, seasons, and sunlight can be fed to the simulator as inputs. Similarly, the type of the driver's vehicle and other intelligent vehicles and their numbers can also be parametrically determined. The driver is able to drive in the heavy and light traffic conditions. Currently we are focusing on incorporating the hardware components into the system. Following the tests for the candidates with the system is expected to take place in driver training schools. (C) 2010 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Guest Editor.
  • Küçük Resim Yok
    Öğe
    The development of a hardware- and software-based simulation platform for the training of driver candidates
    (Tubitak Scientific & Technological Research Council Turkey, 2013) Cavusoglu, Abdullah; Kurnaz, Ismail
    In this study, a traffic simulation system (TSS) to provide novice driver candidates with opportunities for training and testing has been developed. Autonomous vehicles that follow the flow of traffic in a microsimulation environment were prepared using a hierarchical concurrent state machine. Autonomous vehicles are skilled and have behavioral aspects such as tracking the lanes, following the vehicles, complying with traffic rules, decelerating, accelerating, and intersection crossings. These driver behaviors are parameterized to allow the autonomous agents to act while disregarding the rules (i.e. aggressive behaviors) or behaving normally. The TSS is operated in 3 different modes, namely the orientation, training, and testing modes. During the orientation phase, the candidate driver's target is to get used to the system and the vehicle, along with traffic rules in city conditions. During training, the driver is warned orally (when necessary) and given written handouts about the mistakes that occurred during the training session. The rules to be obeyed in traffic are kept in an XML file in the system and the data are used to follow the driver's behaviors. During the testing phase, an evaluation mechanism is employed. It observes whether the drivers obey or disregard the rules during the testing time interval. At the end of the test drive, a report showing the driver's mistakes is given. The reports and test results can be recorded in the database with the drivers' names for further analysis and evaluation processes. Driver candidates perform the driving using a steering wheel and pedals, along with a screen platform consisting of 3 monitors. With the TSS user interface, parameterized items such as vehicle selection, the crowdedness of the traffic, the timing of the traffic lights, and the determination of air conditions are possible. The system provides a cheap, affordable, and nonrisky platform for the trainees. Test results show that the system improves the drivers' skills and builds trust in them.
  • Küçük Resim Yok
    Öğe
    Gesture Recognition using SAX Method
    (Ieee, 2016) Kurnaz, Ismail; Durgut, Rafet
    In this study, an application is developed to recognize human gestures using data which was recorded by using Microsoft Kinect. The data set used in the study is MSRC-12, and it is created by Microsoft. It has several daily human gestures which were recorded from different users. Before gesture recognition process, recorded data was reduced by PAA method and then it was classified by SAX method. Symbols (which are generated by SAX) of percentage similarity is calculated by developed algorithm. The application can recognize all human gestures in dataset correctly.
  • Küçük Resim Yok
    Öğe
    A study on the effect of psychophysiological signal features on classification methods
    (Elsevier Sci Ltd, 2017) Erkan, Erdem; Kurnaz, Ismail
    The most important factor affecting the performance of a BCI (Brain Cothputer Interface) systems, is classification feature set. Choosing the right features to increase the success of classification is the key point. In BCI systems, signals from brain are used to store into dataset. In this study, BCI Competition III dataset 1 consisting of ECoG (Electrocorticography) signals is preferred. In the first part, in order to decrease the processing load, the number of channels are reduced by eliminating Channels (electrodes) which have low separation success. We developed new algorithm ADA (Arc Detection Algorithm) based on visual channel selection to determine quickly optimal channel subset. Than Obtained Wavelet coefficients by Discrete Wavelet Transform (DWT) and determined classification features from Wavelet coefficients. These features are used to classify by KNN (K Nearest Neighbors), SVM (Support Vector Machine) and LDA (Linear Discriminant Analysis) by different feature set combination. The classification successes of feature combinations which are used in classification are compared. The impact on the classification performance of the right channel and the right property choice is observed. Test results are made with different frequency bands are compared with the same feature set. As a result, the highest classification accuracy of 95% was obtained by selected channels and feature. (C) 2017 Elsevier Ltd. All rights reserved.
  • Küçük Resim Yok
    Öğe
    URBAN TRAFFIC MODELING WITH MICROSCOPIC APPROACH USING CELLULAR AUTOMATA
    (Univ Osijek, Tech Fac, 2016) Kurnaz, Ismail
    Traffic jam is one of the hardest problems of the crowded cities, and it needs to be solved. In this study, the effect of the minimum speed limit signs in addition to the maximum speed signs and their locations in traffic flow has been examined by using cellular automata (CA). Urban traffic is modeled by two dimensional CA. The model includes traffic signs, traffic lights and some kinds of vehicles (such as automobiles, vans, buses, metro buses) that are often encountered in traffic.