Rasim Aşkın Dilan - Academia.edu (original) (raw)

Uploads

Papers by Rasim Aşkın Dilan

Research paper thumbnail of Hareketli robotlar için yapay sinir ağları kullanılarak görüntü işleme ile düzensiz yol tanıma ve takibi

For an autonomous outdoor mobile robot ability to detect roads existing around is a vital capabil... more For an autonomous outdoor mobile robot ability to detect roads existing around is a vital capability. Unstructured roads are among the toughest challenges for a mobile robot both in terms of detection and navigation. Even though mobile robots use various sensors to interact with their environment, being a comparatively low-cost and rich source of information, potential of cameras should be fully utilized. This research aims to systematically investigate the potential use of streaming camera images in detecting unstructured roads. The investigation focused on the use of methods employing Artificial Neural Networks (ANNs). An exhaustive test process is followed where different kernel sizes and feature vectors are varied systematically where trainings are carried out via backpropagation in a feed-forward ANN. The thesis also claims a contribution in the creation of test data where truth images are created almost in realtime by making use of the dexterity of human hands. Various road pr...

Research paper thumbnail of Bir Doğru Akım Motorunun FPGA Üzerinde Gerçek Zamanlı Benzetiminin Gerçekleştirilmesi

Research paper thumbnail of An online intelligent algorithm pipeline for the elimination of springback effect during sheet metal bending

Procedia Engineering, 2017

An intelligent control algorithm pipeline is proposed to eliminate the effects of variation of ph... more An intelligent control algorithm pipeline is proposed to eliminate the effects of variation of physical properties of sheet metals on bending. This pipeline can be applied to any conventional press brake without the necessity of additional sensors and/or equipment. The overall pipeline is capable of extracting features representing sheet metal during bending in an online manner, classifying it accordingly, running a neural network model specific to the classified material, and calculating the correct punch displacement in order to eliminate springback effect. Moreover, algorithm pipeline can also decide whether the material processed is already in the material database or not. If the material is not in the material database, it directs the user in order to generate a quick reference model for completing the bending procedure and adds this model in the material database. The overall algorithm pipeline provides an autonomous approach to material bending and saves time by eliminating tedious calibration and bending iterations.

Research paper thumbnail of Bir Dogru Akim Motorunun FPGA �zerinde Ger�ek Zamanli Benzetiminin Ger�eklestirilmesi

Research paper thumbnail of �evrimi�i Donanim Benzetimi i�in Yeni bir Yazilim Paketi: Cadmus

Research paper thumbnail of Real-time hardware-in-the-loop simulation of electrical machine systems using FPGAs

2009 International Conference on Electrical Machines and Systems, 2009

Abstract This study focuses on the development an integrated software and hardware platform that ... more Abstract This study focuses on the development an integrated software and hardware platform that is capable of performing real-time simulation of dynamic systems, including electrical machinery, for the purpose of hardware-in-the-loop simulation (HILS). The ...

Research paper thumbnail of Rapid training data generation from image sequences for pattern recognition

2011 IEEE International Conference on Mechatronics, 2011

Abstract This study focuses on the development of a novel technique for the rapid generation of a... more Abstract This study focuses on the development of a novel technique for the rapid generation of artificial neural network training data from video streams. Videos captured on an off-road terrain are used to train artificial neural networks that learn to differentiate road ...

Research paper thumbnail of 3 Serbestli̇k Derecesi̇ne Sahi̇p Bi̇r Hareket Takli̇tçi̇si̇ni̇n Mafsal Uzayi Eni̇yi̇lemesi̇ Ve Çözüm Anali̇zi̇

... iki parametre optimum değerlerinde sabit tutularak silindirlerin üst platforma bağlanma yarıç... more ... iki parametre optimum değerlerinde sabit tutularak silindirlerin üst platforma bağlanma yarıçapı değiştirilerek ve her türlü faz ve durum ... 2006 dan bu yana ODTÜ Makina Mühendisliği Bölümünde Araştırma Görevlisi olarak çalışmaktadır ve Doktora çalışmalarını yürütmektedir. ...

Research paper thumbnail of Çevrimiçi Donanım Benzetimi için Yeni bir Yazılım Paketi: Cadmus

me.metu.edu.tr

Page 1. Çevrimiçi Donanım Benzetimi için Yeni bir Yazılım Paketi: Cadmus Serdar Üşenmez1 , Rasim ... more Page 1. Çevrimiçi Donanım Benzetimi için Yeni bir Yazılım Paketi: Cadmus Serdar Üşenmez1 , Rasim Aşkın Dilan2, Ulaş Yaman3 , Barış Ragıp Mutlu4 , Melik Dölen5 , Ahmet Buğra Koku6 Makina Mühendisliği Bölümü Orta ...

Research paper thumbnail of Application of Multivariate Adaptive Regression Splines (MARS) to the Preference Mapping of Cheese Sticks

Journal of Food Science, 2006

ABSTRACT: A novel modeling technique named MARS (Multivariate Adaptive Regression Splines) can au... more ABSTRACT: A novel modeling technique named MARS (Multivariate Adaptive Regression Splines) can automate variable selection as well as model selection. The main purpose of this study was to apply MARS to consumer preference mapping using consumer test data for cheese sticks. The results show that MARS was capable of modeling consumer's preference patterns for cheese sticks. One distinct advantage of MARS in preference mapping is that it has the ability to model hedonic-scale response variables (such as overall acceptance, acceptance of appearance, flavor, and texture) from “Just About Right” (JAR) predictor variables (such as color, size, saltiness, breading, and cheese texture). In addition, MARS can reveal the underlying relationship between the predictors and the response in a piecewise regression function. This study shows that MARS has potential uncovering underlying patterns hidden in complex data.

Research paper thumbnail of Hareketli robotlar için yapay sinir ağları kullanılarak görüntü işleme ile düzensiz yol tanıma ve takibi

For an autonomous outdoor mobile robot ability to detect roads existing around is a vital capabil... more For an autonomous outdoor mobile robot ability to detect roads existing around is a vital capability. Unstructured roads are among the toughest challenges for a mobile robot both in terms of detection and navigation. Even though mobile robots use various sensors to interact with their environment, being a comparatively low-cost and rich source of information, potential of cameras should be fully utilized. This research aims to systematically investigate the potential use of streaming camera images in detecting unstructured roads. The investigation focused on the use of methods employing Artificial Neural Networks (ANNs). An exhaustive test process is followed where different kernel sizes and feature vectors are varied systematically where trainings are carried out via backpropagation in a feed-forward ANN. The thesis also claims a contribution in the creation of test data where truth images are created almost in realtime by making use of the dexterity of human hands. Various road pr...

Research paper thumbnail of Bir Doğru Akım Motorunun FPGA Üzerinde Gerçek Zamanlı Benzetiminin Gerçekleştirilmesi

Research paper thumbnail of An online intelligent algorithm pipeline for the elimination of springback effect during sheet metal bending

Procedia Engineering, 2017

An intelligent control algorithm pipeline is proposed to eliminate the effects of variation of ph... more An intelligent control algorithm pipeline is proposed to eliminate the effects of variation of physical properties of sheet metals on bending. This pipeline can be applied to any conventional press brake without the necessity of additional sensors and/or equipment. The overall pipeline is capable of extracting features representing sheet metal during bending in an online manner, classifying it accordingly, running a neural network model specific to the classified material, and calculating the correct punch displacement in order to eliminate springback effect. Moreover, algorithm pipeline can also decide whether the material processed is already in the material database or not. If the material is not in the material database, it directs the user in order to generate a quick reference model for completing the bending procedure and adds this model in the material database. The overall algorithm pipeline provides an autonomous approach to material bending and saves time by eliminating tedious calibration and bending iterations.

Research paper thumbnail of Bir Dogru Akim Motorunun FPGA �zerinde Ger�ek Zamanli Benzetiminin Ger�eklestirilmesi

Research paper thumbnail of �evrimi�i Donanim Benzetimi i�in Yeni bir Yazilim Paketi: Cadmus

Research paper thumbnail of Real-time hardware-in-the-loop simulation of electrical machine systems using FPGAs

2009 International Conference on Electrical Machines and Systems, 2009

Abstract This study focuses on the development an integrated software and hardware platform that ... more Abstract This study focuses on the development an integrated software and hardware platform that is capable of performing real-time simulation of dynamic systems, including electrical machinery, for the purpose of hardware-in-the-loop simulation (HILS). The ...

Research paper thumbnail of Rapid training data generation from image sequences for pattern recognition

2011 IEEE International Conference on Mechatronics, 2011

Abstract This study focuses on the development of a novel technique for the rapid generation of a... more Abstract This study focuses on the development of a novel technique for the rapid generation of artificial neural network training data from video streams. Videos captured on an off-road terrain are used to train artificial neural networks that learn to differentiate road ...

Research paper thumbnail of 3 Serbestli̇k Derecesi̇ne Sahi̇p Bi̇r Hareket Takli̇tçi̇si̇ni̇n Mafsal Uzayi Eni̇yi̇lemesi̇ Ve Çözüm Anali̇zi̇

... iki parametre optimum değerlerinde sabit tutularak silindirlerin üst platforma bağlanma yarıç... more ... iki parametre optimum değerlerinde sabit tutularak silindirlerin üst platforma bağlanma yarıçapı değiştirilerek ve her türlü faz ve durum ... 2006 dan bu yana ODTÜ Makina Mühendisliği Bölümünde Araştırma Görevlisi olarak çalışmaktadır ve Doktora çalışmalarını yürütmektedir. ...

Research paper thumbnail of Çevrimiçi Donanım Benzetimi için Yeni bir Yazılım Paketi: Cadmus

me.metu.edu.tr

Page 1. Çevrimiçi Donanım Benzetimi için Yeni bir Yazılım Paketi: Cadmus Serdar Üşenmez1 , Rasim ... more Page 1. Çevrimiçi Donanım Benzetimi için Yeni bir Yazılım Paketi: Cadmus Serdar Üşenmez1 , Rasim Aşkın Dilan2, Ulaş Yaman3 , Barış Ragıp Mutlu4 , Melik Dölen5 , Ahmet Buğra Koku6 Makina Mühendisliği Bölümü Orta ...

Research paper thumbnail of Application of Multivariate Adaptive Regression Splines (MARS) to the Preference Mapping of Cheese Sticks

Journal of Food Science, 2006

ABSTRACT: A novel modeling technique named MARS (Multivariate Adaptive Regression Splines) can au... more ABSTRACT: A novel modeling technique named MARS (Multivariate Adaptive Regression Splines) can automate variable selection as well as model selection. The main purpose of this study was to apply MARS to consumer preference mapping using consumer test data for cheese sticks. The results show that MARS was capable of modeling consumer's preference patterns for cheese sticks. One distinct advantage of MARS in preference mapping is that it has the ability to model hedonic-scale response variables (such as overall acceptance, acceptance of appearance, flavor, and texture) from “Just About Right” (JAR) predictor variables (such as color, size, saltiness, breading, and cheese texture). In addition, MARS can reveal the underlying relationship between the predictors and the response in a piecewise regression function. This study shows that MARS has potential uncovering underlying patterns hidden in complex data.