home

Yrd. Doç. Dr. Ümit Atila


Karabük Üniversitesi, Mühendislik Fakültesi
Bilgisayar Mühendisliği Bölümü

profile

Ümit ATİLA, 1979 yılında Tarsus’ta doğdu. Gazi Üniversitesi Teknik Eğitim Fakültesi Elektronik ve Bilgisayar Eğitimi Bölümü'nden 2002 yılında mezun oldu. 2005 yılına kadar Aksaray’da Milli Eğitim'e bağlı çeşitli okullarda öğretmenlik yaptı. 2007 yılında Gazi Üniversitesi Fen Bilimleri Enstitüsü İleri Teknolojiler Ana Bilim Dalı'nda yüksek lisans eğitimini tamamladı. 2009 yılına kadar Milli Eğitim Bakanlığı Eğitim Teknolojileri Genel Müdürlüğü Bilişim Hizmetleri Dairesi'nde bilgisayar programcısı olarak çeşitli projelerde görev aldı. 2009-2012 yılları arasında Gazi Üniversitesi Bilgi İşlem Dairesi Başkanlığı'nda Uzman olarak görev yaptı. 2012 yılında Gazi Üniversitesi Ankara Meslek Yüksekokulu'na öğretim görevliliği yaptı. 2009 yılında Karabük Üniversitesi Bilgisayar Mühendisliği Bölümü'nde başladığı doktora çalışmalarını 2013 yılında tamamladı. Aynı sene Karabük Üniversitesi Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüne Yardımcı Doçent olarak atandı ve halen bu görevini sürdürmektedir.

Başlıca çalışma alanları arasında makine öğrenmesi, yapay sinir ağları, optimizasyon, 3 Boyutlu CBS, 3 Boyulu Konumsal Ağlar yer almaktadır. Alanında ulusal ve uluslararası bilimsel toplantılarda sunulmuş bildirileri, hakemli dergilerde yayınlanmış makaleleri ve görev aldığı projeleri bulunmaktadır.

Signature Ümit ATİLA

İş Deneyimi

  • (Devam ediyor) 2013

    Yrd. Doç. Dr.

    Karabük Üniversitesi, Bilgisayar Mühendisliği

  • 2013 2012

    Öğ. Gör.

    Gazi Üniversitesi, Ankara Meslek Yüksek Okulu

  • 2012 2009

    Uzman

    Gazi Üniversitesi, Bilgi İşlem Dairesi Başkanlığı

  • 2005 2009

    Programcı

    Milli Eğitim Bakanlığı, Bilgi İşlem Dairesi Başkanlığı

  • 2002 2005

    Öğretmen

    Milli Eğitim Bakanlığı

Eğitim Bilgileri

  • 2013

    Doktora

    Bilgisayar Mühendisliği ABD, Karabük Üniversitesi, Fen Bilimleri Enstitüsü

  • 2008

    Yüksek Lisans

    İleri Teknolojiler ABD, Gazi Üniversitesi, Fen Bilimleri Enstitüsü

  • 2002

    Lisans

    Bilgisayar Sistemleri Öğretmenliği, Gazi Üniversitesi, Elektronik Bilgisayar Eğitimi

service

PROJELER

Biten Projeler

image
image
Proje kapsamında, yüksek binalarda meydana gelen yangın durumunda binadan tahliye olmak isteyen bir kişi için olay anında oluşan çevresel ve insan kaynaklı etkenleri dinamik olarak göz önüne alan, etkileşimli ve gerçek zamanlı bir şekilde ağ analizini gerçekleştirerek kişiye özel tahliye güzergâhını üreten bir Akıllı Tahliye Modeli geliştirilmiştir. Modelin tasarlanmasında İleri Beslemeli Yapay Sinir Ağları kullanılmıştır. Geliştirilen modelin uygulanabilmesi için ayrıca, afetzedeleri cep telefonlarını kullanarak sesli ve görüntülü yönlendirmek amacıyla; sunucu-istemci mimarisinde gerçek zamanlı olarak çalışan; RFID tabanlı bir mobil Konum Belirleme ve Navigasyon Sistemi tasarlanmıştır.
image
Proje kapsamında, yüksek binalarda meydana gelen yangın durumunda binadan tahliye olmak isteyen bir kişi için olay anında oluşan çevresel ve insan kaynaklı etkenleri dinamik olarak göz önüne alan, etkileşimli ve gerçek zamanlı bir şekilde ağ analizini gerçekleştirerek kişiye özel tahliye güzergâhını üreten bir Akıllı Tahliye Modeli geliştirilmiştir. Modelin tasarlanmasında Genetik Algoritma kullanılmıştır.

resume

AKADEMİK YAYINLAR

SCI / ESCI İndekslerde Taranan Makaleler

Today the number of complex and multi-storey buildings, such as skyscrapers, airports and shopping centers, is on the increase with each passing day. In parallel to this, the number of people spending time in such buildings is also on a rapid increase. In these buildings, many people lose their direction, fail to find the places they are seeking or the exits, and thus, they end up with experiencing problems in such cases. Beyond that, it becomes much more difficult for people to exit these buildings under emergency cases, particularly in case of a fire. Congestions occur in certain spots of the building, which then leads to panic and confluence. In the fire, some victims cannot even find an escape route and lose their lives either by catching the fire or by jumping out of the window. Within this context, a dynamic, intelligent, real-time indoor navigation system for the fire evacuation has been developed, which navigates each user within the building according to their own physical features and varying conditions of the building in the case of a fire. In this system, the positions of the users are tracked by the Radio-Frequency Identification (RFID) Technology. The necessary instructions for guidance to evacuate the users are prepared on a neural network- based module over a server and are sent to the users’ smartphones in a real-time manner. The proposed system navigates the users over their smartphone instantaneously via vocally-visual elements and allows them to be transported to the exit confidently.
Recently, with the increasing interest in using handheld devices, the application of navigation systems that provide driving information to the drivers has become widespread in daily life. An efficient route guidance system should consider the influential factors of traffic flow such as traffic density and allowable velocity limits of the roads. As the number of influential factors and amount of nodes in road network increase, the computational cost increases. On navigation systems, using handheld devices with limited processing speed and memory capacity, it is not feasible to find the exact optimal solution in real-time for the road networks with excessive number of nodes using deterministic methods such as Dijkstra algorithm. This paper proposes a Genetic Algorithm approach applied to a route guidance system to find the shortest driving time. Constant length chromosomes have been used for encoding the problem. It was found that the mutation operator proposed in this algorithm provided great contribution to achieve optimum solution by maintaining the genetic diversity. The efficiency of the genetic algorithm was tested by applying it on the networks with different sizes.

Diğer İndekslerde Taranan Makaleler

3D navigation within a 3D-GIS environment is increasingly getting more popular and spreading to various fields. In the last decade, especially after the 9/11 disaster, evacuating the complex and tall buildings of today in case of emergency has been an important research area for scientists. Most of the current navigation systems are still in the 2D environment and that is insufficient to visualize 3D objects and to obtain satisfactory solutions for the 3D environment. Therefore, there is currently still a lack of implementation of 3D network analysis and navigation for indoor spaces in respect to evacuation. The objective of this paper is to investigate and implement 3D visualization and navigation techniques and solutions for indoor spaces within 3D-GIS. For realizing this, we have proposed a GIS implementation that is capable of carrying out 3D visualization of a building model stored in the CityGML format and perform analysis on a network model stored in Oracle Spatial. The proposed GUI also provides routing simulation on the calculated shortest paths with voice commands and visual instructions.
People‘s orientation to the mobile devices all over the world have made the using of route guidance systems that assist drivers on the traffic widespread in daily life. For an effective routing, these systems should take into account the effectual factors of traffic flow such as allowable velocity limits of the roads and density. The computational cost of the system is up to the amount of nodes in road network and effectual factors. When we consider the road networks with excessive number of nodes, finding the exact routes in real time using some well known deterministic methods such as Dijkstra‘s algorithm on such routing systems may not be accurate using mobile devices with limited memory capacity and processing speed. In this paper, a Genetic Algorithm (GA) approach applied on a route guidance system for finding the shortest driving time is proposed. A different gene search approach on crossover operation named ―first-match-genes‖ had been introduced. A mobile application for the traffic network of Ankara and the performance of the genetic algorithm tested on networks with 10, 50, 250, 1000 nodes was presented.

Uluslararası Kitap Bölümleri

The need for 3D visualization and navigation within 3D-GIS environment is increasingly growing and spreading to various fields. When we consider current navigation systems, most of them are still in 2D environment that is insufficient to realize 3D objects and obtain satisfactory solutions for 3D environment. For realizing such a 3D navigation system we need to solve complex 3D network analysis. The objective of this paper is to investigate and implement 3D visualization and navigation techniques and develop 3D routing instruction engine for indoor spaces within 3D-GIS. As an initial step and as for implementation a Graphical User Interface provides 3D visualization based on CityGML data, stores spatial data in a Geo-Database and then performs complex network analysis. By using developed engine, the GUI also provides a routing simulation on a calculated shortest path with voice commands and visualized instructions.
Research on evacuation of high-rise buildings in case of disasters such as fire, terrorist attacks, indoor air pollution incidents, etc., has become popular in the last decade. In case of such disasters, people inside the buildings should be evacuated out of the area as soon as possible. However, organizing a quick and safe evacuation is a difficult procedure due to the complexity of high-rise buildings and the huge number of people occupied inside such buildings. Besides, problems such as smoke inhalation, confluence, panic, and inaccessibility of some exits may arise during the evacuation procedure. Therefore, an efficient user-centric evacuation system should be developed for quick and safe evacuation from high and complex buildings. Routing someone to an appropriate exit in safety can only be possible with a system that can manage the 3D topological transportation network of a building. Realizing an evacuation of a building in such systems also called navigation systems ...
Designing 3D navigation systems requires addressing solution methods for complex topologies, 3D modelling, visualization, topological network analysis and so on. 3D navigation within 3D-GIS environment is increasingly growing and spreading to various fields. One of those fields is evacuation through the shortest path with safety in case of disasters such as fire, massive terrorist attacks happening in complex and tall buildings of today’s world. Especially fire with no doubt is one of the most dangerous disaster threatening these buildings including thousands of occupants inside. This chapter presents entire solution methods for designing an intelligent individual evacuation model starting from data generation process. The model is based on Multilayer Perceptron (MLP) which is one of the most preferred artificial neural network architecture in classification and prediction problems. We focus on integration of this model with a 3D-GIS based simulation for demonstrating an individual evacuation process.
The need for 3D visualization and navigation within 3D-GIS environment is increasingly growing and spreading to various fields. When we consider current navigation systems, most of them are still in 2D environment that is insufficient to realize 3D objects and obtain satisfactory solutions for 3D environment. One of the most important research areas is evacuating the buildings with safety as more complex building infrastructures are increasing in today’s world. The end user side of such evacuation system needs to run in mobile environment with an accurate indoor positioning while the system assist people to the destination with support of visual landscapes and voice commands. For realizing such navigation system we need to solve complex 3D network analysis. The objective of this paper is to investigate and implement 3D visualization and navigation techniques and solutions for indoor spaces within 3D-GIS. As an initial step and as for implementation a GUI provides 3D visualization of Corporation Complex in Putrajaya based on CityGML data, stores spatial data in a Geo-Database and then performs complex network analysis under some different kind of constraints. The GUI also provides a routing simulation on a calculated shortest path with voice commands and visualized instructions which are intended to be the infrastructure of a voice enabled mobile navigation system in our future work.

Uluslararası Bildiriler

Bir enerji kaynağı ve hava kütlelerinin hareketi olarak bilinen rüzgar, enerji ihtiyacını karşılaması bakımından ekonomik ve çevresel olarak çok büyük öneme sahiptir. Hava hareketleri, temel olarak güneşin dünyayı ısıtmasındaki ısıl farklar ve basınç farklılıklarından kaynaklanmaktadır. Rüzgarı yapısındaki türbülanslı çalkantılardan dolayı analitik olarak incelemek zordur. Enerji üretiminin ve Rüzgar Enerji Sistemlerinin(RES) planlanmasında rüzgar hızının tahmin edilmesinin çok büyük önemi vardır. Bu maksatla literatürde bir çok çalışma bulunmaktadır. Bu çalışmada Karabük rüzgar hız verileri, Yapay Sinir Ağları(YSA) ve Çoklu Lineer Regresyon(ÇLR) yöntemleri ile tahmin edilmiş ve modellerin kıyaslaması yapılmıştır.
High rise, complex and huge buildings in the cities are almost like a small city with their tens of floors, hundreds of corridors and rooms and passages. Due to size and complexity of these buildings, people need guidance to find their way to the destination in these buildings. In this study, a mobile application is developed to visualize pedestrian's indoor position as 3D in their smartphone and RFID Technology is used to detect the position of pedestrian. While the pedestrian is walking on his/her way on the route, smartphone will guide the pedestrian by displaying the photos of indoor environment on the route. Along the tour, an RFID (Radio-Frequency Identification) device is integrated to the system. The pedestrian will carry the RFID device during his/her tour in the building. The RFID device will send the position data to the server directly in every two seconds periodically. On the other side, the pedestrian will just select the destination point in the mobile application on smartphone and sent the destination point to the server. The shortest path from the pedestrian position to the destination point is found out by the script on the server. This script also sends the environment photo of the first node on the acquired shortest path to the client as an indoor navigation module.
In this study, an RFID based indoor positioning system has been proposed. In the system, while RFID readers have been considered to be mobile, RFID tags have been attached on fixed positions inside building. Performance of various types of readers and tags on indoor positioning has been investigated and most appropriate tag/reader couple has been used. In the experiments of this study, geographical proximity approach has been used. As the results of tests performed on three different model proposed for indoor positioning, it has been shown that best rate for position estimations without error have been obtained from third model with the rate of approximately 76% and in the worst case, position estimation error has been obtained 2 meters.
In this study, a knowledge management based Decision Support System has been suggested. By collecting the data of people, event and properties of building, a 3D navigation system has been developed to support building management and users during the extraordinary circumstances. Most of the current navigation systems are still in the 2D environment and that is insufficient to visualize 3D objects and to obtain satisfactory solutions for the 3D environment. Therefore, there is currently still a lack of implementation of 3D network analysis and navigation for indoor spaces in respect to evacuation. 3D navigation within a 3D-GIS environment (Three Dimensional Geographical Information Systems) is increasingly getting more popular and spreading to various fields. In the last decade, especially after the 9/11 disaster, evacuating the complex and tall buildings of today in case of emergency has been an important research area for scientists. The objective of this paper is to implement 3D visualization and navigation techniques and solutions for indoor spaces within 3D -GIS. For realizing this, we have proposed a GIS implementation that is capable of carrying out 3D visualization of a building model stored in the CityGML format and perform analysis on a network model stored in Oracle Spatial. The proposed GUI also provides routing simulation on the calculated shortest paths with voice commands and visual instructions.
One of the most dangerous disaster threatening the high rise and complex buildings of today's world including thousands of occupants inside is fire with no doubt. When we consider high population and the complexity of such buildings it is clear to see that performing a rapid and safe evacuation seems hard and human being does not have good memories in case of such disasters like world trade center 9/11. Therefore, it is very important to design knowledge based realtime interactive evacuation methods instead of classical strategies which lack of flexibility. This paper presents a 3D-GIS implementation which simulates the behaviour of an intelligent indoor pedestrian navigation model proposed for a self -evacuation of a person in case of fire. The model is based on Multilayer Perceptron (MLP) which is one of the most preferred artificial neural network architecture in classification and prediction problems. A sample fire scenario following through predefined instructions has been performed on 3D model of the Corporation Complex in Putrajaya (Malaysia) and the intelligent evacuation process has been realized within a proposed 3D-GIS based simulation.
This paper describes the usage of MUSCLE (Multidirectional Scanning for Line Extraction) Model for automatic generation of 3D networks in CityGML format (from raster floor plans). MUSCLE (Multidirectional Scanning for Line Extraction) Model is a conversion method which was developed to vectorize the straight lines through the raster images including floor plans, maps for GIS, architectural drawings, and machine plans. The model allows user to define specific criteria which are crucial for acquiring the vectorization process. Unlike traditional vectorization process, this model generates straight lines based on a line thinning algorithm, without performing line following-chain coding and vector reduction stages. In this method the nearly vertical lines were obtained by scanning the images horizontally, while the nearly horizontal lines were obtained by scanning the images vertically. In a case where two or more consecutive lines are nearly horizontal or nearly vertical, raster data become unmanageable and the process generates wrongly vectorized lines. In this situation, to obtain the precise lines, the image with the wrongly vectorized lines is diagonally scanned. By using MUSCLE model, the network models are topologically structured in CityGML format. After the generation process, it is possible to perform 3D network analysis based on these models. Then, by using the software that was designed based on the generated models, a geodatabase of the models could be established. This paper presents the correction application in MUSCLE and explains 3D network construction in detail.
The need for 3D visualization and navigation within 3D-GIS environment is increasingly growing and spreading to various fields. When we consider current navigation systems, most of them are still in 2D environment that is insufficient to realize 3D objects and obtain satisfactory solutions for 3D environment. One of the most important research areas is evacuating the buildings with safety as more complex building infrastructures are increasing in today’s world. The end user side of such evacuation system needs to run in mobile environment with an accurate indoor positioning while the system assist people to the destination with support of visual landscapes and voice commands. For realizing such navigation system we need to solve complex 3D network analysis. The objective of this paper is to investigate and implement 3D visualization and navigation techniques and solutions for indoor spaces within 3D-GIS. As an initial step and as for implementation a GUI provides 3D visualization of Corporation Complex in Putrajaya based on CityGML data, stores spatial data in a Geo-Database and then performs complex network analysis under some different kind of constraints. The GUI also provides a routing simulation on a calculated shortest path with voice commands and visualized instructions which are intended to be the infrastructure of a voice enabled mobile navigation system in our future work.
Designing 3D navigation systems requires addressing solution methods for complex topologies, 3D modelling, visualization, topological network analysis and so on. 3D navigation within 3D-GIS environment is increasingly growing and spreading to various fields. One of those fields is evacuation through the shortest path with safety in case of disasters such as fire, massive terrorist attacks happening in complex and tall buildings of today’s world. Especially fire with no doubt is one of the most dangerous disaster threatening these buildings including thousands of occupants inside. This chapter presents entire solution methods for designing an intelligent individual evacuation model starting from data generation process. The model is based on Multilayer Perceptron (MLP) which is one of the most preferred artificial neural network architecture in classification and prediction problems. We focus on integration of this model with a 3D-GIS based simulation for demonstrating an individual evacuation process
Nowadays, with the advancement of the technology on mobile devices, route guidance systems that assist drivers on the traffic have become widespread in daily life. For an accurate routing, a route guidance system should consider the effectual factors of traffic flow such as density and allowable velocity limits of the roads. With the increase of effectual factors and amount of nodes in road network, the computational cost increases. It is not proper to find exact optimal solution in real time for the road networks with excessive number of nodes using some well known deterministic methods such as Dijkstra's algorithm on navigation systems using mobile devices with limited processing speed and memory capacity. This paper proposes a route guidance system and a Genetic Algorithm (GA) approach applied on this routing system to find the shortest driving time. Excluding classical methods, a gene search method of chromosomes named "first-matched-genes" on crossover operation had been introduced . The efficiency of the genetic algorithm was tested by applying on the networks with different sizes and a mobile application on the traffic network of Ankara was presented
3D network analysis for indoor provides strong decision support for users in searching optimal routes on applications such as emergency services, transportation, security and visitor guiding. Genetic algorithm is used to solve non-linear problems with complicated constraints. Therefore, the implementation of genetic algorithm into route finding algorithms is needed. This paper explains the demand using genetic algorithm approach on dynamic network routing problems especially for 3D navigation. Abilities of genetic algorithm is investigated as a search strategy and necessitates of genetic algorithm on use for 3D dynamic network routing is presented.

portfolio

  • Filtrele
  • Tüm Dersler
  • Lisans
  • Seçmeli
  • Lisans Üstü
img01

BLM-111 Programlama Dilleri 1

lisans

img02

BLM-112 Programlama Dilleri 2

lisans

img03

BLM-411 Yapay Zeka

4. Sınıf Seçmeli

img04

BSM-767 Makine Öğrenmesi

lisans üstü

img05

BSM-746 Yapay Sinir Ağlarında Seçme Konular

lisans üstü

BLM-111 Programlama Dilleri 1

Dersin Amacı

Problem çözümüne yönelik algoritma tasarlama ve C programlama dili kullanarak program geliştirmenin öğrenilmesi. C programlama tekniklerini kullanarak çeşitli problemlere çözüm bulunması.

Dersin İçeriği

Algoritma kavramı, Giriş/Çıkış işlemleri, Değişken Kavramı, Basit matematiksel işlemler, Kontrol yapıları (if/if-else/switch-case), Döngü yapıları (while/do-while/for), Algoritma örnekleri ve analiz, C programlamaya giriş, C derleyicisinin işleyişi, C dilinde değişken tipleri, Temel giriş/çıkış işlemleri (printf, scanf), C dilinde kontrol ve döngü yapıları, Diziler, Çok boyutlu diziler, Karakter tutan diziler, Fonksiyonlar

Kaynaklar

C How to Program, Deitel&Deitel, 6/e,2010, Prentice Hall


Problem Solving & Program Design in C 7th Edition, Jerry H. Hanly, B.Koffman, Pearson, 2012


A'dan Z'ye C Klavuzu, Kaan Aslan, Pusula Yayıncılık,2002

BLM-112 Programlama Dilleri 2

Dersin Amacı

İşaretçiler ve listelerin kullanımını anlamak. Basit sıralama ve arama algoritmalarını öğrenmek. Öğrencilerin dosya işlemleri, bitişlemler, görsel programlama ve temel grafik işlemleriyle etkin programlar yazmasını sağlamaktır.

Dersin İçeriği

Rekürsif fonksiyonlar, işaretçiler, değer yoluyla çağırma, referans yoluyla çağırma, dinamik bellek yönetimi, işaretçiler ile ilgili örnekler, struct, enum ve typedef tanımlamaları, tek bağlı doğrusal listeler, sıralama ve arama algoritması (seçmeli sıralama-ardışıl arama), string (strcpy, strlen, strcmp, vb.) ve matematiksel (rand,pow,floor,ceil vb.) fonksiyonlar, dosya işlemleri, sıralı erişimli dosyalar, rasgele erişimli dosyalar, bitişlem operatörleri, C programlama dili ile temel grafik işlemleri.

Kaynaklar

C How to Program, Deitel&Deitel, 6/e,2010, Prentice Hall


Problem Solving & Program Design in C 7th Edition, Jerry H. Hanly, B.Koffman, Pearson, 2012


A'dan Z'ye C Klavuzu, Kaan Aslan, Pusula Yayıncılık,2002

BLM-411 Yapay Zeka

Dersin Amacı

Yapay Zeka, zeki davranışta hesaplamalı çalışmaya yöneliktir. Yapay zeka alanlarının hepsindeki ortak esas, “düşünebilen” etmenler/makinalar oluşturmaktır. Bu ders, etmenlerin/bilgisayarların akıllı davranmasına olanak tanıyan yöntemlere (problem çözme, öğrenme, algılama ve yorumlama) ilişkin geniş bir teknik giriş içermektedir. Dersin büyük bir bölümünde bu yöntemlerdeki çeşitlilikler yansıtılmaktadır. Derste, temel yapay zeka soruları ve unsurları incelenecek ve ana teknikler araştırılacaktır.

Dersin İçeriği

Yapay Zeka Kavramı, Akıllı Etmenler, Problem çözme ve Arama, Bilgili ve Bilgisiz Arama, Yerel arama ve optimizasyon,Genetik Algoritmalar, Kısıt sağlama problemleri; Oyun oynama ve rekabet ortamında arama; Öğrenme ve Karar Ağaçları, Örnek Temelli Öğrenme, Sinir Ağları ve Yapay Nöron Modeli, Doğrusal Regresyon ve Doğrusal Sınıflandırıcı Perceptron, Eğim Düşümü Yöntemi ve Tek Katmanlı Perceptronlar, Çok Katmanlı Perceptronlar ve Geri Yayılım Algoritması.

Kaynaklar

Artificial Intelligence: A Modern Approach. Stuart Russell, Peter Norvig, Prentice Hall, Second


Edition Yapay Zeka, Vasif. V. Nabiyev, Seçkin Yayıncılık


BSM-767 Makine Öğrenmesi

Dersin Amacı

Bu ders Makine öğrenmesi için temel teori, algoritma ve uygulamaları içermektedir. Makine öğrenmesi, büyük verilen içeren finans, sağlık, ticari ve bilimsel uygulamalar için anahtar teknolojidir. Makine öğrenmesi, hesaplama yapabilen sistemlerin örneklerden edinilen tecrübe ile performanslarını artırmalarını sağlar. Bu ders hem teorik hem de uygulama açısından dengeli bir şekilde matematiksel alt yapısı verilerek makine öğrenmesi kavramlarını açıklamaktadır.

Dersin İçeriği

Bu derste, Makine Öğrenmesi yöntemlerinin teorik ve uygulamalı temelleri incelenerek örüntü tanıma problemlerine bu yöntemlerle çözüm bulunması amaçlanmaktadır.

Kaynaklar

T. Mitchell, "Machine Learning", McGraw-Hill, 1997.


Peter Flatch, "Machine Learning: The Art and Science of Algorithms that Make Sense of Data", Cambridge University Press, 2012


BSM-746 Yapay Sinir Ağlarında Seçme Konular

Dersin Amacı

Bu dersin amacı sezgisel bir yaklaşım olan Yapay Sinir Ağlarının ve onunla ilgili teorilerin matematiksel alt yapısıyla öğretilmesidir.

Dersin İçeriği

Yapay Sinir Ağlarına (YSA) Giriş, Yapay nöron modeli ve doğrusal regresyon, Eğim düşüm yöntemi, Doğrusal olmayan aktivasyon üniteleri, yapay sinir ağı mimarileri ve öğrenme mekanizmaları, İstatistiksel açıdan öğrenme, VC-Dimensions, Yapısal risk minimizasyonu, Tek katmanlı algılayıcılar, Perceptron yaklaşma teoremi, Çok katmanlı algılayıcı modeli, Geri yayılımlı öğrenme, Veri Normalizasyonu, Veri Hazırlanması, Giriş Verilerinin Kodlanması, Çıkış Verilerinin Kodlanması, Radyal temelli ağlar, SOM ağları, Elman Ağları, LVQ Ağları.

Kaynaklar

S. Haykins, "Neural Networks", Pearson (2nd Edition).


Paul E. Keller, Kevin L. Priddy, "Artificial Neural Networks: an Introduction", PHI, 2007


blog

DUYURULAR

  • LİSANS BİTİRME PROJESİ DERSİ DUYURUSU - 08.05.2017

    Lisans bitirme projesi poster sunumları 24 Mayıs Çarşamba günü saat 14:30-16:00 arasında fuaye salonunda yapılacaktır (Hamit Çepni önü). Posterlerinizle birlikte belirtilen saatte hazır olunması gerekiyor.

  • LİSANS BİTİRME PROJESİ DERSİ DUYURUSU - 26.04.2017

    Lisans bitirme projesi vize notu için 3. sunumları 3 Mayıs Çarşamba günü saat 10:00-15:00 arası uygun bir saatte odamda yapabilirsiniz.

  • LİSANS BİTİRME PROJESİ DERSİ DUYURUSU - 11.02.2017

    Lisans bitirme tez görüşme günü ve saati her Pazartesi saat 13:00-16:00 saatleri arasındadır..

  • YENİ DÖNEM DUYURUSU - 06.02.2017

    2016-2017 Bahar Döneminde Tüm Öğrencilerimize Başarılar Dilerim...

galeri

contact

İLETİŞİM

  • Ad Soyad : Ümit ATİLA
  • Doğum : 2 Mayıs 1979
  • Phone : +90 (370) 4332021-3811
  • Email-1 : umitatila@karabuk.edu.tr
  • Email-2 : umitatila@gmail.com
  • Resmi Website : muh.karabuk.edu.tr
  • Adres : Karabük Üniversitesi, Mühendislik Fakültesi, Balıklar Kayası Mevkii 78050 KARABÜK