Data in digital form keeps growing with the advances in Internet and Web technologies. Big Data Analytics is the the process of examining large, unconventional (structured, unstructured, semi-structured and mixed) data to find hidden patterns, unknown correlations, other useful information so that the discovered knowledge can be used by organizations, individuals, and governments to make informed decisions. Big Data research area covers a number of different research directions. Our focus is both (1) on the discovery of new methods for the processing, exploration and analysis of large datasets, and (2) on the application of known methods to the existing big data problems in order to discover, learn, and predict from data. Towards this end we use and apply methods from machine learning, data mining, statistical analysis, and recently deep learning techniques. We also utilize and extend many methods in the areas of text mining and analytics, web analytics, information extraction, graph data and analytics, and semantics. Application areas include web, semantic web, Internet of Things (IoT), financial data, and large corpus of text data.
SPM2M: Standard M2M Software Platform. Development of a generic semantic web and big data analtyics-based IoT framework using OneM2M standards. Includes ontology-based knowledge base, rule-based anomaly detection, time-series data analysis, stream data processing, distributed data analytics (map reduce) and data visualisation with applications on smart grid data. Sponsored by TUBITAK TEYDEB program. Consultant: Erdogan Dogdu. 2015-2017
Recent Publications
Sezer, Omer Berat, Dogdu, Erdogan, Ozbayoglu, Ahmet Murat (2017). Context Aware Computing, Learning and Big Data in Internet of Things: A Survey in IEEE Internet of Things Journal, vol. PP, no. 99, pp. 1-1.
Yumusak, Semih, Dogdu, Erdogan, Kodaz, Halife, and Kamilaris, Andreas (2016). SpEnD: Linked Data SPARQL Endpoints Discovery Using Search Engines. In IEICE Tran. on Information and Systems. 100 (4), 758–767
Sezer, O. B., Ozbayoglu, A. M., & Dogdu, E. (2017). An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Framework. In Proceedings of the SouthEast Conference (pp. 223-226). ACM.
Uysal, E., Yumusak, S., Oztoprak, K., & Dogdu, E. (2017). Sentiment Analysis for the Social Media: A Case Study for Turkish General Elections. In Proceedings of the SouthEast Conference (pp. 215-218). ACM.
Ozbayoglu, Murat, Kucukayan, Gokhan, and Dogdu, Erdogan (2016). A Real-Time Autonomous Highway Accident Detection Model Based on Big Data Processing and Computational Intelligence. In IEEE International Conference on Big Data.
Sezer, Omer Berat, Dogdu, Erdogan, Ozbayoglu, Murat, and Onal, Aras (2016). An Extended IoT Framework with Semantics, Big Data, and Analytics. In IEEE International Conference on Big Data.
Karimov, Jeyhun, Ozbayoglu, Murat, and Dogdu, Erdogan (2015). k-means Performance Improvements with Centroid Calculation Heuristics both for Serial and Parallel environments. In Proceedings of the 2015 IEEE International Congress on Big Data.
Hakimov, Sherzod, Oto, Salih Atilay, and Dogdu, Erdogan (2012). Named entity recognition and disambiguation using linked data and graph-based centrality scoring. In Proceedings of the 4th International Workshop on Semantic Web Information Management.
Laboratory
Big Data Analytics Laboratory
Faculty
Assist. Prof. Dr. Ayşe Nurdan SARAN
Assist. Prof. Dr. Gül TOKDEMİR
Semantic Web and Linked Data
The Semantic Web is made up of technologies that will shape the future of the Web, also referred to as Web 3.0, designed to overcome the shortcomings of the current Web. The future of the Web will continue to be a Web of Documents, but at the same time will be a data network (Web of Data). This data network (Semantic Web) will be easily used by not just people, but by machines, computers and software, and the desired information will be found much faster. In the field of semantic web, we are working on the design and development of (1) ontology-based complex software systems, (2) the discovery and analysis of linked data, and (3) the semantically analysing the meaning of texts using linked data. These studies will lead to the development of question-and-answer systems, smart search engines, smart digital assistants. (translation from Turkish by Google, amazing! with some minor corrections)
SEAS: Smart Energy Aware Systems: Increasing energy efficiency and sustainability via smart energy aware systems in building and micro-grid environments. Use case analysis, SEAS information model and ontology design, SEAS information exchange and web services platform. Consultant: Erdoğan Doğdu, Funded by EU ITEA3. 2014-2016
Waste Management Information System: An Expert System Using Ontologies: Funded by The Ministry of Science, Industry, and Technology Research Fund (SAN-TEZ) program. PI: Erdogan Dogdu. 2014-2015
Virtual Enterprise (VE): An ontology and agent-based expert information system that will capture the domain knowledge as well as SME information in detail, and help create VEs quickly and respond to market demands. Funded by The Ministry of Science, Industry, and Technology Research Fund (SAN-TEZ) program. Co-PI: Erdogan Dogdu. 2012-2014
Recent Publications
Sadigh, Bahram Lotfi, Unver, Hakki Ozgur, Nikghadam, Shahrzad, Dogdu, Erdogan, Ozbayoglu, A Murat, and Kilic, S Engin (2016). An Ontology based Multi-Agent Virtual Enterprise System (OMAVE): Part 1: Domain modelling and Rule Management. In International Journal of Computer Integrated Manufacturing. 30 (2-3), 320–343. Taylor & Francis.
Yumusak, Semih, Dogdu, Erdogan, Kodaz, Halife, and Kamilaris, Andreas (2016). SpEnD: Linked Data SPARQL Endpoints Discovery Using Search Engines. In IEICE Tran. on Information and Systems. 100 (4), 758–767
Yucesan, Mehmet Mert, and Dogdu, Erdogan (2016). News Clustering Using Linked Data Resources and Their Relationships. In Proc. of the International Conference on Artificial Intelligence and Data Processing (IDAP)
Sezer, Omer Berat, Dogdu, Erdogan, Ozbayoglu, Murat, and Onal, Aras (2016). An Extended IoT Framework with Semantics, Big Data, and Analytics. In IEEE International Conference on Big Data.
Kulcu, Sercan, Dogdu, Erdogan, and Ozbayoglu, A. Murat (2016). A Survey on Semantic Web and Big Data Technologies for Social Network Analysis. In IEEE International Conference on Big Data.
Hakimov, Sherzod, Oto, Salih Atilay, and Dogdu, Erdogan (2012). Named entity recognition and disambiguation using linked data and graph-based centrality scoring. In Proceedings of the 4th International Workshop on Semantic Web Information Management.
Laboratory
Big Data Analytics Laboratory
Faculty
Assist. Prof. Dr. Abdül Kadir GÖRÜR
Virtual Reality, Serious Games and Gamification
Virtual reality is the use of computing techniques such as 3D modeling, animation, and programming to create interactive 3D worlds in which the individuals have a sense of spatial presence. There is actually a virtual existence without real existence. Inspired by these considerations, these synthetic environments may also provide virtual existence for virtual humans and promotes multimodal interaction in immersive environments. Serious games are a special kind of games with primary goal is not entertainment. They extensively used to simulate real-world events, inform people about social responsibilities or raise individuals’ awareness, and ultimately trigger their problem-solving skills. They may provide participants not only physical but also cognitive, or emotional challenges. Gamification is the use of game elements or design techniques in non-gaming contexts. It is used, as a tool to improve motivation and promote desired behaviors.
ET-044 Modüler Oyun Mimarileri - NATO modelleme ve simülasyon araştırma grubu Destek: NATO, Araştırmacı: Murat YILMAZ 2017-2018
DEPS: Doktora Derecesine Sahip İnsan Kaynağına Yönelik Yönetim Destek Sistemi Geliştirilmesi Projesi, Destek TÜBİTAK (KAMAG), Araştırmacı: Murat YILMAZ 2016-2017.
Sanal Gerçeklik Teknolojilerine yönelik Lokomosyon ve Haptik Tepki Sistemleri Geliştirme , Destek Ideasis A.Ş, TÜBİTAK (1507), Danışman: Murat YILMAZ 2017-2018
Uygulama Yaşam Döngüsü Yönetim Araçlarının Verimini Arttırmak İçin Ciddi Oyun Uygulaması, Destek HAVELSAN A.Ş.,TÜBİTAK (1505), Danışman: Murat YILMAZ 2017-2018
Thesis
Ulaş Güleç, Educational Game-Based Learning Framework About Laws Of The Game For Football Referees, 2015.
Ali AL-TAEI, Automated Classification of MMOG Players among the Participants Profiles in MOOCs, 2015.
Şahin Kayalı, An exploratory study to assess analytical and logical thinking skills of the software practitioners using a gamification perspective, 2015.
Mert Yılmaz, A Gamification approach to improve the software development process by exploring the personality types of software practitioners, 2016.
Ufuk, Aydan, Serious Game to Teach ISO/IEC 12207 Software Lifecycle Process: An Interactive Learning Approach, 2016.
Recent Publications
Aydan, U., Yilmaz, M., Clarke, P. and O’Connor, R., Teaching ISO/IEC 12207 Software Lifecycle Processes: A Serious Game Approach, accepted for publication, Computer Standards and Interfaces, 2017.
Gulec, U., & Yilmaz, M. (2016). A serious game for improving the decision making skills and knowledge levels of Turkish football referees according to the laws of the game. SpringerPlus, 5, 622.
Murat Yilmaz, Berke Atasoy, Rory V. O'Connor, Jean-Bernard Martens, Paul Clarke: Software Developer's Journey - A Story-Driven Approach to Support Software Practitioners. EuroSPI 2016: 203-211
Mehmet Kosa, Murat Yilmaz: Gamifying the Onboarding Process for Novice Software Practitioners. EuroSPI 2016: 242-248
Yilmaz, M. and O’Connor, R. V., A Scrumban Integrated Gamification Approach To Guide Software Process Improvement: A Turkish Case Study, Tehnicki Vjesnik (Technical Gazette), Vol. 23, No. 1, 2016
Gulec U., Yilmaz, M. (2015) Futbol Hakemleri İçin Futbol Oyun Kurallarının Eğitimi Amaçlı Oyun Tabanlı Öğrenme Çerçevesi, 9. Ulusal Yazılım Mühendisliği Konferansı (UYMS 2015), İzmir.
Ulaş Güleç, Murat Yilmaz and Mert Ali Gozcu. (2015) Futbol Hakemlerinin Eğitimi Amacıyla Tasarlanan Futbol Simülasyonunda Maçın Dinamizmini Sağlayan Etmenler. (UYMS 2016), Çanakkale.
Merve Kaymak, Mehmet Namıduru, Eray Tüzün and Murat Yılmaz.(2016) Sanal Ofis Ortamında Kod Gözden Geçirme ile Kod Değerlendirmesi. (UYMS 2016), Çanakkale.
Yılmaz, M., Saran, M. & O’Connor, R. (2014). Towards a Quest-Based Contextualization Process for Game-Based Learning, 8th European Conference on Games Based Learning ECGBL 2014, Berlin, Almanya.
Laboratory
Virtual Reality Laboratory
Faculty
Assist. Prof. Dr. Abdül Kadir GÖRÜR
Assist. Prof. Dr. Murat SARAN
Lecturer Ph.D. Faris Serdar TAŞEL
Artificial Intelligence and Knowledge Discovery
Data Mining
Data mining is the the practice of examining large pre-existing databases in order to generate new information. The goal of the data mining process is to extract information from a data set and transform it into an understandable structure for further use. Aside from the raw analysis step, it involves database and data management aspects, data preprocessing, model and inference considerations, interestingness metrics, complexity considerations, post-processing of discovered structures, visualization, and online updating. Considering the sheer volume of data produced by both social networks and infrastructures today, manual analysis and innovation over such data without automated means is impossible.
Machine Learning
Machine learning is the science of getting computers to act without being explicitly programmed. Evolved from the study of pattern recognition and computational learning theory in artificial intelligence, machine learning explores the study and construction of algorithms that can learn from and make predictions on data– such algorithms overcome following strictly static program instructions by making data-driven predictions or decisions, through building a model from sample inputs. Machine learning is employed in a range of computing tasks where designing and programming explicit algorithms with good performance is difficult or infeasible; example applications include email filtering, detection of network intruders or malicious insiders working towards a data breach, optical character recognition (OCR), learning to rank, and computer vision.
Information Retrieval
Information retrieval (IR) is finding a material of an unstructured nature that satisfies an information need from within large collections. Indeed, IR is the science of searching for information in a document, searching for documents themselves, and also searching for metadata that describe data, and for databases of texts, images or sounds. Most popular application area is the web search engines.
(Engin Demir, Academic Advisor) TUBITAK TEYDEB 1507 Project No: 7141177 Targeted Audience Based Digital Signage System (2015 - 2016) Bilimtek Teknoloji A.Ş., Ankara, Turkey
(Engin Demir, Academic Advisor) TUBITAK TEYDEB 1507 Project No: 7130694 Location Based Real Estate Database Generation using Information Retrieval and Extraction (2013-2015) NODA Bilişim Teknolojileri, Ankara, Turkey
(Engin Demir, Researcher) Query-driven Data Acquisition from Web-based Data Sources, Oxford University, UK. EPSRC EP/H017690/1 (2011-2012)
(Engin Demir, Researcher) Similarity-Based Indexing and Integration of Protein Sequence and Structure Databases, Ohio State University, USA. NSF - 0750891 (2009-2011)
Recent Publications
E. Demir, V. B. Demir "Predicting Flight Delays with Artificial Neural Networks: Case Study of an Airport" Proc. of 25th Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey, 2017.
E. Demir, A. Güneş "Decision Support System for the Unification of Legal Precedents" Proc. of International Conference on Computer Science and Engineering (UBMK), Tekirdağ, Turkey, 2016.
B. Sriram, D.Fuhry, E. Demir, H. Ferhatosmanoglu, M. Demirbas "Short text classification in Twitter to improve information filtering" Proc. of ACM SIGIR 2010: 841-842.
I.S. Altingovde, E. Demir, F. Can, O. Ulusoy "Site-based dynamic pruning for query processing in search engines" Proc. of ACM SIGIR 2008: 861-862.
I.S. Altingovde, E. Demir, F. Can, O. Ulusoy "Incremental cluster-based retrieval using compressed cluster-skipping inverted files" ACM Transactions on Information Systems. 26(3): 1-36, 2008.
F. Can, I. S. Altingovde, E. Demir "Efficiency and effectiveness of query processing in cluster-based retrieval" Information Systems 29(8): 697-717, 2004.
E. Demir, E. Arkun "Constraint Based Update of Large Itemsets" Proc. of 16th International Symposium on Computer and Information Sciences (ISCIS XVI), Antalya, Turkey, Nov. 2001, 105-112.
Faculty
Assist. Prof. Dr. Ayşe Nurdan SARAN
Assist. Prof. Dr. Gül TOKDEMİR
Assist. Prof. Dr. Roya CHOUPANI
Multimedia, Video Coding and Processing
The recent developments in communication technology have resulted in relying on visual information more heavily. However, the available technologies is not sufficient to support the rapid growth in usage of high definition video. Moreover, the demand for high-definition is not expected to slow down and with the increased connectivity of humans on Earth, the available bandwidth is even further stretched despite continuous improvement in network technologies. Therefore, solutions were sought after to fit increasingly higher quality content on the current network technologies leading to compression techniques. Multimedia processing techniques try to find the optimum solutions for encoding and communicating multimedia. One of these solution is Scalable Video Coding. Scalable video coding methods however, are very sensitive to data loss or corruption which are common in wireless networks. Robust and adaptive video coding methods are being developed and used for improving the available methods in scalable video coding.
R. Choupani, Scalable Video Coding, PhD Thesis, TU Delft, 2017
R. Choupani, S. Wong, M.R. Tolun, Drift-free video coding for privacy protected video scrambling (December 2015), 10th International Conference on Information, Communications and Signal Processing (ICICS 2015), 2-4 December 2015, Singapore
R. Choupani, S. Wong, M.R. Tolun, Using wavelet transform self-similarity for effective multiple description video (December 2015), 10th International Conference on Information, Communications and Signal Processing (ICICS 2015), 2-4 December 2015, Singapore
R. Choupani, S. Wong, M.R. Tolun, Hierarchical SNR Scalable Video Coding with Adaptive Quantization for Reduced Drift (March 2015), 10th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2015), 11-14 March 2015, Berlin, Germany
R. Choupani, S. Wong, M.R. Tolun, Spatial multiple description coding for scalable video streams (August 2014), International Journal of Digital Multimedia Broadcasting, volume 2014
R. Choupani, S. Wong, M.R. Tolun, Multiple Description Coding for SNR Scalable Video Transmission over Unreliable Networks (April 2014), Multimedia Tools and Applications, volume 69, issue 3
R. Choupani, S. Wong, M.R. Tolun, Optimized Multiple Description Coding for Temporal Video Scalability (August 2013), Chapter "Advances in Intelligent Systems and Computing", Published by Springer, Heidelberg
Laboratory
Multimedia Laboratory
Faculty
Assist. Prof. Dr. Roya CHOUPANI
Digital Image Processing, Computer Vision and Pattern Recognition
Digital image processing refers to the techniques used for improving the quality, enhancing or suppressing specific visual features, and extracting information from digital images. Computer vision as the subsequent stage of processing the visual information includes object recognition, interpretation of visual data, and analyzing the extracted information. This stage which imitates the human visual system on computers performs high level processing such as recognition, tracking, and interpretation through a-priori patterns or through learning from the sample images. Image processing and computer vision covers a vast range of applications from industrial, space, gaming, medical, security or military technologies, to robotics, human-computer interaction, navigation as well as facilitating daily life.
2 and 3 dimensional segmentation tools for the mitochondria from electron microscope images (2013-2016)
Organ Segmentation in Computed Tomography images (2012-2014)
Video Stabilization Using Radon Transform (2011-2012)
Recent Publications
Tasel, S.F., Mumcuoglu, E.U., Hassanpour, R.Z., Perkins, G., “A validated active contour method driven by parabolic arc model for detection and segmentation of mitochondria”, J. Struct. Biol. 194, 253–271, 2016. doi:10.1016/j.jsb.2016.03.002
Tasel, S.F., Hassanpour R., Mumcuoglu E.U. et al, “Automatic detection of mitochondria from electron microscope tomography images: a curve fitting approach”, Proc. SPIE 9034, Medical Imaging 2014: Image Processing, 903449, 21 March 2014. doi:10.1117/12.2043517
Mumcuoglu, E.U., Hassanpour, R., Tasel, S.F., Perkins, G., Martone, M.E., Gurcan, M.N., “Computerized detection and segmentation of mitochondria on electron microscope images”, J. Microsc. 246, 248–265, 2012. doi:10.1111/j.1365-2818.2012.03614.x
Jafari A., Hassanpour R., Shahbahrami A., Wong S., “A Combined Spatial and Frequency Based Texture Model for Organ Segmentation in Computed Tomography Examinations”, Journal of Medical Imaging and Health Informatics, vol 4(2), pp. 230-236, 2014.
Babagholami-Mohamadabadi B., Bagheri-Khaligh A., Hassanpour R., “Digital Video Stabilization Using Radon Transform”, International Conference on Digital Image Computing Techniques and Applications (DICTA), pp. 1-8, 2012.
Faculty
Assist. Prof. Dr. Ayşe Nurdan SARAN
Lecturer Ph.D. Faris Serdar TAŞEL
Lecturer Efe ÇİFTCİ
Networking and Communication
Data communication refers to transmission of the digital data between two or more computers using cable media or wireless media. Wireless and wired communications are two main components of networking.
Computer Network
Computer network is a set of computers connected together for the purpose of sharing resources. The most common resource shared today is connection to the Internet.
Wireless Sensor Networks
The sensor networks can be used for various application areas (e.g., smart cities, homes, cars, military and health applications). For different application areas, there are different technical issues that researchers are currently resolving. Some problems in this field can be listed as mobile applications, security threats, real-time data analysis, energy efficiency, protocols, algorithms, mac and network layers and optimization.
Energy efficiency is the most important design objective in wireless sensor networks. Optimization of the network architecture for maximal energy efficiency to achieve longest possible lifetime necessitates a sound exploration of the design space.
Cloud Computing
Cloud computing is shared pools of configurable computer system resources and higher-level services that can be rapidly provisioned with minimal management effort, often over the Internet.
Recent Projects
Fully Accessible Network Based Cloud System and Remote Client ThinCloud Project, sponsored by Rakun Bilişim, granted by TUBITAK 1507 Kobi - Arge Program. Consultant: Sibel T. Özyer, 2017-2019.
Fully Automated Remote Control Life Saving Robot, sponsored by Rakun Bilişim, granted by KOSGEB Arge Innovation Program. Consultant: Sibel T. Özyer, 2018-2019.
Recent Publications
Al-Zaghir S, Ozyer, Sibel T., Al-Dagdoog M. "Recruitment of security features for securing VTP3 domain in Campus Environment", UBMK’17, 2nd International Conference on Computer Science and Engineering, IEEE 2017.
Khalaf, Abdulrahman Z., Ozyer, Sibel T. “An Energy-Efficient Clustering Based Communication Protocol with Dividing the Overall Network Area for Wireless Sensor Networks”, New York Science Journal (2014): (11):110-114.
Sarhan, Khalid J., Ozyer, Sibel T. “Design, Implementation and Evaluation of a Low Energy Consumption Method for Wireless Sensor Networks”, New York Science Journal, (2014): 7(11):105-109.
Ozyer, Sibel T., Tavli, B., Dursun, K., Koyuncu, M. "Systematic investigation of the effects of unidirectional links on the lifetime of wireless sensor networks" Computer Standards & Interfaces 36(1): (2013): 132-142.
Ozyer, Sibel T., Bulent Tavli, and Murat Koyuncu. “Optimal energy efficient routing in wireless sensor networks with link asymmetry”, Communications (COMM), 2012 9th International Conference on. IEEE, 2012 (Received Tubitak Event Participation Grant)
Ozyer, Sibel T., B. Tavli, and Murat Koyuncu. "Energy dissipation characteristics of Wireless Sensor Networks with unidirectional links." Signal Processing and Communications Applications Conference (SIU), 2012 20th. IEEE, 2012.
