- Advanced Database Systems and Queries
- Cloud Computing and Resource Management
- Hand Gesture Recognition Systems
- Data Management and Algorithms
- Time Series Analysis and Forecasting
- Software System Performance and Reliability
- Caching and Content Delivery
- Distributed and Parallel Computing Systems
- Data Stream Mining Techniques
- Service-Oriented Architecture and Web Services
- IoT and Edge/Fog Computing
- Human Pose and Action Recognition
- Advanced Data Storage Technologies
- Hearing Impairment and Communication
- Face and Expression Recognition
- Data Mining Algorithms and Applications
- Peer-to-Peer Network Technologies
- Digital Marketing and Social Media
- Fault Detection and Control Systems
- Gaze Tracking and Assistive Technology
- Parallel Computing and Optimization Techniques
- Business Process Modeling and Analysis
- Distributed systems and fault tolerance
- Software Testing and Debugging Techniques
- Semantic Web and Ontologies
Özyeğin University
2012-2024
Selçuk University
2015
Ankara Sosyal Bilimler Üniversitesi
2015
Boğaziçi University
2007-2014
Hewlett-Packard (United States)
2007-2009
Yıldız Technical University
2007
University of California, Santa Cruz
2002-2004
A flash crowd is a surge in traffic to particular Web site that causes the be virtually unreachable. We present model of events and evaluate performance various multilevel caching techniques suitable for managing these events. By using well-dispersed caches with judicious choice replacement algorithms we show reductions client response times by as much factor 25. also eliminate server network hot spots distributing load over entire network.
Cloud computing has emerged as a new paradigm that impacts several different research fields, including software testing. Testing cloud applications its own peculiarities demand for novel testing methods and tools. On the other hand, also facilitates provides opportunities development of more effective scalable techniques. This paper reports on systematic survey published results attained by synergy these two fields. We provide an overview regarding main contributions, trends, gaps,...
Language learning can only advance with practice and corrective feedback. The interactive system, SignTutor, evaluates users' signing gives multimodal feedback to help improve signing.
Many modern applications, including online financial feeds, tag-based mass transit systems and RFID-based supply chain management transmit real-time data streams. There is a need for event stream processing technology to analyze this vast amount of sequential enable operational decision making. Existing techniques such as traditional analytical (OLAP) are not designed pattern-based operations, while state-of-the-art Complex Event Processing (CEP) sequence detection do support OLAP...
Complex event processing (CEP) over streams has become increasingly important for real-time applications ranging from health care, supply chain management to business intelligence. These monitoring submit complex queries track sequences of events that match a given pattern. As these systems mature the need nested sequence query support arises, while state-of-art CEP mostly execution flat only. To assure responsiveness and scalability pattern detection even on huge volume high-speed streams,...
Omnidirectional cameras have a lot of potential for surveillance and ambient intelligence applications, since they provide increased coverage with fewer cameras. We introduce the new BOMNI dataset, collected two omnidirectional simultaneously. The dataset contains single subject multi-subject interaction scenarios, as well actions relevant assisted living, such falling down. describe evaluation protocols on this benchmarking baseline results tracking systems based bounding box interest point...
Edge Computing (EC) became popular again with the rise of IoT, Cloud Computing, and Industry 4.0. In this paper, difficulties application development in EC environment are discussed a container-based solution using remote debugging at edge is proposed. This container allows developers to write code production environment. Our implementation increases speed facilitates in-place for environments.
In this paper, we describe the design of our architecture for continuous, heterogeneous analysis over streams, aka CHAOS that combines stream processing, approximation techniques, mining, complex event processing and visualization. CHAOS, with novel concept computational Cube, provides an effective, scalable platform near real time business enterprise streams. We approach a data center temperature application.
To extract useful and actionable information in real-time, the technology (IT) world is coping with big data problems today. In this paper, we present implementation details performance results of ReCEPtor, our system for "online" Association Rule Mining (ARM) over fast streams. Specifically, added Apriori two different FP-Growth algorithms inside Esper Complex Event Processing (CEP) engine compared their performances using LastFM social music site data. Our most important findings show that...
Internet of Things (IoT) systems promise a seamless connected world with machines integrating their services without human intervention. It's highly probable that the entities participating in such autonomous machine to interactions are be provided by different manufactures. Thus, heterogeneous devices from many providers complicates design and verification IoT at an unprecedented scale. In this paper, we propose novel runtime approach for systems. The contributions our proposed solution...
Large-scale oil refineries are equipped with mission-critical heavy machinery (boilers, engines, turbines, and so on) continuously monitored by thousands of sensors for process efficiency, environmental safety, predictive maintenance purposes. However, themselves also prone to errors failure. The quality data received from these should be verified before being used in system modeling. There is a need reliable methods systems that can provide validation reconciliation real-time high accuracy....
Sign languages are visual languages. The message is not only transferred via hand gestures (manual signs) but also head/body motion and facial expressions (non-manual signs). In this article, we present a database of non-manual signs in Turkish sign language (TSL). There eight the database, which frequently used TSL. contains videos these as well ground truth data 60 manually landmarked points face.
Expressions carry vital information in sign language. In this study, we have implemented a multi-resolution Active Shape Model (MR-ASM) tracker, which tracks 116 facial landmarks on videos. Since the expressions involve significant amount of head rotation, employ multiple ASM models to deal with different poses. The tracked landmark points are used extract motion features by Support Vector Machine (SVM) based classifier. We obtained above 90% classification accuracy data set containing 7 expressions.
Many modern applications including tag based mass transit systems, RFID-based supply chain management systems and online financial feeds require special purpose event stream processing technology to analyze vast amounts of sequential multi-dimensional data available in real-time feeds. Traditional analytical (OLAP) are not designed for pattern-based operations, while Complex Event Processing (CEP) sequence detection do support OLAP operations. We will demonstrate a novel E-Cube model that...
Due to prevalent use of sensors and network monitoring tools, big volumes data or "big data" today traverse the enterprise processing pipelines in a streaming fashion. While some companies prefer deploy their infrastructures services as private clouds, others completely outsource these public clouds. In either case, attempting store first for subsequent analysis creates additional resource costs unwanted delays obtaining actionable information. As result, enterprises increasingly employ...
The pace of proliferation for smart systems in city wide applications is unmatched. introduction Internet Things (IoT), an enabler phenomenon, has incubated a productive environment such innovations. Smart things equipped with IoT capabilities, allow developing at large scale that each application can be represented as system (SoS). Nevertheless, the complexity engineering SoS been major challenge and maintaining applications. One challenges industry face today verification runtime. We...
Internet of Things (IoT) is a new computing paradigm that proliferated by wide adoption application level protocols such as MQTT and CoAP, each which defines different styles sequential interaction events. Even though there considerable effort in the literature for verification complex distributed systems, practical solution IoT systems supports runtime system still missing. In this paper, we present monitoring approach exploits event relations expressed terms messaging model Constrained...
Complex Event Processing (CEP) has become increasingly important for tracking and monitoring anomalies trends in event streams emitted from business processes such as supply chain management to online stores e-commerce. These applications submit complex queries track sequences of events that match a given pattern. While the state-of-the-art CEP systems mostly focus on execution flat sequence queries, we instead support nested specified by (NEsted Language) NEEL. However iterative often...