Skip to content

Research

My primary research interest is centred around the Human-Centred Web; in particular Web accessibility, the mobile Web and using Semantic Web technologies to improve user experience.

Active Projects

Investigation of Analysis and Processing Techniques of Sensor Data for Activity Recognition

Activity recognition is a complex task, however, with the rapid advancements in distributed sensor network technologies, there can be many applications within this field including e-health to behavioural analysis in Psychology and Human-Computer Interaction. In our previous work, we have shown that it is possible to achieve good accuracy in recognising activities of an elderly person living alone in a house with many binary scalar sensors. In this project, we are planning to continue to work in line with our previous research with the main aim of investigating different techniques to automatically recognise activities and creating a framework to automate the process.

Completed Projects

Predicting Trending Path on Web Pages

Eye tracking studies have widely been used for understanding and predicting user behavior in user experience research and development. Even though eye tracking can be used to collect very rich data about user interaction, to make any generalization one needs to bring together individual users’ data. There are many approaches ranging from very informal techniques such as heatmaps to very formal data mining techniques. In our previous work, we introduced a technique called Scanpath Trend Analysis (STA) that aims to analyze a group of users’ eye tracking data to generate a trending path which is the most popular path followed in that page. Even though STA is very successful in identifying this trending path, it still requires a group of users’ eye-tracking data to do the analysis. In this project, we aim to generate this trending path without eye-tracking data automatically. The main goal of this project is to identify the features in a web page that influence the trending scanpath and predict that path by using machine learning algorithms.

DDS: Data-Driven Web Page Segmentation

Web pages are typically designed to support visual interaction and so they include many visual elements. They are visually segmented into a number of blocks with different contents and roles but most of the time these are not explicitly encoded in the source code so are not accessible for machine consump- tion such as for screen readers or for information retrieval agents. To overcome this problem, many approaches have been proposed to automatically segment web pages but they have many shortcomings such as not being able to consider all the components of web pages such as stylesheets, scripts, and con- sidering dynamic content, not being able to learn new visual designs and most importantly they are not driven by the understanding of the end users’ interaction which can be an issue of identifying segments relevant to the users’ task. The main objective of this project is to investigate different techniques for web page segmentation that address these limitations.

eMine: Web Page Transcoding Based on Eye Tracking

The World Wide Web (web) has moved from the Desktop and now is ubiquitous. It can be accessed by a small device while the user is mobile or it can be accessed in audio if the user cannot see the content, for instance visually disabled users who use screen readers. However, since web pages are mainly designed for visual interaction; it is almost impossible to access them in alternative forms. Our overarching goal is to improve the user experience in such constrained environments by using a novel application of eye tracking technology. In brief, by relating scanpaths to the underlying source code of web pages, we aim to transcode web pages such that they are easier to access in constrained environments. The project is supported by the Scientific and Technological Research Council of Turkey (TUBITAK). Detailed information can be found at the eMine Web site.

RIAM

The aim of RIAM is to investigate ways in which to integrate, to mutual advantage, research into the Accessible and Mobile World Wide Webs (Web), to develop a common infrastructure, and to validate this infrastructure using existing Web documents and Mobile client simulators. Detailed information about RIAM can be found at the RIAM Web site.

COHSE

Links on the Web are unidirectional, embedded, difficult to author and maintain. With a Semantic Web architecture, COHSE (Conceptual Open Hypermedia ServicE) aims to address these limitations by dynamically creating links on the Web. This project is funded by Sun Microsystems and detailed information can be found at the COHSE Web site.

Knowledge Web

I am also involved with the Knowledge Web which is a Network of Excellence project funded by the European Commission 6th Framework Programme. Detailed information can be found at the KWeb Web site.

Dante

For visually impaired users, travelling around the Web is a complicated task, since the richness of visual navigational objects presented to their sighted counterparts are neither appropriate nor accessible. Dante investigates principles and techniques to enhance the travel experience for visually impaired Web users. This project is funded by Overseas Research Studentship (ORS) and detailed information can be found at the Dante Web site.

EVITA

EVITA (Enabling Visually Impaired Table Accessing) investigates the problems visually impaired people have in browsing and reading tables. Detailed information can be found at the home page of EVITA.

Research Funding

Students

I had or have the great opportunity to work with the following students either as the main supervisor or co-supervisors:

  • Tianyi Chen, PhD, University of Manchester, completed 2010.
  • Elgin Akpinar, MSc, Computer Engineering, METU, completed 2014;
  • Ugur Donmez, MSc, Computer Engineering, METU, completed 2014;
  • Sukru Eraslan, PhD, University of Manchester, completed 2016;
  • Eda Koksal, MSc, SEES, METU NCC, completed 2016;
  • Huseyin Unlu, MSc, SEES METU NCC, completed 2019.
  • Melih Oder, MSc, Information Systems, METU, completed 2019.
  • Erfan Kalaji, MSc, Computer Engineering, METU NCC, completed 2021.
  • Waqar Haidar, MSc, Computer Engineering, METU NCC, completed 2021.
  • Aslihan Tok, MSc, SEES, METU NCC, completed 2021.
  • Naziha Khalil, MSc, Computer Engineering, METU NCC, completed 2022.
  • Elgin Akpinar, PhD, Computer Engineering, METU, completed 2022.
  • Abdullah Sulayfani, MSc, Computer Engineering, METU NCC, completed 2023.
  • Sameh Algharabli, MSc, Computer Engineering, METU NCC, on-going.
  • Atakan Gundeger, MSc, Computer Engineering, METU NCC, on-going.
  • Ahmad El Cheick Ammar, MSc, Computer Engineering, METU NCC, on-going.
  • Suleiman Suleiman, MSc, Computer Engineering, METU NCC, on-going.
  • Alexander Hamley, PhD, Computer Science, University of Manchester, on-going.
  • Naziha Khalil, PhD, Computer Science, University of Manchester, on-going.

Translations

I have also translated the following Web pages to Turkish:

© Dr. Yeliz Yesilada