Home >> About Us >> People >> Adrian David Cheok >> Research Program

I am presently conducting an extremely active research program, as well as being highly committed and successful in both undergraduate teaching and postgraduate supervision.

Furthermore, I have attracted a large amount of externally attracted funding as well as internal university funding.

My research is quite multi-disciplinary and wide-ranging, it is following a main research vision and goal that I have had from the beginning of my studies and career: to create new human interface technology, with computer and cybernetic systems that will improve our lives and create new and seemingly amazing possibilities in human society. I foresee a future where computers interact with people in a totally simple, natural, and human-like manner.

As my research revolved around human centered media, real user studies and research prototypes are conducted as part of my research.

1.  Mixed reality, Human-Computer Interaction, and Entertainment Computing: Using mixed reality the digital world can to be extended into the user’s physical world. This is made possible through the use of head-mounted see through displays where the user’s real-world view can be overlaid with 3D computer graphics, text, video, audio and speech.

We are bringing developing new systems to implement mixed reality in order to develop an almost magical environment where the virtual world, such as 3D computer graphics images and animations are merged with the real world as seamlessly as possible in real time. For example architects could work on a realistic virtual 3D model on their desk, and then enter the model together to explore the inside of the virtual buildings, surgeons could “see” the inside of a patients body before operating, children could see animals from exotic lands, and play with them in their real physical space, and people could play games with each other together with virtual characters or creatures that appear in their real environment.

The mixed reality project will allow humans to interact with each other in ways that now can only be imagined in movies or television, and will allow humans to interact with computers in a way that goes beyond the desktop computers we have now. It will allow us to create a mystical world that man has never experienced before. There will be applications in a great variety of areas such as education, entertainment computing, architecture, military, medicine, and human welfare.

2.  Wearable computers and smart spaces: the integration of the above research areas will allow the development of tiny wearable computers, that can be worn on the human, as well as be ubiquitously embedded into the environment into smart spaces. These should be able to interact in a natural manner using soft computing and multi-modal speech recognition. Furthermore this platform will allow an exciting new human-computer interaction to develop in conjunction with mixed reality, where virtual objects and characters can be seamlessly integrated into the real world.

3.  Fuzzy systems and soft computing: in order to embed human linguistic type reasoning and biological types of learning to increase the man-machine system intelligence quotient and enable computers to understand and learn complex real-world environments.

4.  Hardware – real time dsp and cpu, embedded systems, and power electronics: in order to implement human-computer systems that will have an impact, real time hardware issues and robustness are critical. Real time computer interaction requires examination of hardware and software issues in dsp and cpu platforms. Furthermore, embedded hardware and sensors will provide the framework for ubiquitous computing. This also extends to the power electronic aspects that are required for motion and control.

5.  Speech and multi-modal recognition: A critical factor in the future generations of human-computer systems will be the achievement of natural interaction. Part of this is the ability to recognize and understand speech and natural language. However, as in humans, the computer should recognize the multi-modal nature of speech (audio and visual).


Return to top