PhD Student Wins at Hackathon in Japan!

Hackathon Image

The hackathon provided a great opportunity to be creative, think outside the box as well as network and collaborate with people from a range of disciplines.

AHMED AZAB, ACSE PHD STUDENT

ACSE PhD student, Ahmed Azab, has won an award at the Brain-Computer Interface (BCI) Hackathon at the IEEE SMC Conference held in Japan - October 2018.

Brain Hackathons are brainstorming and collaborative marathons designed to rapidly produce working prototypes. At IEEE SMC, the hackathons bring together developers, technologists, engineers, students, artists and scientists in teams of 5, over two days to build solutions that they can present. By allowing creative minds from multiple disciplines to come together for a short period of time it gives an opportunity to discover and uncover possibilities for using BCI related hardware and software not readily thought of.

The hackathon consisted of a number of predefined projects, which the participants could choose to work on. Ranging from Systems Science and Engineering to Human – Machine Systems and Cybernetics. The best projects are awarded with prizes.

Ahmed Azab's PhD project and Hackathon experience:

Brain-machine interface (BCI) is a challenging technology used in engineering and neuroscience. The ultimate goal of BCI is to provide a direct pathway from the brain to an external device without any muscular movement. BCIs acquire brain signals, analyse them, and translate them into commands that are used to control the external devices that carry out desired actions. One of the major limitations of BCI is its long calibration time.

My primary research aims to enhance the BCI system by reducing the required calibration time, achieving this will produce a more reliable system. I'm working on developing novel approaches to reduce this calibration time using transfer learning, where data from other sessions or subjects are mined and used to compensate the lack of labelled data from the target user. Transfer learning aims to learn characteristics that are consistent across sessions/subjects and adjust them according to the target user.

Being a member of ACSE gives me an excellent opportunity to follow the latest technologies in my field of research by attending different conferences and seminars run by experts. Moreover, being supervised by two inspirational members of ACSE staff, Dr.Mahnaz Arvaneh and Prof.Lyudmila Mihaylova, who do not hesitate to provide support makes me more determined to succeed. 

I attended the IEEE SMC 2018, flagship annual conference of the IEEE Systems, Man, and Cybernetics Society, conference in Japan to present our paper 'Weighted Multi-task learning in classification domain for improving Brain-computer interface'. This paper presents a new multi-task algorithm to reduce calibration time for BCI. The main theme of the conference this year was about Brain Machine Interface (BMI)and the goal of the workshop was to provide a forum for researchers to present research results, facilitate the interaction and intellectual exchange between researchers, developers and consumers of BMI technology. The workshop was organised by the IEEE SMC Technical Committee on Brain-Machine Interfaces Systems and was technically co-sponsored by the IEEE Brain Initiative. 

One of the main events of the workshop was the Brain-Computer Interface Hackathon. Brain Hackathons are brainstorming and collaborative marathons designed to produce working prototypes rapidly. At IEEE SMC, brain hackathons bring developers, technologists, engineers, students, artists, and scientists together in teams of five participants each over two days to cram and build solutions that they can then present. My team was from three countries, and our project was orthosis control using BCI. Each one applied his/her learning fundamentals to make the project work with acceptable efficiency in this short period. We won one of the neumo prizes - from the second best category of prizes.