The Wearable Prototype

My research focuses on assistive technology to aide mobility for the blind and low vision community, and hence a wearable technology is proposed. The wearable prototype consists of a small embedded computer, a lightweight stereo camera and an inertial measurement unit. The design is minimalistic and therefore unobtrusive, fulfilling a key practical requirement identified by the BLVs.

The following images depict my prototype of the wearable technology, in which it is built to augment the perception of a BLV along their navigation pathway.

Inserted pictures - 
A: a compact stereo camera and IMU (inertial measurement unit) sensors, 
B: an embedded processor,
C: a power source.

The following video shows some data sets collected using the stereo camera of the prototype. Several different surface discontinuities can be seen from the image (video) pair.

Word Cloud created based on my Research Report

Created a word cloud based on some keywords from my milestone report.

The challenges of yesterday are the opportunities of today*

Accepted the invitation to be one of the reviewers for a special session (Applied Assistive Robotic Care) in the ICIRA 2016 conference, and delighted to see some low cost and simple, yet creative solutions for the people with physical impairment.

In the past, being physically impaired often means being condemned to a life of confinement and institutionalization. The society used to view the dysfunction of the disabled people to participate in society as a direct result of their very intrinsic impairment condition, rather than as the result of other external factors of the society – a typical perception rooted in the Medical Model of Disability (Read, 2003; Hersh and Johnson, 2008). Under this model, the cure or assistance being offered to the disabled people revolves around clinical treatment on the person such as occupational therapy and rehabilitation, in the attempt to restore the person back to a normal life within the society.

In contrary, the Social Model of Disability emphasizes the distinction between ‘impairment’ and the ‘disability’ experienced by the disabled people. This model views the problems faced by the disabled people as mainly caused by the physical, environmental and social barriers extrinsic to the individuals rather than the impairment within them (Swain et al., 2003). ‘Disability’ is thus defined as the loss or limitation of opportunities to take part in the society on an equal level with others due to physical, environmental or social barriers (Hersh and Johnson, 2008; Christensen and Byrne, 2014). The lack of consideration in designing a barrier-free society is one of the main causes preventing the disabled people from taking part in most societal functions. Removing the barriers can bring about significant changes to the situation.

In view of the Social Model, it is observable that most modern cities have given considerable emphasis to the policies of universal accessible design. While in the less developed or low to middle income countries where the local policies or systems are not favoring the Social Model, the battle for equal opportunities for the people with impairment may rely on some emerging technological approaches, apart from the conventional aids. With advances of technologies i.e. lower cost in production, pervasion of ubiquitous and smaller hardware, smarter systems with better software; we would expect that the challenges of the past are indeed the opportunities of today.

* This article is part of an open innovation effort to crowdsource ideas and thoughts for a research project in assistive technologies. Assistive technology (AT): products, equipment, and systems that enhance learning, working, and daily living for persons with disabilities.


List of Reference:

CHRISTENSEN, K. M. & BYRNE, B. C. 2014. The Built Environment and Community Integration. Journal of Disability Policy Studies, 25, 186-195.

HERSH, M. A. & JOHNSON, M. A. 2008. Disability and Assistive Technology Systems. In: HERSH, M. A. & JOHNSON, M. A. (eds.) Assistive Technology for Visually Impaired and Blind People. Springer London.

READ, J. 2003. Controversial Issues in a Disabling Society, John Swain, Sally French and Colin Cameron, Buckingham, Open University Press, 2003, pp. v 198, ISBN 0 335 20904 1, 17.99. The British Journal of Social Work, 33, 837-839.

SWAIN, J., GRIFFITHS, C. & HEYMAN, B. 2003. Towards a Social Model Approach to Counselling Disabled Clients. British Journal of Guidance & Counselling, 31, 137-52.


Author Profile:

Kuan Yew is currently a sessional academic staff cum graduate research student in the School of Information Technology at Monash University Malaysia. His research focuses on assistive technology to aide mobility for the blind and low vision community. In his earlier research, he worked on intelligent systems, classification and optimization for biomedical data processing. His current research explores computer vision, image processing, wearable assistive technologies and human-robot interaction.

Intelligent Systems Lab Presentation – Summarising of his PhD experiments (by Tang)

(16/2/2016)

Tang is finalising on his PhD thesis by adding some extra experiments to his work based on suggestion from the Pre-Submission panels. Today, he took the chance of our biweekly presentation to share with us his experiment results. Tang's co-supervisors from Japan has joined the seminar through tele-conference too.

Tang research is focusing on the NLP for the elderly people. He proposed a model based on the working memory of human brain and he implemented the model into a talking robot - the Nao robot. Nao is a little humanoid robot (more from the link) that has video, audio and haptic sensors to interact with people.

Due to confidentiality of the work, most of the sharing are not to be mentioned here. So what have I learned from the session? One important thing that I picked up from the conversation between Tang and the Professors from Japan - there are deeper layers of thinking into even a tiny matter in research. We have to question everything, try not to ignore any of them, as they might bring us closer to the interpretation of our findings.

Intelligent Systems Lab Presentation – Cockroach Swarm Optimisation (by Ali Farid)

(2/2/2016)

We are starting up a more active communication platform for the members of Intelligent Systems Lab. Thus a biweekly presentation of our findings or other relevant works will be presented by the members at a one-hour session.

Cockroach Swarm Optimisation (CSO) is the first in the series of our Intelligent Systems Lab's presentation. CSO emulates the cockroach behaviour in locating dark places for hiding and looking for other cockroaches as a form of social activity.

Ali, the presenter of this seminar pointed out the relevant of this optimisation algorithm to his project in using drones (UAVs) as a swarm. He is thinking of using the CSO in his swarm of drone for locating of target in unknown environment. Quite an interesting sharing session from the presenter, at least, the CSO as compared to other swarm optimisation algorithms is quite a distinctive approach. Nature has given us a lot more of inspiration, it is just a matter of whether we are able to learn from the nature and creatively put ideas into practical solutions.

Methods for Unsupervised Semantic Modelling (by Professor Wray Buntine)

(11/1/2016)

The seminar given by Prof Wray shared some non-parametric methods for unsupervised modelling based on an example in NLP (natural language processing). With current growth of information systems, we need some better tools to help us to deal with the information overload. Such tools should be capable of organizing, searching, summarizng and even understanding the information. The 'understanding of the meaning of natural language' or in other word 'semantic' is the main focus of Prof Wray's methods.

The unsupervised learning in this model is based on Dirichlet distribution from probability and statistic. Throughout the presentation, Prof Wray tried to avoid the complex maths functions he has used. Basically, the concept involves probability vectors for the following elements quoted from Prof Wray's note:

• the next word given (n − 1) previous, 
• an author/conference/corporation to be linked to/from a webpage/patent/citation, 
• part-of-speech of a word in context, 
• hashtag in a tweet given the author.

A Dirirhlet distribution is then used to develop Dirichlet processes for the semantic model. It enable the approximation of vocabularies or documents hierarchically. The benefit of this model as per said by Prof Wray is that it reduces parameters optimisation problem faced by most distribution functions. Also, the nested (or hierarchical) Dirichlet processes have fast samplers as compared to others.

This is indeed a very high level of learning for me as the concepts and functions involved are really something new to me. Anyway, thanks to the seminar, I am more open to some new and advanced algorithms for my research project.

Communicating Research (Workshop 4)

This workshop is the last of the series of Communicating Research in 2015, and it focused on profiling our research. Research profile, when constructed with the right amount of details, would become a basic tool to promote our research across different digital media.

In this workshop, we were told about some common social media that we may consider for promoting our profile. Examples of academic/research social media are Research Gate, Acedmia.edu and Google Scholar. The non-academic profiling media could be LinkedIn or even Facebook. I have personally joined Research Gate a few months ago, in which I find that it is quite a good tool in the way that it tries to connect you with other researchers when common research areas are found. But I don't really like to use Facebook or or other non-academic social media for the similar purpose as I feel that people within my Facebook contact are generally not researchers. However, after some thoughts shared by Julie Holden, I do agree that other social media like Facebook, if organized and managed properly, can be a good place to promote our research as well.

Knowing the benefit of profiling our research, especially with the help of social media, I begin to fill-in more details in Research Gate and start organizing my Facebook contents. Hopefully, as suggested by this workshop, our profile will benefit us not only in our career, but also gets our findings and works reaching out to more people, inclusive of even friends and family members who aren't experts in our field. One day, they are going to understand and appreciate our works.

PS: At the end of the workshop, we were asked to complete our profile based on a template provided to us, and with delight, the profile is going to be published at Monash website! That's great.