This blog is to update our major events and achievements: 1) International Visitors, 2) BlueSky Forum Event, 3) NHMRC grant, 4) Smart Services CRC conference

1. International Visitors:

In February 2013, we were honoured to host two visiting Professors, who were very engaging speakers with world-class research capacity. During their stay, both Professors have interacted with staff and students at our Information Systems School and beyond, sharing their knowledge and experience and inspire our researchers.

2. BlueSky Forum 2013 “Smart Cities for Ultimate Traveller Experience”

The inaugural forum (6 March 2013) has united 80 expertise from academics, government, and industry professionals to generate ideas and scope for innovative projects. The open interactive workshop generated innovative ideas for solving grand challenges in future sustainable, smart, and adaptive cities for ultimate experiences in commute, transports, and mobility. The topic is strongly aligned with The Science and Engineering Faculty, and Institute for Future Environment’s “Intelligent Environment and Adaptive Community” theme. Theforum places a strong emphasis on the application of scholarly excellence to ‘real world’ issues (QUT Blueprint).  

The BlueSky forum brought together leaders in industry including:

• Daniel Suter (Road Operations Coordinator, Department of Transport and Main Roads), 
• Simon Washington (Chair of Transport and Main Roads, QUT), 
• Ben James (Airline Development Manager, Brisbane Airport Corporation),
•  Nandor Locher (Manager ecommerce, Virgin Australia) and 
• Alexander Dreiling (Chair of Future Airport Innovation, QUT). 

Three teams of postgraduate research students from QUT will be collaborating with Virgin, Brisbane Airport Corporation (BAC), and Transport and Main Roads (TMR) on the following projects as a result of the forum.

• The End-to-End Personalised Mobile Traveller Assistant project: An intent based assistant with personalised choices that promotes customer satisfaction by simplifying travel.
• The Real-Time Hotspots Navigator: Through the use of augmented reality displays dynamic hotspots of tourist sites, social events and interests with the potential to be used on the new Google Glass technology.

These initiatives will become part of the research undertaken at the Mobile Innovation Space (Y601) for “Smart Cities for Ultimate Traveller Experience” in the new Science and Engineering Centre at QUT. Second stage prototypes resulting from these projects will be showcased at a Mobile Innovation Lab event later this year.

Photos can be found from our Facebook page: Link 1 (instagram), Link 2 (photos)

3. Successful NHMRC Partnership grant

On 10 Apr 2013, we are delighted to receive the news that the grant is approved ($1.6M) as MILAB continues to contribute towards health-related projects. This project brings together a collaborative of leading researchers, health service providers, and consumer advocates to facilitate the future integration of the Women’s Wellness After Cancer Program  in post-treatment support services for cancer patients across Australia:

Academic: Queensland University of Technology (QUT – CIs Anderson, McCarthy, Yates, King and Tjondronegoro), University of Queensland (UQ – CI Turner, AI Reeves), University of Notre Dame (UND – CI Monterosso), University of Sydney (UoS – CI White), University of California San Francisco (UCSF – AI Lee), Central Queensland University (CQU – CI Hall).

Clincial: Cancer Services Southern Clinical Network (CSSCN – AI Walpole); Royal Brisbane and Women’s Hospital (RBWH – CI Turner); St John of God Murdoch Hospital (SJGM – CI Monterosso); Peter MacCallum Cancer Institute (PMCI – CI Krishnasamy); Royal Prince Alfred Hospital (RPAH – CI White); and Kim Walters Choices Program (KWC – AI Porter-Steele).

4. Showcase demo at Smart Services CRC Conference

On 10 Apr 2013, Dr. Ivan Himawan, Dr. Wei Song and A/Prof Dian Tjondronegoro presented a cutting edge demo on our Adaptive Video Encoding and Delivery, showcasing the latest capabilities of our Region-of-Interest encoding with Human-Vision-System based post processing to optimise perception quality. The conference was attended by researchers across Australia with keynote speakers from Woolworths, and InfoSys. During the conference, we also actively contributed to the discussions for CRC rebid.

 The success of this year’s showcase is a testament to the hard work and accomplishments of what the students have put together throughout the semester. This is an important milestone for our ongoing efforts in delivering real-world teaching of Mobile and Ubiquitous Computing (INB345) and Mobile App Development (INB348) for Bachelor and Master Students in Faculty of Science and Engineering. The showcase brings together professionals from industry and government, and academia to share their expertise and allow students to gain insights for their innovative apps.

We are privileged to have many special guests from Virgin Australia, Woolworths, State Library of Queensland (SLQ), Microsoft, Mincom, Queensland Government (Department of science, IT, innovation and Art), Reading Room, etc.

The showcase features a board spectrum of mobile apps including health, transport, utility, game and interactive entertainment, teaching/learning, etc. Most of the mobile apps have been well received and some of the highlights during the event were:

1. Bus stop navigator
(Preview available at http://www.youtube.com/watch?v=NhtJUjLS6wg&feature=youtu.be)

The app provides user friendly information about bus stops, their location, timeable, POI, etc by tracking user’s journey in the bus and notifies users their destination is approaching. Similarly, Station Display synchronizes with the train schedules at the train station and allows users to view train schedules in mobile format. The app has “Can I make it?” feature which accurately measure distance calculation and informs user if they are able to catch the train on time.

2. Urbanex
(Preview available at http://www.youtube.com/watch?v=GWJfzMNrx7Y&feature=youtu.be )

The app shows urban exploration locations. It allows users to explore not usually seen components of the man-made environment such as bat cave, etc. At the same time, the app allows users to add new location when user made new exploration.

3. GO Fishing
(Preview available at http://www.youtube.com/watch?v=ZPNOK6bNwPo )

GO Fishing locates the current position of the device and identifies users nearest fishing spots. The app uses fish recognition technology to identify fish species along with details and info for each fish.

Please visit our facebook page http://www.facebook.com/mobileinnovationlab  for more pictures.

We have a community of Mobile Apps Developers at: http://www.facebook.com/groups/qutmobiledev/

The paper itself discusses about how to address the problem of face recognition on video by employing the recently proposed probabilistic linear discriminant analysis (PLDA). The PLDA has been shown to be robust against pose and expression in image-based face recognition. We extend the method and apply it to video where image set to image set matching is performed. Experiments on the VidTIMIT and Honda datasets show that the proposed heteroscedastic PLDA achieves improved recognition rates compared to the traditional PLDA and some other baseline methods. The PLDA has also been employed in my previous work of “On the Application of the Probabilistic Linear Discriminant Analysis to Face Recognition across Expression” which was presented at the Second IEEE International Workshop on Interactive Ambient Intelligence Multimedia Environments (AIME), Melbourne, 9th – 13th July 2012.

It is such a privilege to be able to go to this year’s DICTA. I would like to get the most out of it, learning things from the experts, having feedback and advices for my research, developing contacts and network, and broadening experience under the fresh and friendly atmosphere of the stunning Western Australia.

This paper discusses users’ query reformulation behaviour while searching information on the Web. Query reformulations have emerged as an important component of Web search behaviour and human-computer interaction (HCI) because a user’s success of information retrieval (IR) depends on how he or she formulates queries. There are various factors, such as cognitive styles, that influence users’ query reformulation behaviour. Understanding how users with different cognitive styles formulate their queries while performing Web searches can help HCI researchers and information systems (IS) developers to provide assistance to the users.

An accepted version of the conference paper can be downloaded from QUT Eprint.

a message from my mentor – Dr Dian T.

I would like to share with my readers an epiphany that I recently had while having my fortnightly meeting with my mentor. To put things into context, after weeks of brainstorming and reading literatures I have had come up with three distinctive ideas of potential solutions, or should I say research direction from the lens of a researcher.  I quickly find myself trapped in a state wherein I would call it as “Fully-filled Cup” state. A state in which one could not possibly contain and accept potential new good ideas, suggestions, and feedback from the people around you.

For a complete coverage of the story including lessons that I’ve learnt from this occasion, please click on this link.

Michael Hermano

PhD Candidate

MichaelHermano.com

The presentation slides can be downloaded from below

Wei’s presentation on MiLab Weekly Seminar (27Jul12).

Third: ZACHARY FITZ-WALTER

Principal Supervisor: Aspro Dian Tjondronegoro
Associate Supervisor: Dr. Peta Wyeth 

Thesis: Exploring the use of pervasive mobile games as tools of motivation, engagement and learning  (Zac – 3MT)

SEF Three Minute Thesis (3MT) is a research communication competition held annually and the winner will represent the Faculty for University stage of competition.The exercise develops academic, presentation, and research communication skills and supports the development of research students’ capacity to effectively explain their research in language appropriate to an intelligent but non-specialist audience.

Research higher degree (PhD, Prof Docs, Masters) students have three minutes to present a compelling oration on their thesis topic and its significance. 3MT is not an exercise in trivialising or ‘dumbing-down’ research but forces students to consolidate their ideas and crystalise their research discoveries.

One of the highlights was the technique to capture 3D reconstruction of geo-context (e.g. Sydney’s Opera House area) from many users’ p

hoto captures, so that the mobile can tell where a user currently is, by taking a photo of a building from

any angle (Collaborative Collaboration). This could be great for indoor location awareness for navigation,

and possibly 3D augmentation of the surrounding shops, friends, and other POI’s. His work on visual attention, and use of crowdsourced knowledge to suggest the most opt

imum (i.e. aesthetically pleasing) composition of mobile photography is very related to our work on Video Region of Interest detection.

We look forward to exciting opportunities for collaborations with Dr. Mei, and wish him all the best!

Adam Fraser is one of our postgraduate research students in Milab who’s working on the project called ”iPlayer“ in Semester 1, 2012 at QUT. The first iPlayer prototype was built for iOS 3.0. Since then, iOS has advanced to iOS 5.0 and iPlayer needed a face lift. Adam has completely re-designed and re-built the iPhone app from scratch, featuring the latest news feed and custom video player specially made for iOS devices. With the new iPlayer app, it changes the way you watch news video on mobile devices again.

Here’s Adam’s thoughts on how he went with this project throughout the semester. He also shared his learning progress and findings each week in his blog here: http://adamfraserios.tumblr.com/.

When I decided to do a Project Subject (INN 693) this semester I was looking for the opportunity to do some project based learning around iOS development. Ever since I started learning to program and becoming a developer I’ve realised that I learn much more effectively when I have a specific project to work on, a goal to aim for.  Working on the iPlayer app at miLab was exactly that, it gave me the opportunity to learn iOS development whilst working on an fun and challenging project.

At the beginning of the semester I had no experience at all with iOS development and while working on this app I learned about everything from how to work with xcode, to delegates and core animation. The whole process was a challenge but I learned something new every step of the way and ended up with a finished iPhone app that I am proud of.  The project subject provided me with a great balance of freedom to work on my own time and the structure of having a set project that had a delivery date.  My weekly meetings with Tony ensured that I didn’t get stuck on a problem for too long and were a great way to break down the project into smaller tasks so that I could keep on top of the apps progress.

In the end the I found the project to be a great learning experience, I learned a lot about iOS development but also about the software development process in general. I had to deal with how to manage a production schedule, unexpected bugs, changes in design and all sorts of other problems that non-practical subjects don’t cover. I think this project will be one of the most important subjects I complete in my degree and it definitely helped me to become a better developer.

Good job on the app, Adam.

This is the 1st of several upcoming post about Context-Aware Mobile Computing, focusing on the area of Context Fusion especially.

Mobile Sensing is increasingly part of everyday life due to the rapid evolution of the mobile phone into a powerful sensing platform. Most consumer smartphones are now equipped with the necessary sensors to monitor a diverse range of human activities and commonly encountered contexts [1]. The sensing capabilities on mobile devices have the potential to enhance applications to provide useful services to users based on their situation. However, research has shown that most of the context-aware mobile applications developed are still lacking in utilising the sensing capabilities, and the key challenges of interpreting high-level and reliable context still remains unclear in mobile sensing research.

The advanced sensors embedded in the smartphones, has turned these devices into a powerful sensing platform. With the sensing capabilities, it may potentially provide valuable information from the users and identify their activities [1]. Researchers are currently looking at the area of mobile sensing in many different aspects, ranging from personal sensing to global sensing, from looking at using hard (physical) and soft (social network, web services) sensors, and investigating continuously sensing to maximise energy efficiency [2]. However, my research is only focusing on personal sensing (which is sensing people and their environment), due to the scope of my research project. Personal sensing applications are designed for single individuals, and are focused on collecting and analysing the data and the process of this is what this research is investigating.

As technologies shift toward mobility, Contextual Information becomes the most important piece of information and plays a major role in both mobile technologies and ubiquitous computing [3]. A system understands and using the context information around the mobile users, can provide a more natural way of interaction and can change their life significantly and by taking advantage of contextual information in a mobile environment (such as time and location) can provided great services to the users [4]. Dourish [7] categorised context into 2 different views; one is describing the setting of the where user is or whats around him, what he is doing. The other one is looking from a social science point of view, such as why is he doing this? Currently, I’m focusing on deriving context for mobile application, therefore is focusing on representational view of context. Moreover, research has shown most of the applications are only using low-level information (straight from sensor data)[6], and most of the applications believe the context they are using is completely accurate, but in reality context is often inaccurate and ambiguous [5]. Therefore, this research will investigate 2 aspects: Context fusion techniques: how sensor data can be derived into high-level context information for mobile applications to use, and Context Reliability: look into improving the accuracy of the derived context.

In order to test and development a framework for context fusion, I’m planning to undertake a case study on public transport. Transportation is a mobile activity, and mobile devices are well suited to sense and provide feedback about these activities. Mobile applications have the potentially to provide immediate feedback that may impact on how people travel on their daily transportation activities. The interaction of this case study along with mobile sensing and contextual information is my research focus. So the overall argument approach for context fusion has the potential.

References: