Hiring

October 31st, 2016 § 0

I am actively looking for highly motivated and talented PhD students, masters students, undergraduate interns, post-doctoral research fellows, research engineers, and visiting scholars to work in the areas of human-computer interaction, ubiquitous / pervasive computing, internet-of-things, sensors, data analytics and data visualization. If you are interested in working with me, please email me with your CV and transcript!

If you are a prospective PhD student, please check out details of the NUS Computer Science PhD programme and apply online.

Please see the hiring page for some specific projects.

TasteHealthy

March 1st, 2016 § 0

Love tasty food? So do many young adults.
Concerned about your health? So are we.
Difficult to find tasty healthy food? Not anymore!

I am developing TasteHealthy, a mobile app for easy logging and recommendation of tasty and healthy food.
tastehealthy-card

Hackathon@SG 2015: Brio

July 31st, 2015 § 0

Hackathon_Winners

I led a great team to win 2nd Runner-Up for the Open Category out of 100+ teams in the largest hackathon in Singapore – Hackathon@SG 2015 – with 1100 participants during the 25-26 July weekend.

Idea: A one-click health screening mobile web app for at-risk loved ones. Individuals can book appointments for their loved ones to attend screenings (e.g., breast cancer screening)



Awards & Presentations

2015 Hackathon@SG – 2nd Runner-up

Narrative Visualization: Food Loves Fellowship

October 31st, 2014 § 0

Live Demo (circa May 2016)

I led an amazing team of diverse professionals (HCI, UX Designer, Software Engineer, Data Scientist) to create an award-winning data visualization to celebrate Singapore’s love of food.



Live demo (may be slow on first load).

This interactive 3D Map Visualisation celebrates Singapore’s favourite pastime: eating! It illustrates the diversity of local cuisines in various areas around the country. With this interactive visualisation, you can discover where to find your favourite dishes and the best places to enjoy them together.

This tongue-in-cheek visualisation also calculates how long it will take for you to eat all the yummy hawker food in Singapore! In fact, it estimates a good 160 years to sample everything, based on the reported average frequency of eating at hawker centres. Want to enjoy all of this food more quickly? Learn how though interacting with this visual celebration of SG food!

Food Loves Fellowship is an example of the Narrative Visualization Toolkit research done at the Urban Systems Lab at I2R. As more data is being used and released, many insights can be discovered through the use of sophisticated data analytics driven by machine learning algorithms. However, these insights need to be communicated to decision makers, consumers, and urban citizens through engaging narratives. Our research toolkit will make it easy to use state-of-the-art big data visualizations to tell these stories to engage, edify, enlighten and educate users.

Awards & Presentations

IDA Data-in-the-City Visualization Challenge 2014: 3rd Place

» Read the rest of this entry «

FRESH Research Platform

June 30th, 2014 § 0

Home energy management systems (HEMS) can reduce energy consumption while maintaining comfort. However, HEMS suffer from slow adoption and unproven energy savings. As intelligent automation and persuasive design features are increasingly added to HEM products, many research questions remain regarding their efficacy.

We present the FRESH research platform to facilitate
(i) the development of innovative features in HEM applications, and
(ii) their evaluation in field deployments.

FRESH has extensible modules for
(a) sensing to acquire data from wireless hardware sensor nodes and online sources, and actuation to control custom devices and commercial-off-the-shelf appliances,
(b) adaptive and intelligent modeling to test various machine learning and control algorithms,
(c) flexible user interface to explore the design of features based on behavioral research, and
(d) field experimentation with tools for user interaction logging, automatic context-aware surveys and messaging, and data visualization.

We have deployed FRESH in residential apartments and commercial offices used as test beds. We demonstrate the versatility of FRESH with four application use cases: environmental monitoring, non-intrusive load monitoring (NILM), an elevator energy display, and a smart thermostat. We have used FRESH to iterate on sensor nodes, develop and evaluate intelligent algorithms and models, and design mobile and web user interfaces to investigate HEM usability.



Publications & Presentations

  1. Lim, B. Y., Roth, K., Nambiar, S., Rayakota, H. 2014. Rapid Prototyping of Energy Management Applications with FRESH. In ACEEE Summer Study 2014.
    pdf-icon

Thesis Defense: Improving Understanding and Trust with Intelligibility in Context-Aware Applications

April 10th, 2012 § 0

I will be defending my thesis in late April 2012 about my work in providing intelligibility in context-aware applications.

When:   April 23rd, Monday @ 9.30am
Where:  Newell Simon Hall 1507

THESIS DEFENSE
Improving Understanding and Trust with Intelligibility in Context-Aware Applications

COMMITTEE
Anind K. Dey (Chair), Carnegie Mellon University, Human-Computer Interaction Institute
Scott E. Hudson, Carnegie Mellon University, Human-Computer Interaction Institute
Aniket Kittur, Carnegie Mellon University, Human-Computer Interaction Institute
Margaret M. Burnett, Oregon State University

DOCUMENTS
Flyer
Dissertation

ABSTRACT
To facilitate everyday activities, context-aware applications use sensors to detect what is happening, and use increasingly complex mechanisms (e.g., by using big rule-sets or machine learning) to infer the user’s context and intent. For example, a mobile application can recognize that the user is in a conversation, and suppress any incoming calls. When the application works well, this implicit sensing and complex inference remain invisible. However, when it behaves inappropriately or unexpectedly, users may not understand its behavior, and this can lead users to mistrust, misuse, or even abandon it. To counter this lack of understanding and loss of trust, context-aware applications should be intelligible, capable of explaining their behavior.

We investigate providing intelligibility in context-aware applications and evaluate its usefulness to improve user understanding and trust for context-aware applications. Specifically, this thesis supports intelligibility in context-aware applications through the provision of explanations that answer different question types, such as: Why did it do X? Why did it not do Y? What if I did W, What will it do? How can I get the application to do Y? Etc.

This thesis takes a three-pronged approach to investigating intelligibility by (i) eliciting the user requirements for intelligibility, to identify what explanation types end-users are interested in asking context-aware applications, (ii) supporting the development of intelligible context-aware applications with a software toolkit and the design of these applications with design and usability recommendations, and (iii) evaluating the impact of intelligibility on user understanding and trust under various situations and application reliability, and measuring how users use an interactive intelligible prototype. We show that users are willing to use well-designed intelligibility, and this can improve user understanding and trust in the adaptive behavior of context-aware applications.

Laκsa: Mobile App for Intelligible Control of Interruption

March 1st, 2012 § 0

laksa-screenshots

Mobile phones allow people to keep in touch with others and be easily reachable. However, the increasingly intimate use of smartphones also risks more social disruptions (e.g., in meetings and movie theatres) and work interruptions. This is because current smartphones are not smart enough to comprehensively understand the context of where its owner is, what he is doing, what is socially appropriate, and with whom he can be connected to then, etc.

Therefore, we have developed Laκsa, a mobile app to automatically infer the user’s context for social availability. It uses the rich sensors in smartphones (e.g., GPS, microphone, accelerometer, calendar) together with sophisticated machine learning algorithms to infer contextual cues, such as whether the user is in an impromptu conversation at the office, on an evening run outdoors, or at home listening to music. With this, Laκsa can provide contextually relevant features such as automatically silencing or activating the phone’s ringer in an intelligent and appropriate manner.

Laκsa is also intelligible to communicate with users. Using algorithms to provide explanations, Laκsa helps users to understand what it knows and how it makes inferences, and enables users to share such situational and social understanding with friends and family. Hence, Laκsa uses location and activity to connect (κ) users for social awareness.

Publications

We have published several research papers on using Laκsa to investigate the design of intelligible visualizations of context-awareness and to evaluate the usefulness of intelligilibility.

  1. Lim, B. Y., Dey, A. K. 2011. Design of an Intelligible Mobile Context-Aware Application. In Proceedings of the 13th International Conference on Human Computer Interaction with Mobile Devices and Services (MobileHCI '11). ACM, New York, NY, USA, 157-166. DOI=10.1145/2037373.2037399
  2. Lim, B. Y., Dey, A. K. 2011. Investigating Intelligibility for Uncertain Context-Aware Applications. In Proceedings of the 13th international conference on Ubiquitous computing (UbiComp '11). ACM, New York, NY, USA, 415-424. DOI=10.1145/2030112.2030168 .
  3. Lim, B. Y., Dey, A. K. 2013. Evaluating Intelligibility Usage and Usefulness in a Context-Aware Application. In Human-Computer Interaction. Towards Intelligent and Implicit Interaction. Springer Berlin Heidelberg, 2013. 92-101.
    pdf-icon