Research Projects offered in 2016

In 2016 I will be offering projects on four areas (scroll down for more):

1) Text Mining, 2) Web Applications 3) Affective computing  (i.e. emotion detection) 4) Positive Computing: Technology for Health and Wellbeing. If you are interested in any of these topics, have good grades, or other qualifications send me a line.

RAC1: Virtual Reality with Oculus Rift (3-4 projects available)

We a number of projects using the Oculus Rift and you are welcome to bring your own ideas.

This Project is a collaboration with Stanford’s Virtual Reality Lab and selected students will be able to get a paid summer internship in the lab.

In this project you will be developing ‘serious’ VR games and evaluating them.

minecraftRift.png

http://goo.gl/P13kqd

Example project: An immersive virtual dive

In this project you will work with both hardware (the Oculus Rift VR headset and a breathing sensor) and software (the Unity game engine) to develop an immersive (pun intended) virtual diving simulator.

If you have ever dived before, then you will probably remember being very conscious of your breath. Every exhalation causes you to sink slowly and releases a stream of bubbles. Every inhalation causes you to float up slightly. Your breath is almost the only thing you can hear. This project will aim to bring that awareness of your breath into a VR experience.

The work required will involve using bio-sensing equipment to monitor a person's respiration rate, and using this signal to add an extra layer of immersion to an existing Unity diving game. You will also conduct human trials that test whether the game is more or less engaging when it reacts to respiration rate.

Successful candidates will have a strong interest in game development and a good eye for detail. Bonus points if you are a keen diver, or have prior experience with Unity.

RAC2. Evaluation of classification algorithms for Affective Computing

w/Sazzad Hussain

Affective computing aims to make computers that recognize emotions from physiological signals, text, facial expressions etc. In this project you will develop machine learning classifiers that make sense of this data and can be used to detect emotions.

Read: R.A. Calvo and S. D'Mello (2010). "Affect Detection: An Interdisciplinary Review of Models,Methods, and their Applications" IEEE Transactions on Affective Computing. 1(1), 18-37.

RAC3. Mood lighting for mindful meditation

w/David Milne

In this project you will work with programmable lighting and bio-sensing equipment to develop a conducive environment for mindful meditation.

In this environment, the user would sit in a quiet, almost empty room. They would close their eyes and follow an audio-based mindful meditation exercise. Behind closed eyelids, the user would see the room's lighting gently fading in and out and changing colours, as it reacts to their heart rate, breathing and stress level.

The work required involves using bio-sensing equipment to monitor these signals, and programming the lights to be informative without being distracting. You will also conduct human trials that test whether users are able to achieve greater states of mindfulness with or without the lighting.

Successful candidates will have a strong interest in signal processing. Bonus points if you are a Buddhist Monk.

RAC4. Electrophysiological signals for the recognition of emotion

w/Sazzad Hussain

When you fill an emotion your body changes (e.g. if you are scared your heart might accelerate). You will collect and analyse electrocardiogram, electromyogram and skin conductivity recordings to classify emotions. You will evaluate a number of classification algorithms. Experience with signal processing or data mining will be a plus.

RAC5. Recognizing emotions in text -application to addiction treatment platforms.

When you write an emotionally charged document the vocabulary you use might change. Think about the way you write in Facebook or your emails, how is it different from the way your write an assignment? Could you detect automatically what is the mood of someone from what they write on Facebook? Twitter?

In this project you will explore approaches to classifying emotions in text.

This project will be in collaboration with Hello Sunday Morning

Read:

- R. A. Calvo and M. Kim (to appear) "Emotions in text: dimensional and categorical models". Computational Intelligence

- Sunghwan Mac Kim, A. Valituti, R.A. Calvo "Evaluation of Unsupervised Emotion Models to Textual Affect Recognition". Workshop in Computational Approaches to Analysis and Generation of Emotion in Text, part of the Human Language Technologies: The 11th Annual Conference of the North American Chapter of the Association for Computational Linguistics, June 1–6, 2010, Los Angeles

RAC6. Mental Health Software Systems (3-4 topics available)

Help young people be healthy and thrive. This can be done through online peer support groups that are becoming increasingly popular on social networks like Facebook or organizations like ReachOut.com in Australia. In one of our current projects we are developing Moderator Assistant and Cybermate, that use natural language processing techniques to provide automated support for multiple online support groups. The system generates templated interventions that the moderator can use, based on key-terms and concepts extracted from the text posted by participants. In a second project, cybermate, we use NLP and behaviour analytics to build interventions targeted directly to final users. Both systems implement behaviour analysis features to measure the impact of the interventions.

Other projects within this topic:

RAC 7. Biometric sensors

w/Philip Leong

In this project you will develop biometric sensors, using Arduino boards for different physiological signals. Electrocardiogram, pulsimeters, etc can be used for medical and mental health applications. The project is most appropriate for candidates intersted in combining software and computer engineering work.

RAC 8: Predicting Students' Wellbeing from Physiology, Phone, Mobility, and Behavioral Data

With cogniant.co

The goal of this project is to apply machine learning methods to model the wellbeing of undergraduate students. Extensive data is to be obtained from the study (using Cogniant tools), which monitors participating students on a 24/7 basis using smartphones(iOS), collecting data on their location, sleep schedule, phone and SMS communications, academics, social networks. Extract features from this data and apply a variety of machine learning algorithms including and produce the findings. Interesting findings include: when participants visit novel locations they tend to be happier; when they use their phones or stay indoors for long periods they tend to be unhappy; and when several dimensions of wellbeing (including stress, happiness, health, and energy) are learned together, new findings are produced.

RAC 9: Evaluating Subliminal Nudging

With cogniant.co

The goal of this project is to influence consumer/patient behavior via nudging for decision making. Currently information is linear and directed by patient clinic – example healthy eating habits, exercise, and medication adherence is all recommended by clinic, but very seldom it influences consumer/patient behavior. The idea is to harmonize and synthesize stimuli from mobile phones in a meaningful way to influence consumer behavior. This will enable mobiles to send timely and meaningful nudges to consumer/patient which will increase healthy behavior.