Google have a handy tool for finding data sets:
Here are the projects for the next academic year:
Augmented Reality Enhanced Conversational Interfaces (e.g. Alexa)
Augmented Reality Cyber Security Control Centre
Machine Learning Personas from Social Media
Agent Modelling of Cyber Security Attack and Response Scenarios
Medical Checklist App (iOS) for Interventional Radiology
Personalised Exercise App (iOS, Android or both) for Vascular Claudication
Mining Conversational Interface Dialogue
Disaster Response App (IOS, Android or both)
Medical Imaging Selection App (iOS) using Risk-based Technique Selection
Medical App (iOS) for the Selection and Support of Peripherally Inserted Central Catheters
Machine learning using Medical Data Sets
Here are my student projects for next year (from September 2017), exploring how mobile devices (and sensors) can determine, direct and model human behaviour (typically within the physical environment). Importantly, we have most of the required technology within our department (e.g. telepresence robot, Oculus Rift VR hardware). Each projects can focus on one or more of:
- Software on device/s to motivate novel user interaction
- Analysis of data from device/s
- Simulation of human behaviour – and adapting 1.
HEALTHJOURNEY will use smartphone technology to reduce anxiety in children and parents before surgery. A hospital would like to create an engaging information platform, tailored to parents, that delivers information in multiple formats, such as virtual reality/360 panoramic images, videos, animation and written text.
OPGAME: A hospital would like to use mobile technology to reduce stress levels in children prior to an operation (e.g. during anaesthesia). Methods such sound and visual feedback through engaging, age appropriate gamification could be used!
BLOCKSIM is a cyber-physical project that aims to link simple Lego building blocks with simulation. How can users build a simulation model (e.g. movement around the campus, hospital or museum) using only physical blocks?
ROBOHEALTH is a project that requires you to develop software for a telepresence robot that then provides health advice or basic triage. How can robots assess and direct patients?
ROBO-INTERACT explores how the “face” of a telepresence robot can change in response to human interaction. The project could use a robot to interview a human or provide museum guidance to visitors (e.g. working with the London Museum of Water and Steam).
ROBO-ANALYTICS uses data collected by a telepresence robot to decide how to interact with humans in the local environment. Does behaviour change in response to human-robot interaction? An educational or museum setting may be used.
CHATBOTSIM is a project that combines an online bot and simulation. How can online automated discussions support better understanding of human behaviour? Chatbot interaction could be used to generate a simulation model (e.g. hospital attendance locations).
CAMPUSHEALTH is a project that uses mobile technology to improve interaction with health services – campus pharmacy, GPs, Urgent care etc. How can mobile technology better route students to the most effective service?
HEALTHVIZ is a project that extracts data from health “open-data” sites for use in new forms of graph visualisation (utilising Web, VR or mobile technology) – exploring how data is extracted and transformed before visualisation.
MOBILE DISASTER MANAGEMENT is a project that aims to predict the needs of stakeholders in a disaster management scenario.
PLANETHEALTH links a small mobile behaviour change app that you will develop (e.g. one that motivates limited plastic use, recycling or collection) to a wider environmental simulation describing possible impact.
TAGSCOPE combines mobile smartphone sensing technology with smart tagging of museum artefact displays. The project will require you to develop smartphone app that can provide a virtual representation of the internal structure of an artefact and/or its use in a wider system (e.g. a water pump and the supply of 18th century London with water).
How is a designer supposed to make rational decisions about the meaning and features of a product, system or service which will take 2, 3 or even 4 years to develop ? Society might be greatly different by then ! There will always be room for creativity and personal vision, but with development costs spiralling out of […]
Here are my projects for next year (from September 2016). I am always happy to discuss projects and your ideas. See my previous post on getting started.
MOBISIM combines mobile smartphone technology with agent based simulation. The project will require you explore how simulations can execute on smart phones in the physical environment. Importantly, a smart phone is able to detect movement in the local area and this capability can be used as part of the simulation. Consumer behaviour in a retail space or patient behaviour in a hospital provides possible areas of investigation. Students will have the opportunity to learn about agent based simulation and mobile sensing technology.
BLOCKSIM is a cyber-physical project that aims to link simple Lego building blocks with agent based simulation. It is often difficult, especially for end users, to design models using current tools and techniques. This project will allow an end-user to design a model with Lego before transformation into a computational model. Opportunities for 3D printing physical objects instead of or to augment Lego is a possibility. Students will have the opportunity to learn about agent based simulation and image analysis techniques.
VRSIM is a virtual reality project that requires you to develop an immersive interface for agent based simulation models. Typical simulators use a simple grid of images, but VR could allow the user to enter, interrogate and adapt the model in a 3D world. A healthcare context may be explored, with people moving around a hospital environment. Simulation can then be used to re-design new hospitals or wider systems including primary care. Students will have the opportunity to learn about agent based simulation and virtual reality technology.
DISTRIBUTED AGENT SIM is a project for students interested in more server side development (including protocols for software interoperation). We currently have an agent based simulation platform that is web based (PHP) and easy to use. The project aims to create a distributed simulation environment that is able to connect a number of separate, diverse simulations (e.g. infectious diseases and hospitals). The project could also investigate how simulations can operate on a cloud platform. Students will learn about agent based simulation and messaging technologies.
FUTURE TRADING SIM is a project that explores a “design fiction” where we are all trading our own personal data footprints (purchases, movement, viewing/listening). Agent based simulation can be used to understand possible futures, determine what is required for its growth and explore associated economic models. A particular problem when simulating a future state is access to representative data. Students will learn about agent based simulation and data trading.
ROBOSIM is a project that combines an online bot and agent based simulation. How can online discussions gather data that is able to build better understanding of human behaviour? One approach is to use this captured data as a basis for agent based modelling and simulation. Students will learn about artificial intelligence (driving chatbot interaction) and agent based simulation approaches.
HEALTHSTRAT is a project that uses agent based simulation to build a health strategy game. The game itself can explore local (e.g. hospital) or planetary health (see https://www.rockefellerfoundation.org/planetary-health/). The game will allow participant to learn more about healthcare strategy as well as testing new or adapted strategies. Game design techniques can be used to interact with a simulation. Students will learn about agent based simulation, healthcare systems and strategy.
PICTAG is a project that captures pictures and comments from Art installations (or heritage locations). The project will utilise visual and non-visual tagging (e.g. QR Codes, NFC or iBeacon) to track visitors and allow them to send media and comments. The challenge of this project is the subsequent analysis and visualisation of contributions! Heat maps, simulation, sentiment analysis, emotional tracking are all possible directions. Game design and/or social media techniques can also be used to construct a resulting virtual exhibit.
HEALTHVIZ is a project that extracts data from health “open-data” sites for use in new forms of visualisation (utilising underlying graph storage). Most open data is in tabular format and not directly connected. HCI techniques will used to design the visualisation and the user experience (UX).
MOBILE DISASTER MANAGEMENT is a project that aims to predict the needs of stakeholders in a disaster management scenario. Open-data will be used to design, build and drive a mobile app that support various response services. The project can be more focused towards data analysis or mobile app design and usability.
My projects this year will typically use a number of state of art technologies, including semantic web tools, NOSQL data stores and machine learning. These technologies will support a number of highly adaptive and reactive project areas.
Intelligent Adaptive Advertising
A typical electronic advertising screen (in a shop window) will display advertisements at a particular place for a particular time period. This project will investigate how advertising can adapt to groups of people walking in front of a pervasive screen. Machine learning approaches will be used to determine the impact of changes (e.g. movement of the advertisement viewers). The project will utilise the Microsoft Kinect sensor to determine human positioning (infer context) and adapt the screen accordingly. The Kinect API will be used to gather data and Amazon’s cloud infrastructure will be used for predictive analytics. How can motion capture and predictive analytics be used to optimise advertising?
Mobile Trading Environments
A number of financial markets exist that allow users to trade shares, currencies (FX), futures, options and bonds etc. (e.g. LMAX or TradeWeb). These markets typically rely on the matching of buyers with sellers or the real-time access to particular asset prices. This project will investigate how micro-markets can be initiated using mobile technology (e.g. Smart Phones). The project will require you to develop both client and server code to support trading users. Further experience of smart phone development will be gained, along with NOSQL data stores and messaging. A particular market or group of markets could be chosen by the student (e.g. a typical financial market or an advertising market). The project will start by choosing a novel micro market to address.
Haptic controlled Robotics
Controlling the environment using your own movement can have a number of benefits. This project will investigate how a mobile devices can be used to control a remote robot. This project could be undertaken by a two person team – one student focusing on the sensing and the other on the robot control. A number of sensors and mobile devices are available for use. The project will start with experimental work, identifying the sensitivity of the device and designing an associated event model. The project could use event processing, cloud and Web service technology.
Augmented Reality Educational Gaming
This project will investigate how one or more games came be used to extend the educational experience and environment. The educational context can be chosen by the student – primary, secondary, higher or other education. It is envisaged that the student will develop a game using Android and Google Cardboard APIs. How can games make novel use of the smart phone sensors? How could a game be used to help students joining a University at the start of year 1? How can gaming be used to test and simulate ideas (virtual lab or business)? One of more of these questions could form part of the project. The project will start by focusing on the problem being addressed and experimenting with augmented reality glasses.
Augmented Heritage Experience Applications
This project will investigate how smart phones can be used to interact with artistic or heritage content (typically supplied by museums). The project will explore how content can be produced (by museum or artists) and then delivered to user in the physical environment (e.g. accessing a painting from where it was painted). The mobile application should consider the multi-disciplinary user and provide innovative media tailed to the user. The project will start by selecting the context (e.g. museum or art) and investigating current content. New media could be created in tools such as Blender or Unity3D.
Analysing public mood and emotion using social media
A number of academic papers have investigated the public mood or emotional state through the analysis of twitter feeds. Some have looked at the correlation to financial markets. This project will extend some of this work and look at mix of social media and markets. One use of such approach could be the prediction of the FTSE100 index. The project will involve the development of server based (web service or cloud) software that is able to read and analyse a number of data feeds – producing models of the source data and associated predictions. The project could (if the student is interested) also have a strong visualisation or semantic web component.
Agent based simulation using open data
This project will involve the construction of an agent based simulation model from one of the many open data sites (e.g. health, economic or traffic data) in order to predict a future state or states. The project will need to use open data to build a simulation model using manual or automated approaches (such as clustering or classification). The model will then be executed in a recognised simulation tool or within a student coded simulation model. The coded simulation model could be produced in a functional language such a Clojure (if you are interested in learning a new language).
Agent based hospital simulation using NFC/RFID data
This project will involve the construction of an agent based simulation model from a physical model of a hospital (build already and containing Phidget sensors) in order to predict future movement and/or optimise movement. The project will use a physical model of Mount Vernon hospital to build a simulation model using manual or automated approaches (such as clustering or classification). The model will then be executed in a recognised simulation tool or within a student coded simulation model. The coded simulation model could be produced in a functional language such a Clojure (if you are interested in learning a new language).
There is no standard way to prepare for your FYP, but before we meet I suggest that you:
– Decide on some technologies and reacquaint yourself with the language/IDE etc.
– Find some papers on topics close to your project (initially try Communications of the ACM CACM)
– Have a go a writing some aims and objectives for your project. Remember, your problem should be manageable.
– Attempt some design work – use cases, screen sketches.
You do not need to attempt all of these as your project will become clearer when we have our first meeting in late September.
Email if you are interested in any of these projects (with the project name in the email title):
Mobile collection of device effectiveness
Patient-device movement around the physical environment using GPS
Patient-device movement around the physical environment using RFID tags
Monitoring patients with home robots
Patient-device movement around the physical environment using NFC tags
Medical Device Data Simulator
Cloud storage of real-time medical device data
Real-time medical device data storage in a NOSQL document store
Real-time medical device data storage in a NOSQL graph store
Real-time medical device data storage in a NOSQL property-value/triple store
Synchronisation of data between mobile and cloud storage
Storage and querying of device data with semantic web (Web 3.0) technologies
Data security using mobile medical apps
Relational data hub: Cleaning and normalising medical device data
Predicating medical outcomes from Big Data
Medical dashboard for medical device tracking
Medical dashboard for patient pathways tracking
Medical dashboard data verbasizer for improved communication
Identifying past and future medical event from Big Data
Predicting patient behaviour from Big Data
Agent based simulation of medical device networks
Agent based simulation of patient outcomes
A nice Hadoop tutorial – http://blog.cloudera.com/blog/2014/01/how-to-create-a-simple-hadoop-cluster-with-virtualbox/ . Moving on from a single test machine. Next step is having a play around with spark – https://amplab.cs.berkeley.edu/2013/10/23/got-a-minute-spin-up-a-spark-cluster-on-your-laptop-with-docker/ (nice way to kick start a spark cluster with Docker).
Which do you prefer? Why and what for?