Ambient Kitchen

Measuring Cooking Competence

Lack of cooking competence is often a contributing factor to poor diet. In this project I aim to find an objective measure of people’s cooking competence using the Ambient Kitchen as a platform to carry out my research. This information can be used to provide personalised and situated support to help the user improve both their cooking competence and diet.

Start Date: 2007

Project Supervisor: Patrick Olivier, Thomas Ploetz

Collaborators: Philips Research, Eindhoven.

Language Learning in the Wild

Foreign languages are generally taught within a classroom setting using textbook exercises. Despite its wide usage, there are a number of problems with this approach. Students are only able to “rehearse” the language, rather than use it practically. The classroom setting also makes it difficult for students to immerse themselves in the foreign culture. Studies have shown that Task-Based Learning, in which students utilise the language they have learned within a practical setting, is a far more effective way to learn languages.

For this project, we worked with researchers from the School of Education, Communication and Language Sciences to turn the Ambient Kitchen into a platform for Task-Based Learning of French. Originally created to assist older people and those with cognitive impairments in their day-to-day lives, the Ambient Kitchen technology was adapted to offer users a recipe in French. It uses motion sensors to ensure that they have understood each step, and supports the user by repeating or translating instructions where necessary. Students can apply their skills practically and with tangible results, making the experience of this Task-Based Learning more rewarding than the traditional classroom setting. With cookery as the context, they are also able to experience something of French culture, as the recipes offered by the kitchen are classic French dishes.

We carried out a study among 46 staff and students from the university to assess whether the kitchen had a positive, negative, or neutral impact on the way they learned French, and to see how people with varying levels of fluency in the language responded to the learning environment. This provided insight into how we might improve the technology and influenced its adaptation for the ongoing European kitchen project.

See also: iLAB: Learn Kitchen

Press release: French kitchen is recipe for success

 

Date: Jun 2010 – Nov 2011

Funding: EPSRC: Engineering and Physical Sciences Research Council, Digital Economy Programme £162,525

Researchers: Paul Seedhouse (PI) – School of Education Communication and Language Sciences, Patrick Olivier (CI).                                                                                     Dan Jackson, Thomas Ploetz, Jack Weeden, Saandia Ali – School of Education Communication and Language Sciences.

Collaborators: Newcastle College, and CILT: The National Centre for Languages.

Balance@Home

The aim of this project is to help European citizens to obtain consumer solutions for hassle-free guidance towards a balanced lifestyle regarding meal planning and preparation and personal choice. We explore methods for inferring eating habits in an unobtrusive way, and seek to use this information to provide situated feedback on meal planning and preparation, as well as creating pervasive kitchen technology that will help to underpin this advice.

The research for the project takes place in the Ambient Kitchen and Experience Lab at Philips Research in Eindhoven, as these research facilities represent a real-world environment. We will also take advantage of the geographical distance between ourselves and our partners at Philips Research to explore the role of social networking in sharing cooking experiences and the promotion of balanced eating habits.

We are adopting a User-Centred Development approach in order to develop successful solutions, meaning the starting point for each of our developments will be the insights of the groups we intend to use it, and testing prototypes with users during further developments. The three groups we are specifically looking at are single-person households, two-person households, and families with young children.

Date: April 2009 – March 2013 (48 month Project)

Funding: Marie Curie Action under the European 7th Framework Program (FP7). £190,201

Researchers: Patrick Olivier (PI). Paula Moynihan – Institute of Ageing & Health, and Martyn Dade-Robertson – Architecture, Planning & Landscape (CIs). Juergen Wagner, Robert Comber, Jack Weeden.

Collaborators: Aart van Halternen, Jettie Hoonhout, Peggy Nachtigal, and Gijs Geleijnse (Philips Research, Eindhoven).

Press: Balancing Act”  – ResearchMediaLtd

See the Balance@Home project website

Publications:

[mendeley type=”folder” id=”8070971″ groupby=”year” filter=”title=Ambient kitchen: designing situated services using a high fidelity prototyping environment”]

[mendeley type=”folder” id=”8070971″ groupby=”year” filter=”title=Ambient Intelligence. Slice&Dice”]

Human Activity Recognition for Pervasive Interaction

In this project, we developed a Human Activity Recognition (HAR) framework using sensors embedded into kitchen utensils. The first version of HAR framework, Slice&Dice, was developed to detect 11 low-level, fine-grained food preparation activities using modified Wii Remotes integrated into three knives and one serving spoon. This was followed by the real-time version of HAR, which works with Culture Lab’s wireless accelerometers and a new set of utensils including knives, a spoon, a whisk, a ladle and a peeler. The real-time HAR framework was integrated into the Ambient Kitchen and iLAB Learn kitchen.

We also developed a chopping board that used fibre optic technology to detect food ingredients. A webcam camera and a microphone were integrated into the chopping board. A computer vision algorithm based on colour and shape was developed for food ingredient classification; this was more than 78% accurate in a pilot study we carried out with twelve different foods, showing our approach to be very promising for food recognition. A later version of this algorithm was based on fusion sensing data: colour and feature to detect food before it is chopped and audio and acceleration data intensities to detect food being chopped on the fibre chopping board.

This was followed by automatic recipe tracking and video summarisation applications, which were developed based on the HAR framework. Such applications can monitor which steps of a recipe the user is doing or has done, and are thus able to advise the next step to the user. There is also potential for these applications to assist in calorie intake monitoring or planning meals.

Start Date: February 2008

Project Supervisor: Patrick Olivier, Thomas Ploetz

Funding: Ministry of Education and Training of Vietnam

[mendeley type=”folder” id=”8070971″ groupby=”year” filter=”title=Real-Time Activity Recognition”]
[mendeley type=”folder” id=”8070971″ groupby=”year” filter=”title=Slice&Dice”]