Nt1310 Unit 1

1.Identify the problem being addressed and is it a new problem or a well known problem?

There are a variety of wearable sensors like location beacons, accelerometers, cameras, and physiological sensors. But then, there is a need to develop a single device that can monitor a wealth of activities. Secondly, there is a need to develop tools and techniques for continuously sensing user activities of interest, in order to develop a variety of truly ubiquitous computing applications.

Humans have always tried to monitor activities via the use of sensors, the introduction of Bodyscope to gather a plethora of data at once, proves that the problem is already a well-known one.

2. Describe the main novel ideas. Are they obvious or do they represent a

These are all basic and OBVIOUS ways of continuously gathering sound data.

3. Why are the ideas better than the state of art?

The idea behind the Bodyscope acoustic device is that a single sensor would collect a number of data with great success while the state of the art ones can only monitor a few activities at a time.

Also, the Bodyscope is a very practical device. Unlike state of the art devices that needs to be worn around the wrist, attached to phones or integrated with cameras; the Bodyscope latches directly with the part of the body responsible for sending out these acoustic signals, that is, the neck or throat.

4. What assumptions are the authors making?

The experiment is based on the assumption that sounds generated by humans pass through their neck or

The Bodyscope has also been used to monitor twelve activities including dietary related activities like eating and drinking.

6. Are disruptive technologies being used?

Bodyscope itself is a form of disruptive technology which aims to avoid the use of multiple sensors for numerous tasks. Also, Noronha et al. developed Platemate, which allows the user to analyze her food consumption by taking a picture of the food with a mobile phone and getting food annotations through a crowdsourcing system. With BodyScope, a wearable camera (like SenseCam) automatically can identify the moments when the user is eating, and perform analysis on her food consumption through Platemate.

7. How did they evaluate / prove that their ideas were good?

A laboratory study was used to examine the accuracy of activities of the body scope sensor in the three tiers.

Firstly, data was gathered by asking participants to perform twelve activities while wearing the Bodyscope around their neck. After this, there was the training and testing phase. At this stage, ‘Leave-one-participant-out cross validation’ and the ‘Leave-one-sample-per-participant-out cross validation’ was employed. Lastly, the lab results were evaluated using the Support Vector Machine for classification and the small-scale in-the-wild