Wearable Computing - Science topic

With each passing year, the Industrial Internet of Things matures. But coinciding with that growth can be increased complexity—more tools and techniques can create more confusion even as they optimize processes. As such, automation platforms (like those spotlighted in this Technology Report) are similarly maturing and growing increasingly important in the era of IIoT...

We have used plethysmography data. A plethysmograph measures blood volume in the subject’s thumb. We have used this data to detect emotions of the participants. But plethysmography measurement can also be used to compute the heart rate (HR). We have also seen that blood pressure and heart rate variability correlate with emotions. Further details can be found via

I suspect that your question is too general. My wrist movement is somewhat independent of my body movement. For example, I may be playing a guitar and so my wrist will be moving in a certain manner. However, while playing the guitar I may be either, sitting down, standing up, walking or dancing to the music that I am playing. From this you can see that my wrist movements do not define my body movements and so one can not be inferred from the other.

Another situation where this "confusion" occurs can be manufactured if you have a chair that rotates. You can then sit in the chair with your wrist still while a friend quickly rotates the chair and (if you don't get dizzy) then if you look at the reading from your wrist sensor you will see that it seems to indicate that the wrist is moving (and it is but so is your whole body) and so you can not assume that a movement registered at the wrist only comes from the wrist.

Heart Rate is also heavily explored.

I am hoping to look at multimodel multichannel research attempts

This is a great computer vision question. In addition to @Abedallatif Baba's interesting answer, there is a bit more to add.

There are a couple ways to detect moving objects with a wearable camera such as a fisheye camera used by bikers.

real-time: triangulate each frame and measure the persistence of selected triangles relative to their location in each successive frame. Microprocessors such as the raspberry pi are fast enough so that triangulation and triangle measurement can be done in a few milliseconds.

off-line: repeat real-time steps off-line for each of the frames in a captured video.

I would be interested to see the final result. This could be of interest to my students.

Please let me have it!

I am not sure if your interest is focused on the validity and accuracy (as some of the main characteristics in order for the data to have an actual value) of the generated data. If yes, I believe that you will find useful the following sources: 

can anyone tell how to design micro strip patch antenna for body area network in hfss to measure body parameters such as blood pressure, glucose level, ECG, respiration rate etc and how to transfer the parameters information to a remote location or doctor.

Hi Md

That is a definite no. I agree with Martin that the Internet of Things is still very much an "unregulated space". Add to that, the general lack of realisation that often components with have limited or no real security. On top of that, many users fail to grasp the significance of this from a security and privacy perspective, and you have a recipe for disaster. Equally, very few users actively monitor what is happening with their systems, and many fail to ensure the proper maintenance of a full forensic trail. Another shortcoming is the propensity to assume that their personal, or corporate, firewall will shield them from attack. The short answer to that is no it won't.

So, with no current security standards for IoT, no specific regulations, limited understanding of security requirements by users, often no or poor security on devices and add to that the number of people trying to create vast botnets using the Mirai virus, and you can see there will be no meaningful security any time soon. And no meaningful security means there will be little chance of privacy. You can have security without privacy, but you can't have privacy without security. So, without security, you can never ensure privacy.

Think of a number of recent hacks on IoT devices. within the last three years, we have seen various cars being hacked while being driven, where the engine has been cut, brakes disabled, cars accellerated; in medical environments, we have seen hospital drug pumps hacked to send fatal drug doses, pacemakers turned off; in domestic environments smart fridges turned off, smart heating interfered with, smart meters hacked; to name just a few (thankfully by researchers). However, we have also seen a number of real time hacks, such as power utilities being shut down, sewage works interfered with, and of course massive DDOS attacks using IoT devices hacked using the Mirai virus. Add to this, the recent porting of the Mirai virus to Windows, means insecure IoT devices can now provide an easy route in to corporate and domestic systems. A great deal will have to be done before we can look forward to a decent level of security and privacy in IoT devices.

A recent new virus, BrickerBot, actively seeks out insecure IoT devices, but instead of trying to harvest them instead tries to kill them, so that they can no longer be exploited. Of course, this might also destroy the device in the process, which could be an issue for a critical device. A couple of years ago, the Linux.Wifatch virus broke in to insecure IoT devices, and installed patches to make the devices secure and resistant to conventional attack, a much better approach to the problem.

In the US, the Federal Trade Commission have started fining manufacturers for selling insecure IoT devices, so that might give them an incentive to do better. Asus was pursued for simply failing to distribute security patches for their routers, and settled for a $400,000 fine. No doubt, fines will get more punitive, and that could well help get the attention of the manufacturers. Of course, it does not help when users buy insecure devices without considering the lack of security.

So, don't hold your breath waiting.

I hope that helps.

Regards

Bob

It would matter a lot when your technology stack is proliferating into new spaces where either/both space and time are constraints. I would like to bring to this discussion a major avenue of future, a potential market, and a topic of research interest - IoT (Internet Of Things). With almost every device that is capable of connecting to the network, one cannot expect every device around us to have enough compute and storage power right from day-1 for their code and execution. Code optimisation is crucial here.

Besides, ignoring code optimisation could never be assumed would have an upper bound on the extent of ignorance. Even a server with multiprocessing compute power and peta bytes of storage capacity cannot sustain a code which is not optimised in time and space over a long run. So, whatever be the platform on which your software is running, code optimisation always matters, just that we see immediate effects of it on low-end devices, and see it after few years on high-end ones.

Several validation studies can be found here https://www.fitabase.com/research-library/

Good luck!

Evenson, K. R., Goto, M. M., & Furberg, R. D. (2015). Systematic review of the validity and reliability of consumer-wearable activity trackers. The International Journal of Behavioral Nutrition and Physical Activity, 12, 159. https://doi.org/10.1186/s12966-015-0314-1

Dear Michal 

        I like the answer of Ferenc . As you are looking for the classification then I could suggest you an Application specific study of BASN applications my students carried out  and the work published in Elsevier (full text available on my RG profile )

"Application Specific Study, Analysis and Classification of Body Area Wireless Sensor Network Applications"

Dr Adnan

There is a lot of work in this area, although much of it is in the form of disparate design case studies rather than focused research programs. Two examples of design cases are: 

Veerasawmy, Rune, and Ole Sejer Iversen. "Bannerbattle: introducing crowd experience to interaction design." Proceedings of the 7th Nordic Conference on Human-Computer Interaction: Making Sense Through Design. ACM, 2012.

Or.. Particularly..

Woźniak, Paweł, et al. "RUFUS: Remote Supporter Feedback for Long-Distance Runners." Proceedings of the 17th International Conference on Human-Computer Interaction with Mobile Devices and Services. ACM, 2015.

Good luck with your thesis!

From my perspective, working in a related field, the most important question is why you need emotion sensing systems? If the answer is because you want to improve health, then that is the challenge, not the sensing systems as systems, but the success of the health improving interventions. And then the challenge become, how one create good health interventions, how do one stop the destructive behavior and motivate the health improving behavior. Here I think social and cultural aspects, long time behavior and learning/mastery curves is important.

What cultural and social values do the system promote and reproduce?

How do one maintain the health improving behavior over time?

How do one create good and challenging learning and mastery experiences (curves) over time?

In our project RHYME we create multi-sensory Internet of Things (interactive MSE) to motivate social and aesthetic co-creation for children with severe disabilities and their families. Here we use musical improvisation (advanced musical algorithms) and sensory stimulation to motivate social co-creation (positive and equal creative behavior that promote both aesthetical experiences and musical mastery). 

There are a lot of researches done actually about weareables. Here you'll find some mentions: http://www.businessinsider.com/wearable-devices-create-a-new-market-2013-10

I think, there is still a killer wearables gadget/tool to be found, but it seems clearly that sooner or later all our smartphones will be enhanced by wearables.

The next step will be embedded computers and we become robots.

Maybe they make it multilayer contact lens, so refractive index change do the Job!!

The use of Google Glass in surgery, especially for learning and teaching purposes, is certainly fascinating. It will be an ideal device for recording the procedures without losing concentration on the actual task. Imagine the possibilities of looking up information, when needed, without even moving your head.

Well, I will mention pupils since they are not on your list of less interesting inputs. :) There was a surge in pupillometry in the 60's, and there has been some pupil-based applications in HCI, but so far it is not a very widely used sensor. If we consider the combination of gaze directed interaction + see-through displays any prediction of the future, I think we are likely to see more pupil measurements being used as an indicator of cognitive load and emotional response in the near future.