Tag Archives: Ubicomp

Action items from Ubicomp

This is a list of specific things to follow up on from Ubicomp:

Ubicomp 2008 blogging, day 3: location aware applications

The most interesting part of day 3 for me was the session on location-aware applications. The first paper was The potential for location-aware power management from Robert Harle and Andy Hopper of the University of Cambridge. They analyze a set of highly-accurate location data from a commercial office to see what energy savings could be enabled by knowing where the user is located in the building. They found the potential for savings for devices that can be switched on and off quickly (like lights or waking a computer from sleep), but the problem is much harder for slower systems like HVAC. For the slow systems, only outside office hours and lunchtime could be predicted with the accuracy required to have rooms ready when the user returned.

The other big paper for me was Understanding mobility based on GPS data, which covered using GPS data to determine what transportation method was being used (sound familiar? 🙂 ) They found that just using velocity data from GPS doesn’t work well (< 50% accuracy). They follow the standard machine learning process: segmentation of the data, extracting features that are representative of those segments, and feeding that into a generative model. They had 70 people using their system for a year, which is a huge amount of GPS data. This is definitely a paper I need to fully understand.

I had to leave to catch my flight before the closing panel session finished, but what I heard was interesting. There was spirited debate on where ubiquitous computing was going, where the conference was going, complaints about the many related conferences (Pervasive, MobileCHI). Too bad I had to leave early.

Ubicomp 2009 is in Orlando FL. Not sure at this point if I’ll be going or not.

Ubicomp 2008 blogging, day 2: location sensing and more

[Getting back to blogging Ubicomp from my notes. Unfortunately ran out of time while the conference was going on]

Location sensing was the first session of the day, and this is one of the most developed areas in ubiquitous computing. The first talk was on using signals injected into the power wiring of a building to sense location. The idea being that you attach a transmitter to normal home power wiring to inject some signals (earlier work used 2 frequencies, this paper was using wideband) that can be sensed throughout the house. Then you can map out the received values for those signals throughout the house, and then later use that mapping to sense where a receiver is located. The second talk was on using CDMA signals (from carriers like Sprint in the US) to locate users based on the signal delay. Using GSM and WiFi signals are already well established, apparently, but all three require mapping the signal strength/delay in the space to be used for location.

The best paper award for the conference went to Pedestrian localisation for indoor environments. The goal of this system is to be able to track pedestrians indoors using no infrastructure, unlike ultrasonic systems that can be extremely accurate, but require expensive transducers every couple meters. The system uses a combination of pedestrian dead reckoning and robot localization techniques. A shoe-mounted inertial sensor can detect the users steps, but accelerometers have drift that eventually creates too much error. That drift is compensated for using the robot localization technique. A model of the building’s floor plan is created or derived from blueprints, and given the motion information from the inertial sensor, guesses can be made on where the user is located in the building. Since the user cannot walk through walls, as they walk further the system uses a particle filter to winnow down the set of possible locations. It’s neat work, though it does require an accurate map of the indoor environment.

Another interesting paper in a completely different area is Towards the automated social analysis of situated speech data. The authors use automated voice recorders that record everything the subjects say, but then throw away the raw audio data and keep only information about which subjects talk to each other, and some variables about their speech (pitch, number of conversational turns, etc). Using this data they can create an automated sociogram based on who spoke to who.

In the security and privacy track there was a talk about the privacy problems associated with the fine-grained sensors used for activity sensing in the home. The authors point out that one can snoop on the wireless data transmissions, and even through they are encrypted, one can infer which sensors are being activated based on time of day and standard usage patterns.

The conference day ended with a Town Hall session. This was a discussion about the administrative aspects of an ongoing conference: location of next year’s conference, whether to be sponsored by ACM, straw polls on whether to go all digital for the proceedings, etc. It was quite cool to see the internal aspects of the conference discussed in an open and somewhat democratic forum.

ICS 699 Fall 2008 week 4 & 5: Ubicomp!

It was a long 2 weeks, but it went by quickly. Ubicomp was great, saw a lot of interesting work, some with direct application to PET. Rather than try to summarize it all here, I’ll finish off my Ubicomp blog entries this week.

There is continuing interest in the LaTeX thesis style I worked on back in 1998, with requests from two more ICS grad students. Based on a suggestion from Josh Wingstrom, I’m going to put it in Google Code so that changes can be kept under version control. Hopefully this will improve maintainability and longevity as students graduate.

Of course this means I have to finally get around to installing TeX on my MacBook Pro. It appears the situation is less complicated than it was a year ago, MacTeX-2008 seems like the obvious way to go now. There’s been a lot of changes in the TeXspace in the last decade: WYSIWYG editors, direct to PDF output, etc. Gotta catch up.

Past weeks accomplishments:

  • Prepared short presentation on SocialSense for DAP workshop
  • Presented to CSDL for Ubicomp practice
  • Read workshop papers (on plane)
  • Some GPS data logging
  • Attended 2 workshops and Ubicomp proper
  • Wrote blog entries on Ubicomp

Hours worked: oodles (target: 15 hr)

Plans for coming week:

  • Finish blogging last 2 days of conference
  • Write up items relevant for PET from conference
  • Write up lessons learned for future conference attendances
  • Read papers on transportation activity sensing for lit review
  • Install TeX
  • Put UHM LaTeX thesis style up on Google Code for broader adoption
  • Create CSDL tech report for proposal draft
  • Start filling in proposal literature review from papers read

Pointers to work products:

Cool links:

  • SlideShare was mentioned at Ubicomp as the preferred way for presenters to make their presentations available to others, basically it’s YouTube for presentations. The preferred tag for Ubicomp this year is ubicomp2008.

Ubicomp 2008 blogging, day 1: activity sensing & wearables

Today marked the opening of Ubicomp 2008. There are approximately 341 attendees, of whom 154 are students. 76 people signed up for the workshops. There were 226 paper submissions (160 full papers, 66 notes), of which 42 were accepted, making the acceptance rate 19%.

Attendees were urged to make their presentations available on SlideShare, and it was recommended that ubicomp2008 be used as a standardized tag for the conference across all sharing sites (SlideShare, Flickr), etc) (hmm, folksonomy breaks down 🙂 )

The first session today was on activity recognition. While the papers were mostly about human motion (in buildings or moving around), PET’s transportation data analysis is clearly a type of activity recognition and presumably the same sets of techniques (Hidden Markov Model, Conditional Random Field) will be relevant, as will the methods of evaluation (such as a confusion table). Good to know there’s a literature I can look towards there.

During a paper on activity recognition in the home, the presenter mentioned providing software for annotating activities to provide ground truth for the activity data set. This might be helpful in my annotation of transportation activities.

Another interesting talk was a fitness motivation system using a glanceable display on a cell phone. The idea is that as the users work towards their fitness goals (recorded either manually through a journal or automatically via a fitness sensor), a garden of flowers is placed as the background on their cell phone interface. This provides a constant reminder of how they are doing in pursuit of their goals. This got me thinking that maybe PET could benefit from a similar glanceable display of GHG emission estimates.

I’m looking forward to the talk tomorrow on indoor inertial tracking.

Ubicomp 2008 blogging, day 0: workshops

Today I had both workshops I was participating in. There was a lot of information packed in, too much for me to summarize in one late night blog post. A sampling of stuff from the workshops:

Ubiquitous Sustainability:

  • Using air quality monitors on street sweepers to provide lots of regular coverage of streets
  • Designing for positive social change, instead of instilling fear
  • Monday 9/22 is no car day in Seoul!
  • Privacy is the counterpoint to measurement (the more you measure, the less privacy you have)
  • Intrinsic vs. Extrinsic motivations for change (intrinsic being more valuable long term)
  • Getting away from any association between sustainability and sacrifice
  • Sustainability is a long term societal learning process
  • Thinking of a building as a country, in which the citizens (users) can vote democratically on the air conditioning temperature!
  • Beijing Olympics, polluters like factories shut down to improve air quality for the games, but now that games are over they want to start up again. However residents have now experienced better air quality and heard discussion about it in the media, and want to keep the air cleaner.

Devices that Alter Perception:

  • Artificial Synesthesia: Stetten et al 2007, finger-mounted laser bounces of objects and returns to a photosensor, which converts the intensity of reflected light into vibrations of the finger
  • Opaque technologies are ones where the technology is the focus, transparent technologies are ones where the task becomes the focus because the tech has disappeared.
  • Haptic research “Feel the Force” that recreates the light saber training that Luke Skywalker got in Episode IV of Star Wars. Sam would love this. 🙂
  • Thinking about haptic output for SocialSense (belt?) to provide awareness of other people without looking at a screen.

OK, tired and that’s only a fraction of my notes. I noticed the split between Mac and PC laptops at about 50/50.

Ubicomp 2008 blogging, day -1: travel

I’m going to try to blog daily about my experiences at Ubicomp 2008. Today was all travel, starting in Honolulu at noon on Friday 9/19, ending at 9 PM 9/20 in Seoul (damn you International Date Line!).

When I got to the airport in Honolulu, I realized that I had no idea when or what I was going to be fed so I grabbed lunch at the new Kona Brewing Company outlet in the airport. The food was fine, marked up like airport food always is. However, I now realize that US airlines crappiness has now lowered my expectations of how air travel should be. Korean Air fed me lunch (which became lunch #2) of bibimbap that was quite tasty, and then dinner before landing at Incheon. This was in coach of course. Their in-flight magazine even has a listing for each route they fly that shows the various meal & beverage services that you will receive, but also the timing of each.

The KAL flight attendants were all female and none could have been more than 40 years old (probably late 20s early 30s). The probabilities of that happening by chance seem low to me. One even had to stare down a passenger that claimed he would pee in his seat if she didn’t let him go to the bathroom (the seatbelt sign was on due to turbulence).

The Incheon airport had a Dunkin Donuts right outside the exit from customs. I suppose I should be sad that American chains are taking over the world, but I have a soft spot in my heart for fried dough and Dunkin Donuts in particular.

On the road from the airport I noticed that periodically along the side there were stationary lights of the type you would see on a police car. Some were on the middle of straightaways, others were at forks in the road. I’m guessing these were placed to get drivers’ attention (maybe to get them to stop speeding). I bet it is effective, from a distance when I saw the first one I thought a cop had pulled someone over.

Tomorrow the workshop portion of the conference starts. I’m attending the Ubiquitous Sustainability workshop in the morning, and the Devices that Alter Perception one in the afternoon. I’m presenting and giving a quick demo of SocialSense at the DAP workshop.