The title of my talk for NECHFES2008 student conference was “Multi-threaded spoken dialogs in hands-busy and eyes-busy environments: Human-human experiments”. That talk was mostly about our new experiments that we plan to run. We will use variation of a Twenty Questions game in our experiments. This game allows us to control the search space for the solutions and clear identification of adjacency pairs. I’ll be posting more information about the experiments later.

Thanks,

Alexander Shyrokov

I’m reporting today from the NECHFES Student Conference held this year at the Northeastern University in Boston. Here you can see our participants: Matt, Mark, Zeljko, Nemanja and Mike. Alex was also present.

So far we have heard very interesting driving simulator talks from NEU students. Hui Cai presented his results on estimating driver emotional state using various physical measurements (heart rate variability, skin conductance, etc.)

After him, Z. Yin presented his study on driving simulator sickness. He has found that, optical flow affects largely this type of motion sickness.

That’s all for now. We will have more posts about today’s very interesting conference.

Oszkar

Finally, the Project54 video for the IACP is finished. This meeting is a major conference and exposition organized by the International Association of Chiefs of Police happening in San Diego this year. As the name says it gathers top police officials from all over the world. Project54 will have its booth there, presenting the P54 system and our driving simulator. This is also the topic of our newly made video: the driving simulator and its capabilities for in-car device evaluation. Here it is:

I would like to thank Nate Purmort, the lead role actor/narrator, for his patience with taking, retaking and re-retaking scenes for the video, and professors Andrew Kun and Thomas Miller for their suggestions and guidance.

Oszkar

Hello ecebloggers,

In my previous post I wrote about Naturalistic Driving and Analysis Symposium at Virginia Tech University. The most interesting event on the symposium was demonstration of the Smart road, a research facility managed by Virginia Tech Transportation Institute. It is a 2.2 mile twp-lane road with a capability to produce a wide range of weather conditions (see pictures below).

VTTI’s Smart road (just the bridge)

Fog

Rain

Smart road uses 500,000 gallon water tank which supplies 75 water towers to produce rain, a fog like mist, or snow. It is also equipped with variable lighting to study effects of lighting technologies on visibility (see pictures below).

Smart road’s lighting system

Rain by night

Of course, everything needs to be coordinated (weather, traffic, lighting). This is done in control room.

Control room

Control room (downstairs)

VTTI uses real cars in their experiments on the Smart road. They are measuring speed, traveled distance, lighting conditions… Almost anything you can think of. Examples of the equipment you can find in the cars are in the pictures below.

Thousands of hours of on road research have been conducted on th Smart road. It is intended to become a part of the public transportation system connecting Blacksburg, VA to Interstate 81.

Pictures from the conference can be found here.

Have a good one,

Nemanja Memarovic

Hello ecebloggers.

Last week, from Monday 25th ’till Wednesday 27th of August, I went to Naturalistic Driving and Analyses Symposium at Virginia Tech Institute. Symposium was about naturalistic observation in driving. Simply said, naturalistic observation is unobtrusive observation of subjects in their natural environment. Tom Dingus, seen in the picture below, from Virginia Tech Transportation Institute (VTTI) held the opening session and gave a brief overview of naturalistic driving methods and their role in driving safety.

Robert Skinner, in the picture below, TRB executive director, continued the opening session and talked about the importance of naturalistic driving research to highway safety. He discussed Tom Vanderbilt’s book “Why we drive the way we do (and what it says about us)” as one of the most important books in the filed of driver behavior.

Dan McGehee from the University of Iowa (in the picture below) conducted a very interesting research on critical events in driver behavior using event triggered video records.

In his study he wanted to find out what causes those critical events. The study was 52 weeks long, 6 weeks of baseline, 40 weeks of feedback and another 6 weeks for secondary baseline and involved 12 subjects. In that period of time 6000 events were recorded including 15 crashes and 25 near crashes. He found out that the most common reason for a critical event is improper speed for turns. Other events where reported, like abrupt braking due to snow.

One of more interesting talks for me was from Shane McLaughlin from VTTI (in the picture below) on data mining in cars.

He gave an overview on how to conduct successful data mining and challenges in doing that. Some of the challenges he mentioned are recognition of the data that might help the research, importance of being familiar with the data, and challenges in evaluation of the data.

The most interesting event on the symposium was demonstration of the Smart road. I’ll write more about that in my next post.

Have a good one,

Nemanja Memarovic

A few day ago, Prof Andrew Kun, Andras Fekete and I visited the Intelligent Environments ‘08 Conference in Seattle, WA. An earlier post already introduced this conference on eceblogger. We presented three works there. Andras had a great poster on the deployment of his new P54 PDA software. The poster session took place in the afternoon of the first day. I think his work drew the biggest crowd.

Andras presented the PDA study with great confidence and answered the questions flawlessly. Besides him, I also presented my research results from the past year. I had two oral presentations. The first one was on the steering wheel sensor device. This was a mixture of a regular slide-show presentation and a demonstration. For this purpose we shipped out a scaled down version of our driving simulator equipped with the new sensor. Here, we are testing the system right before the the start of the presentation.

Luckily, none of the equipment got broken during transportation, so everything worked perfectly. My other presentation took place in the afternoon of the second day. It was on the results of the PTT glove experiment that we mentioned here before. This presentation also went smoothly.

The conference was organized very nicely, with helpful hosts and great food. They even scheduled a visit for us to see the Microsoft Home project. The location of the conference was on the campus of the University of Washington in Seattle. It proved to be a beautiful place. I didn’t even know that there are campuses in the USA that are built in gothic style. I have seen this before only in Europe. Here Andras and Andrew explore the square in front of the landmark library building of the university, that looks more like a gothic cathedral.

Thanks go to Prof Kun for helping us and actively participating in writing all three papers (second author on all of them). Also, thanks to Erika Clifford for doing all the logistics for the trip and shipping the equipment.

Oszkar

Zorana and I just got back from a fun trip to Taiwan.  Zorana was invited to speak at the Psychology of Creativity Conference at Taiwan National Normal University, and they paid her ticket and a honorarium.   We decided to turn it into a vacation as well, so we booked a ticket for me too, and we spent two weeks there.   I will leave it to Zorana to describe the conference, which was a rather interesting cross-cultural experience in its own right.    You can check out our slideshow at http://picasaweb.google.com/zivcevic/Taiwan_jmp/photo#s5211542192009555298 — just click the link labeled slideshow on the right of the page.

The trip was wonderful.   I was not prepared for how interesting Taiwan was — I had really no image of it in my head.  It is fizzing with energy, entrepreneurial and otherwise.   Everybody is very helpful, and tries hard to help you, even if they do not have a word of English.    You are never more than a few blocks from a little street side food shop, in which they serve their specialty on rice or noodles.   They will show you what they have, or mime the animal (fish and chicken are easy to get, but pork is a bit harder).   There are little temples everywhere, and several grand ones in every big town, and many big ones in the big cities.  Each is dedicated to one or two or more deities or deified people (it’s complicated and ecumenical — see http://en.wikipedia.org/wiki/Religion_in_Taiwan).

In many ways the country combines the best part of traveling in a developing and developed country — the food and lodging are quite reasonable (Dinner in a street side restaurant, about 5$.  Mediocre hotel, but with a bathroom and AC, 30$.  Very nice hotel, 50$ a night).   Every place is well staffed by competent people, even little tea-shops in the mountains, and they are all very flexible with clueless foreigners — often they just guessed what we wanted, and were nearly always correct.   One of the things is that it is a much richer country than I expected.  It is about twice as wealthy as Croatia, and many people have been tourists, so they know what that is like.  We saw very few western tourists, and nearly everything is geared to local tourism.   And of course, the roads, subway, airport and most other infrastructure is brand new and excellent.

The language barrier is real — but much more in the written than the verbal.   Everyone is supposed to have studied English, but it is only the last few years that they have actually practiced any conversation.  English is a BIG thing, so there is often a panic reaction anytime they need to speak it.   Often you will see the entire restaurant staff huddle, and nominate the youngest one to be the designated speaker.   But you can always work it out, and they are good at working with you.  (Every little kid says “Hi” and “bye-bye”, and parents often push their kids to practice English with you, to the kids’ terror).    But not being able to interpret the ideograms quickly can be a chore, especially when driving.   You can memorize the characters for your hotel or road, but that is hard to do quickly.  Many signs have roman transliterations on them, but they are often much smaller then the main text.  Also, there are several different ways to go from Chinese characters to the Roman alphabet, and Taiwan uses all three main ones with wild abandon.   You can usually sort it out if you say them out loud with a fake accent (sounds corny, but it works).   If you look at a map of the Alishan forests, from our mountain trip, you can spot our two routes — 159-flyswatter and 162-flyswatter (http://maps.google.com/maps?q=alishan,+taiwan&ie=UTF8&oe=utf-8&client=firefox-a&ll=23.481826,120.696487&spn=0.167837,0.211143&t=h&z=12).  The written English is often a bit odd — see the examples in our slides.   But it is most often understandable and often a bit entertaining.

We started out with a few days in Taipei, the capital, enjoying the temples and food and the excellent museums — check out the world class National Palace Museum (http://www.npm.gov.tw/en/collection/selections_01.htm).   We then traveled down to Lugang, and old and well preserved port city to enjoy the old style architecture that has mostly been obliterated elsewhere.  After that we went to the mountains, to enjoy the spectacular scenery of rugged mountains and tea plantations (and many nice tea shops and ceremonies).   There we saw abundant fireflies, flowers, squirrels, friendly dogs and a monkey!  The landscape really does look like Chinese landscape painting.  Then we returned to the coastal plane and the old capital of Tainan, where there were many nice temples, including our favorite, the Confucian temple (predictable, that).  We then drove back to Taipei, and took the subway to the mountains, hot springs, night markets, food courts and more museums.  Then we flew back.

We highly recommend Taiwan — a bit off the beaten path, but fun and easy and interesting.

So check it out in our pictures –  http://picasaweb.google.com/zivcevic/Taiwan_jmp/photo#s5211542192009555298

Cheers,
Jamie & Zorana

My colleague, Zeljko Medenica and I are participating at this year’s Young Researchers’ Roundtable on Spoken Dialog Systems in Columbus, Ohio.

This is a very interesting event with lots of young speech researchers from all over the world. There are also representatives from different research and development companies interested in spoken dialog systems like: Microsoft Research, Nuance, VoiceObjects, AT&T, Toyota ITC, Harman/Becker, etc.

During the days of YRRSDS we have participated in several roundtable discussions, which covered some very interesting topics: multimodal systems, next killer-apps, dialog system develpoment, how to make spoken dialog systems human-like, etc.

More detailed description on the topics will be provided in future posts.

Zeljko and I also presented our posters which summarized our research interests. Participants were very interested in hearing about our experiments and results. This will also be discussed in future posts.

Columbus is a very nice city with a huge university campus OSU (biggest single campus in the USA), where the event took place. The organizers put a lot of effort in making this roundtable a very interesting one.

Oszkar Palinko and Zeljko Medenica

Last week, May 12-13, the IEEE held a conference on Homeland Security technologies in Waltham, MA. Eric Ramsey, a former Project54 employee, was presenting a paper related to his master’s thesis on the development of a Project25 data radio basestation. I went down to accompany him for the 2nd day of the conference and view some of the other presentations on Homeland Security technologies.

During the opening talks of the day, it was immediately apparent that this was not a gritty engineering conference, but instead more of an business-oriented affair, discussing the industry that has grown up around Homeland Security rather than the gory details of the technologies themselves. This put Eric’s presentation a little out of place as it was a very detailed engineering breakdown of his work, but it didn’t seem like he lost anyone as people asked intelligent questions and were more than willing to discuss the topic with us afterward!

Here is Eric presenting:

The presentations which particularly interested Eric and I, since we are both involved (or were at one point, in the case of Eric) in the Project25 basestation project at Project54, were those concerning radio interoperability. We saw many different takes on how to solve the problem of facilitating better bandwith and channel usage, allocation, and communication in general between public safety organizations. From creative (in terms of today’s standards) radio policy management to satellite-based communications (rather than LMR), to shifting bandwidth to the 700MHz band (formerly occupied by analog television) to improving the radios themselves, there are a lot of little pieces to the puzzle! We even saw a presentation from a fellow NIJ COMTEC fundee, Nancy Jesuale.

On a side note, one of the professors here at the UNH ECE Department, Andrzej Rucinski, was co-chair of a session at the conference. Unfortunately, the session ran at the same time as Eric’s presentation, so we were unable to head over and say “hi”.

The conference was a great experience - I hadn’t been to one since the Network Security conference I attended a few years back in Boston, and this one was just as interesting. It’s always nice to take a step back from your own work and check out what other people in the field are doing! Radio interoperability is a huge undertaking, and it’s great to see so many smart people working on the problem!

Each year at UNH, the Electrical and Computer Engineering Seniors join with other engineering disciplines in the Undergraduate Research Conference (URC). Here they present their research projects that they have been working on for months, some even up to a year. This year, the projects range from renewable energy to digital imaging processing to audio noise canceling.

One interesting project was “InterFACE”, which utilizes digital image processing to track the movement of a face. It then uses that data to recreate the motion in a robotic head sculpture. The pictures below depicts their system design.

Another project which incorporated electrical design was the “Tidal Power Generation”. This project was a combined effort of the Mechanical, Ocean and Electrical Engineering Departments. Here the idea of utilizing tidal action, and the related currents, to convert into electrical power by way of a turbine was investigated.

Above we see the display of the system, as well as a demonstration of the theory behind the project.

Overall, the conference was exciting and impressive, and the Seniors really worked hard to put forth their best efforts. For both myself and Mark Taipan, we were especially excited due to our recent award of a SURF Grant for the summer of 2008 to work on our project Kingsbury Location Awareness System (KLAS). We will be presenting our project at the URC next year, and so it was very helpful to see this year’s projects which will help us plan our presentation for next year.

Matthew Lape