Hello readers!

I come to you with a post on my travels in Hungary. This summer I had the opportunity to vacation there. For those of you wishing for a change of scenery from UNH, I suggest you take advantage of the exchange program offered by UNH to go visit BUTE (Budapest University of Technology and Economics). The program is perfectly compatible with your studies at UNH so your graduation won’t be delayed by going. The professors are really good there, and everything is taught in english so you won’t have to learn hungarian. You do have the option of taking some culture classes to learn about life for the natives here.

You can see in these pictures the campus (click to enlarge). It is located along the Danube river. The “K” building, as it’s called is the main building of the university. It is where a lot of the courses are held for the Hungarian students.

“R” building is essentially a giant cluster building. The third and fourth floors are filled with only clusters of computers. There are computer monitors in the halls displaying which systems are in use, reserved, or otherwise unavailable.

On the left is the view of the outside of the ECE building, basically the equivalent of Kingsbury at UNH. It is a very new building, and air conditioned. This other building is right outside the ECE building, in it you can order all sorts of freshly cooked food and drinks between your classes. This is not the only one, there is one basically on every street. Food is relatively cheap in Hungary.

Across the Danube on the other side, you can see the Parliament building, the “White House” of Hungary. It contains the crown and accessories that the king of Hungary used to wear. You can take a tour inside during the summer at specific times when tours start. Very worthwhile trip. Hungary is also in the middle of Europe, and you can travel to other countries very easily on the weekends. Not like Hungary doesn’t have anything to offer, but while abroad, you might as well step outside the borders to see what surrounding countries have. BUTE offers lots of small weekend trips to many places in Europe for a very reasonable price.
Hope you grasp this wonderfull opportunity, even I have and I was born there!

András Fekete

I would first like to say I have thoroughly enjoyed my 3 weeks interning at Project54. During my time here, I have created four “hazardous” traffic incidents. Hazardous in the sense that there is perceived danger, which requires the driver to take preventative actions to avoid collisions or accidents. While none of these are commonplace events, they are quite possible and have probably happened to all of us at one point or another.

The first is a driver pulling out from the shoulder, cutting you off. The second is a pedestrian who is unaware of your approach and walks out into the road in front of you. Due to the possibility of emotional impact on participants in a study from harming a simulated pedestrian, there is no way for the driver to actually hit the pedestrian accidentally. Either the person turns around upon “seeing” you, or they start to run if you do not slow down. The third event is a “trick” light, which turns yellow a little too late, forcing you to stop or run a red light. The final event I created causes the surrounding traffic to pass a very slow bicyclist heading towards you. When the vehicles pass the bicyclist, they swerve into your lane, forcing you to stop and swerve into the shoulder. Here is a video that demostrates these four incidents as they occur in the Project54 driving simulator:

I wrote these scripts in such a fashion that they can be used in any driving simulation scenario. This was a critical aspect since the final goal of all these events is implementation in a sort of distraction test course, which can be used as a gauge of how safe a piece of equipment is, based on how well the driver is able to navigate the course while using the equipment.

Owen Derby

Christopher Gaudreau, one of my graduate students for the past 2 years, has defended his MS thesis. Chris worked on developing software for a handheld computer version of the Project54 system. Chris’ software enables officers to interact with the in-car Project54 system from outside the cruiser. Chris conducted a pilot deployment of the software in which 3 officers used his software. Chris collected log data from the officers’ interactions with handheld computers. The pilot deployment resulted in valuable feedback. For example, we realized that the handheld computer’s built-in speaker is not powerful enough for outdoor applications. We also learned about an interesting usage scenario. One of the officers used the handheld as a remote control for the radar: he parked the cruiser, observed radar readings on the handheld from a distance and, when he wanted to stop someone, he remotely turned on the lights to get the driver’s attention.

Here is a picture of Chris at the defense.

At the end of the defense Chris received several good suggestions. One of them was by Ben McMahon, who suggested retrieving log data from the handheld wirelessly. We discussed this idea and decided to try using the 802.11 connection between the handheld and the car to move log data from the handheld to the car. It can then be uploaded at wireless update stations which we are currently working on. Of course, Ben is familiar with the idea of remotely accessing log data, since this is what is done in the Project54 datacasting effort, which he is a part of (for more on this, see Ben’s Project54 page for the list of papers he is a co-author on).

As for Chris, he has already been working in industry for several weeks. He is an engineer with 54ward in Manchester, NH. 54ward specializes in deploying the Project54 system and hopes to extend its reach throughout the US (and probably other places!). Congratulations Chris on a great thesis and best of luck in your future endeavours.

Andrew Kun

Owen Derby, a participant of the St. Paul’s Advanced Studies Program, spent several weeks during this summer working in the Project54 lab. He created several scenarios for the Project54 driving simulator. The scenarios are to be used in testing driver distraction. Here is a picture of Owen during the presentation he gave about his work at Project54.

Owen’s scenarios are meant to surprise the driver; for example in one of the scenarios a pedestrian quickly walks into the street (on a collision course with the simulated vehicle) from behind a parked bus. If the driver is distrated he/she may not apply the brakes in time. Btw, Owen will make sure you cannot actually hit the pedestrian! While hitting an animated character does no harm, it may have an emotional effect on a participant in a study, and this is something we’d like to avoid.

Andrew Kun

Skimming Slashdot today, I stumbled across a Youtube-esque site for the science community. It’s called SciVee and is operated by the Public Library of Science (PLoS), the National Science Foundation (NSF) and the San Diego Supercomputer Center (SDSC).

According to their about page, SciVee provides a place for scientists to attach video content to papers they write. It allows contributors to create profiles of themselves with all of their papers and videos linked.

Perhaps this is an appropriate site for posting Project54 media.

Ever wonder what the difference is between ubiquitous computing (ubicomp), pervasive computing, ambient computing, and a plethora of other terms used by researchers to refer to interconnected computing devices embedded into the world around us (hmm, is this a definition?). Albrecht Schmidt takes a crack at making sense of the different terms in this post on his blog.

Also, for the fun of it, try searching “define: pervasive computing” in Google, follow the Wikipedia link, and check out the title.

Andrew Kun

Hello again. This year was very productive for our papers at different conferences, so we are getting ready for another one. This time we published a paper at the conference called Interspeech 2007, which will be held at the end of August in Belgium. Our paper, The Effect of Speech Interface Accuracy on Driving Performance, written in collaboration with Tim Paek of Microsoft Research, was accepted for the poster session. Here, I will say a couple of words about the research that was performed in the paper.

With increasing the number of electronic devices that are finding their way into vehicles, the number of potential sources of distraction increases as well. As we showed in our paper that was presented at Driving Assessment 2007, speech interaction with in-vehicle devices has a potential to eliminate or at least decrease this distraction.

While designing speech user interfaces, there are several important factors that must be paid attention to: speech recognition accuracy, push-to-talk (PTT) button, and dialog repair.

Speech recognition accuracy refers to the accuracy of the speech recognizer, and it is clear that it is desired to be as high as possible. Because current speech recognizers do not work well with ambient recognition, PTT buttons still have to be used in order to improve the recognition rate. Dialog repair refers to the procedure the user has to perform when the recognizer makes a mistake.

Now, if we take these factors into account, the logical question would be what the influence of these factors is on driving performance. In order to investigate this, we designed an experiment with these factors: speech recognizer accuracy (Low accuracy 44% vs. High accuracy 89%), PTT button usage (with vs. without), and dialog repair (misunderstanding – the system responds with incorrect recognitions vs. non-understanding – the system responds with “unrecognized”).

The experiment was performed in our driving simulator. Twenty subjects participated in the study. From the simulator we collected three variables: lane position, steering wheel angle, and velocity. We calculated the variances of these variables taking into account only the road segments on which subjects performed interactions with the system. Higher variances indicated worse driving performance.

The video below will help you get a feel for how the experiment was performed. The subject was involved in all interaction combinations: successful recognition, misrecognition, and dialog repair. Dialog repair is performed in the case of a misrecognition by issuing a “cancel” command and repeating the misrecognized command. The interactions were performed using the PTT button.

After performing statistical analyses on the data that we obtained from the simulator, there were two major conclusions that we could draw. First, the steering wheel angle variance is higher (which indicated worse driving performance) when the speech recognition accuracy is Low. Second, lane position variance is higher (worse driving performance) when the speech recognition accuracy is Low and the PTT button is being used. The type of dialog repair did not have any statistically significant influence on driving performance.

These results are very important for the design of in-vehicle speech interfaces. Although, connected with these factors there are interactions with some other variables that can also influence driving performance, such as the position of the PTT button and frustration that is induced in subjects when the speech recognizer performs poor recognition. These questions will be investigated in our future research.

The conference starts in a couple of weeks, and after we come back, we will probably have more experiences and information to share. So, stay tuned!

Zeljko Medenica

Hello,

My name is Oskar Palinko. I’m a grad student at UNH. For some time now, I have been working on a wireless glove push-to-talk interface for Project54. I inserted push-buttons into the fabric of a glove, under the fingertips of the index finger and the thumb. These buttons activate an RF remote controller (AirClick) which triggers the speech user interface of P54 to listen to the operator.

We supposed that this design could help the driver issue commands more easily and more efficiently than with the standard PTT button that is fixed to the crossbar of the steering wheel. The main problem with the old design is that the push-button drifts away from the fingertips of the driver whenever taking a turn, driving in a sharp curve or during any other maneuver that needs the steering wheel to be turned more than +/-90 degrees from its straight position. These situations occur most often when driving in a city.

We designed and conducted a pilot study to examine if the drivers, when allowed, would like to use the whole steering wheel as a push-to-talk surface, instead of clicking only at a certain place. The glove allows this freedom, because the PTT button is always under the fingertips. The subjects were fellow grad students at the project.

The study proved that on average, the drivers preferred the new method of entry and that they tend to use the glove PTT buttons at various angles on the surface of the steering wheel. The pilot, however, did not show statistical significance to prove that using the glove would be a safer way of PTT operation (measured by the steering wheel and lane position variance).

A short paper and a poster were submitted to the 2007 Symposium on User Interface Software and Technology (UIST2007). Unfortunately they were not accepted. You can view the accompanying video below:

Further experiments will be performed with a larger, non-Project54 population. Hopefully, the new data will allow us to improve our understanding of different modes of user interaction.

Oskar Palinko

Here is an interesting article from the New York Times on the reading habits of successful CEOs.

Andrew Kun

While my main research interest is in speech user interfaces, I have to say that the Microsoft Surface looks very nifty. I really like the ideas for interaction between virtual objects and physical objects shown in the third (rightmost) video on the Surface website. By the way, I found out about the Surface from my wife who was browsing the Ikea Hacker website and found this article (if you’ve been to our house you’re not surprised that she was on this website).

Andrew Kun