Open up your mind and say, ahh...

Hoping to make it easier for crime victims and witnesses to recall license plate numbers, Massachusetts may begin handing out plates with fewer characters and a symbol in place of one digit.

The proposal is the brainchild of Gary Richard, a Bay State businessman and inventor. After reading about several high-profile kidnappings, Richard dedicated himself to using his time and skills to prevent future abductions. What does that have to do with license plates?

“I set about trying to analyze the dynamics of an abduction,” he said. “The common denominator is a private vehicle, and how do you identify a vehicle? The license plate.”

Unfortunately, young children and anyone with limited literacy often cannot recognize some letters and numbers, especially if they go by in a flash. Hell — most adults can barely remember their own plate numbers. Armed with studies that show symbols can ingrain themselves in the minds of toddlers for more than a week, Richard set to work.

He designed a license plate with fewer characters and symbols alongside the typical alphanumerics. He calls it the EZ-ID license plate, and has for 10 years been pushing his home state of Massachusetts to adopt it for all randomly issued general-issue registrations.

He’s finally gaining traction.

EZ-ID license plates add a symbol and use fewer characters to make license plates easier to remember. Image: Gary Richard

Under Richard’s plan, which is gaining support from legislators, law enforcement and child advocacy organizations throughout New England, EZ-ID license plates would add a diamond, star, heart or triangle to the existing set of characters. Registries would need no more than four characters to allow for 107 million possible combinations, or three times what current plates allow. Fewer characters also allows using a larger font, making plates easier to read.

“If such license plates are indeed easier to memorize or recognize, this could help, for example, a victim relay a license plate to law enforcement after an incident,” said Cynthia Lum, a professor of criminology and director of George Mason University’s Center for Evidence-Based Crime Policy. “Memorizing a plate is difficult in a stressful situation.”

No one’s empirically tested the effectiveness of the new plates, but the math shows that fewer numbers on a license plate makes even a partially remembered registration more valuable. According to Richard, just the style and color of the car with a symbol alone would narrow it down to one of 360 cars, and more information would further focus the search.

“If you said it was a blue SUV and ‘Diamond 5,’ it’s one of about 12 cars,” he said.

The ability to quickly narrow a list of suspected vehicles helps law enforcement track down the owner of a vehicle. Although the owner of the vehicle may have had nothing whatsoever to do with the crime, it is still an important lead.

“By connecting with the owner, the police can determine who had the vehicle at a given time, or whether the car or license plate had been stolen,” Lum said.

Because there’s no easy way to input a star or diamond on a computer keyboard (unless you’re using a Commodore 64), EZ-ID uses a small two-digit code to indicate its symbol and where it’s located in the character stream. For instance, a diamond in the second position would be entered as “D2.” Vanity and affinity plates would stay the same, so Bostonians could keep their coveted low-number or Red Sox plates, and the addition of symbols would open up a slew of personalized plates people may be willing to pay for.

A bill to adopt EZ-ID has been wending through the state Legislature for years, but Richard remains hopeful lawmakers will act on it this year. The only significant pushback he’s received has been about the cost of the program, but he’s convinced supporters in the State House that implementing EZ-ID would be a minimal expense. Richard said state officials estimate it would cost $30,000 to upgrade the tooling to manufacture the new plates.

“If that’s an obstacle, I’ll pay for that myself,” he said.

Photo: Whirling Pheonix/Flickr

I took my first ever yoga class the other day, thanks in part to having a yoga instructor girlfriend. It was at a really nice studio in northern Massachusetts called Roots to Wings. My instructor, Beth, was very aware that I was new. She was very aware that this was my first ever yoga class, and that how I received every bit of this class would likely shape my perception of yoga. Think about that, the burden on that instructor’s shoulders. Beth is watching me try to figure out her instructions worrying (at least a bit) that if I don’t get it, if I don’t enjoy the class, and thinking that she’s got to deliver a great experience to me so that I’ll consider going forward with the practice she holds so dear.

How often do we think about our own business that way? How often do we build experiences such that we’re welcoming of new people? Do we work enough on that? Do we help people get connected and involved? Do we make them feel like we realize it’s their first time and we’re here to guide them?

Researchers at the Massachusetts Institute of Technology are developing a tool to mine aircraft black boxes for valuable data after every flight, something they say will improve daily operations and prevent accidents.

An airplane’s black box, or flight data recorder, continuously records performance data and other information during flight. That data has long been used to reconstruct the events that occurred before an accident to understand what happened. But the researchers believe that data can be used proactively, and daily.

Retrieving and analyzing data from a flight data recorder after a typical flight is not new. Airlines often check a quick access recorder that operates in parallel with the flight data recorder, examining certain parameters to improve operations and safety. But current tools are limited to looking for known issues, and the amount of data can be staggering. MIT professor John Hansman says the key is developing analysis tools that can effectively utilize all the information.

“It’s a classic data mining problem,” he says. “You may be getting 300 parameters, 30 times a second, flying 7,000 flights a day.”

Commercial airlines in the United States are not required to implement a flight data monitoring program. But the Federal Aviation Administration has a flight operations quality assurance program that includes guidelines airlines can follow on a voluntary basis.

Airlines typically monitor known parameters that have helped identify issues in the past. Things like engine thrust and aircraft speeds, as well as flight control positions such as elevator and rudder inputs, are among the things studied at the end of a day’s flying or when flight data is analyzed after a crash.

It works well enough, Hansman says, but it focuses on flagging known parameters and measuring them against known baselines. That makes it difficult to know what you don’t know but should be looking for. Hansman and his team developed software that uses cluster analysis to to spot potential problems without knowing in advance what parameters to monitor.

“We’re trying to flag problems we don’t know about,” he says, “and we don’t know what the baseline is.”

The cluster analysis tool can create its own baseline for reference.

“You don’t need to know ahead of time what the problem is,” Hansman says. “It finds the normal behavior in the clusters.”

Using flight data from a defunct airline that flew Boeing 777s, the team collected data from 365 flights. They found several cases where the cluster analysis software identified problems. With each parameter represented by a vector, they were then mapped in a multiple-dimension “hyperspace” where outliers could be seen outside the data clusters that represent a normal flight.

Once identified, the outliers can be investigated further to determine what, if any, impact they might have. In some cases, they are nothing to worry about, but in others they may flag a potential issue that could improve safety and operations.

Hansman hopes to further develop the cluster analysis software with larger data sets from more airlines in the future.

The Spark of Genius Series highlights a unique feature of startups and is made possible by Microsoft BizSpark. If you would like to have your startup considered for inclusion, please see the details here.

Name: Medify

Quick Pitch: Medify mines data from millions of studies to make assessing medical experts and treatments easier.

Genius Idea: Visually explaining how medical conditions and their treatments have been studied.

Searching “autism,” for instance, brings up a Wikipedia page, a fact sheet from the National Institutes of Health and an overview from MayoClinic. If I get more specific with my search, and type in “Risperdal,” a drug that is sometimes used to treat autism symptoms, I get a result titled “What Risperdal did to me” and another for a dense 2002 study by the Massachusetts Medical Society.

Derek Streat, Medify’s co-founder and CEO, didn’t find these sorts of search results helpful when his daughter was diagnosed with a rare and threatening illness.

“If you spend any decent amount of time with a doctor,” he says, “you will surpass what a WebMD will tell you within a half hour conversation.”

Meanwhile, sifting through troves of studies intended for medical professionals was frustrating.

Medify attempts to find a productive compromise between these two extremes of online health information. It aggregates published research from the U.S. National Institutes of Health’s Medline, a database that contains more than 18 million references to journal articles going back to 1946. Then it scrapes data points like the number of patients studied, their treatments, symptoms and side effects to generate insights about medical treatments and experts.

It arranges these datapoints in easy-to-read graphs. At a glance, it’s easy to see what treatments are being studied the most and where most of the research is coming from.

A “strength of evidence” graph, for instance, uses an algorithm that bases rankings of treatments for a given medical condition on factors such as how far the drug has gotten in clinical trials, how often it has been studied, how many people it has been studied on and how quickly that treatment is evolving. Users can personalize the search by selecting their demographic information or symptoms to see studies that involved only people like themselves or their loved ones.

Ranking treatments this way might make doctors and researchers — whose papers include pages of caveats for a reason — squirm in their lab coats.

“Every patient is different, but if you get a big enough signal, that matters,” Streat argues.

He says that the platform intends to make it easier to have informed conversations with doctors rather than deliver a verdict on one treatment or another.

“At the end of the day, there’s no drug that you’re going to be able to look at on Medify that you can go buy yourself. It’s not going to spit out a pill.”

If nothing else, Medify helps narrow down relevant studies that might be hard to extract from Medline’s database without assistance. Each customized graph the site creates cites the long version of the studies from which it has pulled data.

Medify is still in beta and without a revenue stream. It is considering either offering premium research services or opt-in marketing services in the future, and Streat says that unexpected attention from the medical community might make a version for doctors another viable source of income.

For now, the company is operating on $1.8 million of funding from Voyager Capital and several angel investors.

Image courtesy of iStockphoto, peepo

The Spark of Genius Series highlights a unique feature of startups and is made possible by Microsoft BizSpark, a startup program that gives you three-year access to the latest Microsoft development tools, as well as connecting you to a nationwide network of investors and incubators. There are no upfront costs, so if your business is privately owned, less than three years old, and generates less than U.S.$1 million in annual revenue, you can sign up today.

“Zero-emissions” is a tricky phrase. Electric vehicles produce zero emissions at the tailpipe, but more often than not there are emissions at the power plant. The only way to have a truly zero-emissions EV is to get your power from a renewable source like the sun.

SolarCity is making it a whole lot easier to do that. The California company has started offering solar EV chargers to customers in 11 states and Washington, D.C., allowing people to drive their cars purely on sunshine.

“It allows for the carbon-free lifestyle. You can go EV and PV and drive on sunshine power,” Ben Tarbell, vp of products, told us. “There are a lot of environmental and economic benefits for our customers.”

The company, fresh off a $280 million investment from Google, makes it easy for people to embrace solar power by leasing them complete photovoltaic packages. It’s been dabbling in solar chargers for awhile, and it installed solar EV charging stations along highway 101 between Los Angeles and San Francisco in 2009.

But the arrival of the Nissan Leaf and Chevrolet Volt, not to mention the plethora of EVs and plug-in hybrids automakers promise to deliver by 2015, makes it time to go all-in, Tarbell said.

“There are a significant number of mainstream electric vehicles available, and our customers are asking for this,” he said. “The market is catching up. We’re seeing an uptick in demand for this.”

The Level 2 (240 volt) ClipperCreek charger costs $1,500 installed. The photovoltaic cells needed to keep the juice flowing will set you back $50 a month. By SolarCity’s math, the average urban driver spends about $230 a month on gasoline (at an average of $3.65 a gallon). Plugging into the grid cuts that to $107 a month, and a SolarCity rig brings it to $54.

Of course, SolarCity is happy to set you up with solar power for the entire house. The cost varies with your energy needs, but a typical home in the San Francisco Bay Area will pay $60 to $200 a month for a 20-year lease, the company says.

The solar chargers are available now in Arizona, California, Colorado, Hawaii, Maryland, Massachusetts, New Jersey, New York, Oregon, Pennsylvania, Texas, and Washington D.C.

Photo of a Chevrolet Volt plugged in: General Motors

The Global Innovation Series is supported by BMW i, a new concept dedicated to providing mobility solutions for the urban environment. It delivers more than purpose-built electric vehicles — it delivers smart mobility services. Visit bmw-i.com or follow @BMWi on Twitter.

In order to tackle urban transportation challenges in cities around the world, the Massachusetts Institute of Technology (MIT) and the National Research Foundation of Singapore launched a five-year cooperative project in 2009 — Future Urban Mobility (FM) — to look at new models and technology tools aimed at sustainability. The FM team is one of four interdisciplinary research groups that are part of the Singapore-MIT Alliance for Research and Technology Centre, or SMART Centre. FM is developing SimMobility, a simulation platform where researchers explore transportation, environmental impacts, energy and land use and the activities of individual travelers in the mix.

Some of the projects of FM include autonomous driving — as in, cars that drive themselves — and simultaneous research is being done in the areas of vehicle-to-vehicle communication and vehicle-to-infrastructure communication. Vehicle-to-vehicle communication looks at applications for both safety and information retrieval.

Applications are being developed so your car will get information about the location and intentions of vehicles in your vicinity, contributing to the process of autonomous driving. Vehicle-to-infrastructure projects are less safety-related and more focused on traffic operations, including the possibility of your car receiving information from traffic signals regarding data like when an upcoming stoplight will turn green. With this data, you can adjust your speed and slow down without having to stop at the signal, thus reducing stop-and-go traffic movement.

Mobility On Demand

Another area of the FM project is mobility on demand. A bike-sharing services is an example of mobility on demand: You get the mobility you need, when you need it, at the place you need it, and you can take it to your destination and drop it off without having to return it to the pickup location. At this time, car-sharing services like Zipcar are not considered mobility on demand because you have to return the car at the same location you obtained it. One solution investigated in 2007 to address the issue of space for car-sharing stations was CityCar, led by the late MIT professor William J. Mitchell. The mobility on demand project is exploring additional solutions.

“Today’s phones have more computing power — in number of transistors — than supercomputers of 50 years ago. Yet, we don’t use it much beyond individual computing,” explains Li-Shiuan Peh, associate professor of electrical engineering at MIT. “Phones have to access all web services through the Internet as they are computed on servers. My group is exploring ways to better harness the immense computer power of phones, networking a collection of phones together to run and drive novel services.”

A recent application Peh’s team developed and prototyped consists of phones mounted on car windshields with no Internet and no servers — just phones talking to each other. SignalGuru is an iPhone app service that lets users know when traffic lights will turn red or green so they can avoid stop-and-go driving and save on gasoline. They deployed the service at MIT and in Singapore and saw a one- to two-second accuracy in predictions and a 30% savings in gas.

LIVE Singapore

The LIVE Singapore! project is “a convergence of art, digital media and information technology” that gives citizens access to visualizations of data from multiple digital streams from the city. The public exhibition of this project opened at the Singapore Art Museum (SAM) and consisted of five large-scale projections of multi-dimensional maps of the city showing the movements of people, vehicles including planes and automobiles, electricity consumption and other elements.

“Employing real-time data recorded and captured by a vast system of communication devices, microcontrollers and sensors commonly found in our urban environment and mapping this information onto multi-dimensional maps of Singapore, we have been able to merge cartography, statistical analysis and data platform technology,” says Carlo Ratti, director of the MIT SENSEable City Lab. “This suggests new ways to view, understand and ultimately navigate our city like never before.”

DynaMIT

The DynaMIT project is a computer system that predicts the future of traffic and transportation conditions and provides the information in real-time to travelers and traffic managers. DynaMIT, led by Moshe Ben-Akiva, professor of civil and environmental engineering at MIT, stands for “Dynamic Network Assignment for Managing Information to Traveler.” Ben-Akiva and his research group at the MIT Intelligent Transportation Systems (ITS) recently received the The Institute of Electrical and Electronics Engineers (IEEE) ITS Outstanding Applications Award in 2011.

So what does it do? DynaMIT provides short-term predictions of congestion in a specific traffic network and then attempts to anticipate congestion before it occurs. DynaMIT uses a mash-up of real-time and historical traffic data for a given area and operates on a continuous basis to not only analyze real-time information, such as from traffic sensors, but add a behavioral model to show the potential impacts of human reaction to the data received (i.e. gaper’s block). The output offers a prediction for a “short horizon” and essentially simulates a network of transportation for an hour into the future every five minutes, completing each simulation in about a minute. The simulations are run faster than real-time using both parallel and distributed computing. The system utilizes “network decomposition” — a traffic network is divided into sub-networks that are then simulated on multiple processors. This kind of work couldn’t be done without modern computer methods.

“DynaMIT allows us to look into the future and see what the travel times, speeds and bottlenecks will be in the next hour,” explains Ben-Akiva. “If we develop and broadcast information about future traffic conditions, it will affect the behavior and as a result, will affect what will happen in the future and invalidate the prediction unless we take that in account.”

Right now, Ben-Akiva’s team is working on DynaMIT 2.0 to re-engineer the system for new data that might become available to incorporate into their system, including navigation systems and travelers equipped with smartphones.

DynaMIT has been tested in a variety of locations including Los Angeles (but not in relation to the recent “Carmageddon”) and Irvine, California, Beijing and Singapore. How well does DynaMIT predict?

Says Ben-Akiva, “We’re testing it right now in Lisbon, Portugal, and it predicts very well. It has a unique advantage over other prediction methods in that it can be used to predict how a network will behave under situations where there is an event affecting demand or supply of transportation, whether it’s a planned event or unplanned event.”

Ben-Akiva explains that a “planned event” might be roadwork, in which case capacity is taken away because a lane is closed or road blocked. An “unplanned event” might be an accident or flooding or another occurrence that causes a reduction in capacity. There could also be events that increase demand, such as a sporting event. In all of these situations, historical data is hindered because there is an unusual or unexpected change in either demand or supply, and that is exactly where DynaMIT excels.

“We did a test of unusual situations or unplanned events in Portugal and demonstrated that the system of DynaMIT has a significant advantage over data-mining, artificial intelligence or statistical methods that essentially combine historical with real time data to extrapolate it into the future,” says Ben-Akiva.

Where do we go from here? In the future, car manufacturers will be installing more and more electronics in our vehicles. Soon, there will be equipment that allows vehicles to communicate with some sort of traffic information hub to provide information in real-time about the locations and the speed of travel and much more, as well as receive information that can be applied by the vehicle and the traveler. And when will we have cars that “drive themselves?” Soon, say the experts — soon.

The Global Innovation Series is supported by BMW i, a new concept dedicated to providing mobility solutions for the urban environment. It delivers more than purpose-built electric vehicles; it delivers smart mobility services within and beyond the car. Visit bmw-i.com or follow @BMWi on Twitter.

Are you an innovative entrepreneur? Submit your pitch to BMW i Ventures, a mobility and tech venture capital company.

Image courtesy of LIVE Singapore!, MIT

Your flying car is almost ready.

Uncle Sam has signed off on the exemptions Terrafugia needs to begin building the Transition, the “roadable aircraft” it plans to begin selling for $250,000 or so late next year. The Massachusetts company, founded by MIT grads, has spent more than four years developing the aircraft, which first took to the air in 2009.

The National Highway Traffic Safety Administration granted all of the exemptions Terrafugia sought to make the funky flying machine as capable on the road as it is in the air. The exemptions allow the company to install tires more suited to the unique vehicle, for example, and use polycarbonate windows instead of heavier glass.

“We further conclude that the granting of an exemption from these requirements would be in the public interest and consistent with the objectives of traffic safety,” the feds said.

Catching a break from the feds will allow Terrafugia to begin delivering the Transition to customers once it completes certification testing. The company also is hip-deep in crash testing.

The exemptions follow a decision the FAA made last year to grant the company an extra 110 pounds to the light sport aircraft limit of 1,320 pounds maximum takeoff weight. That will allow the firm to install vehicular safety equipment like airbags while still competing with other LSA aircraft in terms of range and payload.

As much as we love calling this a flying car, the company insists it’s an airplane you can drive, not a car you can fly. Whatever. We want to try one no matter what it’s called.

Photo: Terrafugia

Smartphone apps may be the key to getting people out of their cars and onto mass transit.

An interesting study of commuters in Boston and San Francisco found people are more willing to ride the bus or train when they have tools to manage their commutes effectively. The study asked 18 people to surrender their cars for one week. The participants found that any autonomy lost by handing over their keys could be regained through apps providing real-time information about transit schedules, delays and shops and services along the routes.

Though the sample size is small, the researchers dug deep into participants’ reactions. The results could have a dramatic effect on public transportation planning, and certainly will catch the attention of planners and programmers alike. By encouraging the development of apps that make commuting easier, transit agencies can drastically, and at little cost, improve the ridership experience and make riding mass transit more attractive.

Putting Riders In Control

The point is for transit agencies to provide enough information to put riders in control of their experience and have greater choice in when and where to ride. People don’t want to feel they are at the mercy of paper schedules, even if they are, and there’s nothing worse than waiting for buses that may or may not be on time.

“You still haven’t made the train change its route or made it (run) on my schedule, because that’s impossible,” said Neela Sakaria, a senior vice president at Latitude Research, the consulting firm that designed the deprivation study. “But you can give enough information that they have control.”

Transit agencies are catching on. A growing number offer real-time schedule information and updates on delays at stations, online and via smartphone apps, said Tom Radulovich. He sits on the board of the Bay Area Rapid Transit system that serves the Bay Area, and he is the CEO of Livable City, a sustainable transit advocacy group.

Although loads of data is no substitute for frequent, and punctual, service, smartphone apps will be essential for attracting new riders, serving casual riders and in neighborhoods or regions with few transit options, Radulovich said.

“Especially if you’re used to the automobile, that real time transit info is something that’s going to make you feel more in control,” he said.

Filling The Information Deficit

Latitude chose Boston and San Francisco for its study because there is a relative abundance of information about public transit. Both cities provide open-source data to developers who can create any number of apps. More than 30 apps have been created with data provided by the Massachusetts Bay Transportation Authority. Those apps increase riders’ sense of autonomy so they don’t feel they’re at the mercy of someone else’s schedule.

“Mobile technology has allowed us to provide customers with dramatically more information about their commutes at a relatively low cost,” said Richard Davey, MBTA general manager. “Just a few years ago, providing riders with real-time information would have required the installation of costly signs at bus stops throughout the system or building a complicated phone system. Today, new technology allows us to simply open our data allowing third parties to provide great solutions for customers.”

Unfortunately, gathering and releasing all that data requires some tech savvy, which too often is lacking at some transit agencies.

“Muni, until recently, had very little information as to where their buses were, how many riders they had,” Radulovich said, referring the to San Francisco Municipal Transit Agency. When Muni started gathering data, it not only helped riders but gave transportation planners the information they needed to manage transit systems more effectively. Other agencies can learn the same lesson.

“That’s going to be a boon to the agencies,” he said. “If they use those tools customers can have more information and feel empowered, and the agencies themselves can manage reliability.”

A Sense of Community

Study participants reported that ditching their cars made them feel more connected with the communities where they work and live. That feeling grows stronger still with technology that connects riders to the cityscape.

“We heard of a sense of community, and a serendipitous sense of experiencing their community that they wouldn’t be doing if they were going from point A to point B in their cars,” Sakaria said.

Without cars, participants rediscovered their neighborhoods while walking or biking to and from transit stations. Many said they’d like more information about the areas they pass through while riding mass transit. For example, if there’s a supermarket where they can grab something for dinner or a gym where they can work out, have it show up on the transit map.

To be clear, none of the participants had a lifestyle that left much time for exploration. They all had jobs and pretty rigorous schedules.

“What was really interesting is the people we talked to were inherently in need of getting to work,” said Sakaria. “If someone could get other things done on their public transit ride — what other errands they need to run, for example — this time that you’re using to get to work can actually be more productive than time spent in your car.”

Radulovich says transit riders, pedestrians and cyclists have a better sense of the communities through which they traveling, which increases social cohesion. Technology, he said, can take some of the unease and guesswork out of finding what lies between the stops.

“You might not know that there’s a dry cleaner here, there’s a hardware store here,” he said. “Things might be closer to you than you imagined.”

Making Connections

For all that BART and the MBTA have done to share data, Sakaria says there is still a disconnect between transit apps and services that might be useful to riders. For example, MBTA and BART have teamed up with car sharing services to allocate parking for shared cars. Ideally, an app would meld the two services, allowing transit riders to have a car reserved the moment their train arrives.

Another example is a new parking app in San Francisco that shows how many spaces are available at a given location. If it included transit schedules and other data, it could quickly and easily tell commuters whether they’re better off driving or taking a bus.

Places less connected than San Francisco or Boston can benefit, too.

“Cities where giving up a car is out of the question can certainly learn something from what we did here.” Sakaria said. “There are things technology can do to improve the perception of public transit that can overcome some of the barriers around infrastructure. It can overcome some of the hurdles that infrastructure can’t.”

In many cities, Google Maps offers directions via bike and transit in addition to driving and walking. Combining each and every mode of transportation into what Sakaria calls a “service ecosystem” can only increase the number of choices open to a commuter.

“I don’t need to be 100 percent a car person, or 100 percent a transit person — but two, three or four days a week I can make the decision to make incremental choices that make me feel good about saving money,” Sakaria said. “Information access becomes a great democratizer. It can start to create equity between public transit, bikes and personal cars.”

Photo: Flickr/takomabibelot

Ask someone what they think the future of driving is and the most likely response is autonomous cars. It’s true sensing and autonomy are dramatically changing cars, but there’s another information revolution afoot. Cheap sensors and network availability aren’t just making cars smarter, they’re boosting the brainpower of the environment cars drive in.

Networks of sensors connected by the Web make it possible to monitor traffic, parking availability, air pollution, road quality and more in real time across vast distances. Traffic monitoring in particular has been revolutionized. This kind of data gives drivers real-time travel time predictions, fosters creation of smart roads where tolls and signals can adapt to changing conditions and provides urban planners with accurate pictures of traffic usage and its effects, improving planning.

One of the most widespread and powerful sensors is the mobile phone. With their GPS and Internet access, smartphones are an important source of information used to provide traffic data. Google Maps, for example, makes extensive use of data collected from users on mobile phones.

Mobile Millennium was among the first large-scale phone-based traffic monitoring projects in the United States. The project, launched by Nokia, NAVTEQ and UC-Berkeley in 2007, is intended to develop and demonstrate technologies needed to allow large-scale data collection for traffic monitoring. The project combines data from a smartphone app and traditional traffic sensors to provide accurate real-time monitoring of traffic conditions in the San Francisco Bay Area.

Designing and running these sensor networks is no trivial task. Data floods in from many sources in many places, and useful data must be separated from noise. Algorithms and models are needed to fuse the incoming data into a comprehensible whole, and protecting individual privacy is also a major challenge. Yet the potential gains are huge, so there is an unceasing demand for more and better data.

In this article, we go behind the scenes at Mobile Millennium to examine the technology behind a distributed sensor network. We look at how the system protects user privacy, examine how data from thousands of mobile phones and hundreds of static sensors are combined to measure traffic flow, and we’ll look at how this technology will impact the future of driving.

Mobile Millennium traffic monitoring software. Image: UC-Berkeley.

An Intelligent Highway

The most obvious use of traffic data is providing drivers with options for reducing the effects of traffic jams and accidents, either by taking alternate routes or simply by changing their travel times. Trip-planning software can use traffic speed information to minimize travel time or fuel usage, and hybrids and electric vehicles might use the data to help optimize battery usage.

This kind of real-time data also lets civil engineers create traffic control schemes that react intelligently. For example, “smart” signals could eliminate the need to wait for red lights at empty intersections. Large-scale efforts might involve roads that actively change the direction of traffic in response to changing traffic flows.

The data is of more than immediate importance. Good data on road usage is vital to predicting future traffic patterns, which is important for planning purposes. Congesting pricing, for example, uses dynamic tolls adjusted according to road usage in an effort to ease traffic at peak times. The success of such schemes depends heavily on being able to measure the effects of pricing changes on driving patterns.

Accurately measuring traffic also is useful beyond the immediate realm of driving. Cars and roads have a huge impact, and traffic has many secondary effects. It is a major source of noise, for example, and creating “noise maps” of the city is one project piggybacking on the Mobile Millennium data and network. By correlating noise patterns to population maps, it’s possible to assess the impact of noise on residents. Cars also are a major source of air pollution, and traffic data can be correlated and combined with measurements taken by pollution sensors to build a map of vehicular pollutants around the city.

Going Mobile

For a long time, traffic sensing relied largely on static sensors. Inductive loop detectors — metal rings embedded in the road — detect the metal in cars passing over them. Traffic cameras are another common tool, and RFID tags used for electronic toll payment can be tracked to provide still more data.

Such tools are generally accurate, but fixed infrastructure is expensive to deploy and operate. It’s also expensive to repair and replace, so these tools typically are installed at key places like intersections and on/off-ramps. But when traffic conditions change downstream — say, during an accident — those changes aren’t detected until the impact ripples upstream to the sensor.

The need for more data from more sensors has made mobility a necessity, and mobile phones are an obvious choice. It’s often said there are more cell phones than toothbrushes in the world, and a growing number of them are smartphones with GPS and Internet connectivity. Mobile Millennium was among the first large-scale projects to take advantage of this development for traffic monitoring.

“This was back in 2007, and at the time we were trying to do traffic estimation using these aftermarket GPS units that you put on your dashboard,” said Prof. Alexandre Bayen, the principle investigator on the Mobile Millennium project. “Right around this time, Nokia put out some of the first phones with GPS — this was before the iPhone — and it became obvious that with Internet connectivity and GPS and the explosion of the cell market that this was a way more cost-effective way to get information.”

The rise of GPS-enabled phones was crucial. Using cell phone signals to measure traffic flow had been attempted before, but cell tower triangulation isn’t very accurate. It also requires direct access to cell towers, which would be expensive and difficult to negotiate with service providers.

Built-in GPS provides accurate data and the net connection provides a simple way of collecting it without special access to the cell network’s infrastructure. It also provides an incentive to drivers to participate — accurate real-time traffic info can be displayed in the same app used to collect data.

Nokia, NAVTEQ, and UC Berkeley teamed up to explore these possibilities with funding from the California Department of Transportation. Nokia provided phones for initial testing and the technology to gather the data. NAVTEQ provided the mapping information needed to match collected measurements to roads. The university developed data fusion techniques to make sense of it all.

The group had to address several interrelated technical challenges. First, information collection had to be done in such a way to preserve the privacy of the users so individual cars could not be tracked using the data gathered. The server architecture had to be designed and set up to do this. Then, theory and algorithms had to be developed to make sense of the incoming data and aggregate the measurements into a unified picture of the state of traffic.

Gathering Data, Privately

User privacy was an overriding concern from the beginning. Project leaders knew users would participate only if their information was protected, and that dictated the structure of the system. How the data was to be gathered would heavily influence both the hardware infrastructure and the algorithms used to process the data.

Maintaining user privacy meant meeting two main needs: preventing, as much as possible, the path of a single vehicle from being reconstructed over time, and separating the identification of the phones from the measurements.

Anonymity was, in some ways, the easy part. Data sent from phones is tagged so the service provider knows where to send the bill. This data needs to be anonymized before processing; this requires passing it through two sets of servers.

When a phone takes a measurement, it creates a data packet containing its position, speed and anything else that might be of interest. This packet is encrypted using the public key of the data processing server, but instead of going straight to that server, it goes to a proxy server that strips the packet of any identifying information. Then the packet is passed on to a virtual trip line (VTL) server that processes it and sends it to the data aggregation servers.

Reading the contents of the packet requires a decryption key. The proxy doesn’t have the private key needed to perform the decryption, so although it knows the identity of the phone, it doesn’t know where the data comes from. The packets that arrive at the VTL server have no identifying information. There isn’t a single machine that can be compromised to provide position and speed information that can be attached to a particular phone.

Preventing paths from being reconstructed was trickier and required the use of virtual trip lines (VTLs), something Nokia developed for this purpose. Instead of constantly reporting location and speed, each phone checks its current location against a downloaded database of VTL positions, and measurements are only sent when the phone crosses a VTL location. This drastically reduces the amount of data collected from any one phone, lessening the likelihood that someone could reconstruct individuals’ paths from the data.

Data is only collected at virtual trip lines placed around the city, helping to maintain user privacy. Image: UC-Berkeley.

This still leaves the possibility a sequence of measurements can be processed to build up a trajectory. Nokia created an algorithm for placing the virtual trip lines in order to minimize the probability that two measurements from consecutive VTLs could be linked to the same vehicle.

Matching up measurements means taking a reading from one VTL and correctly associating it with another reading taken at the next VTL down the road. The more measurements there are from the next VTL that could match the first, the harder it is to determine which belong together. The algorithm uses the number of cars on the road and their speeds to determine the best spacing to maximize the number of cars that might match going through any given VTL pair. In addition, the server that decides where to put the VTLs is separated from the one that processed the incoming data, making it less likely anyone could manipulate VTL placement to make tracking a car easier.

Finally, another layer of protection comes from randomizing measurements. Instead of transmitting when crossing every VTL, the phones perform a virtual coin flip to decide whether to transmit. This makes it much harder to reconstruct individual trajectories.

The final architecture is illustrated below, showing the multi-layered server architecture. These precautions aren’t foolproof, especially in an extreme case like a single car driving down an empty road at night, but they provide a pretty stiff layer of protection.

The architecture for gathering and processing data. Image: UC Berkeley.

Making Sense Of It All

Developing the algorithms for data fusion fell to researchers at UC-Berkeley. In addition to the GPS measurements from the phones, the system incorporates GPS data from buses, taxis and other fleet vehicles. Data from static sensors in the region, such as loop detectors and RFID tag readers, also are included. The question that the data fusion algorithms try to answer is: Given all the measurements gathered from a given road, what is the best estimate of the number of cars on that road and how fast are they going?

GPS tracks in general are hard to process for traffic monitoring, and there were many challenges. One of the first was figuring out what road the measurements were coming from.

“You had to create a fully integrated geo-localizing system to fuse the data,” Bayen said. “You need the underlying road network on which you map measurements to.”

NAVTEQ’s mapping information was vital, but there was a lot of post-processing to be done.

“The maps aren’t perfect, you have roads that lead to nowhere, that kind of thing,” Bayen said. In fact, one of the side benefits of the Mobile Millennium data was that GPS measurements collected for traffic monitoring also improved the map data by revealing and filling in gaps.

Even with complete maps, matching measurements to a road can be tough. People may be walking alongside the road with their phone in their pocket, or they may park the car and forget to turn the GPS off. In urban canyons like downtown San Francisco, many of the GPS data points do not exactly match known roads because buildings obscure satellites. Measurements have to be associated with particular roads using machine-learning methods. These methods attempt to find the most likely road for a particular data point and reject those not likely to be moving cars.

The biggest challenge, and one that remains, is using the measurements with mathematical models of traffic flow to estimate and predict traffic that isn’t directly measured. Sensors only give a partial picture of the world at the time and place where a measurement is taken.

“There’s no way you can have sensors everywhere all the time,” Bayen said. “Look at Google. They have the most data of anyone, and even they don’t have enough to cover the secondary network.”

Models of the physical world are needed to relate those measurements to the rest of the world. The problem is that existing models aren’t well equipped to integrate the kind of data mobile phones provide.

“The integration of mobile data into physical models is difficult, from a scientific perspective,” Bayen said. “There’s no completed theory for it.”

Unlike traditional static sensors, instead of measuring all cars passing a particular location, a GPS measurement gives a single measurement for a single car. This is hard to deal with. To understand why, we must look at how traffic flow is modeled.

The Flow of Traffic

The obvious thing to do when modeling cars on a roadway is track each car individually. This is important in some applications, but the computational resources needed to track thousands of cars and the spatial relationships between them get expensive quickly.

To get around this limitation, researchers often treat the movement of cars as liquid flowing through a series of tubes. Each segment of tube is a portion of road; instead of having to track many individual cars, the number and speed of cars on that road is represented by the density and velocity of the liquid. By using a specialized set of equations similar to those that govern the flow of air or water, the properties of traffic flowing along a road can be modeled and computed.

The equations that govern fluid flow come from conservation relations. The basic idea is straightforward: given a volume of space and some fluid flowing through it, the amount of fluid in that space at a given time is whatever was in there to begin with, plus the amount that goes in, and minus the amount that comes out.

To get a fine-grained picture of fluids flowing through our road network, we break the network down into a connected sequence of small volumes, where each volume is a cell connected to others. The flow properties in each cell affect those neighboring it. And matching the outflow of each cell with the inflow of the next one down the line produces a system of equations that relate the flow properties over time in each cell to its neighbors.

Instead of counting individual cars, traffic is modeled as flow in a series of cells. Image: UC-Berkeley

Two more pieces of information are needed to solve the equations. First, the boundary conditions must be specified — that is, the values coming into the cells on the outside edges. In the case of traffic networks, that’s usually the cars coming into and going out of the road area of interest.

The second requirement is to provide initial conditions: How much fluid starts out in each cell and how fast it’s going. Once this information is provided, we can solve the equations in sequence and over time by integrating all of flow coming in and going out. The solutions give the fluid density and velocity at any given point in the network over time. Solving for fluid flow like this is known as computational fluid dynamics, and the same basic concept is used in many applications, for example, computing the flow of air over an airplane’s wing or water around a ship’s hull.

The fluid dynamics model of traffic flow works well with fixed sensors. Put sets of sensors at the beginning and end of a stretch of a road and these give the boundary conditions for that bit of road. Cameras and satellites can provide initial conditions, and the flow density and velocity along that road can be calculated. These methods have been around awhile and are pretty accurate within the limitations of the sensors.

This would be fine if the cars truly were a fluid, but driver actions lead to perturbations that cause slowdowns or accidents. These disruptions can’t be detected until their effects ripple down to a sensor, usually in the form of a traffic jam. Finer-grained spatial detail requires finer-grained placement of sensors — which is where the smartphones come in.

Using GPS measurements to augment sensors like traffic cams and loop detectors makes the entire system much more versatile. Unlike fixed sensors, the virtual trip lines can be moved and augmented as needed, perhaps to get more measurements on roads where the state of traffic is changing rapidly.

Although virtual sensors can be placed more densely than physical ones, their measurements are less complete. A physical sensor will count and measure the speed of every car passing it. Even complete GPS trajectories from vehicles being tracked provide data for a single car, which must then be related to the cars around it. Virtual trip lines only generate measurements from cars with phones running the Mobile Millennium software, and even then only in accordance to the privacy-protecting randomization scheme. This makes the data fusion problem like trying to calculate the flow of a river given the properties of a few drops of water.

This means the mobile phone measurements can’t simply be fed into the system as additional boundary conditions. To use the data from the phones, the researchers and graduate students on the project had to develop new methods of solving the flow equations.

The team ultimately developed many different algorithms for a variety of different models. The details are arcane and described in papers available on the Mobile Millennium website. Basically, the new methods allowed GPS measurements to be incorporated as special internal conditions for the flow to satisfy. Density and velocity aren’t computed directly from boundary and initial conditions. Instead, the flow is calculated as the result of an optimization that finds the flow values that best match the measured data.

With these algorithms in place, the models can synthesize data from point sources. Measurements from loop detectors and cameras can be combined with GPS data from phones and with GPS trajectories from other sources, like buses. The resulting estimates of traffic flow are much better than those available from static sensing alone.

Field experiments validated the technology behind Mobile Millennium and captured an accident in real time. Image: UC Berkeley.

Mobile Century

The initial design of the Mobile Millennium system culminated in a proof-of-concept test called Mobile Century on February 8, 2008. One hundred cars, each equipped with a Nokia smartphone running the GPS tracking software, were mixed in with traffic along a 10-mile stretch of Interstate 880 in the Bay Area. To get ground-truth data to compare against, the project team recorded data from fixed inductive loop detectors along the same stretch of road and posted students with video cameras on overpasses.

The test ran nearly 10 hours and required more than 150 student drivers; the results were a great success. Although Mobile Century cars accounted for no more than 2 to 5 percent of cars on the road at any given time, the system very accurately measured the speed and density of traffic, and at a much higher spatial resolution than the fixed system of loop detectors. The test also provided a startling demonstration of the potential of using mobile phones to gather data quickly.

Traffic estimates calculated with the test data were displayed in real-time at a control center and observed by researchers and various transportation officials. At 10:50 a.m. the team noticed its data displaying a serious slowdown in traffic, while data from Google Maps, which at the time drew data primarily from static loop detector sensors, showed things were all clear.

“We were getting nervous,” Professor Bayen said. “There were all these officials watching, and we thought maybe something had gone wrong.”

Everyone let out a sigh of relief when the Google display slowly caught up and beepers sounded as automated alerts went out to the visiting transportation officials. There had been a five-car pileup exactly where the Mobile Century system first reported the slowdown. It was clear validation of the project. The sudden slowdown had been detected and reported in less than a minute, well before its effects could propagate back through the chain of cars to a static detector upstream.

The phone-based measurements had dramatically out-performed the fixed sensor network.

Until All Are One

After the proof-of-concept demonstration, Mobile Millennium went live in November of 2008 as an operational test and has been running ever since. Though the software is no longer available for download, there are some 5,000 users with it driving around the San Francisco Bay Area.

The concepts and technology demonstrated in Mobile Millennium are now widespread. Google’s mobile Maps app also fuses mobile GPS data with static sensors and other sources. Many companies that provide traffic monitoring data do something similar, either using phones or other dedicated mobile sources. A large number of cities use similar means of combining static and mobile sensors to measure traffic patterns.

The future of mobile sensing isn’t limited to traffic monitoring. The CarTel project at Massachusetts Institute of Technology demonstrated the use of accelerometers mounted on a fleet of a local limo company to detect and map potholes. A machine-learning algorithm was taught to recognize the distinctive bump associated with driving over a pothole. Each time a pothole was detected it could be instantly reported and mapped.

Although this particular experiment used a custom sensor unit with accelerometers, it’s not difficult to imagine that a similar system could be designed to take advantage of the accelerometers built into smartphones. The pothole detection also was based on detecting extremes in the measured roughness of the road. With a larger base of reporting sensors, it would be possible to build a constantly updated map of road conditions everywhere in a city. Data from this could be used to warn drivers of unsafe conditions or inform maintenance planning.

In the coming years, mobile sensing is going to transform the driving experience. It’s only a matter of time before our cars are fully networked and the traffic flow becomes all but self-aware. Tighter integration of phones and data networks with cars will make still more data available. The CarTel project has suggested that shared engine sensor information, for example, will allow owners to see if their car is deviating from the norm, possibly indicating a maintenance problem.

It’s obvious that as these technologies proliferate, privacy is going to be even more of a concern and the data collection systems that are built will need robust privacy protections. One can only hope the companies building such systems are as wary of the potential dangers as they are hopeful about the rewards.

This story was written by Haomiao Huang and originally published by Ars Technica.

Main photo: silva613 / Flickr