Cell Phones That Listen and Learn

New software tracks a user's behavior by monitoring everyday sounds.

By Kristina Grifantini

MONDAY, JUNE 22, 2009

Researchers are increasingly using cell phones to better understand users' behavior and social interactions. The data collected from a phone's GPS chip or accelerometer, for example, can reveal trends that are relevant to modeling the spread of disease, determining personal health-care needs, improving time management, and even updating social-networks. The approach, known as reality mining, has also been suggested as a way to improve targeted advertising or make cell phones smarter: a device that knows its owner is in a meeting could automatically switch its ringer off, for example.

Credit: Technology Review

MULTIMEDIA   See SoundSense logging a user's activities.

Now a group at Dartmouth College, in Hanover, NH, has created software that uses the microphone on a cell phone to track and interpret a user's activity. The software, called SoundSense, picks up sounds and tries to classify them into certain categories. In contrast to similar software developed previously, SoundSense can recognize completely unfamiliar sounds, and it also runs entirely on the device. SoundSense automatically classifies sounds as "voice," "music," or "ambient noise." If a sound is repeated often enough or for long enough, SoundSense gives it a high "sound rank" and asks the user to confirm that it is significant and offers the option to label the sound.

The Dartmouth team focused on monitoring sound because every phone has a microphone and because accelerometers provide only limited information. "When we think about sounds, we don't typically think that they can also represent a location that has a unique signature," says Andrew Campbell, a professor of computer science at Dartmouth and a lead researcher on the project. The researchers made sure the program is small, so that it doesn't use too much power. To address privacy concerns, they designed SoundSense so that information is not removed from the device for processing. Additionally, the program itself doesn't store raw audio clips. A user can also tell the software to ignore any sounds deemed off limits.

In testing, the SoundSense software was able to correctly determine when the user was in a particular coffee shop, walking outside, brushing her teeth, cycling, and driving in the car. It also picked up the noise of an ATM machine and a fan in a particular room. The results of the experiments will be presented this week at the MobiSys 2009 conference, in Krakow, Poland.

"The SoundSense system is our first step in building a system that can learn [user behavior] on the go," says Tanzeem Choudhury, an assistant professor at Dartmouth who was also a leader on the project and a TR35 winner. Choudhury says that enabling the software to learn to recognize new sounds will be essential for practical applications. "A system that can recognize sounds in a person's life can be used to search for others who have the same preferences," she says. Using sounds to classify events can give users feedback on their daily activities for health or time-management applications, she adds.

The phones have ears: SoundSense listens to a user’s environment through a phone’s microphone and learns to connect certain sounds to activities.  Credit: Dartmouth College

Kurt Partridge, a researcher at Palo Alto Research Center, who has also created cell-phone software that tracks behavior, believes that the SoundSense project exploits an underused resource. "I don't think the field has really realized both how little power audio-based activity-sensing takes, and how informative it can be," Partridge says. "Audio can distinguish so many more activities [and] adds a social aspect to contextual sensing that's not possible otherwise."

Dan Ellis, an associate professor at Columbia University, who has researched the use of continuous audio recordings, says that this type of "life logging" could someday be used as routinely as the outbox in an e-mail application. "Maybe you don't look at your outbox very often, but given the right tools to quickly find what you're looking for, it's very convenient to keep a record of every e-mail you're ever sent," he says. "A near-continuous, audio-based record collected by a personal device could be similarly desirable."

Robots Take Center Stage in U.S. War in Afghanistan

Monday, March 23, 2009
By Matt Sanchez

 Boston Dynamics

A BigDog robot climbs a hill in a test of its versatility. The U.S. military is deploying the robots to Afghanistan to navigate the country's treacherous terrain.

• 
• 

The U.S. military is calling out the "BigDogs" in addition to its big guns as it deploys more troops to fight terrorists in Afghanistan.

The BigDogs — four-legged robots that can navigate the country's treacherous terrain — and pilotless helicopters than can transport tons of supplies to very remote bases are just two of the new weapons being tested in Afghanistan.

The war zone is increasingly becoming a development laboratory for machines that don't eat, sleep, polish their boots or suffer casualties. But can they succeed where man struggles?

It takes a moment for the senses even to comprehend BigDog, a four-legged robot that vaguely resembles a headless pack animal.

• Click here for photos.

The machine's creator, Boston Dynamics, has a motto — “dedicated to the way things move” — and that’s precisely what is both jarring and fascinating about its invention. Using a gasoline engine that emits an eerie lawnmower buzz, BigDog has animal-inspired articulated legs that absorb shock and recycle kinetic energy from one step to the next.

Its robot brain, a sophisticated computer, controls locomotion sensors that adapt rapidly to the environment. The entire control system regulates, steers and navigates ground contact. A laser gyroscope keeps BigDog on his metal paws — even when the robot slips, stumbles or is kicked over.

Boston Dynamics says BigDog can run as fast as 4 miles per hour, walk slowly, lie down and climb slopes up to 35 degrees. BigDog's heightened sense can also survey the surrounding terrain and become alert to potential danger.

All told, the BigDog bears an uncanny resemblance to a living organic animal and not what it really is: A metal exo-skeleton moved by a hydraulic actuation system designed to carry over 300 pounds of equipment over ice, sand and rocky mountainsides.

So much for the ground war. With IED attacks in Afghanistan increasing on land, air transportation has become a major focus for the military.

PHOTO ESSAYS

• BigDogs and Big Guns

Routine helicopter flights operating 24 hours a day, year round, are crucial for the American mission. The Marine Corps has recently called for unmanned cargo flights to carry essentials to isolated areas that can be reached only by air.

Enter the K-MAX, a remote-controlled helicopter designed to transport heavy loads — even in Afghanistan's high altitudes.

The K-MAX's unique rotor design — two intermeshed rotors turning in opposite directions and slightly angled to prevent the blades from colliding — give this unmanned aircraft a distinct advantage.

“All the energy goes into the lift and eliminates the need for the tail rotor,” said Frans Jurgens, spokesman for Lockheed Martin Systems Integration, which has partnered with Kaman Aerospace Corp. to manufacture the unmanned K-MAX aircraft.
.

The design enables the relatively small chopper to tow up to 6,000 pounds. “The K-MAX is basically an aerial truck,” Jurgens said.

A ground controller “pilots” the unmanned aircraft using a “digital tablet” — a portable device the size of a clipboard attached to a backpack. The controller has visual contact with the aircraft during takeoff and can see where the K-MAX is going through a camera attached to the unmanned helicopter.

Unlike other unmanned aerial vehicles (UAVs), the K-MAX currently requires some visual contact — ground controllers to launch and retrieve the aircraft.

During a flight, K-MAX's “autonomous flight brain” calculates the best route to its destination and can automatically re-route itself should an area be designated a “no-fly” zone.

After launch, control transfers to a second ground controller waiting at the point of capture. Once the K-MAX has been sighted, the destination controller discharges the cargo by remote command.

But some in the military remain skeptical that a robot and a distant operator can replace a skilled pilot.

“When you’re dealing with a small area and a very small margin of error, mountains, temperatures, and other factors like heavy unpredictable winds, it’s hard to believe unmanned flights could account for all the variables,” Chief Warrant Officer Timothy Smail, a pilot from Eagle Lift, the 7th battallion 101st Aviation Regiment, told FOXNews.com in a phone interview from Afghanistan.

“Everything those troops have we’re responsible for bringing,” Smail said. “Not saying it can’t be done, I would just be skeptical.”

After two tours in Iraq, Smail is serving a second tour in Afghanistan, which he says is the “most difficult place to pilot in the world.”

But, Jurgens is not concerned.

“The K-MAX will fly repetitive flights that can be predictably programmed,” he said. “Given the fact that traveling by ground convoy is not the preferred transportation, unmanned cargo flights can save pilots from routine unnecessary exposure.”

KMAX has never been deployed to a war zone, but the unmanned aircraft has been a robotic workhorse in the logging industry, where it transfers heavy loads at high altitudes. It has also been used to transport water to fight forest fires.

They'll never fully replace actual people, but robots and unmanned vehicles will spare soldiers from routine tasks and enable them to focus their experience and skills on missions that require the human touch.

UK team builds robot fish to detect pollution

1 of 2Full Size

LONDON (Reuters) - Robot fish developed by British scientists are to be released into the sea off north Spain to detect pollution.

If next year's trial of the first five robotic fish in the northern Spanish port of Gijon is successful, the team hopes they will be used in rivers, lakes and seas across the world.

The carp-shaped robots, costing 20,000 pounds ($29,000) apiece, mimic the movement of real fish and are equipped with chemical sensors to sniff out potentially hazardous pollutants, such as leaks from vessels or underwater pipelines.

They will transmit the information back to shore using Wi-Fi technology.

Unlike earlier robotic fish, which needed remote controls, they will be able to navigate independently without any human interaction.

Rory Doyle, senior research scientist at engineering company BMT Group, which developed the robot fish with researchers at Essex University, said there were good reasons for making a fish-shaped robot, rather than a conventional mini-submarine.

"In using robotic fish we are building on a design created by hundreds of millions of years' worth of evolution which is incredibly energy efficient," he said.

"This efficiency is something we need to ensure that our pollution detection sensors can navigate in the underwater environment for hours on end."

The robot fish will be 1.5 meters (nearly 5 feet) long -- roughly the size of a seal.

(Reporting by Ben Hirschler, editing by Tim Pearce)

Every Military Net Accessed at Once, Thanks to ‘OB1′

January 31st, 2009

Machines that are physically connected to the public internet are going to share physical connections with classified networks.

* grin *

What could possibly go wrong?

If the hacker owns the hypervisor, he/she owns all data traversing the hypervisor and is in a position to sample, redirect, or spoof anything. Without some form of fail-safe, guest operating systems would have no way of knowing they are running on a compromised platform. This “hyperjacking” scenario is particularly frightening if we consider large-scale virtualization platforms that offer 10, 50, even hundreds of hosted servers running on a single piece of hardware.

Have a nice day.

Via: Wired:

U.S. Central Command has 14 different, physically separated networks. To get access to the info on all of ‘em, a military type needs as many as five different computers, sitting on his desk. But new software being tested by CENTCOM would enable a single computer to connect to all those networks at once — from the open internet to the top secret stuff. “If it proves secure, could save more than $200 million for CENTCOM,” UPI’s Shaun Waterman reports. And a ton of hassle, too.

But the best part of the project might be its acronym. The demonstration is called “One Box, One Wire” — OB1, for short. Use the Force, sysadmins!

The key to OB1, retired U.S. Air Force Gen. Eugene Habiger tells Waterman, is the “separation kernel,” a piece of software “guaranteed to keep the different networks separate.”

The software… creates “what we call security domains … in essence virtual machines or virtual servers … each one of them is impregnable. Even viruses that operate at the very deepest level of the operating system cannot get around the new software,” he said.

“We sit literally on the bare metal … on the microprocessor. What we create is a secure platform, and on top of that platform you can run Windows or Linux … inside of a securely separated domain, where … your top-secret or confidential corporate data … can be protected and cannot be accessed by an intruder” from any one of the other domains.

But isn’t that a huge security risk? The NSA apparently has tested the system out, and given OB1 its blessing.

Pentagon Wants “Virtual Renditions” of Deployed Personnel to Interact with Their Children

anuary 8th, 2009

“My real daddy died in Iraq, but daddy_lite v3.7.2 lives in my cell phone now. The kind man from the Army also gave mommy a backup disk in case we need to re-install daddy on any of our computers or mobile devices. Mommy cries a lot, but daddy seems happy inside the screen.”

Via: Department of Defense Small Business Innovation Research:

Title: Virtual Dialogue Application for Families of Deployed Service Members

Research & Technical Areas: Biomedical, Human Systems

Objective: To develop a highly interactive PC or web-based application to allow family members to verbally interact with “virtual” renditions of deployed Service Members.

Description: The Defense Centers of Excellence for Psychological Health and Traumatic Brain Injury recognizes that family outreach and advocacy is pivotal for both the psychological health of the family and the resilience of the Service Member. Deployments put stress on the entire family, especially small children and communication is key. The ability to reach out and communicate with loved ones from areas of conflict is better than at any time in history. Nevertheless, the stresses of deployment might be softened if spouses and especially children could conduct simple conversations with their loved ones in immediate times of stress or prolonged absence. Historically, families have derived comfort and support from photographs or mementos, but current technology SHOULD allow for more personal interactive messages of support. Over 80% of American children between the ages of three and five regularly use computers, and 83% of families have a computer in their home.So, computer-based applications would resonate with children and capture their interest and imagination. The challenge is to design an application that would would allow a child to receive comfort from being able to have simple, virtual conversations with a parent who is not aivailable “in-person”. We are looking for innovative applications that explore and harness the power of “advanced” interactive multimedia computer technologies to produce compelling interactive dialogue between a Service member and their families via a pc- or web-based application using video footage or high-resolution 3-D rendering. The child should be able to have a simulated conversation with a parent about generic, everyday topics. For instance, a child may get a response from saying “I love you”, or “I miss you”, or “Good night mommy/daddy.” This is a technologically challenging application because it relies on the ability to have convincing voice-recognition, artificial intelligence, and the ability to easily and inexpensively develop a customized application tailored to a specific parent. We are seeking development of a tool which can be used to help families (especially, children) cope with deployments by providing a means to have simple verbal interactions with loved ones for re-assurance, support, affection, and generic discussion when phone and internet conversations are not possible. The application should incorporate an AI that allows for flexibility in language comprehension to give the illusion of a natural (but simple) interaction. The current solicitation is not aiming to build entertainment, but a highly accurate and advanced simulation platform. Voice-recognition and voice-interaction are required. The User Interface is a critical component for this program. Application must be user friendly and application must be easy to install and maintain. Verbal interactions should be as normal as current technology will allow. Proven track record for creating similar types of applications is desired, but not required. Development plans should include the use of trained psychological health and family advocacy experts with experience providing services to military populations. Project MUST include discussion of how personal information would be collected, recorded, and rendered as well as address issues about information content and complexity of proposed simulation application. If using a web-based application, security and maintenance issues must be addressed. Application must run on typical family-owned computer systems.

PHASE I: Work with DoD Subject Matter Experts to define exact needs and scope of the application. Provide for the development of a complete concept plan, concept design for the overall system and a simple working proof-of-concept demonstration. In this concept plan, address the following items with respect to the Phase II requirements: 1. Develop metrics to determine user acceptance, usability, and content requirements. 2. Describe, illustrate, and storyboard a complete scenario with the help of Subject Matter Experts. 3. Outline technology limitations and risks, including minimum system requirements. 4. Identify development tools for producing the simulation. 5. Devise an implementation and plan for a detailed usability study 6. Develop a basic proof-of-concept demonstration of technology

PHASE II: 1. Finalize application design based on Phase I results 2. Build, refine, and demonstrate the prototype system. 3. Perform user acceptance and usability study 4. Develop strategy for customizing simulation for military families.

Phase III: DUAL USE COMMERCIALIZATION: This technology would be useful for providing support for civilian families and could be easily expanded to provide highly-interactive training and “lessons-learned” from experts in the field.

Research Credit: ltcolonelnemo

Related posts:

1. Australia: ABC TV Advises CO2-Emitting Children to Die Early
2. Traumatized U.S. Soldiers Being Treated in ‘Virtual Iraq’
3. UK: ‘Supernannies’ to Tackle Antisocial Children
4. Anti-Psychotic Drug Use Soars in U.S. and U.K. Children
5. UK Police: Designate Children as Pre Criminals Based on DNA