dartmouth
Latest
AI could study your brain to help teachers improve their courses
Teachers don't always know how well their methods work. They can ask questions and hand out tests, of course, but it's not always clear who's at fault if the message doesn't get through. AI might do the trick before long, though. Dartmouth College researchers have produced a machine learning algorithm that measures activity across your brain to determine how well you understand a given concept.
3D modeling helps gym climbers replicate real mountain routes
You can create a seemingly endless array of things with commercial 3D printers, but they won't be very durable. Dartmouth researchers developed a novel method combining multiple fabrication techniques to make robust, custom-made artifacts. The challenge they set themselves to test their new method? Simulating real-world rock walls by recreating every handhold using their process.
Researchers use an app to predict GPA based on smartphone use
What a person does on their phone call tell you a lot about them -- including their GPA. Researchers from Dartmouth College and the University of Texas at Austin have developed an app that tracks smartphone activity to compute a grade point average that's within 0.17 of a point. The software is called smartGPA and using it alongside "periodic self reports" keeps tabs on how hard a student is studying and partying -- on top of physical activity, sleep, attendance and social interactions. Members of the research team were also responsible for the StudentLife app that kept up with mental health and its effect on grades, and this goes a step further by taking into account a broader picture of daily life. "We show that there are a number of important behavioral factors automatically inferred from smartphones that significantly correlate with term and cumulative GPA," the study explains. Installing the app, which is built with cloud and machine learning algorithms, monitored a group of undergrads 24 hours a day for 10 weeks.
Dartmouth's StudentLife app can tell you if your mental health is hurting your grades
Not sure if you're depressed? Your smartphone may be able to clue you in. Researchers at Dartmouth have developed an Android app that keeps tabs on student behavior -- silently logging how long they sleep, the number of conversations they have, how much time they spend in class, at social events or at the gym and even stress levels and eating habits. Using well-known mental health surveys as a benchmark, researchers were able to use the data to determine if students in its test group were depressed, stressed out or lonely, and eventually found correlations between mental health and academic performance.
Researchers use bioimpedance as a biometric, let health monitor devices know who you are
Wouldn't it be great if fitness and medical gadgets automatically knew who was wearing them? Researchers from Dartmouth have come up with a new way to provide health monitors just such an ability using a tiny electric current and a bioimpedance sensor. You see, each person's body provides a different amount of opposition to electrical current, so bioimpedance can be a unique biometric identifier. The researchers' idea is to create a bracelet that uses bioimpedance readings to recognize its wearer in a secure, unobtrusive manner and communicate that identity to other wearable devices. Using such a bracelet, "the devices discover each other's presence, recognize that they are on the same body (and transitively learn from the wrist device whose body), develop shared secrets from which to derive encryption keys, and establish reliable and secure communications." As opposed to other biometrics or password authentication, bioimpedance readings can be taken passively, which is much more appealing than remembering passcodes or scanning fingerprints and retinas. For now, the researchers have created an eight-electrode proof-of-concept bracelet, but its accuracy leaves something to be desired -- it correctly identifies its wearer only 80 to 90 percent of the time, whereas fingerprint recognition has a failure rate of less than 1 in 1,000. So, we're a ways off from bioimpedance-based security, but research is ongoing, and you can learn all about it at the source below.
Nokia toys with context-aware smartphone settings switch, Jigsaw provides better context for apps like this
If Intel prognosticated correctly, context is the future of apps -- your device's array of sensors will determine where you are and what you're doing, and clever programs will guess from there. Problems arise, however, when one tries to run those accelerometers, microphones, radio antennas and GPS tracking devices constantly on the battery life of an average smartphone and determine what the raw data means, and that's where a group of Dartmouth researchers (and one Nokia scholar) are trying to stake their claim. They've got a bundle of algorithms called Jigsaw for iPhone and Symbian that claims to be able to continually report what you're up to (whether walking, running, cycling or driving) no matter where you place your device, and only pings the sensors as needed based on how active you are. (For better or for worse, Jigsaw also dodges the privacy concerns Intel's cloud-based API might raise by storing all personal data on the phone.) Of course, we've had a very basic version of context-aware functionality for years in apps like Locale for Android and GPS-Action for Symbian -- which modifies your smartphone settings under very specific conditions you specify. Now, Espoo's doing much the same with an app called Nokia Situations. Presently in the experimental stage, Situations is a long ways away from the potential of frameworks like Jigsaw, but here you won't have to wait -- you can download a beta for Symbian^3, S60 5th Edition and S60 3.2 at our source links without further delay.
