Neural networks generate synthetic fingerprints
Fingerprint authentication systems are a widely trusted, ubiquitous form of biometric authentication, deployed on billions of smartphones and other devices worldwide. Yet a new study reveals a surprising level of vulnerability in these systems. Using a neural network trained to synthesize human fingerprints, the research team evolved a fake fingerprint that could potentially fool a touch-based authentication system for up to one in five people.
Portable cancer test uses smartphone, new gold biosensor
A research team is creating a new cancer-spotting tool that health care providers could eventually use in areas that lack hospitals, clinics and other treatment centers. The tool is based upon a unique gold biosensor the research team created. When paired with a computer or smartphone and other inexpensive tools, the system is capable of spotting cancer biomarkers from a blood sample.
Using personal data to predict blood pressure
Engineers used wearable off-the-shelf technology and machine learning to predict, for the first time, an individual's blood pressure and provide personalized recommendations to lower it based on this data.
Model helps robots navigate more like humans do
When moving through a crowd to reach some end goal, humans can usually navigate the space safely without thinking too much. They can learn from the behavior of others and note any obstacles to avoid. Robots, on the other hand, struggle with such navigational concepts.
Implantable, biofuel-powered sensor that runs on sugar
Researchers have developed an implantable, biofuel-powered sensor that runs on sugar and can monitor a body's biological signals to detect, prevent and diagnose diseases.
Personalized soft exosuit breaks new ground
Fully wearable soft exosuit with automatic tuning helps users save energy and walk outside over difficult terrain.
Large Opportunity for 48VMH Medium and Large Trucks?
Like the car equivalents, 48V mild hybrid trucks do not start as electric vehicles (driving the wheels electrically some or all of the time) but they are headed that way.
If military robot falls, it can get itself up
Scientists at the U.S. Army Research Laboratory and the Johns Hopkins University Applied Physics Laboratory have developed software to ensure that if a robot falls, it can get itself back up, meaning future military robots will be less reliant on their Soldier handlers.
Ultra sensitive skin for robots
A smart skin that will give robots more sensitive tactile feeling than humans. The smart skin technology allows the robots to sense temperature changes and surface variations, which would allow a person alongside the robot to be safer or react accordingly.
A kernel of promise in popcorn-powered robots
Researchers have discovered how to power simple robots with a novel substance that, when heated, can expand more than 10 times in size, change its viscosity by a factor of 10 and transition from regular to highly irregular granules with surprising force.
Strengthening US manufacturing using advanced robotics
The project focuses on advanced robotics manufacturing and will develop an operator-guided, semi-automatic assembly process using industrial robots integrated with multiple sensors.
Tracking cancer-cell development with "drinkable" electronic sensors
Thanks to an unorthodox approach being proposed by researchers, patients may soon be able to track their illness simply by drinking a solution containing millions of tiny electronic sensors disguised as bacteria.
Sharing the workplace with robots?
A research team is helping robot developers design machines less likely to injure the humans they work with. How? With their novel 'safety map'.
WL Gore: Gore Patch Project
Gore Patch Project is an initiative from WL Gore to work with start-ups that can potentially use ePTFE in wearables, and especially skin patches.
Tiny injectable sensor for long term alcohol monitoring
Engineers have developed a miniature, ultra-low power injectable biosensor that could be used for continuous, long-term alcohol monitoring. The chip is small enough to be implanted in the body just beneath the surface of the skin and is powered wirelessly by a wearable device, such as a smartwatch or patch.
Novel method for energy-efficient deep neural networks
A method to improve the energy efficiency of scientific artificial intelligence is showing early promise in efforts to parse insights from volumes of cancer data.
Programming drones to fly in the face of uncertainty
Companies have big ideas for drones that can deliver packages right to your door. But even putting aside the policy issues, programming drones to fly through cluttered spaces like cities is difficult. Being able to avoid obstacles while traveling at high speeds is computationally complex, especially for small drones that are limited in how much they can carry onboard for real-time processing.
Auto-tuning data science: New research streamlines machine learning
A new automated machine-learning system performs as well or better than its human counterparts — and works 100 times faster.