MIT researchers have demonstrated an approach for identifying and quantifying the ways that a specific algorithm is biased, and actually showing how changing the data collection methods can reduce the bias while still preserving predictive accuracy.
Can artificial intelligence be a useful tool to help young victims tell their stories? What if AI could support forensic interviewers with tools to help gather information in an appropriate manner? This is paper documents what is believed to be the first attempt to develop and apply custom software to automatically detect and categorize speech patterns in the course of forensic interviews.
MIT Media Lab researchers have developed a wireless system that leverages the cheap RFID tags already on hundreds of billions of products to sense potential food contamination -- with no hardware modifications needed. With the simple, scalable system, the researchers hope to bring food-safety detection to the general public.
Photo-based information services that use image recognition can identify a user's location and other private information, such as personal interests and tendencies. Osaka University researchers developed an encryption-free framework called EnfPire to preserve users' privacy. EnfPire transforms a visual feature extracted from a photo so that it cannot be uniquely identified. The photo-based information service's server returns a set of candidates, which the user compares with the original image to determine the final recognition result.
Virginia Tech researchers found a way to give high-performance computing data systems the flexibility to thrive with a first-of-its-kind framework called BespoKV, perhaps helping to one day achieve the HPC goal of performing at the exascale, or a billion billion calculations per second.
NIMS and the Toyota Technological Institute at Chicago have jointly developed a Computer-Aided Material Design (CAMaD) system capable of extracting information related to fabrication processes and material structures and properties--factors vital to material design--and organizing and visualizing the relationship between them. The use of this system enables information from thousands of scientific and technical articles to be summarized in a single chart, rationalizing and expediting material design.
University of Cordoba researchers are able to improve prediction systems by reducing the quantity of information
Researchers at the University of Waterloo have taken a huge step towards making smart devices that do not use batteries or require charging.
By creating a machine-learning algorithm that predicts how human and mouse cells respond to CRISPR-induced breaks in DNA, a team of researchers discovered that cells often repair broken genes in ways that are precise and predictable, sometimes even returning mutated genes back to their healthy version. In addition, the researchers put this predictive power to the test and successfully corrected mutations in cells taken from patients with one of two rare genetic disorders.
Researchers from MIT and Massachusetts General Hospital (MGH) have developed a predictive model that could guide clinicians in deciding when to give potentially life-saving drugs to patients being treated for sepsis in the emergency room.