Researchers use facial quirks to unmask ‘deepfakes’
Facial tics might be the key to distinguishing real videos of people from deepfakes, researchers say.... Read More...
AI
Your brain activity can be used to measure how well you understand a concept
A new deep learning algorithm is able to detect how well a STEM student understands a concept based on their brain activity.... Read More...
Spotting objects amid clutter
Researchers have developed a new algorithm that enables robots to identify objects hidden in 3D data. The new system may help with improving robotic vehicles and autonomous robots. ... Read More...
Fibromyalgia linked to variations in microbiome composition
Using a range of clinical techniques, including deep learning, researcher identify changes in the microbiome of people with fibromyalgia which were not associated with diet, medications or aging. Additionally, the severity of symptoms was directly correlated with an increased presence, or more pronounced absence, of certain bacterias.... Read More...
First-ever successful mind-controlled robotic arm without brain implants
Using EEG and brain computer interface technology, researchers have created a robotic arm that can be controlled without brain implants.... Read More...
‘Alexa, monitor my heart’: Researchers develop first contactless cardiac arrest AI system for smart speakers
A new skill artificial intelligence app for smart speakers like Google Home and Amazon Echo can detect the gasping sounds of agonal breathing and call for help. The AI can detect breathing events with 97% accuracy from up to 20 meters away. ... Read More...
From one brain scan, more information for medical artificial intelligence
A convolutional neural network, designed by researchers at MIT, uses MRI datasets to find anatomical structures of the brain. The system could help in diagnosing and treating a range of brain conditions.... Read More...
3D model shows how ‘face identity information’ is stored in the brain
The 'Generative Model of 3D Face Identity' is able to reconstruct facial models using information stored in a person's brain when recalling the familiar face of another person.... Read More...
The whisper of schizophrenia: Machine learning finds ‘sound’ words predict psychosis
A new deep learning algorithm can predict those at risk of psychosis with 93% accuracy by examining the latent semantic content of an individual's speech.... Read More...
AI used to detect brain’s response to multiple sclerosis treatment
Combining artificial intelligence technology with MRI brain scans, researchers are able to detect the brain's response to Natalizumab treatment for those with relapsing-remitting multiple sclerosis.... Read More...
Brain activation provides individual-level prediction of bipolar disorder risk
Combining neuroimaging data with machine learning, researchers have identified patterns of brain activation during reward anticipation, associated with an increased risk of developing bipolar disorder. The patterns of neural activation predict the severity of mania symptoms in young adults who have not yet developed the disorder.... Read More...
Research moves closer to brain-machine interface autonomy
Findings allow for the development of an autonomously updating brain-machine interface, which is able to improve on its own by learning about its subject without additional programming. The system could help develop new robotic prosthetics, which can perform more naturally.... Read More...