However, suppose these classifiers were constructed from a small number of samples (e.g., tens of participants) from a single site. In such a case, it would not be possible to generalize to data obtained from other imaging sites. No one…
Tag: ROBOTRY/ARTIFICIAL INTELLIGENCE
Image-based navigation could help spacecraft safely land on the moon
Research demonstrates how a series of lunar images could provide key navigational data
This flexible and rechargeable battery is 10 times more powerful than state of the art
A team of researchers has developed a flexible, rechargeable silver oxide-zinc battery with a five to 10 times greater areal energy density than state of the art. The battery also is easier to manufacture; while most flexible batteries need to…
No strings attached: maximizing wireless charging efficiency with multiple transmitters
New control strategy dynamically changes transmitter currents for optimal wireless charging in moving devices, such as robots and electric cars
Gestational age linked to ADHD in children with Down syndrome
A new study by the UC Davis MIND Institute finds a connection between gestational age and attention deficit/hyperactivity disorder (ADHD) symptoms in children with Down syndrome. The research, published in Scientific Reports , focused on children born at 35 weeks…
Artificial intelligence collaboration seeking to hasten COVID-19 insights
WEST LAFAYETTE, Ind. – During the COVID-19 pandemic, health care professionals and researchers have been confined mostly to using local and national datasets to study the impact of comorbidities, pre-existing medication use, demographics and various interventions on disease course. Now,…
Robot fleet dives for climate answers in ‘marine snow’
Australian research voyage to investigate how life in the Southern Ocean captures and stores carbon from the atmosphere
Human Brain Project-supported innovation published in Science
One step closer to a brain prosthesis for the blind
Restoring a rudimentary form of vision in the blind
Using a brain implant to make the blind see again
Army computer models unveil secret to quieter small drones
ABERDEEN PROVING GROUND, Md. — It’s no secret the U.S. Army wants its small unmanned aerial systems to operate quietly in densely-populated regions, but tests to achieve this can be expensive, time-consuming and labor-intensive according to researchers. Miranda Costenoble, a…
Oddly satisfying metamaterials store energy in their skin
When you press the dimpled circles on a fountain drink lid, they become either convex or concave. Materials or structures that have two stable states demonstrate a concept called bistability.
Living with autonomous systems “we can trust”
New report calls for greater input from society on future direction of autonomy
Self-repairing gelatin-based film could be a smart move for electronics
Dropping a cell phone can sometimes cause superficial cracks to appear. But other times, the device can stop working altogether because fractures develop in the material that stores data. Now, researchers reporting in ACS Applied Polymer Materials have made an…
IOPP expands OA journal portfolio with launch of Neuromorphic Computing and Engineering
IOP Publishing (IOPP) has launched a new, multidisciplinary, open access (OA) journal devoted to the design, development and application of artificial neural networks and brain-inspired systems towards advancing scientific discovery and realising emerging new computing technologies. The scope and characteristics…
Future advantage: Cruser funds FY21 robotics and autonomous systems research
Key to the nation’s future advantage in autonomous systems, the Naval Postgraduate School’s (NPS) Consortium of Robotics and Unmanned Systems Education and Research (CRUSER) approved FY21 funding for novel research in robotics and autonomous systems through its Seed Research Program.…
AI abdominal fat measure predicts heart attack and stroke
OAK BROOK, Ill. – Automated deep learning analysis of abdominal CT images produces a more precise measurement of body composition and predicts major cardiovascular events, such as heart attack and stroke, better than overall weight or body mass index (BMI),…
Automatic deep-learning AI tool measures volume of cerebral ventricles on MRIs in children
CHARLOTTESVILLE, VA (DECEMBER 1, 2020). Researchers from multiple institutions in North America have developed a fully automated, deep-learning (DL), artificial-intelligence clinical tool that can measure the volume of cerebral ventricles on magnetic resonance images (MRIs) in children within about 25…
Predicting Breast Cancer Recurrences
A new tool combining traditional pathology with machine learning could predict which breast cancer patients actually need surgery. The technology, reported in the November issue of American Journal of Physiology — Cell Physiology (vol. 319: C910-C921; https:/ / doi. org/…
Shrinking massive neural networks used to model language
A new approach could lower computing costs and increase accessibility to state-of-the-art natural language processing
Tackling ethics concerns regarding use of ‘carebots’ to assist older adults
A new analysis from North Carolina State University highlights the realistic pros and cons of apps and other technologies that use artificial intelligence (AI) to benefit older adults, including those facing dementia and cognitive decline. The work focuses on how…
The (un)social network: The emergence of digital thought clones and what to do about them
Digital thought clones that prey on and manipulate real-time online behavior can be tackled with tough legislation, say experts
Learning at your own pace with AI
SMU Office of Research & Tech Transfer – When Singapore emerged from a two-month long COVID-19-imposed Circuit Breaker (CB), AI Singapore, a national Artificial Intelligence (AI) programme set up by the National Research Foundation (NRF) to anchor deep national capabilities…
AI-based ‘OxyGAN’ is a robust, effective method to measure tissue oxygen levels
New AI-based algorithm processes tissue oxygenation data faster and more accurately than conventional techniques
How automated vehicles can impede driver performance, and what to do about it
University of Toronto Engineering study reveals some in-vehicle displays, such as takeover displays, leads to driver overreliance.
When consumers trust AI recommendations–or resist them
Researchers from Boston University and University of Virginia published a new paper in the Journal of Marketing that examines how consumers respond to AI recommenders when focused on the functional and practical aspects of a product (its utilitarian value) versus the experiential and sensory aspects of a product (its hedonic value).
1 in 3 who are aware of deepfakes say they have inadvertently shared them on social media
A Nanyang Technological University, Singapore (NTU Singapore) study has found that some Singaporeans have reported that, despite being aware of the existence of ‘deepfakes’ in general, they believe they have circulated deepfake content on social media which they later found out was a hoax.
1 in 3 who are aware of deepfakes say they have inadvertently shared them on social media
Author says results highlight need to educate citizens to deal with deepfakes
More skin-like, electronic skin that can feel
What if we didn’t have skin? We would have no sense of touch, no detection of coldness or pain, leaving us inept to respond to any situation. The skin is not just a protective shell for organs, but rather a…
Brain waves guide us in spotlighting surprises
If you open your office door one morning and there is a new package waiting on your desk, that’s what you will notice most in the otherwise unchanged room. A new study by MIT and Boston University neuroscientists finds that…
Which speaker are you listening to? Hearing aid of the future uses brainwaves to find out
In a noisy room with many speakers, hearing aids can suppress background noise, but they have difficulties isolating one voice – that of the person you’re talking to at a party, for instance. KU Leuven researchers have now addressed that…
NIST AI system discovers new material
CAMEO algorithm identifies new compound potentially useful for photonic devices and biologically inspired computers
Eye exam could lead to early Parkinson’s disease diagnosis
OAK BROOK, Ill. – A simple eye exam combined with powerful artificial intelligence (AI) machine learning technology could provide early detection of Parkinson’s disease, according to research being presented at the annual meeting of the Radiological Society of North America…
Misinformation or artifact: a new way to think about machine learning
A researcher considers when – and if – we should consider artificial intelligence a failure
Coaching sales agents? Use AI and human coaches
News from the Journal of Marketing
A new kind of artificial intelligence provides breakthrough in breast cancer diagnosis
State-of-the-art technology which helps doctors more accurately diagnose breast cancer has been hailed as a breakthrough by the US Food & Drugs Administration (FDA) for its exceptional potential clinical value in improving patient care. The 4D Q-plasia OncoReader Breast uses…
Field geology at Mars’ equator points to ancient megaflood
ITHACA, N.Y. – Floods of unimaginable magnitude once washed through Gale Crater on Mars’ equator around 4 billion years ago – a finding that hints at the possibility that life may have existed there, according to data collected by NASA’s…
Arturo Azcorra, recipient of the Reginald Fessenden Award
The director of the IMDEA Networks Institute has been recognised for his contribution to the development of 5G technology
Zebra finches amazing at unmasking the bird behind the song
The spirited songbirds can rapidly memorize the signature sounds of at least 50 different members of their flock
Higher efficiency and longer lifetime for the next generation OLED
Shorter period of development realized by materials informatics
A neural network learns when it should not be trusted
A faster way to estimate uncertainty in AI-assisted decision-making could lead to safer outcomes.
Army, MIT explore materials for transforming robots made of robots
ABERDEEN PROVING GROUND, Md. — Scientists from the U.S. Army and MIT’s Center for Bits and Atoms created a new way to link materials with unique mechanical properties, opening up the possibility of future military robots made of robots. The…
Showing robots how to drive a car…in just a few easy lessons
USC researchers have developed a method that could allow robots to learn new tasks, like setting a table or driving a car, from observing a small number of demonstrations.
New test reveals AI still lacks common sense
Despite advances in natural language processing, AI still doesn’t have the common sense to understand human language, finds a new USC study.
Artificial intelligence-based tool may help diagnose opioid addiction earlier
Researchers have used machine learning, a type of artificial intelligence, to develop a prediction model for the early diagnosis of opioid use disorder. The advance is described in Pharmacology Research & Perspectives . The model was generated from information in…
Curved origami provides new range of stiffness-to-flexibility in robots
Tempe, AZ, Nov. 18, 2020 – New research that employs curved origami structures has dramatic implications in the development of robotics going forward, providing tunable flexibility – the ability to adjust stiffness based on function – that historically has been…
Magnetic spray: Giving inanimate objects new bionergy
Millirobots that can adapt to unstructured environments, operate in confined spaces, and interact with a diverse range of objects would be desirable for exploration and biomedical applications. However, the development of millirobots has faced difficulty due to their complicated fabrication…
Novel magnetic spray transforms objects into millirobots for biomedical applications
An easy way to make millirobots by coating objects with a glue-like magnetic spray was developed in a joint research led by a scientist from City University of Hong Kong (CityU) . Driven by the magnetic field, the coated objects…
Fostering creativity in researchers: how automation can revolutionize materials research
At the heart of many past scientific breakthroughs lies the discovery of novel materials. However, the cycle of synthesizing, testing, and optimizing new materials routinely takes scientists long hours of hard work. Because of this, lots of potentially useful materials…
Machine learning uncovers missing info about ethnicity in population health data: Study
University of Alberta epidemiologist says these key social determinants of health are often not tracked adequately in Canada
Deep learning helps robots grasp and move objects with ease
Combining neural networks with motion planning software gives robots the speed and skill to assist in warehouse environments