Communications of the ACM
Spotting High-Risk Behavior Online
Using machine learning to identify signs of dangerous behavior on social media.
From ACM NewsAn edited collection of advanced computing news from Communications of the ACM, ACM TechNews, other ACM resources, and news sites around the Web.
From ACM TechNews
Making Data-Informed Covid-19 Testing Plans
Massachusetts Institute of Technology (MIT) researchers have developed a Web-based Covid-19 testing impact calculator.
From ACM TechNews
A Neural Network Learns When It Should Not Be Trusted
Researchers have enabled a neural network to rapidly process data, yielding both predictions and confidence levels based on the quality of the available data.
From ACM TechNews
AI Model Detects Asymptomatic Covid-19 Infections Through Cellphone-Recorded Coughs
A new artificial intelligence model between asymptomatic people infected with Covid-19 and healthy individuals via forced-cough recordings.
From ACM TechNews
Toward an ML Model That Can Reason About Everyday Actions
Researchers trained a hybrid language-vision machine learning model to recognize abstract concepts in video.
From ACM TechNews
Robot Takes Contact-Free Measurements of Patients' Vital Signs
Researchers are using dog-like robots from Boston Dynamics to remotely measure patients' vital signs.
From ACM TechNews
Algorithm Quickly Simulates Roll of Loaded Dice
Researchers have created an algorithm to produce random numbers with the best mix of speed, accuracy, and low memory currently available.
From ACM TechNews
Sensors Woven Into a Shirt Can Monitor Vital Signs
Researchers have developed a method of incorporating electronic sensors into stretchy fabrics to create clothes that monitor vital signs.
From ACM TechNews
System Trains Driverless Cars in Simulation Before They Hit the Road
Massachusetts Institute of Technology researchers have created a simulation system to train driverless cars prior to their deployment on actual streets.
From ACM TechNews
Protecting Sensitive Metadata So It Can't be Used for Surveillance
MIT researchers have developed a scalable metadata-protection scheme to shield the information of millions of users.
From ACM TechNews
Automated System Can Rewrite Outdated Sentences in Wikipedia Articles
A new system can automatically update factual inconsistencies in Wikipedia articles.
From ACM TechNews
Using AI to Enrich Digital Maps
A new artificial intelligence model uses satellite imagery to tag road features in digital maps.
From ACM TechNews
How Well Can Computers Connect Symptoms to Diseases?
A new study found that health knowledge graphs perform poorly for diseases with high percentages of very old or young patients, or high percentages of male or female...
From ACM TechNews
Helping Autonomous Vehicles See Around Corners
Massachusetts Institute of Technology engineers have created a system that perceives tiny fluctuations in ground shadows to ascertain whether an unseen object is...
From ACM TechNews
System Helps Smart Devices Find Their Position
A new system helps networks of smart devices find their positions in environments where GPS usually fails.
From ACM TechNews
Algorithm Tells Robots Where Nearby Humans are Headed
A new algorithm accurately aligns partial trajectories in real time, allowing motion predictors in self-driving cars to accurately anticipate the timing of a person's...
From ACM TechNews
This Robot Helps You Lift Objects--By Looking at Your Biceps
A new robotic system uses machines to help people lift objects by monitoring their muscle movements, producing a smoother robot-human collaboration.
From ACM TechNews
Bringing Human-Like Reasoning to Driverless Car Navigation
A new system could enable autonomous vehicles to navigate complex environments by checking a basic global positioning system-like map and employing video feeds....
From ACM TechNews
New Approach Could Accelerate Efforts to Catalog Vast Numbers of Cells
A new technique can derive fully comprehensive samples, or "sketches," of vast cellular datasets, to simplify analysis.
From ACM TechNews
Improving Security as AI Moves to Smartphones
Researchers suggest the vulnerability of compressed, or quantized, artificial intelligence models to adversarial attack could be remedied by adding a mathematical...
From ACM News