Using AI to see through walls

MIT’s new AI can now see through walls. MIT has given a computer x-ray vision, but it didn’t need x-rays to do it. The system, known as RF-Pose, uses a neural network and radio signals to track people through an environment and generate wireframe models in real time. It doesn’t even need to have a direct line of sight to know how someone is walking, sitting, or waving their arms on the other side of a wall.


Using wireless signals, RF-Pose could serve as a healthcare system to monitor patients’ movements from the other side of a wall. Source: MIT CSAIL

The MIT researchers decided to collect examples of people walking with both wireless signal pings and cameras. The camera footage was processed to generate stick figures in place of the people, and the team matched that data up with the radio waves. That combined data is what researchers used to train the neural network. With a strong association between the stick figures and RF data, the system is able to create stick figures based on radio wave reflections. One idea is to use the system to monitor those who might be at risk of a fall—a sick or elderly person, say.

Here’s the video which might help in comprehending the topic more.

Sources: MitTechReview, Extremetech, Popular Science

The World’s fastest Supercomputer – Summit

The US is again the home to the world’s fastest supercomputer – the Summit. For five years, China had the world’s fastest supercomputer, the Sunway TaihuLight. But the United States retook the lead thanks to a machine, called Summit, built for the Oak Ridge National Laboratory in Tennessee.


Summit – The machine’s 4,608 servers and associated gear fill the space of two tennis courts and weigh more than a large commercial aircraft.


The Summit’s theoretical peak speed is 200 petaflops or 200,000 teraflops. To put that in human terms, approximately 6.3 billion people would all have to make a calculation at the same time, every second, for an entire year, to match what Summit can do in just one second. For certain scientific applications, Summit will also be capable of more than three billion-billion mixed precision calculations per second. Summit will provide unprecedented computing power for research in energy, advanced materials, and artificial intelligence (AI), among other domains. Summit will enable scientific discoveries that were previously impractical or impossible.

Summit is 60 percent faster than the previous supercomputing leader, the Sunway TaihuLight based in the Chinese city of Wuxi. However, China still has the world’s most supercomputers overall. And China, Japan, and Europe are developing machines that are even faster, which could mean the American lead is short-lived. As of now, Summit’s computing capacity is so powerful that it has the ability to compute 30 years’ worth of data saved on a desktop computer in just one hour. These capabilities mark a huge increase in computing efficiency that will revolutionize the future of American science.


(source: The New York Times, MitTechReview, Quartz, Wired,



AI to detect Wrist Fractures

Imagen’s OsteoDetect, an AI-based diagnostic tool that can quickly detect distal radius wrist fractures. Its machine learning algorithm studies 2D X-rays for the telltale signs of fractures and marks them for closer study. It’s not a replacement for doctors or clinicians, the FDA stressed — rather, it’s to improve their detection and get the right treatment that much sooner.

OsteoDetect uses AI software to analyze two-dimensional x-ray images for distal radius fracture. The software, intended as an adjunct to clinician judgment, marks the fracture location on posterior-anterior and medial-lateral x-ray images. The company submitted a retrospective study of 1,000 radiograph images that assessed the independent performance of the image analysis algorithm for detecting wrist fractures and the accuracy of the fracture localization of OsteoDetect against the performance of three board certified orthopedic hand surgeons. Imagen also submitted a retrospective study of 24 providers who reviewed 200 patient cases. Both studies demonstrated that the readers’ performance in detecting wrist fractures was improved using the software, including increased sensitivity, specificity, positive and negative predictive values, when aided by OsteoDetect, as compared with their unaided performance according to standard clinical practice.