US Safety Board: More Tech Investment Needed to Prevent Aviation Accidents

The US National Transportation Safety Board logo
The US National Transportation Safety Board logo
TT

US Safety Board: More Tech Investment Needed to Prevent Aviation Accidents

The US National Transportation Safety Board logo
The US National Transportation Safety Board logo

The US needs to invest more in aviation safety technology solutions after a series of close-call runway incidents this year, the head of the US National Transportation Safety Board said on Tuesday.

The NTSB is investigating six runway incursion events since January including some that could have been catastrophic.

Technology systems that help detect aircraft and ground vehicles at airports to prevent runway incursion are currently used at 43 US airports. That technology needs to be upgraded and all other commercial airports also need additional technology, Jennifer Homendy, chair of the NTSB, told reporters.

She was speaking after a five-hour meeting with industry, union, government and academic representatives on ways to address runway incursions.

"We have to make sure all these upgrades to safety can be funded," Homendy said, adding that proper pilot and air traffic control staffing was also important.

The US has about 500 commercial airports.

The US runway incursion rate steadily increased from late 2022 and into 2023, peaking in March at 33 per 1 million takeoffs and landings. That rate fell to 19 in April.

According to Reuters, Transportation Secretary Pete Buttigieg said the rate was coming closer to normal levels and vowed continued vigilance.

The US has not had a major fatal US passenger airline crash since February 2009.

In March, the FAA said it was taking steps to improve air traffic control, convening a safety summit and issuing a safety alert. In April, it named an independent safety review team and on Monday, it announced an investment of $100 million in 12 airports for improvements to taxiways and lighting to reduce runway incursions.

Homendy said a FedEx cargo plane and a Southwest Airlines Boeing 737 that came within about 115 feet (35 meters) of each other in Austin on Feb. 4 in poor visibility conditions could have been a "terrible tragedy."

She disclosed Tuesday that the FedEx plane's first officer saw a single light from the Southwest 737 and then a silhouette of the plane before they aborted their planned landing.

"The first officer said, 'Hey this is what I see' and then says 'I think we should perform a go around,'" Homendy told reporters. "This crew did a great job."

Near-miss incidents have also occurred in Boston, Florida and include a near collision at New York's JFK airport between a Delta Air Lines plane and an American Airlines Boeing 777.



SDAIA, KAUST Launch MiniGPT-Med Model to Help Doctors Diagnose Medical Radiology through AI

SDAIA, KAUST Launch MiniGPT-Med Model to Help Doctors Diagnose Medical Radiology through AI
TT

SDAIA, KAUST Launch MiniGPT-Med Model to Help Doctors Diagnose Medical Radiology through AI

SDAIA, KAUST Launch MiniGPT-Med Model to Help Doctors Diagnose Medical Radiology through AI

The Center of Excellence for Data Science and Artificial Intelligence at the Saudi Data and Artificial Intelligence Authority (SDAIA) and King Abdullah University of Science and Technology (KAUST) have introduced the MiniGPT-Med model.

The large multi-modal language model is designed to help doctors quickly and accurately diagnose medical radiology using artificial intelligence techniques.

Dr. Ahmed Alsinan, the Artificial Intelligence Advisor at the National Center for Artificial Intelligence and head of the scientific team at SDAIA, explained that the MiniGPT-Med model is capable of performing various tasks such as generating medical reports, answering medical visual questions, describing diseases, locating diseases, identifying diseases, and documenting medical descriptions based on entered medical images.

The model was trained on different medical images, including X-rays, CT scans, and MRIs.

The MiniGPT-Med model, derived from large-scale language models, is specifically tailored for medical applications and demonstrates significant versatility across different imaging methods, including X-rays, CT scans, and MRI. This enhances its utility in medical diagnosis.

Dr. Alsinan highlighted that the MiniGPT-Med model was developed collaboratively by artificial intelligence specialists from SDAIA and KAUST.

The model exhibits advanced performance in generating medical reports, achieving 19% higher efficiency than previous models. It serves as a general interface for radiology diagnosis, enhancing diagnostic efficiency across various medical imaging applications.