air transportation


Black box problem stunting ML adoption in default risk analysis

#artificialintelligence

Difficulties in explaining machine learning (ML) models is causing concern as banks look to the technology for default risk analysis, according to market participants. "Many different types of'black-box' models have been developed out there even by banks claiming that they can accurately predict mortgage defaults. This is only partially true," said Panos Skliamis, chief executive officer at SPIN Analytics in an email. "[These models] usually target a relatively short-term horizon and their validation windows of testing remain actually in an environment too similar to that of the development samples. However, mortgage loans are almost always long-term and their lives extend to multiple economic cycles, while the entire world changes over time and several features of ML models severely influenced by these changes of the environment," he said.


Facial recognition scanners are already at some US airports. Here's what to know

USATODAY - Tech Top Stories

Many airports hope to start using biometric scanners in lieu of passports to identify travelers. Buzz60's Tony Spitz has the details. The next time you go to the airport you might notice something different as part of the security process: A machine scanning your face to verify your identity. U.S. Customs and Border Protection (CBP) has been working with airlines to implement biometric face scanners in domestic airports to better streamline security. But how does the process work?


The Amazing Ways Dubai Airport Uses Artificial Intelligence

#artificialintelligence

As one of the world's busiest airports, (ranked No. 3 in 2018 according to Airports Council International's world traffic report), Dubai International Airport is also a leader in using artificial intelligence (AI). In fact, the United Arab Emirates (UAE) leads the Arab world with its adoption of artificial intelligence in other sectors and areas of life and has a government that prioritizes artificial intelligence including an AI strategy and Ministry of Artificial Intelligence with a mandate to invest in technologies and AI tools. The Emirates Ministry of the Interior said that by 2020, immigration officers would no longer be needed in the UAE. They will be replaced by artificial intelligence. The plan is to have people just walk through an AI-powered security system to be scanned without taking off shoes or belts or emptying pockets.


AI startup Gather uses drones and computer vision for warehouse inventory

#artificialintelligence

Gather, a company that uses autonomous drones for warehouse inventory, launched out of stealth today. Founded in 2017, the company of about 10 employees is based in Pittsburgh. Gather's founding team is made up of Robotics Institute at Carnegie Mellon University graduates, including cofounder and chief robotics officer Sankalp Arora, whose work with the Office of Naval Research on autonomous helicopters won the 2018 Howard Hughes Award. Earlier this year, Gather closed a $2.5 million funding round to bring its products to market and grow its computer vision and software offerings. Gather supplies software for the autonomous operation of drones that can connect with existing warehouse management systems and IoT devices such as motion sensors.



UNH robot ship is part of latest search for aviation pioneer Amelia Earhart

#artificialintelligence

A robotic ship from the University of New Hampshire's Marine School that can map the ocean floor is part of the latest effort to find out what happened to famed pilot Amelia Earhart, who disappeared over the Pacific Ocean eight decades ago. The autonomous vessel, known as BEN, the Bathymetric Explorer and Navigator, will be mapping the seafloor near the island where Earhart sent her last radio transmission. The area is too deep for divers and too shallow for safe navigation by deep-water sonar systems. Maps produced by BEN will be used to target later dives by remotely operated vehicles, searching for remnants of Earhart's plane. The work is part of the mission led by oceanographer Robert Ballard, best known for finding the wreck of the Titanic, to look into the disappearance of Earhart in 1937.


Pittsburgh airport uses artificial intelligence to help inform travellers – Business Traveller

#artificialintelligence

It may not help you get through the airport faster, but artificial intelligence (AI) can now give you information on wait times at Pittsburgh International Airport security checkpoints in real time. The airport recently announced a partnership with Zensors, a Pittsburgh-based company that applies AI to feeds from airport security cameras to estimate wait times at the airport's three Transportation Security Administration (TSA) checkpoints on a minute-by-minute basis. Wait-time information is then posted on the airport's information screens and website, including predictions about whether wait times will increase or decrease. Zensors' AI observes passenger volume and also includes factors like time of day and TSA staffing levels to make its estimates. "We know security can be a frustration for travellers and having accurate wait estimates can help set expectations and aid in planning trips," said Pittsburgh International Airport CEO Christina Cassotis.


Artificial intelligence could help air travelers save a bundle

#artificialintelligence

Researchers are using artificial intelligence to help airlines price ancillary services such as checked bags and seat reservations in a way that is beneficial to customers' budget and privacy, as well as to the airline industry's bottom line. When airlines began unbundling the costs of flights and ancillary services in 2008, many customers saw it as a tactic to quote a low base fare and then add extras to boost profits, the researchers said. In a new study, the researchers use unbundling to meet customer needs while also maximizing airline revenue with intelligent, individualized pricing models offered in real time as a customer shops. The results of the study will be presented at the 2019 Conference on Knowledge Discovery and Data Mining on Aug. 6 in Anchorage, Alaska. Airlines operate on very slim margins, the researchers said.


Is this the future of air travel? BA reveals robotic air stewards and self-packing luggage

Daily Mail - Science & tech

They may look like sketches from a sci-fi film - but these futuristic images are in fact a glimpse of what air travel could look like in the coming decades. The series of photographs, which feature in a British Airways exhibition at London's Saatchi Gallery, are inspired by a study undertaken by BA into the future of flyingcould look like in the coming decades. One image includes a robotic air stewardess, who's able to interpret every passengers' needs through emotional analysis and cater to this by bringing each person what they need before they've even asked. The AI, known as AVII, would produce a log for the cabin crew based on individual personal requirements, enabling them to build a stronger relationship with each traveller and deliver intuitive service. The Curio, a hypersonic aircraft – meaning it exceeds the speed of sound – which circumnavigates the world, collecting travellers from'megacities' as it flies on a non-stop mission Another set of images reveals potential plans for Curio, a hypersonic aircraft – meaning it exceeds the speed of sound – which circumnavigates the world, collecting travellers from ''megacities' as it flies.


Not always a black box: Machine learning approaches for model explainability

#artificialintelligence

Topic: Not always a black box: Machine learning approaches for model explainability Schedule: 6:00pm - 6:30pm - ODSC Intro, Pizza & Refreshments 6:30pm - 7:20pm - Talk 7:20pm - 7:30pm - Q&A 7:30pm - 8:00pm - Networking Bio: Violeta has been working as a data scientist at ABN AMRO bank for the past 2 years. Before that she worked as a data science consultant at Accenture, the Netherlands for about 1,5 years. Before working in the industry, Violeta was working in academia. She completed a Ph.D. degree from Erasmus University in the field of applied econometrics. Abstract: Most data scientists will agree that in most cases, a more complex model will result in a more accurate model.