Accurate demand forecasting of different public transport modes(e.g., buses and light rails) is essential for public service operation.However, the development level of various modes often varies sig-nificantly, which makes it hard to predict the demand of the modeswith insufficient knowledge and sparse station distribution (i.e.,station-sparse mode). Intuitively, different public transit modes mayexhibit shared demand patterns temporally and spatially in a city.As such, we propose to enhance the demand prediction of station-sparse modes with the data from station-intensive mode and designaMemory-Augmented Multi-taskRecurrent Network (MATURE)to derive the transferable demand patterns from each mode andboost the prediction of station-sparse modes through adaptingthe relevant patterns from the station-intensive mode. Specifically,MATUREcomprises three components: 1) a memory-augmentedrecurrent network for strengthening the ability to capture the long-short term information and storing temporal knowledge of eachtransit mode; 2) a knowledge adaption module to adapt the rele-vant knowledge from a station-intensive source to station-sparsesources; 3) a multi-task learning framework to incorporate all theinformation and forecast the demand of multiple modes jointly.The experimental results on a real-world dataset covering four pub-lic transport modes demonstrate that our model can promote thedemand forecasting performance for the station-sparse modes.
On the street outside Joseph Baca's home in El Paso, Texas, there is a traffic light that always seems to be red. Whether the intersection is clear, the traffic waits. He knows that, like most traffic lights in El Paso, this one has a camera. Why, he often said to his family, couldn't the camera be used to monitor the road and control the signal? That question eventually led to the development of an idea that could save not only time but also, potentially, lives.
QUT researcher Dr Aaron Mcfadyen has mapped air traffic around airports. Airservices and Queensland University of Technology (QUT) have inked a partnership to develop an automated and near real-time flight approval system to speed up how quickly drones can operate in the air, particularly during emergencies and pandemics. The technology will be used to replace the current manual process that typically requires drone operators to fill out paper-based forms to be considered for approval to operate their drones. This process can often take weeks and lack consistency due to the manual assessments that are undertaken. However, by introducing an automated approval system, which will involve developing risk maps to understand where it's safe to allow drones to operate, drone operators will be able to receive approvals much faster.
Dubai's Roads and Transport Authority (RTA) is exploring the use of artificial intelligence (AI) to plot more efficient bus routes based on how they are used throughout the day. Machine learning (ML) algorithms could eventually inform updates to 150 routes used by 2,158 buses across Dubai, the RTA said. The authority trialled the system on ten public bus routes over thirty days, using Nol Card (Dubai's public transport smart card) data to understand patterns such as which bus stops were busy all day, which were primarily used during peak hours and those that were rarely used. The one-month trial cut wasted time on bus routes by 13.3 percent, the RTA reports. Ahmed Mahboub, Executive Director of Smart Services, Corporate Technology Support Services Sector, RTA, commented: "By using machine learning algorithms in analysing the captured data, departments can build up systems and take decisions with reference to abolishing certain stops, or proposing an express service that skips those stops, while ensuring customer needs are always addressed. Such a process will contribute to improving this vital service."
A bus waits at a stop in Dubai. Dubai's Roads and Transport Authority (RTA) has started experimenting the use of artificial intelligence (AI) technologies (machine learning algorithms) in plotting bus routes in Dubai, based on the extent of usage throughout the day. The step is part of RTA's endeavours to apply technology in saving the time and effort of all parties and improving the experience of public transport riders. "The use of artificial intelligence technology, such as machine learning algorithms, in planning the routes of public buses aims to revamp the planning of 150 routes used by 2,158 buses all over Dubai. During a trial period, RTA experimented the use of technology on 10 routes where nol card data was employed to figure out all-day busy bus stops, stops used during peak hours, and rarely used stops," said Ahmed Mahboub, Executive Director of Smart Services, Corporate Technology Support Services Sector, RTA.
Drone technology continues to advance, as more research and development is targeted toward traffic control systems for the small, flying devices. The Nevada Institute for Autonomous Systems (NIAS) was recently awarded the bulk of a roughly $1.8 million earmark by the Federal Aviation Administration (FAA) to study and test virtual unmanned traffic management technology, known as UTM. The effort is a partnership among NIAS, an FAA-designated drone test site; Switch, maker of data-center technology; and ANRA Technologies, which produces drones. Switch and ANRA will lead demonstrations and testing of unmanned flight systems, while NIAS will explore some of the system and requirements to operate drone fleets safely. Advances in drone traffic control could not be more timely, say makers of the devices, as companies explore using drones for any number of on-demand deliveries -- from groceries to chicken wings.
SYDNEY, AUSTRALA - Artificial intelligence that automatically detects threatening behavior at train stations is part of a new trial to improve safety for women traveling at night in Australia. The New South Wales state government says nine out of 10 Australian women have experienced harassment on the street. It asked researchers to submit ideas to improve safety as part of its Safety After Dark Innovation Challenge. Four entries have been chosen and will be tested over the next six months. One group from the University of Wollongong will develop artificial intelligence (A.I.) software that will examine real-time feeds from security cameras and alert an operator when it detects suspicious activity or an unsafe environment.
Getting an Amazon package delivered from the sky is closer to becoming a reality. The Federal Aviation Administration said Monday it had granted Amazon approval to deliver packages by drones. Amazon said that the approval is an "important step," but added that it is still testing and flying the drones. It did not say when it expected drones to make deliveries to shoppers. "This certification is an important step forward for Prime Air and indicates the FAA's confidence in Amazon's operating and safety procedures for an autonomous drone delivery service that will one day deliver packages to our customers around the world," said David Carbon, vice president of Prime Air.
The US Federal Aviation Administration (FAA) over the weekend gave Amazon the green light to begin testing customer drone deliveries in the US. With an FAA Part 135 certification in hand, Amazon's drones will be able to fly out of an operator's line of sight. Earning the certification is a key milestone for Amazon's years-long effort to launch commercial drone deliveries. Amazon's ultimate goal is to deploy drones to make deliveries in 30 minutes or less. "This certification is an important step forward for Prime Air and indicates the FAA's confidence in Amazon's operating and safety procedures for an autonomous drone delivery service that will one day deliver packages to our customers around the world," David Carbon, VP of Prime Air, said in a statement.
Amazon has just gotten the thumbs up from the Federal Aviation Administration (FAA) to start using its Prime Air drone fleet for customer deliveries. On Saturday, the FAA granted Amazon Part 135 Certification, which means the company has the go-ahead to use drones to "safely and efficiently deliver packages to customers," according to a statement from the FAA. That doesn't mean drones are going to start delivering packages immediately, per Amazon. Instead, it indicates that the FAA has reviewed all of Amazon's safety procedures, and the company has passed muster. The certification gives Amazon the ability to begin testing and scaling a system which would use drones to deliver lightweight packages in 30 minutes or less from order.