Dubai’s Roads and Transport Authority (RTA) is implementing the seasonal network operation initiative for maritime transportation after completing its project to automate the system of tickets through the use of big data.

This includes all information related to maritime transportation services including the number of passengers, and revenue and occupancy rates achieved, which aims to enrich studies on service development and improve network efficiency.

Mohamed Abu Bakr Al Hashemi, Director of Maritime Transport Department at the Public Transport Agency at the Roads and Transport Authority, said: “The initiative to automate maritime transport tickets through the use of big data has given us more flexibility to prepare for the implementation of the seasonal network initiative for maritime transport.

“The methodology of studying this project included using the method of predictive analysis in analysing the data of the maritime transport network, where the impact of the changes and the flexibility of the network in the operating times and the frequency of trips on the number of passengers, occupancy rates, revenue and number of passengers of maritime transport were expected. With this project, we developed internal algorithms to analyse and process big data from multiple sources and develop a flexible operating plan for the maritime transport network that can also be used to analyse future data in this sector.

“We have developed a flexible seasonal network for maritime transport services that includes the summer and winter months, the holy month of Ramadan, holidays and events in the Emirate of Dubai, so that they are applied in each season separately.”

Al Hashemi expects that the flexible seasonal network initiative for maritime transport will reduce the number of unnecessary trips, reduce direct operational costs, and increase the percentage of sea transportation occupancy affiliated to the authority.

The post Dubai uses big data to develop marine transportation ticketing system appeared first on Artificial Intelligence.

The migration of the firm’s data to a cloud-based environment will enhance operational efficiencies through greater productivity and business agility, and enhanced service levels. This is part of IGM’s ongoing execution of a previously announced five-year transformation to modernize its digital platforms and technology infrastructure.

Adopting Google Cloud will also provide IGM with access to a wide range of capabilities, including advanced analytics, data mining and artificial intelligence (AI), enabling the firm to better harness its data for the benefit of all its stakeholders.

“We’re excited to be working with an industry leader such as Google Cloud and to leverage their extensive and expanding global expertise and best practices,” said Jeff Carney, President and CEO, IGM Financial Inc. “This collaboration will not only provide us with increased operational efficiencies but also with the ability to better anticipate, understand and respond to evolving needs through Google Cloud’s machine learning and AI solutions.”

Mr. Carney noted that enhanced AI capabilities will provide IG Wealth Management’s financial advisors with a broader set of insights in the development of IG Living Plans, the firm’s industry leading approach to financial planning which provides a single, comprehensive view of an individual’s finances.

“We look forward to working hand-in-hand with IGM throughout their digital transformation journey – from accelerating implementation times to quickly bringing new features to market,” said Jim Lambe, Managing Director, Canada, Google Cloud.

IGM’s collaboration with Google Cloud will also go beyond the standard customer-vendor relationship. This includes a variety of unique initiatives, such as extensive investments in training and development equipping IGM’s data science centre of excellence team with world-class skills and expertise. In addition, there will be the opportunity for current and future employees to work with cutting edge technologies, leveraging advanced GCP capabilities. Google Cloud will also host future IGM hackathons and both companies will work together to roll out a series of IGM recruitment events.

“IGM is one of the largest employers in Winnipeg and our presence in the city spans almost 100 years so we’re particularly proud to be partnering with Google Cloud to ensure our Winnipeg-based team has the opportunity to do their very best work using the latest technologies,” concluded Mr. Carney. 

The post IGM Financial signs for Google Cloud appeared first on Artificial Intelligence.

Shan–who founded China’s leading truckload service provider in 2015–shared her insights during the FullSTK and binate.io tracks, which examine how coding and data analysis are influencing modern businesses and society. During her keynote, Shan highlighted how technology had enabled the optimization of revenue and customer service in one of Asia’s fastest-growing industries.

Following the demand for freight transportation as a result of the eCommerce explosion in China, market share of the truckload services are worth over CNY 1.92 trillion. Truckload services currently represent almost two-thirds of China’s mammoth freight transportation market and this figure is predicted to reach CNY 2.42 trillion by 2020. Despite its rapid expansion, the industry is hugely fragmented with more than 20 million trucks on the road–70% of which are operated by individuals or small and medium-sized enterprises.

According to Shan, there are three pain points plaguing today’s industry a lack of standardized pricing, inefficient dispatching and unreliable service quality. To address these, ForU Trucking developed its world-leading online truck logistics platform, which uses intelligent pricing, intelligent service and intelligent dispatch to handle fuel efficiency and customer experience.

Historically, the freight transportation industry has suffered from variable pricing and frequent cost fluctuations as a result of seasonal changes in supply and demand. In traditional operating models, it requires an average of ten calls and one hour to obtain and negotiate a quotation in China. To streamline and optimize pricing, ForU Trucking’s platform uses an algorithm that harnesses information collected from big data (such as truck capacity, distance, historical pricing, seasonality and existing demand versus supply, etc.) to provide an accurate and standardized quotation in under two minutes.

In addition, traditional dispatch modes are often inefficient, amounting to high operational costs and low-profit margins. Powered by artificial intelligence, ForU Trucking’s intelligent dispatch system optimizes routes for drivers, increasing a truck’s monthly operating mileage from 6,520 km to over 11,000, and reduced the transportation cost per load by 20%. These savings have also directly benefited drivers with a 12.5% increase in monthly revenue.

Finally, the platform’s real-time system monitoring delivers consistent service standards for enhanced customer experience. Freight transportation is often subject to significant service issues, including traffic delays, a lack of transparent tracking and damaged goods due to unpredictable road conditions. ForU Trucking harnesses real-time location-based services, big data and GIS, and predictions calculated by AI to automatically detect and report any abnormalities that occur throughout the transportation process. These systems reduce the number of calls received by customer service teams and allow for greater operational efficiency, resulting in a tenfold increase in the number of orders processed per day per person.

The post ForU Trucking CEO Shares How Big Data And AI Have Revolutionized Freight Transportation appeared first on Artificial Intelligence.

Applying artificial intelligence to self-driving cars to smooth traffic, reduce fuel consumption, and improve air quality predictions may sound like the stuff of science fiction, but researchers at the Department of Energy’s Lawrence Berkeley National Laboratory (Berkeley Lab) have launched two research projects to do just that.

In collaboration with UC Berkeley, Berkeley Lab scientists are using deep reinforcement learning, a computational tool for training controllers, to make transportation more sustainable. One project uses deep reinforcement learning to train autonomous vehicles to drive in ways to simultaneously improve traffic flow and reduce energy consumption. A second uses deep learning algorithms to analyze satellite images combined with traffic information from cell phones and data already being collected by environmental sensors to improve air quality predictions.

“Thirty per cent of energy use in the U.S. is to transport people and goods, and this energy consumption contributes to air pollution, including approximately half of all nitrogen oxide emissions, a precursor to particular matter and ozone – and black carbon (soot) emissions,” said Tom Kirchstetter, director of Berkeley Lab’s Energy Analysis and Environmental Impacts Division, an adjunct professor at UC Berkeley, and a member of the research team.

“Applying machine learning technologies to transportation and the environment is a new frontier that could pay significant dividends – for energy as well as for human health.”

Traffic smoothing with Flow

The traffic-smoothing project, dubbed CIRCLES, or Congestion Impact Reduction via CAV-in-the-loop Lagrangian Energy Smoothing, is led by Berkeley Lab researcher Alexandre Bayen, who is also is a professor of electrical engineering and computer science at UC Berkeley and director of UC Berkeley’s Institute of Transportation Studies. CIRCLES is based on a software framework called Flow, developed by Bayen’s team of students and post-doctoral researchers.

Flow is a first-of-its-kind software framework allowing researchers to discover and benchmark schemes for optimizing traffic. Using a state-of-the-art open-source micro simulator, Flow can simulate hundreds of thousands of vehicles – some driven by humans, others autonomous – driving in custom traffic scenarios.

“The potential for cities is enormous,” said Bayen. “Experiments have shown that the energy savings with just a small percentage of vehicles on the road being autonomous can be huge. And we can improve it even further with our algorithms.”

Flow was launched in 2017 and released to the public in September, and the benchmarks are being released this month. With funding from the Laboratory Directed Research and Development program, Bayen and his team will use Flow to design, test, and deploy the first connected and autonomous vehicle (CAV)-enabled system to actively reduce stop-and-go phantom traffic jams on freeways.

How reinforcement learning can reduce congestion

Some of the current research into using autonomous vehicles to smooth traffic was inspired by a simple experiment done by Japanese researchers 10 years ago in which about 20 human drivers were instructed to drive in a ring at 20 mph. At first everyone is proceeding smoothly, but within 30 seconds, the traffic waves start and cars come to a standstill.

“You have stop-and-go oscillation within less than a minute,” Bayen said. “This experiment led to hundreds if not thousands of research papers to try to explain what is happening.”

A team of researchers led by Dan Work of Vanderbilt University repeated the same experiment last year but made one change: they added a single autonomous vehicle in the ring. As soon as the automation is turned on, the oscillations are immediately smoothed out.

Why? “The automation essentially understands to not accelerate and catch up with the previous person – which would amplify the instability – but rather to behave as a flow pacifier, essentially smoothing down by restraining traffic so that it doesn’t amplify the instability,” Bayen said.

Deep reinforcement learning has been used to train computers to play chess and to teach a robot how to run an obstacle course. It trains by “taking observations of the system, and then iteratively trying out a bunch of actions, seeing if they’re good or bad, and then picking out which actions it should prioritize,” said Eugene Vinitsky, a graduate student working with Bayen and one of Flow’s developers.

In the case of traffic, Flow trains vehicles to check what the cars directly in front of and behind them are doing. “It tries out different things – it can accelerate, decelerate, or change lanes, for example,” Vinitsky explained. “You give it a reward signal, like, was traffic stopped or flowing smoothly, and it tries to correlate what it was doing to the state of the traffic.”

With the CIRCLES project, Bayen and his team plan to first run simulations to confirm that significant energy savings result from using the algorithms in autonomous vehicles. Next they will run a field test of the algorithm with human drivers responding to real-time commands.

DeepAir

The pollution project, named DeepAir (Deep Learning and Satellite Imaginary to Estimate Air Quality Impact at Scale), is led by Berkeley Lab researcher Marta Gonzalez, who is also a professor in UC Berkeley’s City & Regional Planning Department. In past research, she has used cell phone data to study how people move around cities and to recommend electric vehicle charging schemes to save energy and costs.

For this project, she will take advantage of the power of deep learning algorithms to analyze satellite images combined with traffic information from cell phones and data already being collected by environmental monitoring stations.

“The novelty here is that while the environmental models, which show the interaction of pollutants with weather – such as wind speed, pressure, precipitation, and temperature – have been developed for years, there’s a missing piece,” Gonzalez said. “In order to be reliable, those models need to have good inventories of what’s entering the environment, such as emissions from vehicles and power plants.

“We bring novel data sources such as mobile phones, integrated with satellite images. In order to process and interpret all this information, we use machine learning models applied to computer vision. The integration of information technologies to better understand complex natural system interactions at large scale is the innovative piece of DeepAir.”

The researchers anticipate that the resulting analysis will allow them to gain insights into the sources and distribution of pollutants, and ultimately allow for the design of more efficient and more timely interventions. For example, the Bay Area has “Spare the Air” days, in which traffic restrictions are voluntary, and other cities have schemes to restrict traffic or industry.

While the idea of using algorithms to control cars and traffic may sound incredible at the moment, Bayen believes technology is headed in that direction. “I do believe that within 10 years the things we’re coming up with here, like flow smoothing, will be standard practice, because there will be more automated vehicles on the road,” he said.

Lawrence Berkeley National Laboratory addresses the world’s most urgent scientific challenges by advancing sustainable energy, protecting human health, creating new materials, and revealing the origin and fate of the universe. Founded in 1931, Berkeley Lab’s scientific expertise has been recognized with 13 Nobel Prizes. The University of California manages Berkeley Lab for the U.S. Department of Energy’s Office of Science. For more, visit www.lbl.gov.

DOE’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States, and is working to address some of the most pressing challenges of our time.

The post Machine Learning to Help Optimize Traffic and Reduce Pollution appeared first on Artificial Intelligence.

Forbes Insights research shows that 65% of senior transportation-focused executives believe logistics, supply chain and transportation processes are in the midst of a renaissance—an era of profound transformation. But of the most visible forces of change, perhaps none carries more potential for innovation and even disruption than the evolution of artificial intelligence (AI), machine learning (ML) and related technologies.

Leading companies are already harnessing artificial intelligence and machine learning to inform and fine-tune core strategies, such as warehouse locations, as well as to enhance real-time decision making related to issues like availability, costs, inventories, carriers, vehicles and personnel. While these new technologies bring about truckloads of data, the transportation industry has been capturing data for years. Decades ago, trucking, rail and sea cargo began being tracked by satellite via telematics, and versions of electronic driver logs have been around for nearly 20 years. The industry has also for many years now applied high-level decision theory to optimize the costs and transit times associated with high-value vehicles and often even higher-value cargoes.

The difference today, however, is not only more data but also vastly more powerful computing power and algorithms to sort, evaluate and accelerate understanding and action. According to John Langley, a clinical professor of supply chain management and the director of development for the Center for Supply Chain Research at Penn State’s Smeal College of Business, though the transport industry has always been data-focused, today “we see all of this added computing power—IoT/telematic data collection, data mining, artificial intelligence and machine learning—that can be focused on making better decisions, not only from an overall strategic and resource planning basis but in real-time decisions.”

Practical Applications

AI, ML and associated technologies promise to enable leaders to focus IoT and myriad other data feeds on achieving greater optimization and responsiveness across the whole of their logistics, supply chain and transportation footprint. Consider examples such as:

• Augmented real-time decision making: Logistics teams often handle a wide range of complex but repeatable tasks that require large amounts of input data in order to make the best choices. Optimal carrier selection, for example, means combing through thousands of possible candidates, routes and schedules. In practice, workers often require 10 minutes or more to gather the needed information. But with AI and associated tools, supply chain professionals can automate the analysis and narrow their selections to just two or three within a matter of seconds. Human intuition then closes the deal.
• Predictive analysis: When will customers be ready to order? Of course the sales team wants to know, but this is also vital information for logistics, supply chain and transportation planning—an example where an AI platform could collaborate closely with sales and marketing. Looking specifically at transportation needs, telematics/IoT can help determine when a vehicle might need preventative maintenance, thus avoiding breakdowns and reducing the risk of failing to meet customer needs and expectations.
• Strategic optimization: Where, when and how? Leaders in these disciplines are learning how to gather and comb information to make the best decisions regarding the deployment of not only inventories but also the transportation assets needed to connect all the dots from origin to customer location. Where are the drivers? Where are the vehicles? What commitments have been made? Where are the customers?
  These and related variables can be fed to AI and machine learning engines that can crunch the data and then present a range of scenarios for optimization. With sophisticated tools that continuously learn and improve, industry professionals are able to make better, up-to-the-minute decisions as well as more informed longer-term, strategic choices, such as warehouse locations, fleet size/specifications, etc.

A Call To Action

But these and related examples are merely the tip of the iceberg. No doubt as AI and machine learning become more widely used, practitioners will find an ever-expanding array of use cases—some evolutionary and others potentially disruptive.

Small wonder that a growing body of evidence suggests that the technology-infused future of transportation will arrive faster than many are expecting. Consider a recruiting ad for supply chain and logistics roles for global retailer Target, which telegraphs the company’s expanding focus on tools such as artificial intelligence. As stated in the ad: “We’re becoming more intelligent, automated and algorithmic in our decision-making. We’re constantly reimagining how we get the right product to our guests even better, faster and more cost effectively than before.”

Target’s ad is yet another piece of evidence suggesting that leading logistics-, supply chain- and transportation-focused executives are waking up to new opportunities. The Forbes Insights survey shows that expected benefits from advanced technologies include enhanced productivity, better speed/response times and the ability to see end-to-end across the value chain. Additional benefits include improved accuracy in deliveries, higher quality at lower cost and the ability to better anticipate customer needs.

Overall, as one CEO interviewed for the report explained, “we’re putting a lot of [investment] into artificial intelligence and machine learning to augment the human role.” Certainly, as the Forbes Insights research shows, it is time for all transportation- and supply chain-focused executives to consider following suit.

The post How Artificial Intelligence And Machine Learning Are Revolutionizing Logistics, Supply Chain And Transportation appeared first on Artificial Intelligence.