A New Wave of Machine Learning: Carnival Adds Sophisticated Wearable to its Cruise Ship Fleet

Create: 01/24/2017 - 09:29

IoT heads to the high seas as Carnival creates a new smart wearable device, the Ocean Medallion, for passengers on its Regal Princess ship.

 At CES 2017, Carnival CEO Arnold Donald made a splash by announcing the Ocean Medallion, the company’s new machine learning device to be used on its cruise ships. Set to debut on the Carnival Regal Princess ship in November 2017, the 1.8 oz. smart wearable is a quarter-sized metal disc provided free to all passengers.

Inside each medallion are multiple communication technologies including Near Field Communication (NFC) and Bluetooth Low Energy (BLE). Passengers can carry the medallion in a pocket, pin it to a shirt, or wear it on their wrist or as a necklace. The medallion doesn’t require charging and does not have an on/off switch or a menu to navigate.

Medallion IoT sensor

Photo credit: Carnival/

Described by Carnival as “a device that facilitates guest vacation experiences to make cruising more personal and simple,” the Ocean Medallion will pair with the Ocean Compass™, which is Carnival’s proprietary digital portal. The Ocean Compass portal is available online, on smart devices, on kiosks in port terminals, on stateroom TVs, on interactive surfaces throughout the cruise ship and on devices carried by crew members. Ocean Compass also serves as a digital media platform that features custom experiential media content and offers passengers access to vacation photos and videos captured during the cruise.

Digital Identity and Location

Before a cruise begins, Carnival will preload the Ocean Medallion with a passenger's unique digital identity information and ship it out to them in advance of departure. It will be laser-etched with a passenger’s name, ship and sail date.

The medallion can communicate with the more than 4,000 sensors onboard the ship and in port. It serves multiple functions, including payments for purchases, keyless entry into the passenger’s cabin and speeding up embarkation. It will log passenger’s purchases and preferences and note what they choose to do while on board and which invitations they accept, allowing the Carnival crew to personalize future invitations and offers for its guests. The medallion also works as a personal tracking device and has wayfinding capabilities, so passengers can more easily locate friends and family on the cruise ship.

The Cruise Network

The medallion and Ocean Compass work with the network of sensors throughout the ship using what Carnival calls xIOS, Experience Innovation Operating System.

“The network supporting the Ocean Medallion had to be scalable and flexible enough to deliver an unprecedented level of guest personalization and be delivered in an accelerated timeframe,” said Michael Jungen, Senior Vice President of Guest Experience Design and Technology for Carnival Corporation, in a BusinessWire article.

Nytec built and installed the hardware for Carnival. The software for medallion was developed by The Experience Engine (TE2), a platform-as-a-service company in San Diego, CA. TE2 participated in key portions of the platform development with an emphasis on core identification, data orchestration, legacy systems integration and industrialization services. According to TE2 and Carnival, the new platform and medallion is expected to scale to 100 ships in 147 destinations.

Learn more about Ocean Medallion from Carnival. 

IoT News: Week of January 12-January 19, 2017

Create: 01/19/2017 - 20:43

This week’s top takeaways have IoT boarding Carnival Cruise ships, while some IT leaders continue to stay on the IoT sideline. A top 10 list of IoT companies to watch names familiar tech leaders and newbies. Plus, retail tracks inventory and logistics with a new platform from Intel and Honeywell.   

CIO Jury: 50% of IT Leaders will Invest in IoT in 2017

In a room of 12 IT leaders, the consensus is evenly split on IoT investment in the coming year. Some IT leaders see IoT as a clear differentiator, and others are still waiting for six to 12 months to see positive business outcomes and ROI before recommending investments.  Regardless of their business plans for IoT, offices are seeing IoT devices and wearables enter the workplace at a rapid pace.  

10 IoT Companies to Watch in 2017

Familiar companies are putting their brands and resources behind IoT and are intent on bringing IoT into businesses everywhere. Intel, GE, Google, Cisco, Davra and five others top the list of who to watch in 2017. Will the vanguards focus on change from within or acquisitions to maintain their leadership position in IoT?

Honeywell, Intel to Develop IoT Solutions for Retailers, Logistic Providers

Honeywell and Intel want to improve operations for retailers and logistic providers. The future offerings will utilize sensors, handheld computers, processors, bar code scanners, RFID tags and readers and cloud-based software. In the not too distant future, solutions providers will have more options to help their customer track, monitor and assess the condition of goods moving through the supply chain as well as in brick-and-mortar stores.

Five Digital Initiatives Supply Chain Must Follow in 2017

Software AG expects major changes in the supply chain and advises companies to embrace these five trends to achieve success. Companies across the supply chain will need to pay attention to demand sensing, build resiliency that prevents disruption, create a Micro-Logistics network, prepare for digital transformation and expect shrinkage.

Carnival Ocean Medallion: 5 Takeaways from One of 2017’s Premier IoT Projects

IoT’s ship may have come in now that Carnival Cruise Lines is adding the technology to vacation packages starting in late 2017. When IoT sets sail at Carnival, passengers will carry a quarter-sized Ocean Medallion that tracks purchases, activities, meals and more. With more than 11 million passengers each year, Carnival promises to be an excellent gateway for IoT.

Cruising through Campus: Driverless Smart Shuttles

Create: 01/19/2017 - 13:10

Students at Santa Clara University (SCU) this semester can pack away the skateboard and hop on a driverless shuttle that can cart them around campus. Auro Robotics in nearby Sunnyvale, CA, has chosen the university as the location for its three-month test of autonomous vehicles, and the shuttles are now charged up and rolling through SCU.

The size of a typical golf cart, the Auro driverless shuttle is operated by an onboard computer. Each shuttle is equipped with laser cameras that have a 360-degree view of the campus and can detect pedestrians within 200 meters to avoid hitting them. To catch a ride, students board the vehicle by waving their hands in front of it, which makes it come to a halt.

Auro Robotics began the project by using the Polaris GEM, an off-the-shelf, $30,000, four-person electric vehicle. Auro spent an additional $30,000 to outfit the GEM with cameras, light detection and ranging (LIDAR) technology, GPS sensors, and controls for brakes and steering. All technology is connected to deep-learning software.

SCU autonomous vehicles

Photo: Joanne H. Lee, Santa Clara University

Unlike other driverless car designs, the Auro shuttle is intended to move people not on public roads but rather on private paths and closed roadways. It follows a pre-programmed route on the SCU campus. The company says it takes approximately one week to create a new shuttle route, which includes a day to drive the loop to develop detailed 3-D maps, and a few days of computer simulation to work out bugs.

While routing on closed roadways on campus may seem easier than public roads, the environment has other obstacles—including the many squirrels that live in SCU’s tree-lined campus. Early in testing, Auro added a squirrel cam—a small lidar at the bottom of the front bumper, as an adaptation to help the shuttle avoid hitting darting rodents. The shuttle also has a large emergency stop button on the dash, which the company intends to move within reach of all passengers after testing.

Real-time Path Planning

The Auro electric shuttle travels at about 10 miles per hour and operates in all weather conditions. “When more people are comfortable with the idea of being driven autonomously, we can increase the speed,” said Nalin Gupta, Auro’s CEO, in an article in The Mercury News.

The campus shuttle seats up to four passengers. During the test phase, a safety engineer is on board and sits in the front of the cart. The engineer can take control and navigate obstacles if, for instance, the shuttle may have to find its way around a badly parked vehicle blocking one of its pre-programmed stops.

Over time, Auro says the on-board engineer will no longer be needed. “We are confident that our technology can do path planning in real time,” says Auro hardware engineer Ben Stinnett in an article in IEEE Times. “But we need to get the university to share that confidence.” Auro plans to transition to remote supervision, which will consist of an off-campus operator who gets an alarm if intervention is needed. That operator can then tele-operate the vehicle. Eventually, Auro predicts one remote operator will be the human backup for an entire fleet of shuttles.

In the near term, SCU officials are aiming to have five shuttles running 24x7 that students can summon with an iPhone application. The university says the shuttles will be of particular help to transport disabled students.

Future Applications

Looking beyond the campus, Auro Robotics wants to market this type of shuttle to retirement communities, resorts, airports, and large corporate campuses with building-to-building commutes.

Auro plans to offer its shuttle service for a subscription-based model of $5,000 to $7,000 a month, including insurance and vehicle charging, with a shuttle fleet that can operate 24x7. According to numbers collected by the San Francisco Chronicle, this is a bargain price: a bus driver’s salary, gas, and insurance total approximately $9,000 a month for 40 hours a week, and that doesn’t include the cost of the vehicle.

Watch a video of the Auro shuttle on campus at Santa Clara University, and see how object detection using 3D Lidar works. 

Transforming Fleet Transportation with Intel IoT Technologies

Create: 01/17/2017 - 15:44

Business outcomes ride on the performance of the fleet. Smart transportation solutions built on Intel IoT technologies enable businesses to increase fleet productivity using advanced sensing, interconnected big data, and intelligent features embedded in vehicles and the environment.

Download infographic

Airport Security: IoT Tech and Predictive Analytics Are Ready for Take Off

Create: 01/09/2017 - 12:00

Airports have continued to spend millions of dollars to implement smart security measures, including tighter security checkpoints, facial recognition software, full-body scanners, IoT-based access control systems, intrusion detection, alarms, video surveillance and increased security personnel.

Behavior recognition may soon contribute its part in airport security programs. For more than a decade, airports have made finding dangerous items their primary objective to protect passengers and crews.  Those techniques may be joined soon by a more thorough cross check, possible by analyzing passenger behavior picked up by surveillance cameras and stored in passenger and airport data.

Current security solutions evaluate at a ‘single point in time’ rather than a summation of a person’s entire behavior over an extended period of time. The theory behind behavior recognition is that when someone is in the process of carrying out a criminal or terrorist act, that person exhibits behavior that is out of the norm.  The behaviors can be split into two categories – micro behavior and macro behavior.

Airport security surveillance  

Photo credit: Intel Digital Security and Surveillance Solutions,

Facial expressions, perspiration, lack of eye contact are micro examples. Macro behavior is broader movement throughout the space, such as attempting to hide his or her face by turning away when someone approaches; trying to stay out of sight, behind obstructions or shadows to avoid being seen; or leaving an area when the person in question believes he or she has been detected.

 In the ideal scenario, airports would build a 360-degree view of each person. Data collected would be security screenings, behavior tracking, information from other sources such as bookings, travel history and so on. By applying predictive analytics and reviewing these large sets of structured and unstructured data, airport security would grade each person on their risk potential.

A 360-Degree View of Behavior

Tracking the full set of passenger data sets has been too expensive and difficult—until now. Recent analytics advancements make it possible to build a 360-degree view of passenger activities. Add in rich graphical interfaces, mapping tools, and geolocation information, and the security team has the resources and insight to understand which passengers in crowded airports are likely security threats.

Ironically, technology is often better than humans are at recognizing atypical human behavior. We’ve trusted security, staff, or another traveler to spot something out of the ordinary, but what is most difficult for staff is tracking all the acts that combine to denote terrorist behaviors. Each of these acts on its own may not raise suspicion. It’s only when the security team can see behavior end-to-end that they can get a complete view.

IoT technology such as smart cameras in the terminals and door locks for authorized airport personnel can offer a complete view, from parking lot to boarding to baggage handling to the runway. Once predictive analytics identify an individual as high risk, the security team can request a private interview to find out if they need to investigate further.

Insider Threats

While threats can come from outside sources such as terrorists, drug smugglers or passengers, they can also be instigated from within, planted by a disgruntled airport employee, vendor/tenant or contract worker. By using predictive analytics, security operations managers can monitor both access and behavior of internal employees and contractors, identifying dangerous insiders and halting an attack before it happens.

By gathering Big Data from IoT cameras, sensors and locks and using predictive analytics, the security ops team can automatically monitor and note suspicious behavior or irregular employee movements. For example, is an employee assigned to one area of a terminal using a card key trying to enter another terminal? Is a baggage handler at the airport entering a restricted area on their assigned day off?

Using predictive analytics, the security team can correlate data sets on employees from disparate sources and analyze blended threats. The team can use analytics to track: HR flags, such as an employee who has a history of performance issues; personal data such as criminal records; information system access including on-site VPN usage; and physical movement within the airport terminals from badge scans or IoT-based door locks and geo-spatial scanners.

Machine Learning platforms can process these large data sets and tie together and connect the dots across multiple behaviors and employee actions. Using in-memory computing, the security team has the speed capabilities—minutes vs. days—needed to use analytics and determine a real-time response that can prevent internal incidents from happening.

With a combination of IoT technology, behavior recognition and predictive analytics, airport security teams can continuously monitor the airport environment. If they can connect the dots across multiple actions, they can use the data and analyze risk in real-time, preventing malicious threats before they occur.

Learn more about gathering real-time analytics with the Intel IoT platform and SAP


Subscribe to Transportation