Categories
Tech News

The USPS’ dog attack rankings is the 2020 scorecard we never knew we needed

The United States Postal Office released a chart ranking individual cities and states in dog attacks for the year 2020. This is not the first time the USPS released such a chart – as such, they have numbers of dog attacks available for both the top 25 cities and the top 10 states. While it’s certainly not a ranking a state should be proud of, it’s interesting to see which states have the most (reported) dog attacks on postal workers this past year – and which states have had the most dog attacks reported since the ranking system began to be tabulated.

The reason this listing is made public by the USPS is to make citizens of the United States aware of the dangers of dog interaction with postal workers. A dog doesn’t need to be a BAD dog to have a violent encounter with a postal worker – they could be a GREAT dog defending their family from what they perceive as a threat.

As the USPS suggested in their dog promotion: Dog bites are entirely preventable, and “one bite is too many.” To avoid negative interactions, the USPS recommends that, when a letter carrier comes to deliver the mail, dogs should be inside the house or behind a fence, “away from the door or in another room,” and/or on a leash.

For the year 2020, the number 1 city for reported dog attacks on USPS employees was Houston, Texas. Houston had a total of 73 attacks in the year 2020. The next entry on the list was Chicago with 59 attacks, followed by Los Angeles with 54. Cleveland had 46, Denver had 44, Baltimore had 43.

Number 7 on the list for 2020 was Columbus, OH, with 37 attacks. San Antonio, TX had 36, San Diego, CA had 35, tied with Detroit for 10th place. The rest of the list was pretty close, with between 13 and 34 attacks in the year 2020.

The ranking went as follows: Louisville, St. Louis, Phoenix, Indianapolis, Cincinnati, Philadelphia, Las Vegas, Sacramento, Jacksonville, Minneapolis, Toledo, Miami, Long Beach, and Albuquerque. Next was Shawnee Mission (KS), Charlotte (NC), Dayton, Canton, New Orleans, Omaha, Fort Worth, Wichita, Memphis, Richmond, Flint, Tulsa, San Francisco, Rockford, Syracuse, Arlington, Jamaica (NY), Rochester (NY), Pittsburgh, Salt Lake City, and Seattle. The last 5 entries were tied for 25th place with 13 bites.

The top 10 dog bite states for the year 2020 started with California, with 782 attacks. Texas was second with 402 attacks in 2020, then Ohio with 369. The rest of the list went as follows: NY (295), PA (291), IL (290), MI (253), FL (198), NJ (179), and VA (169). About half the states on the top list had attack rates go down, somewhat, from 2019 to 2020. California went up – as did IL, MI, NJ, and VA.

ALSO NOTE: One of the most important tips the USPS has for families with kids, is the following. “Pet owners should remind their children not to take mail directly from a letter carrier as the dog may view the carrier as a threat.”

Repost: Original Source and Author Link

Categories
Computing

How the USPS uses Nvidia GPUs to Track Mail With A.I.

USPS

The United States Postal Service, or USPS, is relying on artificial intelligence-powered by Nvidia’s EGX systems to track more than 100 million pieces of mail a day that goes through its network. The world’s busiest postal service system is relying on GPU-accelerated A.I. systems to help solve the challenges of locating lost or missing packages and mail. Essentially, the USPS turned to A.I. to help it locate a “needle in a haystack.”

To solve that challenge, USPS engineers created an edge A.I. system of servers that can scan and locate mail. They created algorithms for the system that were trained on 13 Nvidia DGX systems located at USPS data centers. Nvidia’s DGX A100 systems, for reference, pack in five petaflops of compute power and cost just under $200,000. It is based on the same Ampere architecture found on Nvidia’s consumer GeForce RTX 3000 series GPUs.

The algorithms are then deployed and used on a network consisting of 195 distributed Apollo servers created by Hewlett Packard Enterprise, with each server equipped with four Nvidia V100 GPUs. The result is a system called the Edge Computing Infrastructure Program, or ECIP, which tracks items for the postal service.

Combined with optical character recognition, these systems can locate missing mail that goes through the USPS network. In the past, it would take days to track down packages, but A.I.-powered technologies is reducing the manhunt for lost packages down to just mere hours.

“It used to take eight or 10 people several days to track down items, now it takes one or two people a couple hours,” said Todd Schimmel, the manager who oversees USPS systems in an Nvidia blog post.

The use of graphics-accelerated computing was perfect for this A.I. task, as it would have taken a network of 800 CPUs more than two weeks to complete to do the same thing that four Nvidia V100 Tensor Core GPUs could accomplish in a span of 20 minutes on the HPE Apollo 6500 server.

Each of the Apollo edge servers process 20 terabytes of images daily from more than 1,000 mail processing machines, Nvidia stated. The USPS contract was awarded in September 2019, Schimmel said, and the hardware installation was completed by August 2020.

“The app that checks for mail items alone requires coordinating the work of more than a half dozen deep-learning models, each checking for specific features,” Nvidia stated. “And operators expect to enhance the app with more models enabling more features in the future.”

In addition to mail tracking, the USPS is working on different use cases for A.I. at the edge, ranging from enterprise analytics to finance and marketing. There are currently 30 applications planned for ECIP, and the postal service hopes to implement a few of its ideas this year. One such idea would have A.I. analyze if a package has the correct postage for its size, weight, and destination, and another ECIP app could decipher a damaged barcode, for example.

Editors’ Choice




Repost: Original Source and Author Link