Monday, November 25, 2019

Everything Thankful

Sometimes being thankful isn't easy, but you know you will be a better person for it. This year has had its challenges for me and my family. We lost our youngest daughter to a fentanyl-laced sleeping pill that a friend gave her and we lost our loving dog, Maggie Mae. Still, God is good to us by introducing a new grandson to our world. We welcomed Jackson Thomas Sinur to our family. Yet there are so many things to be thankful for these days. Just let me highlight a few that are meaningful to me.

The Special Years We Had with Beth Sinur Who Had the Biggest Heart

The Newest Love of Our Family Jackson Thomas Sinur

Our Loving Maggie Mae Who Loved Unconditionally 

I am so thankful for:

Life and health that allows us to still be active and vibrant

My ever-patient wife, Sherry. Great adult children in Andy(RIP), Melissa, Bryon, Dave, Emily, Steve & Beth(RIP). Fantastic grandkids in Keegan, Karson, Xander, Gabriella, Jackson, Hope, Kale, Nolan & Amanda. Finally, a mom who keeps it going at 92 living in northern Wisconsin. 

The local music community that allows us to hang. Especially Susan Alexander, Greg Chaison, Ethan Foxx, Rick Greenly, Moe Mustafa, Heath Underwood, Bob Desiderio, 
Jimi Taft, Donnie Crist, Dan Seethaler, James Graves & Jim Nugent

My friends all over the world that stay in contact and keep me up to date with their adventures. Especially Adrian Bowles, Mark McGregor, Ed Peters, Jim Duggan, Ken Kleinberg, Benoit Lheureux, Toby Bell, Bob Weerts, and Mike West

My customers, work associates and followers that keep me honest

The gifts that God gave me and continues to allow me to grow

Freedom to worship and to choose. Faith Bible Church & great leadership in Dan Lind. 

Family and friends in glory today especially Dad, Andy and Beth Sinur. 

Net; Net:

We all have so much to be thankful for these days if we just take a moment to meditate on thankfulness awhile. A habit I'm trying to employ daily. 

Monday, November 18, 2019

Combining Image, AI & Analytics For Safety and Cost Reasons

The steel teeth on mining excavation equipment like rope shovels and front end loaders are wear items that must be replaced as part of regular maintenance. During normal operation, the connection that affixes a tooth to the shovel or loader bucket occasionally fails, causing tooth detachment. A detached tooth presents a serious hazard if it enters the haulage cycle and makes its way into a crushing unit, where it may become stuck and require the dangerous task of manual removal. Furthermore, wayward teeth cause substantial lost time and production due to jammed crushers and damage to downstream processing equipment. Therefore, it is critical to detect when a shovel tooth goes missing as soon as possible so that preventative action may be taken.

The Problem:

Current methods use equipment mounted cameras and computer vision techniques to generate real-time automated alerts in the event of a missing tooth. While these methods can identify missing teeth with good sensitivity, they produce an unacceptable number of false alarms, which causes equipment operators to ignore the alerts entirely. In some cases, a false positive rate (FPR) of 25% has been observed. Due to the relative infrequency of broken shovel teeth, the false discovery rate (FPR) may be greater than 99%.

There are several challenges associated with the real-time detection of broken shovel teeth. For example, the quality of captured images is compromised by a variety of factors. Dusty operating conditions and variations in lighting, location, and orientation of the shovel bucket, and background composition can make the shovel teeth difficult to distinguish from the material behind it. Furthermore, the biting edge of the shovel bucket is often partially or completely obscured by mined material during operation, which can cause a failure detection algorithm to produce undesirable results. In addition to image quality challenges, the problem itself does not fall neatly into the paradigm of traditional object detection because the target object is an anomalous nuance of the image subject.

The Solution:

A 2-stage approach was selected to address these challenges: 1) row-of-teeth detection and 2) equipment status classification. The location and orientation of the shovel teeth within the images captured by shovel-mounted cameras are highly variable. The purpose of stage 1 in the approach is to isolate relevant information from the image and disregard the rest. This step both normalizes and reduces the size of the images for downstream processing. This technique has been used extensively in real-time facial detection. Stage 2 of the approach performs a binary classification on the detected region from a stage 1. An optimization procedure was applied that aligns sequences by warping them in temporal space such that the distance between signals is minimized. This alignment enables matching of time series based on underlying patterns, irrespective of non-linear temporal variations.

The Result:

This methodology could be used to improve current industry methods, which produce false alarms for 25% of image captures. There are, however, some important points of consideration in the direction of developing a robust, deployable implementation of this methodology.

Net; Net:

New combinations of machine learning methods, even borrowed from different domains, can be leveraged for impressive results. This is not likely without cross-pollination of data science techniques that are likely to come from outside your organization. 

This case study was provided by World Wide Technology (WWT); a leading provider of system integration and global supply chain solutions

Monday, November 11, 2019

What Are Folks Reading These Days?

People barely have time to read these days, so it's important to understand what they are spending their precious time on for sure. In order to help with that task, here are some useful charts and links to help others set some reading priorities. I would appreciate any ideas for new post topics if you have a hot button or two. A bit of background here for you, if you have the time or otherwise skip to the charts.

Since I left Gartner in 2013, I have written over 500 blogs that were about the digital world we are interacting with, developing or planning to develop. I have a pie chart showing those posts that are most popular over that period of time. I also have a chart showing where in the world most of the activity comes from other than the U.S. that dominates the numbers with 70 percent of the activity (defined as "hit count"). In addition to my own blog, I have been a writer, presenter, and researcher for hundreds of organizations after my Gartner life. Starting in 2019, I have also become a Forbes contributor on the topic of AI and Big Data. I have also included a chart for the hottest activity.

                                        LINKS TO THE GREATEST HITS

                      LINKS TO RECENT TOP HITS


Again, if you have any hot button ideas for blog posts, please reach out.


Tuesday, November 5, 2019

A Digital Assist for Active Shooter Incidents

If you have not heard of active shooter incidents recently, you have been living under a rock. Imagine what 2D floor plans and 3D models can do to assist these situations. Even without intelligent digital assistants, law enforcement can get a better handle on the structure involved with any particular incident. While these digital models are helpful, they are difficult and time consuming to create. This case study is about the evolving scanning, creation, and leverage of visual digital models on a large scale.

The Problem:

Usually, we think of scanning on a small scale in and around smaller sized products. Imagine a much larger scale like all the K-12 schools in the US? According to scanning professionals, to map just the K-12   schools in the U.S., it would take a scanning team, scanning 100,000 square feet per day, seven days a week, a total of 188 years to complete. This estimate addresses only the public schools and does not address any of the many private schools, let alone the post-secondary school facilities.
Robert W. Meyers J.D. from the Entropy Group LLC says ““Active shooter incidents are a growing concerns in the United States, with death tolls, most predominantly in schools, rapidly rising and law enforcement resources stretched beyond breaking point. With the unpredictability of these incidents, both in scale and location, the team at Entropy Group LLC has been working alongside law enforcement and the US attorneys nationwide in order to compress response times, by utilizing 2D floor plans and 3D models.

The Solution:

When confronted with the magnitude of the effort it was immediately obvious to Entropy Group   that we needed to join forces with 3D mobile mapping and monitoring technology specialists, GeoSLAM because their ZEB REVO line of scanners provide the necessary accuracy and are much more time-efficient than other laser scanner technologies. To finalize the proof of the efficacy of the patent filing, Entropy Group LLC recently completed a simulated active shooter incident where six law enforcement officers were tested by responding to a fictitious scenario. Officers were provided a detailed floorplan of the two-building which is currently used as a church and parochial school facility. The structure is quite complex with many classrooms, counseling rooms, worship sanctuary, multi-media studios, cafĂ© area, and church offices.

The Results:

The results of the exercise indicate that officers which have access to the 2D floor plans ahead of time, improve their situational awareness, their confidence in responding to a facility that they have never been to previously, by gaining “facility familiarity” thorough review of floor plans and other data prior to their response. Additionally, response times were documented to decrease by up to 21%. This improvement in response will directly result in fewer deaths and casualties. GeoSlam claims to deliver at least a 10X time reduction in the scanning process.

Net; Net:

The ability to scan large spaces and facilities effectively and efficiently will start to deliver more successful digital implementations including city planning, real estate inventory and another large scale geo problems.

Entropy Group LLC

Entropy Group LLC is a full-service Forensics and Security Consultancy firm providing services for Executive Protection, Accident Reconstruction, Security Threat Assessments, Building Information Modelling, Security Design Reviews, Security Program Reviews / Audits, Litigation Support, Pre-Travel Security Front Team Assessments, and Access Control Assessments.

Designed for surveyors, engineers and geospatial professionals, and serving the surveying, engineering, mining, forestry, facilities, and asset management sectors, GeoSLAM technology is used globally by anyone needing to create the digital twin of their world, quickly and accurately. GeoSLAM provides geospatial hardware and software solutions provide rapid and easy mapping and highly-accurate monitoring solutions.