AI Based Traffic Management

Or other kinds of of process management?  Could be integrated with RPA?

AI-Based Traffic Management Gets Green Light    By ZDNet

The new system switches traffic-light coordination from a timer-based model to one based on demand.

The NoTraffic autonomous traffic management company has deployed an artificial intelligence-driven traffic management system in Phoenix, AZ.

The NoTraffic autonomous traffic management company has deployed an artificial intelligence (AI)-driven traffic management system in Phoenix, AZ, switching traffic-light coordination from a timer-based model to one based on demand.

The goal is to improve traffic flow and cut vehicle and pedestrian delays at intersections, and the system has reduced vehicle delays by up to 40% in some instances.

The NoTraffic platform monitors road assets as they approach an intersection and calculates optimal service for the intersection in real time, autonomously changing signals accordingly.

Phoenix Street Transportation director Kini Knudson said, "We are now seeing the convergence of technology-enabled automobiles and traffic management systems working together to move vehicles more effectively through busy corridors."

From ZDNet
View Full Article

Protecting Industrial Control

Probably one of the most important things we can do well.  When involved in this space in the 80s, things were far less connected, so both the threats and remedies are far more possible.   Here an overview of SCADA.  And add to that the ability to find patterns of much more subtle changes in a system.

Protecting Industrial Control Systems   By Keith Kirkpatrick
Communications of the ACM, October 2019, Vol. 62 No. 10, Pages 14-16    10.1145/3355377

While most commercial and government organizations have a corporate network to handle administrative, sales, and other back- or front-office data, a growing number of organizations also have implemented one or more supervisory control and data acquisition (SCADA) systems. These systems incorporate software and hardware elements that allow industrial organizations, utility companies, and power generators to monitor and control industrial processes and devices, including sensors, valves, pumps, and motors. Today's SCADA systems also allow organizations to harvest data from these devices, and then to analyze and make adjustments to their operational infrastructure to improve efficiency, make smarter decisions, and quickly address system issues to help mitigate downtime.  .... " 

Monitoring and Improving Process by Trusted Measuring and Adapting

Considerable article brought to my attention my Alex Renz. Connecting Distributed Ledgers and Operations Technology,  Ultimately my closest goal.  How do we improve process  by measurement, goals and analytics?  Here a novel direction example:

“OT is hardware and software dedicated to detecting or causing changes in physical processes through direct monitoring and/or control of physical devices such as valves, pumps, etc.”
— Gartner IT Glossary, as of Jan. 2019

IILA x IOTA — Bridging the Gap between OT and IT in Production Metrology

Creating a Wireless Smart Device Gateway for Quality Applications using Mahr Measuring Instruments

By Daniel Trauth
Co-Authors: Ashri Anggia, Semjon Becker, Sascha Kamps

Quality Applications in Production Metrology

Quality applications and production measurement technology (referred to as Production Metrology) cover an important market, see Figure 1. In Germany alone, revenues from the manufacture of measuring and testing instruments rose from USD 28 billion to USD 38 billion between 2010 and 2016. According to a statistic by Statista, a further increase to USD 41 billion is expected in Germany by 2020. Although Germany is an important industrial nation, the figure below shows an incredible worldwide potential in the field of quality applications and production measurement technology.

In quality applications and production metrology, measured data — referring to the quality of a product — is exchanged between manufacturers (e.g. OEMs) and their suppliers; most probably in a different variety of formats and in a short notice. This non-standardised exchange of quality data is associated with considerable financial losses, because on one hand there is no reasonable exchange standard and on the other hand cooperation between manufacturers and suppliers without exchange standard simply does not work.

In recent years, few attempts for exchange protocols like Quality Data eXchange (QDX) or Advanced Quality Data Exchange Format (AQDEF) have become increasingly common in use. For direct integration of devices into Statistical Process Control (SPC) software, some standards such as the MUX-50 data format are available. However, this is an error-prone process with low trustworthiness.

It is imperative that the measured data should be transferred immutably conforming high data security standards and existing data exchange protocols. With advancing digitisation and globalisation, the use of Distributed Ledger Technology (DLT) as a decentralised protocol can lead to a worldwide backbone for measured quality data, enabling trust, data security and widely useful exchange format. But first, one needs a concept to combine Operational Technology (OT) and Information Technology (IT). .... " 

Swarms in Control

A favorite topic.  All systems are controlled by multiple entities.   Call that a swarm.   Stanford and their Platform Lab developing infrastructure for such systems.   Call it 'Big Control'.

Who Will Control the Swarm? 
A team of computer scientists and engineers are developing the infrastructure to centrally manage autonomous cars and drones ...
Stanford News   by Andrew Myers

Researchers at Stanford University believe future device swarms will operate via centralized management, using applications running in large data centers, similar to the way the cloud centralizes big data. In order to achieve this goal, the Stanford team has established the Platform Lab to develop infrastructure for these new "Big Control" applications. Although most current research into autonomous vehicles assumes a distributed model controlled in a peer-to-peer manner, with each machine doing its own calculations, a more concentrated model would have significant advantages, says Platform Lab faculty director John Ousterhout, who received the ACM Grace Murray Hopper Award for 1987, and the ACM Software System Award for 1997. Ousterhout notes this more concentrated model would provide a big-picture view of the world that enables better control of higher-level tasks such as system-wide situational perception, decision-making, and large-scale traffic planning. In addition, Ousterhout says the centralized applications can utilize powerful machine-learning algorithms that let the control systems learn and improve their behavior. The researchers are outlining a roadmap of the platform architecture. .... " 

AI for Manufacturing Process Control

Interesting process manufacturing example.  Weight control is a very often used, and a simple control process.   Interesting to see how this differs.

Hershey adopts AI process to perfect Twizzlers production

The Hershey Co. is seeing success after partnering with Microsoft to develop an artificial intelligence solution to a longstanding production variability issue that impacted product weights. The confectioner's production machines are now able to auto-adjust factors such as temperature and pressure up to 240 times a day to make sure that the product that goes into the package is the correct, advertised weight.  .. " 

Closing the Loop

From the Edge Foundation.  A Conversation with Chris Anderson.  I have worked with process control systems that are closed loop, and designed to be ...  We have many in our lives,  but many are hidden, from the lowly thermostat to ambient computers that continually wait for our commands.  In some cases its very obvious when the loop is closed,  but in most computing systems it is not. You should be able to tell if you map the process.

In the Edge: 
Closing the loop is a phrase used in robotics. Open-loop systems are when you take an action and you can't measure the results—there's no feedback. Closed-loop systems are when you take an action, you measure the results, and you change your action accordingly. Systems with closed loops have feedback loops; they self-adjust and quickly stabilize in optimal conditions. Systems with open loops overshoot; they miss it entirely.

Chris Anderson is the CEO of 3D Robotics and founder of DIY Drones. He is the former editor-in-chief of Wired magazine.  ..... "     Podcast and text ... "

Grafana for Time Series

Brought to my attention. Grafana.

" ... The leading open source software for time series analytics ... Grafana is an open source metric analytics & visualization suite. It is most commonly used for visualizing time series data for infrastructure and application analytics but many use it in other domains including industrial sensors, home automation, weather, and process control.    .... " 

Autonomic Platforms Evolving

I had not used this precise tag 'Autonomic'  before, but it is understandable:  How do you fully or partially automate systems that support business process?  The definition is broad.  And to be clear has been around for a long time.  Notably in process control.

Need to now link these systems to current architectures and systems, and to people who are still making decisions.  Cognitive systems, AI, Machine learning, Predictive Algorithms ... have all evolved to the point this will lead to more autonomy.  Topic often mentioned in this blog.

Good Overview from Deloitte-WSJ:

Autonomics Shake Up IT Systems Management
IT organizations are increasingly pursuing self-managing autonomic platforms, which can detect and fix their own problems without human intervention.

Autonomic computing platforms, which are IT systems capable of configuring, optimizing, and even healing themselves, could free up IT staffers to focus on more valuable activities and help relieve strain on IT budgets. Many traditional IT operations are candidates for autonomics, including those that are workflow-driven, repetitive, or require reconciliation between systems. CIOs overseeing large, complex IT operations stand to benefit enormously from these burgeoning systems, says George Collins, CTO at Deloitte Digital.

“Autonomic platforms have arisen from a confluence of advancements in technology, from virtualization to containerization, more intelligent configuration management, and a more agile manner of delivering technology environments,” Collins says. “Autonomic platforms allow us to shift attention away from building the scaffolding of IT to creating a more repeatable way of packaging, delivering, and managing IT.”  .... " 

Reinforcement Learning and AI

This bears some relationship to looking directly at business process and attempting to control it directly.  A kind of context simulation with rewards.   Thus similar to game play and process control.   I will follow in a post with a real world example.

Reinforcement Learning and AI   Good piece with many related examples.
Posted by William Vorhies

Summary:  At the core of modern AI, particularly robotics, and sequential tasks is Reinforcement Learning.  Although RL has been around for many years it has become the third leg of the Machine Learning stool and increasingly important for Data Scientist to know when and how to implement. ... " 
" ... The key to understanding when to use Reinforcement Learning is this:

Data for learning currently does not exist
Or you don’t want to wait to accumulate it (because delay might be costly)
Or the data may change rapidly causing the outcome to change more rapidly than a typical model refresh cycle can accommodate.

What problems fit this description?  Well robotic control for one and game play for another, both a central focus of AI over the last few years.   ... " 

(Read the full article)   See also in the WP, which does a good broad overview.

Autonomous Selection of Mars Laser Targets

An example of autonomy for a complex system.  Here the Curiosity Rover on Mars.   At one level this is similar to closed loop process control, but with more complex sensor analysis being done in that loop.  

Assume this increases accuracy, speed in going through analysis goals ... and even decreases targeting labor required to enact,  thus decreasing cost.     So is  closed loop process control we did in manufacturing, though the adjustments here appear to start to arise to the strategic.   Article and image examples:

From the Jet Propulsion Lab: 
  " .... NASA's Mars rover Curiosity is now selecting rock targets for its laser spectrometer -- the first time autonomous target selection is available for an instrument of this kind on any robotic planetary mission.

Using software developed at NASA's Jet Propulsion Laboratory, Pasadena, California, Curiosity is now frequently choosing multiple targets per week for a laser and a telescopic camera that are parts of the rover's Chemistry and Camera (ChemCam) instrument. Most ChemCam targets are still selected by scientists discussing rocks or soil seen in images the rover has sent to Earth, but the autonomous targeting adds a new capability. ... "

Controlling Smartphones With Your Eyes

In CACM:
" ... In an effort to make eye tracking cheap, compact, and accurate enough to be included in smartphones, a group of researchers is crowdsourcing the collection of gaze information and using it to teach mobile software how to figure out where you’re looking in real time.  ... " 

Driving Light Show with Pattern Recognition AI

An example of using sensors to drive performance light position.  In the BBC.  Ultimately a good example.  The sensors gather data.  Patterns can be matched to scripts (goals).   Adaptations to performance are made to achieve results.  Potential to learn by feeding back results to performers ( or script writers) . Whole thing recorded for later strategy adaptation.  So what is AI?  The advanced machine learning / pattern recognition. Not dissimilar from more complex versions of adaptive process control.

Wi-Next and Advanced Analytics

I recently attended a webinar from Wi-Next.  This is a natural next step.  Process control is an area we first experimented with rule based AI systems.

IBM will bring more advanced analytics to Wi-Next's industrial IoT systems

        Internet of Things startup Wi-Next will add IBM analytics to its systems for industrial quality control and predictive   ... 

The added capabilities, including some powered by artificial intelligence, are designed to help food-processing companies and consumer product makers keep production lines running smoothly despite what's sometimes a breakneck pace. .... " 

Watson and Vineyards

IBM has been talking much about weather data and internet of things.  So it is natural to see this piece about a process control style application to the watering of vineyards in CA.   The broad idea is not new, we saw it being used a decade plus ago.  Look forward to seeing how Watson 'cognitive' approaches can improve it.

Complex Behaviors from Simple Brains

From Santa Fe Institute.  This is often stated as a precept of complexity theory.  Though the precise arrangement of hardware, connections and rules is often difficult to determine.   Control problem is easier, but not necessarily easy.

Paper: Complex behaviors can arise from simple brains
How much brain power do you need to control your body? It’s a key question for robotics and artificial intelligence researchers, and the answer is, well, not all that much. The key, according to new research from SFI Professor Nihat Ay and colleagues, is that bodies have to obey certain rules — the laws of physics and biomechanics, for example — that make solving the control problem easier. ... " 

Smart Cities Critique

Think of Smart Cities as extremely complex version of process control.  With the added complexity of a mix of difficult to predict people.  It also reminds me of algorithm based AI systems we developed.  SimCIty also inspired us to look at systems that would control enterprises.  That kind of effort continues today.    I liked seeing this article which looks at a critique of the Smart City 'movement'.  There is a long way to go.  The article links to a manifesto that contrasts smart city to smart citizen.

Intel Shows Roadmap

Correspondent Michael Curran of Micro Industries, a company we used extensively for in-store displays,  posts about Intel's Developer's forum, which I do not normally follow.   He suggests this shows a roadmap for technologies destined for intelligent retail signs:

" ... Each September, Intel® demonstrates its latest technology innovations at Intel’s Developer Forum (IDF) in San Francisco. In addition to the traditional rollout of new microprocessors, this year Intel unveiled a number of software initiatives that leverage their recently acquired assets at Wind River and MacAfee to provide a basis for the next generation of personal and embedded computer applications. From a digital signage perspective, the most interesting aspect are Intel’s new software tools that make it easier to integrate various types of interactive technologies into digital signage applications. ...From Intel’s perspective, I am sure that these tools are targeted at the Ultra-Book market but their relevance to the digital signage market is significant. Intel is poised to deliver software development tools that address touchscreen interfaces, gesture control, voice control and facial recognition along with a number of enhancements to their currently available tools for Anonymous Video Analytics (AVS) ... " 

CPG and Eye Tracking

Colleague Herb Sorensen comments on the use of eye tracking by CPG companies in RetailWire.  True,this has become common, and more analytical work is needed. " ... What has become apparent is that visual control, and a whole lot more of the shopping trip, is NOT consciously managed by the shopper, but is under autonomic control. This, in turn, has led me to more in-depth study on the neurobiology behind the guidance/response mechanism, THE fundamental science of the purchase process ... " 

Analytical Ecosystems Explored

Just brought to my attention: 
Alan Greenspan, marketing manager at Teradata,  is quoted: " ... When business justification calls for more than one system, organizations need a way to manage, monitor and control all aspects of the analytical environment—from the hardware and software components to the process and flow of data. This level of management keeps the complexity of the ecosystem low while providing high value to the business.... "

Readying to Unwire the Enterprise

In Knowledge at Wharton: The enterprise still has lots of wires.  Can continued control be effective once the enterprise goes wireless?

" ... In another context, former Procter & Gamble CEO A.G. Lafley summed up the situation this way: "We have to strike the right balance between being in touch and being in control. The irony is the more in control we are, the more out of touch we become."
The notion of relinquishing control in order to win is counterintuitive for most large companies. They have spent their corporate lives putting controls and processes in place to regulate behavior, maintain a common identity/brand and drive efficiencies. But the very controls that define them are also the ones that may impede their ability to innovate around wireless, given that such innovation is all about allowing the end-user to discover what new and useful things they can do with the technology. As enterprises will come to realize, control is just an illusion in the digital world.... "