Cognitive engineering can humanize machines
Optimized systems using cognitive engineering are helping humans by combining knowledge, contextual awareness, and situational intelligence. The human versus machine debate has been going on for entire careers, especially for those who have spent a lifetime building machines, programming them, feeding them with data, and then directing them to provide the needed results.
Machines have the potential to move more quickly with greater strength and analyze faster than humans and without fatigue or becoming distracted. Human differentiation derives from a keen sense of perception, the ability to look at things from numerous angles and make objective, informed decisions.
The human mind perceives and reacts to situations by combining knowledge (acquired through past experiences and learning) with a contextual understanding and situational awareness of things.
What is cognitive engineering?
Cognitive engineering is the rise of technologies that help machines sense, analyze, and learn better, as well as contextualize. At its core, cognitive engineering is about humanizing machines.
Security surveillance systems at airports provide an example.
Security surveillance systems have vast knowledge, acquired through years of image and behavioral recognition and analytics. With thousands of passengers moving through airports every hour, how does the system understand what and who to monitor? It uses contextual intelligence to identify suspicious behavior, survey unusually shaped baggage items, and actively monitor restricted zones. Once the contextual intelligence of the system narrows down a confirmed suspect, the system’s situational intelligence kicks in to generate possible solutions to the problem at hand: should the person be forcibly detained and removed from the location or would that endanger the lives of innocent passengers? Is there time for a physical confrontation? Should passengers be asked to vacate the terminal?
Many products using cognitive engineering or machine intelligence focus on one aspect of cognition: knowledge or contextual awareness or situational intelligence. Intelligent systems combine all three aspects in one machine.
Three areas of focus can advance the capabilities of cognitive systems.
1. Interactions: Interactions must evolve from pushing a button or opening an app to other methods such as gesturing, sign language, facial expressions, voice commands, or interpretation of emotional state.
These require advanced voice and image processing tools. Reinforcement learning algorithms under development will equip cognitive systems, over time, to identify and respond to various gestures and emotions. The challenge is to accurately engineer models, not just cognitive systems, of the broader environment of inputs and interactions, beyond a traditional interface.
Imagine a home automation system that analyzes human expressions to select a desired music track or adjusts a thermostat by assessing human body movements.
Collaborative robotics ("cobotics") in production plants can behave just like another shop-floor co-worker, with greater precision and perhaps more quickly. Robots equipped with advanced machine vision can nearly eliminate errors and quality control issues on the production line.
2. Decision making: Decisions need to be quick, bias-free, based on evidence, and backed by strong reasoning algorithms.
In an industrial manufacturing plant, sensors collect huge amounts of data at every stage of the production line.
The focus must shift from building analytical capabilities on the cloud to edge-empowered businesses with access to real time insights. Fault-model libraries under development can speed-up learning and fast-track reinforcement in cognitive systems. These libraries analyze and study patterns of various plant processes and machinery over an extended period of time. The consolidated learning is then fed to cognitive systems to give them a massive head-start.
Cognitive systems trained this way autonomously can optimize processes to lower costs or speed up production. Artificial intelligence (AI) may be used for monitoring to ensure that production matches wider goals in manufacturing plants.
3. Open standards: With so many companies developing AI and machine learning tools, the creation of industry standards will be a huge boost to the cognition world. Standards will go beyond just bringing in more developers to the ecosystem and enable businesses to invest in a standard set of tools to build machine intelligence.
Cognitive engineering already is present in industrial systems, self-driving cars, autonomous drones, healthcare planning, and virtual assistants, soon will permeate every walk of life. This revolutionary technology applied to machine learning can benefit humans.
Bhupendra Bhate is chief digital officer, L&T Technology Services Ltd., which is a CFE Media content partner. Edited by Mark T. Hoske, content manager, Control Engineering, CFE Media, email@example.com.
Cognitive engineering helps machines sense better, analyze better, learn better, and put content into context.
Using knowledge, contextual awareness, and situational intelligence is best.
Better interactions, smarter decisions, and open standards help cognitive engineering.
What machine or systems could be improved with more knowledge, contextual awareness, and situational intelligence?
See related CFE Media articles on machine learning and artificial intelligence below.