Logo

The Data Daily

How Leading Companies Are Using AI Sensors for Safety

Last updated: 04-13-2021

Read original article here

How Leading Companies Are Using AI Sensors for Safety

New advances in ergonomic training using sensors and biofeedback are forging a step change in manual handling injury reduction. Leveraging the power of artificial intelligence (AI) and machine learning (ML), coaching workers to self-correct their movements in real-time and avoid ergonomic injuries, is stimulating an engaging personalized pathway to behavioural change.

Soter Analytics is leading the way when it comes to developing miniaturized technology using AI and ML tomeasure the capability of humans and calculating how much we can endure.

Kenco Logistics, one of North America’s leading third-party logistics providers have been using the sensors in their warehouses and Miguel Trivino, CSP, director of environmental, health, and safety at Kenco Logistics says, “Nobody likes back pain, but proper lifting is a habit that many new associates have not yet developed. The Soter device gently yet persistently raises the level of awareness, building a good incentive to use better body mechanics”.

What is artificial intelligence (AI) and machine learning?

At a simple level of interpretation, AI can be described as the collection and evaluation of extraordinarily large data sets, commonly known as big data. It is also important to know that ‘machine learning’ algorithms are considered a subset of AI and can be defined as the ability for the machine to ‘learn’ from human behavior and improve its analysis by using the algorithms. The algorithms work by taking large sets of data to recognize patterns and then training the machine to make recommendations. With continual use, the repetitions enhance modifications, and the machine is then able to provide predictions (predictive analysis) about behavior based on input it receives.

How does it work andassist your workers?

Every time a person makes a movement, for example, lifting an object, the Soter device collects high-frequency Inertial Measurement Unit (IMU) data. This data is fed into a neural network which, based on a 2-year study, is trained to understand if the person finds the particular movement difficult or not.

Mr. Shawn Rush, Sr. Director, Environmental, Health & Safety Giant Eagle says,“The solution accurately detects and provides warnings for hazardous movements that have high potential to cause injury. As a result, we’ve seen the number of at-risk postures and movements cut roughly in half for the Team Members involved in the process”.

A worker may lift an item over a duration with correct posture but after some time, the quality of this movement can change. Contributing factors include fatigue, stress, pre-existing injury, distraction. The Soter device uses ML based on algorithms and picks up different qualities of a movement that quantify its safety and will alert the worker. Among many characteristics, it will consider the velocity, jerkiness and bend angle at completion of the movement.

Starting with the individual and spreading to the organization, Sarah Moore, Health and Safety Leadership Partner - Sales & Group Projects - Coca Cola Amatil, discusses using the data collected from the sensors to pinpoint risks.

“Amatil has been partnering with Soter for the past six months, implementing both the SoterCoach and Clip&Go solution within various roles across our business, ranging from our Pickers to our Merchandisers. On average, employees that have completed the program have seen a ~35% reduction in their risky manual handling movements.

The manual handling data and insights provided by Soter identified the key manual handling risk within our business, how this risk differs across roles and individuals and how we compare when benchmarked with our organisational peers. These insights have allowed us to tailor our future manual handling programs to Amatil’s risk profile, and ultimately getting our people home safely to what they love”.

Feedback from employees that have completed the program has been extremely positive. The coaching modules and live Beep/Bizz feedback providing with a real time understanding of their personal risk movements, has empowered them with the information they need to be more mindful of their own manual handling movements, because for the first time they know what ‘good looks like’ for them.

When it comes to declining productivity in the workforce, the main causes are lost workdays and high employee turnover. Gifting workers with the tools to help them learn to move safely and feel valued by the individual attention it can provide them, can help with the pull between productivity and safety and yields proactive injury management. 

Vimel Budhdev, Head of Health, Safety and Environment at Travis Perkins plc was able to implement individual tailored environmental controls to prevent injury.“In one simple instance, the device highlighted that one of our colleagues was bending at a low level roughly around 100 times a day so by easily moving some things around we have reduced around 26,000 high-risk bending movements in a year”

The sensors offered by Soter Analytics enhance a worker’s learning potential by teaching and notifying them specifically about their movements. They can track, share and compare with other colleagues building camaraderie and fun on the job, all known factors to increase workforce retention.

Vimel Budhdev from Travis Perkins plc says,“We found the set up really easy, it was pretty much step 1, 2, 3 and the colleagues easily liked the devices to their mobile phones. Tracking their own data created a really positive engagement and during the debriefing sessions the colleagues continually wanted to know more about their results and how they could do things differently”

Using the advances in technology, individual workers can be responsible to follow their own injury reduction program, harbouring an autonomous learning experience, keeping them safe, engaged and on the job.

Learn more about Soter solutions at soteranalytics.com


Read the rest of this article here