mpiricai helps solve business problems by applying Industrial Internet of Things (IIoT)

and AI technologies. The company uses these technologies to increase the efficiency, reliability and safety of industrial plants. Empiricai’s latest product is WorkSafe Analytics - a tool to assist companies to comply with COVID-19 PPE and social distancing guidelines. Industrial Compliance recently caught up with Empiricai’s Salman Chaudhary to find out more about this safety compliance technology.

HOW DID THE IDEA OF WORKSAFE ANALYTICS EMERGE? We always wanted to do something around health and safety in an industrial plant setting. We also wanted to extend our analytics product beyond the operation of a plant, into health and safety scenarios. And then, COVID hit and plants and customers were less interested in inefficiency and became more interested in just staying open. Health and safety went to the top of their agenda. So we thought ‘what can we do to help these plants?’ This resulted in the creation of WorkSafe Analytics. It is highly relevant to industrial plants but equally relevant to commercial sites and corporate offices. It is aimed at any workplace that is concerned with staying open while keeping employees safe.

HOW DOES WORKSAFE ANALYTICS MONITOR COVID SAFETY COMPLIANCE? When we designed the product we thought about two essential components: safety compliance and the active monitoring of safety guidelines related to COVID. Leveraging a customer’s existing video feeds that feed into a Network Video Recorder (NVR), our state-of-the-art algorithms provide customers with an overview of where any safety violations are taking place. Using Computer Vision and AI, the product is able to tell if someone is wearing a facemask and whether they are wearing it correctly. Our algorithms are also able to measure, even at great distances, how far apart two individuals are. Customers can set thresholds on their own definition of a violation - for example, they can dictate if a violation is considered to be a split second removal of the mask or if it is removed for a longer duration.

CAN THE AI DISTINGUISH BETWEEN FACE MASKS AND FACE SHIELDS? WorkSafe Analytics has a highly trained algorithm for detecting face masks and shields. It was challenging to develop because you want to train the AI to the maximum accuracy but you also

Keeping an AI on COVID compliance

Artificial intelligence (AI) continues to be a hot topic in the industrial space. But what happens when you bring together AI and compliance? We recently caught up with Empiricai’s Salman Chaudhary to find out about the company’s newest product that utilises AI to identify and measure COVID-19 safety guideline compliance

want an algorithm that isn’t too demanding of processing power. There are lots of different configurations of face masks and shields so if a customer uses a particular type of PPE that they want the algorithm to train on, then it is a very quick process.

HOW DOES THE SOFTWARE MONITOR SOCIAL DISTANCING? WorkSafe Analytics is able to calculate distances between people based on a distancing algorithm that measures in real time. For groups ranging from two to 100+ people who are moving constantly, distances between each individual person in that area is being measured in real time. It is then up to customers to identify what they consider a violation. So, for example, if an organisation wants people to be six feet apart in the workplace but will allow occasional lapses to three feet apart, the system can be configured to

consider anything above six feet as safe, between three and six feet as a warning, and anything less than three feet to be considered as a violation. As well as monitoring where violations are

taking place, we also want WorkSafe Analytics to provide insights. For example, you can infer information about violations in particular rooms where people may be more likely to remove a face mask, or in corridors where everyone may be crowding together because of a lack of space. The software can also show if there are particular departments where there is less compliance. It can provide a visual depiction of high traffic areas or high occupancy areas and then layer violation occurrences on top. Organisations then have insights that are really actionable, such as providing more training or increasing awareness in particular areas. This also has a use beyond COVID in terms of the functional design and use of space.

WHAT HAPPENS WHEN A VIOLATION IS DETECTED? The system records the violation and it alerts whoever has been set up in that organisation as the recipient(s) of that information via Email or SMS. Alerts can be customised to trigger for every breach or to notify on an hourly/daily basis, or to provide information at a room or department level. The system is also configurable in terms of how you want to receive


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44