IBM Research-Haifa

Putting wearables to work for improved safety

Share this post:

Safety first, right? That’s a given, but even so, did you know that according to the International Labour Organization every 15 seconds, 151 workers have a work-related accident? The global number of non-fatal occupational accidents reaches a staggering 317 million, annually. Clearly, work accidents remain a huge, cross-industry problem, despite safety regulations and procedures.

At IBM Research-Haifa, my team is working on a new kind of safety management platform. The IBM Employee Wellness and Safety Solution gathers data from all kinds of wearable and environmental sensors, and alerts workers and safety officers when danger is imminent, based on the information gathered. Our focus is on the individual worker and how we can reduce the number of accidents and safety incidents.

A technological ‘guardian angel’

Our new wearables platform serves as a real-time warning system. It analyzes a vast amount of information gathered from wearable sensors embedded in personal protective equipment, such as smart safety helmets and protective vests, and in the workers’ individual smartphones. These sensors can continuously monitor a worker’s pulse rate, movement, body temperature, and hydration level, as well as environmental factors such as noise level, and other parameters.

IBM Employee Wellness and Safety Solution identifies and reports every anomaly and potential risk in real time directly to the worker or manager. It can report specific dangers in the workplace, or send an injury alert. This comprehensive safety measure can actively prevent accidents from happening. For example, the system can give an alert when a worker is onsite without the required safety helmet, goggles, or ear protection.

It can also display a warning when a worker is dangerously close to operating machinery or a slippery area, in danger of prolonged exposure to noise, exposure to toxic materials, reaching a point of dehydration, and even if a worker seems to be suffering from low concentration or fatigue. The platform can also identify emergency situations that require immediate attention, such as when a worker falls or faints, and report it directly to first responders and to anyone in the worker’s immediate environment who can offer assistance.

Information from the sensors and smart protective equipment feeds directly to the worker’s smartphone, which can then immediately process and analyze the personal data. Some of the gathered information is stored in the cloud for further analysis, to study and improve safety regulations and procedures, and even to personally adapt them for specific employees. We can also adapt the solution to company specifications, by developing unique algorithms for pre-defined safety and protection needs in the workplace.

There’s no question that even a non-fatal injury can have a potentially devastating effect on an employee’s health and livelihood. And as for the workplace itself, in addition to the distress of an employee suffering from physical injury, work accidents affect productivity, and companies can suffer significant financial losses. In the United States alone, workplace injuries and illnesses cost employers more than $220 billion annually, with 27 million working days lost per year. These rising costs are also hurting insurance companies and influencing coverage rates.

The IBM Employee Wellness and Safety Solution is a research prototype currently being tested with a major industrial partner in the US. Our team would be happy to discuss possibilities for additional collaborations.

More stories

Meet Ari, the Smart Bike that Helps you Catch Green Lights

As more bikes take to the city streets than ever, researchers at RMIT have designed Ari, a smart e-bike that could help riders cruise the ‘green wave’.

Continue reading

High quality, lightweight and adaptable Text-to-Speech (TTS) using LPCNet

Recent advances in deep learning are dramatically improving the development of Text-to-Speech systems through more effective and efficient learning of voice and speaking styles of speakers and more natural generation of high-quality output speech.

Continue reading

Four Papers Advance Computational Argumentation in IBM’s Project Debater

The latest work on computational argumentation from the IBM Project Debater research team group is being presented at the ACL 2019 conference. Three papers will be presented at the main conference and one more paper will be presented in the co-located Argument Mining Workshop.

Continue reading