Avoid Touching Your Face: A Hand-to-face 3D Motion Dataset (COVID-away) and Trained Models for Smartwatches
The World Health Organisation (WHO) advises that humans must try to avoid touching their eye, nose and mouth, which is an effective way to stop the spread of viral diseases. This has become even more prominent with the widespread coronavirus (COVID-19), resulting in a global pandemic. However, we humans on average touch our face (eye, nose and mouth) 10-20 times an hour, which is often the primary source of getting infected by a variety of viral infections including seasonal Influenza, Coronavirus, Swine flu, Ebola virus, etc. Touching our face all day long is a quirk of human nature and it is extremely difficult to train people to avoid touching their face. However, wearable devices and technology can help to continuously monitor our movements and trigger a timely event reminding people to avoid touching their face. Bharath Sudharshan, a PhD student at the SFI Confirm Centre for Smart Manufacturing working under the supervision of Prof. John Breslin and Dr. Ali Intizar, has developed a Covid-away model which can trigger early warnings to the users of a wearable device before touching their face. The team has collected a hand-to-face multi-sensor 3D motion dataset and named it COVID-away dataset. Then using this dataset, they trained AI data models that continuously monitor human arm/hand movement using a wearable device and trigger a timely notification (e.g. vibration) to warn the device users when their hands are moved (unintentionally) towards their face. Our trained COVID-away models can be easily bundled into apps for the majority of the modern smartwatches and/or fitness bands. The evaluation and testing of the trained models have demonstrated remarkable accurate results.
Protecting the health and safety of factory Workers using COVID-away models
The main team involved in this work intends to apply their solution for the Industry 4.0 use-cases to protect the health and safety of factory workers. Particularly, the factory workers who operate machines in an assembly and frequently touching the common surfaces are unavoidable making them vulnerable to the community transmission of viral infections. COVID-away can help to keep factory workers safe in addition to the standard safety measures such as face-covering, social distancing, etc.
Both our dataset and trained models are freely accessible at: https://github.com/bharathsudharsan/COVID-away
An animation produced as part of this project is also available below:
Confirm works collaboratively with Industry to pioneer research excellence to meet current and future smart manufacturing needs. We give industry partners a competitive advantage by ensuring the right research team is working to drive business readiness for Industry 4.0. Confirm has experience working across MNC and SMEs within diverse sectors, including, Pharmaceuticals, Medical Devices, Chemical, Nutrition & Beverage, Computer, Electronic, Optical, and Electrical equipment. Smart Manufacturing helps fuse intelligence with the production process to improve manufacturing performance via automation and data analytics. For Research and Industry, queries please contact Confirm.
