hüg is a stress detection and monitoring platform for individuals and organizations
Face detection and emotion analysis using convolutional neural networks.
Happier employees make better colleagues. hüg improves the overall productivity of an organization
Better mental well-being for individuals and organizations
Stress & Loss of Productivity
The accounting profession is demanding. Stress levels are high and accounting professionals often experience burnout in their careers. Stressful environments affect the mental well-being of employees and may result in decreased mental capacity and antisocial behaviours. Low job satisfaction, poor team cohesiveness and an overall drop in productivity ensue.
How can embrace help?
hüg empowers individuals and their employers to better manage mental well-being at a personal and managerial level. It is a platform that monitors stress levels and identifying opportunities to provide support. The platform automatically detects heightened stress levels and calls for employer's interventions such as re-delegation of workload, or hosting leisure activities. hüg also empowers individuals to manage their own mental well-being through self-awareness and tips to de-stress. This will foster a more pleasant and productive work environment for accounting professionals.
A happy employee works better. By promoting better mental well-being of employees, hüg increases productivity and cohesiveness in an organization, and reduce loss of talents especially during the peak periods.
How exactly does it work?
hüg uses facial expression recognition to calculate stress level from a face image. Using a convolutional neural network, levels of emotions (anxiety, sadness, joy etc.) are extracted and used to determine a final "stress score".
Individuals can track their own emotions and stress through a dashboard similar to a fitness tracking platform.
Employers will only access to anonymized and aggregated data of their employers, for example by teams or departments. Trends and distribution of stress are monitored using time-series analysis and any anomalies will be flagged out.
Shi Feng - Student (Computer Vision), NUS
Ai Ni - Student (Accounting), NTU