Emotive aid for combating autism

The Thomas Jefferson High School for Science and Technology InvenTeam invented an emotive aid that uses a computational algorithm to extract human emotional signatures from speech and display expressed emotions. Beneficiaries include children with autism and similar disorders that impair the ability to detect emotion, thereby hindering social interactions and the development of meaningful relationships. The bracelet-designed device employs machine-learning techniques to improve accuracy and efficiency relative to current methods. The first prototype was trained to detect four emotions: happiness, sadness, anger, and disgust. Initial accuracy of detecting emotion is 60%, with the ability to improve as the user continues to use and train the system. The computing device and power source can be stored in a pocket or clipped to a belt while the bracelet itself comprises of a microphone and a display. The battery life is sufficient for a full day's use. The alpha prototype cost $150 to fabricate.