The CSAIL group at MIT have a new paper out titled ‘Predicting Latent Narrative Mood using Audio and Physiologic Data‘ that uses a Samsung Simband in combination with audio and physiological data to show how wearables might be used to predict moods. Initial tests have shown an accuracy rate of ~83%.
Figure 3: Real-time estimation of the emotional content in 30 seconds of collected data, using our optimized NN. The color of the text at the top of the plot reflects the ground truth labels generated by the research assistant (blue for negative, red for positive, black for neutral). The predictions of the network (y-axis) reflect the underlying emotional state of the narrator.
Have an amazing project to share? Join the SHOW-AND-TELL every Wednesday night at 7:30pm ET on Google+ Hangouts.
Join us every Wednesday night at 8pm ET for Ask an Engineer!
Learn resistor values with Mho’s Resistance or get the best electronics calculator for engineers “Circuit Playground” – Adafruit’s Apps!
Maker Business — HAX Hardware Trends 2017
Wearables — Stay put, paint!
Electronics — Clarify your supply
Biohacking — Nucleus 7 – A Native Cochlear Sound Processor for iPhone
No comments yet.
Sorry, the comment form is closed at this time.