Understand people better
Computer vision has come a long way the last few years. A machine can now pick-up tiny variations in someone’s face reliably.
Each time a user records a video, we analyze dozens of facial landmarks in frame. During a 15-seconds video recording – where we capture up to 30 frames a second – and adding the other biometric data we evaluate, our algorithm consider more than 11500 pieces of information.
This data has taught us several interesting factoids over time:
+ The expression “having a long face” is very true when people get tired!
+ Understanding bias and data-bias will be the differentiator in the years to come. Any company involved in the field must make sure certain groups do not become disenfranchised.
+ Quality of sleep is almost -almost- as important as the number of hours slept (so get a good mattress in a quiet place!)
Want to learn more about computer vision?
Check out some of our past blogs on the topic.
Going beyond quantitative analysis
Let’s not be data-blind! When assessing someone’s energy levels, it is key to also model someone’s mental and emotional states.
This is why, when using Okaya, our members are exposed to different tests such as Trail Making Tests or the Espworth tests.
We complement these tests with a growing field in computing: Language analysis. Mood, emotions, and trends reflect in how we express ourselves. So we take this information into account.
You must have heard that 80% of communication is non-verbal. While it is true in many cases, what people say -the verbal side of communication- has an incredible level of importance when it comes to seeing how someone is doing.
Our words and beliefs shape who we are and who we may become.
Okaya’s strength – and long-term plan- is being able to personalize this analysis for each user. It will help us tackle one the biggest risk in machine learning: Bias. Dataset are biased by default. Here is a fun video summarizing the problem of biased data.
Rather than keeping a blind-eye to the problem leading companies are taking a proactive approach to identifying, quantifying, and modeling data bias to reduce its impact on algorithm.
Okaya’s experience is making sense of thousands of data points to truly understand an individual’s unique situation and make appropriate recommendations based on their state of being.
If you’d like to learn more about Okaya feel free to reach out we’ll be happy to share more information with you.