Stay well with machine learning

Stay well with machine learning

Anastasiia Kornilova,!SoftServe Data Science Group!

"1

Life expectancy at birth

"2

Medicine evolution

❖ Fighting against diseases!

❖ Monitoring for finding early symptoms!

❖ Preventing diseases /Forming good health habits

"3

Healthy habits

❖ Sleep!

❖ Running!

❖ Swimming!

❖ Walking!

❖ Diet!

❖ …

"4

How measurements can help form good health habits?

❖ Observer effect: Measuring system changes the system!

❖ Gamification!

❖ Psychological effect!

❖ Power, will, willpower

"5

What we can measure?

❖ Easy/Relatively Easy:!

❖ Temperature!

❖ Weight!

❖ Heart rate!

❖ Blood pressure!

❖ Steps

!

❖ How about:!

❖ Activity level!

❖ Sleep quality!

❖ Predicting some diseases

"6

Gadgets examples

❖ Fitness trackers/ Smart watches:!

❖ for every day usage!

❖ for measuring sleep quality!

❖ for trainings!

❖ Smart scale!

❖ Smart toothbrush

"7

Life is short. Do things that matter

❖ http://mytikker.com/

"8

What is machine learning?

"9

ML algorithms

❖ Supervised!❖ Unsupervised !❖ Semi-supervised

"10

How machine learning can help?

"11

Data: Basis Band metrics

❖ Optical blood flow sensor - for measuring heart rate!

❖ Accelerometer - for measuring steps amount!

❖ Body temperature sensor!

❖ Galvanic Skins response sensor

"12

Data

"13

"14

Build K-Means model

"16

"17

How good is our model?

"18

"19

Ways to improve❖ Improve current model: !

❖ Data scaling!

❖ More data!

❖ Imputing!

❖ Use different model:!

❖ Supervised!

❖ Unsupervised!

❖ Use ensemble of models

"20

"21

You can use ML algorithms for

❖ Fraud detection!

❖ Computer vision!

❖ Predicting future!

❖ Recommend product/friends!

❖ Speech and handwriting recognition!

❖ Identify key topics/summarize text!

❖ Find patterns in users behavior/actions

"22

Summary

❖ We built simple «toy»-model for activity recognition!

❖ Output of our model is relevant to to output of existing full-featured commercial service

Q & A

"24