Heart rate data cleaning algorithm for wearables
My PhD advisor and I developed and evaluated a novel algorithm for cleaning heart rate data captured by wearable devices.
Our algorithm improves data quality (concordance correlation coefficient) by 14.4% outperforming Microsoft's solution. One unique feature of the algorithm is its ability to remove motion artifacts without accessing any motion data.
Information about the algorithm was presented at the following conferences:
- The 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’17)
- American Medical Informatics Association Annual Symposium 2017