DescriptionMachine learning has a lot of potential when applied to time series sensor data, yet a lot of this potential is currently not utilized, due to privacy concerns of parties in charge of this data. In this work I want to apply privacy-preserving techniques to machine learning for time series data, in order to unleash the dormant potential of this type of data.
|Period||14 Nov 2020|
|Event title||18th ACM Conference on Embedded Networked Sensor Systems: SenSys 2020|
|Location||Virtual, Yokohama, Japan|
|Degree of Recognition||International|
Research output: Contribution to conference › Abstract › peer-review