CAMALIOT
CAMALIOT
The era of modern smartphones, running on Android version 7.0 and higher, facilitates these days collection of raw dual-frequency multi-constellation GNSS (Global Navigation Satellite Systems) observations. This opens up an opportunity for GNSS community data to be potentially exploited for precise positioning and various scientific investigations. Application of Machine Learning Technology for GNSS IoT data fusion (CAMALIOT) was an ESA NAVISP Element 1 project (NAVISP-EL1-038.2) with activities including acquisition of GNSS observations from the modern generation of smartphones and exploitation of this crowdsourced data for scientific applications through the use of Machine Learning (ML) and Deep Learning (DL).
ESA
software conceptualization, implementation, and testing
March 2021 / 21 months
image source: navisp.esa.int
I was the main person in charge of the conceptualization, testing, and development of the cloud-native application for scalable, automated, and robust processing in relation to high-precision GNSS, crowdsourcing at scale, and ML/DL. The developed proof-of-concept application running on Kubernetes consisted of various micro-services (ingestion service, middleware, monitoring service, S3-based data lake, GNSS processing layer, ML/DL processing layers) that were built with the use of custom images and by leveraging open-source packages.