This story was originally published on HackerNoon at: https://hackernoon.com/real-time-anomaly-detection-in-underwater-gliders-experimental-evaluation.
This paper presents a real-time anomaly detection algorithm to enhance underwater glider safety using datasets from actual deployments.
Check more stories related to data-science at: https://hackernoon.com/c/data-science.
You can also check exclusive content about #data-analysis, #machine-learning, #underwater-gliders, #anomaly-detection, #oceanography, #glider-navigation, #ocean-data, #marine-robotics, and more.


This story was written by: @oceanography. Learn more about this writer by checking @oceanography's about page,
and for more stories, please visit hackernoon.com.



We apply the anomaly detection algorithm to four glider deployments across the coastal ocean of Florida and Georgia, USA. For evaluation, the anomaly detected by the algorithm is cross-validated by high-resolution glider DBD data and pilot notes. We simulate the online detection process on SBD and compare the result with that detected from DBD.

Ver todos los episodios