Gerardo N. Pezzuti Cozzolino
Gerardo N. Pezzuti Cozzolino has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Anna Nora Tassetti
Institute for Marine Biological Resources and Biotechnology (IRBIM), National Research Council (CNR), Ancona, 60125, Italy
1 shared publication - Annalisa Minelli
Italian Institute for Environmental Protection and Research (ISPRA), Via Vitaliano Brancati, 48, 00144 Rome, Italy
1 shared publication - Briony Hutton
Echoview Software Pty Ltd., GPO Box 1387, Hobart, Tasmania 7001, Australia
1 shared publication - Gianna Fabi
National Research Council, Institute for Marine Biological Resources and Biotechnology (CNR-IRBIM), largo Fiera della Pesca 1, 60125 Ancona, Italy
1 shared publication - Toby Jarvis
Echoview Software Pty Ltd., GPO Box 1387, Hobart, Tasmania 7001, Australia
1 shared publication
Latest Publications
- Open Access
Semi-Automated Data Processing and Semi-Supervised Machine Learning for the Detection and Classification of Water-Column Fish Schools and Gas Seeps with a Multibeam Echosounder
Multibeam echosounders are widely used for 3D bathymetric mapping, and increasingly for water column studies. However, they rapidly collect huge volumes of data, which poses a challenge for water column data processing that is often still manual and time-consuming, or affected by low efficiency and high false detection rates if automated. This research describes a comprehensive and reproducible workflow that improves efficiency and reliability of target detection and classification, by calculating metrics for target cross-sections using a commercial software before feeding into a feature-based semi-supervised machine learning framework. The method is tested with data collected from an uncalibrated multibeam echosounder around an offshore gas platform in the Adriatic Sea. It resulted in more-efficient target detection, and, although uncertainties regarding user labelled training data need to be underlined, an accuracy of 98% in target classification was reached by using a final pre-trained stacking ensemble model.
Open AccessSemi-Automated Data Processing and Semi-Supervised Machine Learning for the Detection and Classification of Water-Column Fish Schools and Gas Seeps with a Multibeam Echosounder
Multibeam echosounders are widely used for 3D bathymetric mapping, and increasingly for water column studies. However, they rapidly collect huge volumes of data, which poses a challenge for water column data processing that is often still manual and time-consuming, or affected by low efficiency and high false detection rates if automated. This research describes a comprehensive and reproducible workflow that improves efficiency and reliability of target detection and classification, by calculating metrics for target cross-sections using a commercial software before feeding into a feature-based semi-supervised machine learning framework. The method is tested with data collected from an uncalibrated multibeam echosounder around an offshore gas platform in the Adriatic Sea. It resulted in more-efficient target detection, and, although uncertainties regarding user labelled training data need to be underlined, an accuracy of 98% in target classification was reached by using a final pre-trained stacking ensemble model.