Deep Learning for Deep Water: Robust classification of ship wakes with expert in the loop
| RYAZANOV, Igor | ||
| Göteborgs universitet/Institutionen för data- och informationsteknik | swe | |
| University of Gothenburg/Department of Computer Science and Engineering | eng | |
| 2020-10-06T06:55:32Z | ||
| 2020-10-06T06:55:32Z | ||
| 2020-10-06 | ||
| This work examines the applicability of the deep learning models to pattern recognition in acoustic ocean data. The features of the dataset include noise, data scarcity and the lack of labeled samples. A deep learning model is proposed for the task of automatic wake detection. It takes advantage of the availability of an expert in the marine science domain while using data generation and robustness techniques to enhance performance. The model shows encouraging results, although its performance decreases with heavily unbalanced data and the introduction of noise. | sv | |
| http://hdl.handle.net/2077/66646 | ||
| eng | sv | |
| Technology | ||
| machine learning | sv | |
| deep learning | sv | |
| pattern recognition | sv | |
| acoustic data analysis | sv | |
| shipping data | sv | |
| data augmentation | sv | |
| noise robustness | sv | |
| classification with data imbalance | sv | |
| expert-in-the-loop framework | sv | |
| Deep Learning for Deep Water: Robust classification of ship wakes with expert in the loop | sv | |
| Deep Learning for Deep Water: Robust classification of ship wakes with expert in the loop | sv | |
| text | ||
| Student essay | ||
| H2 |