Japanese information and telecommunication expert OKI has developed a ship classification AI system technology which automatically classifies ship types through deep learning of underwater sounds.
This technology makes it possible to continuously and automatically acquire ship classification data, even in environments such as busy ports with high ship traffic and at night, when visual identification using cameras is difficult.
Internal verification experiments by OKI have demonstrated that the system can classify ships with 90% or better accuracy, even with only small amounts of learning data extracted from ship sound data.
Drawing on its long history of research into underwater acoustic products, the company has developed systems that analyze the characteristics of sounds received by underwater microphones.
The newly developed technology uses AI deep learning to automatically classify ships based on their underwater sounds. This system technology creates deep learning models from sounds recorded by underwater microphones installed in the sea, then automatically classifies ships based on their frequency characteristics.
This allows the classification of ships without relying on human skill levels. Since it requires less human labour than before, it can also address the growing labour-saving demand in recent years.
Deep learning models typically require large amounts of learning data to accurately identify sound types. However, the amount of publicly available underwater sound data is limited.
This is solved by data augmentation which artificially creates variations for actual ship sound data, and semi-supervised learning, which trains the model using ship sound information from partial data. This way OKI’s solution enables classification through the use of only small amounts of learning data.
“Going forward, we will seek co-creation partners to gather field data and conduct practical verification with a view to commercializing this technology,” said Yoichi Kato, senior executive officer of OKI.
