Abstract: The present disclosure discloses a preparation method of an aluminum nitride (AlN) composite structure based on a two-dimensional (2D) crystal transition layer. The preparation method of the present disclosure includes: transferring the 2D crystal transition layer on a first periodic groove of an epitaxial substrate; forming a second periodic groove staggered with the first periodic groove on the 2D crystal transition layer; depositing a supporting protective layer; depositing a functional layer of a required AlN-based material; and removing the 2D crystal transition layer through thermal oxidation to obtain a semi-suspended AlN composite structure. The preparation method of the present disclosure has low difficulty and is suitable for large-scale industrial production.

Abstract: Disclosed is a ship image track tracking and prediction method based on ship heading recognition, which includes the following steps: obtaining a ship image data set, preprocessing the data set to obtain a preprocessed data set; inputting the preprocessed data set into the rotating ship detection network for training, obtaining the trained rotating ship detection network, collecting the ship navigation video, and inputting the ship navigation video into the trained rotating ship detection network to obtain the ship detection result; inputting the ship detection result into the rotating ship tracking network and tracking the target ship to obtain the historical trajectory and the heading information of the target ship; inputting the historical trajectory and ship heading information of the target ship into the ship trajectory and ship heading prediction network, and predicting the navigation trajectory and ship heading at sea.

Abstract: The present invention proposes an ensemble deep learning method for identifying unsafe behaviors of operators in maritime working environment. Firstly, extract features of maritime images with the You Only Look Once (YOLO) V3 model, and then enhance a multi-scale detection capability by introducing a feature pyramid structure. Secondly, obtain instance-level features and time memory features of the operators and devices in the maritime working environment with the Joint Learning of Detection and Embedding (JDE) paradigm. Thirdly, transfer spatial-temporal interaction information into a feature memory pool, and update the time memory features with the asynchronous memory updating algorithm. Finally, identify the interaction between the operators, the devices, and unsafe behaviors with an asynchronous interaction aggregation network. The proposed invention can accurately determine the unsafe behaviors of the operators, and thus provide operation decisions for maritime management relevant activities.

Abstract: The present invention proposes a vessel traffic pattern identification method via data quality control and data compression. Firstly, assort a collection of Automatic Identification system (AIS) data points according to Mobile Service Identify (MMSI) code and sort each collection result by time ascending order, and then delete duplicated vessel AIS data points considering time stamp, latitude, longitude and vessel speed over ground, then segment vessel trajectories. Secondly obtain high-quality AIS data with an AIS data anomaly detection and repair and compress each vessel trajectory with the Douglas-Peucker algorithm. Thirdly, cluster vessel trajectories with the Quick Bundles algorithm, and identify maritime traffic pattern. The invention can efficiently identify vessel traffic patterns, and help maritime traffic management departments to accurately identify a traffic situation.