Abstract
Low quality automatic identification system (AIS) data often mislead analysts to a misunderstanding of ship behavior analysis and to making incorrect navigation risk assessments. It is therefore necessary to accurately understand and judge the quality problems in AIS data before a further analysis of ship behavior. Outliers were filtered in the existing methods of AIS quality analysis based only on mathematical models where AIS data related quality problems are not utilized and there is a lack of visual exploration. Thus, the human brain’s ability cannot be fully utilized to think visually and for reasoning. In this regard, a visual analytics (VA) approach called AIS Data Quality visualization (ADQvis) was designed and implemented here to support evaluations and explorations of AIS data quality. The system interface is overviewed and then the visualization model and corresponding human-computer interaction method are described in detail. Finally, case studies were carried out to demonstrate the effectiveness of our visual analytics approach for AIS quality problems.
Highlights
Automatic identification system (AIS) data are a primary source for maritime supervision and analysis of ship behaviors and they are significant for the research of waterway traffic laws and trends whose accuracy and reliability directly affect the analysis results.the raw AIS data usually have a few quality problems such as invalid data, errors, values missing, abnormal values and duplicate records due to the communication link, channel interference and human tampering on AIS equipment, which are called “dirty”data
As parallel coordinates can represent the hidden relationships of various dimensions in highdimensional data, they were applied in network security anomaly detection [30] and the results indicated that this method could detect network risks in time
According to the visualization of distance in the scatter plot, the data quality problems were of all, the differential distance was calculated from the raw data and displayed in a scatter identified and their spatiotemporal distribution was displayed on the OSM by interacting plot
Summary
Wei He 1,3,4 , Jinyu Lei 2,3,4, *, Xiumin Chu 1,2,3,4 , Shuo Xie 2 , Cheng Zhong 2 and Zhixiong Li 5. Engineering Research Center of Fujian University for Marine Intelligent Ship Equipment, College of Physics and Electronic Information Engineering, Minjiang University, Fuzhou 350108, China
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have