Classification of Ship-Based Automatic Identification Systems Using K-Nearest Neighbors

Damastuti, Natalia; Aisjah, Aulia Siti; Masroeri, Agoes A.

doi:10.1109/isemantic.2019.8884328

Cited by 11 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Feature extraction and classification are two main tasks for the studies on ships AIS data (Sheng et al, 2018). A lot of classification tasks are often conducted by using traditional supervised learning algorithms such as support vector machines (Lang et al, 2018), decision tree (Krüger, 2018;Chen et al, 2018), k-nearest neighbour algorithm (Damastuti et al, 2019), random forest (Zhang et al, 2020a) etc. and the feature extraction is a significant research question due to various application aims.…”

Section: Ship Movement Classification Based On Ais Datamentioning

confidence: 99%

A semi-supervised deep learning model for ship encounter situation classification

et al. 2021

View full text Add to dashboard Cite

Section: Ship Movement Classification Based On Ais Datamentioning

confidence: 99%

A semi-supervised deep learning model for ship encounter situation classification

et al. 2021

View full text Add to dashboard Cite

“…Penelitian berikutnya membahas tentang klasifikasi jenis kapal berdasarkan data DWT, width dan length menggunakan metode K-Nearest Neeighbour (KNN). Sebagai perbandingan, proses klasifikasi data juga diuji menggunakan metode Neighbour Component Analysis KNN (NCA-KNN), dimana hasilnya metode NCA-KNN memiliki akurasi yang lebih baik dibandingkan metode KNN asli [7].…”

Section: Pendahuluanunclassified

Rancang Bangun Aplikasi AIS Backend Untuk Pemantauan Lalu Lintas Kapal di Selat Melaka

Enda¹,

Agustiawan²,

Milchan

et al. 2021

ISI

View full text Add to dashboard Cite

The Malacca Strait is the second busiest strait in the world, where about 80,000 ships pass each year. As an Indonesian territory which is directly adjacent to the southern side of the Malacca Strait, Bengkalis district has an important role in monitoring and surveillance activities in the waters of the Melaka Straits. To achieve this, a monitoring system is needed that can monitor ship traffic passing through the waters of the Malacca Strait. As a system that can capture the signals of ships crossing the Melacca Strait, Automatic Identification System (AIS) is one solution that can be used to carry out ship traffic monitoring activities. This research focuses on the design of a backend application for realtime monitoring of ship traffic in the waters of the Malacca Strait based on AIS. The built backend application functions as a data processing service provider and RESTful API. The performance of the built application is measured based on the efficiency aspect of data storage using the data filtering algorithm that has been designed. Where by applying the data filtering algorithm, the efficiency of using data storage in the database is 18.45%.

show abstract

“…For static information, Damastuti et al [9] use KNN (K-NearestNeighbor) to classify ships based on tonnage, length, and width in Indonesian waters and achieved an accuracy of up to 0.83 on six categories. Zhong et al [10] use Random Forest for static information and achieve an accuracy of 0.865 on a three-classification task.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Feature Ensemble Learning Classification Method for Ship Classification with Space-Based AIS Data

et al. 2021

View full text Add to dashboard Cite

AIS (Automatic Identification System) is an effective navigation aid system aimed to realize ship monitoring and collision avoidance. Space-based AIS data, which are received by satellites, have become a popular and promising approach for providing ship information around the world. To recognize the types of ships from the massive space-based AIS data, we propose a multi-feature ensemble learning classification model (MFELCM). The method consists of three steps. Firstly, the static and dynamic information of the original data is preprocessed and features are then extracted in order to obtain static feature samples, dynamic feature distribution samples, time-series samples, and time-series feature samples. Secondly, four base classifiers, namely Random Forest, 1D-CNN (one-dimensional convolutional neural network), Bi-GRU (bidirectional gated recurrent unit), and XGBoost (extreme gradient boosting), are trained by the above four types of samples, respectively. Finally, the base classifiers are integrated by another Random Forest, and the final ship classification is outputted. In this paper, we use the global space-based AIS data of passenger ships, cargo ships, fishing boats, and tankers. The model gets a total accuracy of 0.9010 and an F1 score of 0.9019. The experiments prove that MFELCM is better than the base classifiers. In addition, MFELCM can achieve near real-time online classification, which has important applications in ship behavior anomaly detection and maritime supervision.

show abstract

Classification of Ship-Based Automatic Identification Systems Using K-Nearest Neighbors

Cited by 11 publications

References 4 publications

A semi-supervised deep learning model for ship encounter situation classification

A semi-supervised deep learning model for ship encounter situation classification

Rancang Bangun Aplikasi AIS Backend Untuk Pemantauan Lalu Lintas Kapal di Selat Melaka

A Multi-Feature Ensemble Learning Classification Method for Ship Classification with Space-Based AIS Data

Contact Info

Product

Resources

About