The Electronic Journal of e-Government publishes perspectives on topics relevant to the study, implementation and management of e-Government

For general enquiries email

Click here to see other Scholarly Electronic Journals published by API
For a range of research text books on this and complimentary topics visit the Academic Bookshop

Journal Article

E‑government Information Application: Identifying Smuggling Vessels with Data mining Technology  pp47-58

Chih-Hao Wena, Ping-Yu Hsu, Chung-Yung Wang, Tai-Long Wuc, Ming-Jia Hsu

© Oct 2012 Volume 10 Issue 1, Editor: Frank Bannister, pp1 - 94

Look inside Download PDF (free)


In spite of the gradual increase in the number of academic studies on smuggling crime, focus is seldom placed on the application of data mining to crime prevention. This study provides deeper understanding and exploration of the benefits of information technology for the identification of smuggling crime. This study focuses on smuggling of vessels. The data source is the complete record of fishing vessels leaving and returning to ports in the Taiwan region. This paper essay applies both artificial neural networks (ANN) and logistics regression (LR) to classify and predict criminal behaviors in smuggling. At the same time, it shows the difference between ANN and human inspection (HI), also the difference between LR and HI. This study establishes models for vessels of different tonnage and operation purposes that can provide law enforcers with clearer judgment criteria. It is needed to construct different models for vessels to achieve the actual cases in the reality since smugglers will use different kinds of ship for different smuggling purposes. The study results show that the application of artificial neural networks to smuggling fishing vessels attains an average precision of 76.3%, and the application of logistic regression to smuggling fishing vessels can achieve an average precision of 60.5%, both of which are of significantly higher efficiency levels compared with the current human inspection (HI) method. This study suggests the value of using an artificial neural networks model to obtain good identification performance for different vessel types as well as average savings of 90.47% on the manpower loading. Information technology can greatly help to increase the probability of seizing smuggling fishing vessels. Nowadays, public administration information is saved electronically however is not employed well. In fact, it can increase the administrative efficiency by proper use of electronic data. In this study, for example, we expect better use of the data stored in the database to establish an identifying model of smuggling. Applying the automatic identification mechanism, it is useful to reduce the probability of smuggling crime.


Keywords: government information application, Crime data mining, smuggling predictions, artificial neural networks, logistic regression.


Share |