Labour Exploitation Investigation using Satellite based Vessel Monitoring Systems

Abstract

Taiwan is one of the most extensive distant water fishing (DWF) and has more than 1,000 ships producing 40 billion N.T. dollars. More than 90% of Taiwanese fishermen are recruited from Indonesia, the Philippines, and Vietnam. However, labour exploitation has become a severe problem in the Taiwan distant water fishing (DWF) industry. The Taiwan government recently amended the law and stipulated that multiple CCTV cameras be installed on DWF vessels to protect against labour abuse. Current technology only records videos captured by CCTV cameras. Thus, detecting labour abuse is nearly impossible. To resolve this problem, we have developed a deep neural network model to predict labour abuse in DWF. The developed model uses satellite-based vessel monitoring systems data for the predictions of labour abuse. The proposed deep neural network model gives better prediction than logistic regression, support vector machine, Random Forest and decision tree.