Afrioni Roma Rio, Berton Maruli Siahaan

PREDIKSI JARAK TEMPUH KAPAL MOTOR SANGIANG MENGGUNAKAN SUPERVISED MACHINE LEARNING

Introduction

Prediksi jarak tempuh kapal motor sangiang menggunakan supervised machine learning. Prediksi jarak tempuh harian kapal motor Sangiang di Indonesia (Bitung-Ternate). Studi ini memakai supervised machine learning dengan multiple regression untuk akurasi tinggi.

Abstract

As a maritime nation with thousands of islands and a vast sea area, sea transportation is the most effective transportation used by the people of Indonesia. A motorboat is one type of maritime transportation that is used to move people or commodities. In this article, we will discuss predicting the daily mileage of one of the motorboats, the Sangiang, which travels from Bitung to Ternate. Three independent variables, Anchor Time (minutes), Speed (knots/hour), and Sailing Time (minutes), are used in supervised machine learning techniques to estimate the daily mileage (mile). Of the various methods evaluated, the multiple regression model was found to be the most accurate at forecasting the Sangiang motorboat’s daily mileage.

Review

The article, "PREDIKSI JARAK TEMPUH KAPAL MOTOR SANGIANG MENGGUNAKAN SUPERVISED MACHINE LEARNING," addresses a highly relevant topic, particularly for a maritime nation like Indonesia where sea transportation is crucial for inter-island connectivity and economic activity. The study focuses on the practical problem of predicting the daily mileage of a specific motorboat, the Sangiang, operating on the Bitung-Ternate route. This focus on a real-world scenario and a specific vessel demonstrates a tangible application of data-driven methods, which is commendable. The adoption of supervised machine learning techniques to tackle this predictive challenge immediately positions the research within contemporary analytical approaches. The methodological approach outlines the use of supervised machine learning, employing three clearly defined independent variables: Anchor Time (minutes), Speed (knots/hour), and Sailing Time (minutes), to predict daily mileage (miles). These input variables appear intuitively sound and directly related to a vessel's travel performance. A key strength highlighted is the evaluation of various machine learning methods, ultimately identifying multiple regression as the most accurate model for forecasting the Sangiang motorboat’s daily mileage. While the abstract does not detail the *other* methods considered, this comparative evaluation is an important aspect of robust model selection. Future readers would likely benefit from a brief discussion in the full paper of why multiple regression, a more traditional statistical approach, outperformed potentially more complex machine learning algorithms in this specific application, perhaps related to data characteristics or model interpretability. The findings of this study, particularly the identification of an accurate predictive model for daily mileage, hold significant practical implications. Such a model could greatly assist in operational planning, logistical optimization, fuel consumption forecasting, and potentially even maintenance scheduling for the Sangiang motorboat and similar vessels. This contributes directly to improving efficiency and reducing operational costs within Indonesia's maritime sector. Overall, the research presents a valuable contribution by applying a data-driven methodology to a critical operational challenge in sea transportation, making it a relevant and potentially impactful piece of work for maritime logistics and data science practitioners alike.

Full Text

Comments

You need to be logged in to post a comment.