Perbandingan Skor Prediksi dalam Pembelajaran Mesin pada Keselamatan Penumpang Kapal
Comparison of Prediction Scores in Machine Learning on Ship Passenger Safety
Abstract
Passenger safety is an important aspect of the shipping industry, and precise predictions of emergencies and safety situations can provide great advantages in managing risks at sea. Precise prediction of emergency and safety situations can provide great advantages in managing risks at sea. This research involves collecting and analyzing historical data on ship accident incidents and their influencing factors. Machine learning methods, such as logistic regression, KNN, Naïve Bayes Classifier, Decision Tree, Random Forest, etc. will be used to identify patterns in the data that can be used to predict ship passenger safety. The data used in this study includes variables such as weather, ship state, number of passengers, and other relevant factors. The research data was taken from titanic passengers. The results of this study resulted in a model that is suitable for predicting the safety of ship passengers, namely the random forest model and decision tree getting the highest score compared to other models, the prediction score is 84.29%.
References
Ashenden, S. K. (2021). The era of artificial intelligence, machine learning, and data science in the pharmaceutical industry. Academic Press.
de Souza, G. F. M., Caminada Netto, A., de Andrade Melani, A. H., de Carvalho Michalski, M. A., & da Silva, R. F. (2022). Chapter 6 - Engineering systems’ fault diagnosis methods. In G. F. M. de Souza, A. Caminada Netto, A. H. de Andrade Melani, M. A. de Carvalho Michalski, & R. F. da Silva (Eds.), Reliability Analysis and Asset Management of Engineering Systems (pp. 165–187). Elsevier. https://doi.org/https://doi.org/10.1016/B978-0-12-823521-8.00006-2
Kakde, Y., & Agrawal, S. (2018). Predicting survival on Titanic by applying exploratory data analytics and machine learning techniques. International Journal of Computer Applications, 179(44), 32–38.
Kenyhercz, M. W., & Passalacqua, N. V. (2016). Missing data imputation methods and their performance with biodistance analyses. In Biological Distance Analysis (pp. 181–194). Elsevier.
Mosavi, A., Ozturk, P., & Chau, K. (2018). Flood prediction using machine learning models: Literature review. Water, 10(11), 1536.
Pratiwi, N., & Setyawan, Y. (2021). Analisis Akurasi dari Perbedaan Fungsi Kernel dan Cost Pada Support Vector Machine Studi Kasus Klasifikasi Curah Hujan di Jakarta. Journal of Fundamental Mathematics and Applications (JFMA), 4(2), 203–212.
Rahmanita, M., Ricardianto, P., Wijayanti, R., Agusinta, L., Asmaniati, F., Djati, S., Tatiana, Y., Arafah, W., Amsyari, I., & Endri, E. (2023). The impact of the safety of passenger ship services on the development of water recreation: evidence from Indonesia. Uncertain Supply Chain Management, 11(3), 1121–1132.
Sanni, S. E., Okoro, E. E., Sadiku, E. R., & Oni, B. A. (2022). Advances in data-centric intelligent systems for air quality monitoring, assessment, and control. In Current Trends and Advances in Computer-Aided Intelligent Environmental Data Engineering (pp. 25–58). Elsevier.
Sarker, I. H. (2021). Machine learning: Algorithms, real-world applications and research directions. SN Computer Science, 2(3), 160.
Sharma, A. (2018). Guided stochastic gradient descent algorithm for inconsistent datasets. Applied Soft Computing, 73, 1068–1080.
Singh, A., Saraswat, S., & Faujdar, N. (2017). Analyzing Titanic disaster using machine learning algorithms. 2017 International Conference on Computing, Communication and Automation (ICCCA), 406–411.
Singh, J., Singh, J., Singh, G., & Kaur, N. (2022). Exploratory Data Analysis for Interpreting Model Prediction using Python. 2022 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), 1–6.
Tipping, M. (1999). The relevance vector machine. Advances in Neural Information Processing Systems, 12.
