The main dimensions data is an important technical parameter that affects the performance of yachts, and it is an important task in the preliminary design stage to determine those values by statistically revealing the relations between the main scales of yachts. Establishing formulas between the main dimensions of yachts through regression analysis is a traditional solution. As an ensemble learning algorithm, the Random Forest algorithm is more suitable for learning the features in the sample data of the main dimensions of yachts and provides better prediction results. On this study, we analysed the distribution pattern of the collected main dimension data of yachts, and use the Spearman's rank correlation to calculate the correlation between different dimensions of the yacht data, generating correlation coefficient matrix, and employ multiple linear regression and box plot methods to identify outliers in the data, thereby enhancing data usability. The Random Forest algorithm (RF) is used to predict the draft and weight of yachts based on length and width. At the same time, the BP neural network algorithm is used to compare the performance of RF. The results show that the Random Forest algorithm can effectively improve the accuracy of main dimension prediction.

Liu Yangbing, Sun Chengmeng, Lin Haihua. Prediction of the main dimensions of yachts based on random forest. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 7: 123-130. https://doi.org/10.25236/AJCIS.2024.070716.

[1] Bülent İbrahim Turan and Mehmet Akman. Practical Design Framework for Lobster-Type Motor Yachts[J]. Journal of ETA Maritime Science, 2023, 11(4) : 282-289.

[2] Tomasz Cepowski. Determination of regression formulas for main tanker dimensions at the preliminary design stage[J]. Ships and Offshore Structures, 2019, 14(3) : 320-330.

[3] Tomasz Abramowski and Tomasz Cepowski and Peter Zvolenský. Determination of Regression Formulas for Key Design Characteristics of Container Ships at Preliminary Design Stage[J]. New Trends in Production Engineering, 2018, 1(1) : 247-257.

[4] Radojcic D V, Zgradic A B, Kalajdzic M D, et al. Resistance and Trim Modeling of a Systematic Planing Hull Series 62 (with 12.5°, 25°, and 30° Deadrise Angles) Using Artificial Neural Networks, Part 1: The Database[J]. Journal of Ship Production and Design, The Society of Naval Architects and Marine Engineers, 2017, 33(03): 179–191.

[5] Radojcic D V, Kalajdzic M D, Zgradic A B, et al. Resistance and Trim Modeling of a Systematic Planing Hull Series 62 (with 12.5°, 25°, and 30° Deadrise Angles) Using Artificial Neural Networks, Part 2: Mathematical Models[J]. Journal of Ship Production and Design, The Society of Naval Architects and Marine Engineers, 2017, 33(04): 257–275.

[6] Bertram and Mesbahi. Simple Design Formulae for Fast Monohulls[J]. Ship Technology Research, 2004, 51(3) : 146-148.

[7] Romero-Tello P. and Guti..rrez-Romero J.E. and Serv..n-Camas B.. Prediction of seakeeping in the early stage of conventional monohull vessels design using artificial neural network[J]. Journal of Ocean Engineering and Science, 2023, 8(4) : 344-366.

[8] Liu Yang, Zhang Mingxia, Zhao Yuhao. Regression Model for Principal Dimensions of Bulk Carriers Based on New IMO Regulations [J]. Ship & Boat, 2013, 24(04): 78-81.

[9] Liu Fei, Lin Yan, Li Na, et al. Research on Principal Dimension Models of Marine Surveillance Ships and Fishery Administration Ships [J]. Ship Science and Technology, 2012, 34(07): 49-54.

[10] Li Hongwei, Guan Guan. Analysis of Principal Dimensions of Marine Law Enforcement Vessels Based on Multiple Regression Methods [J]. Ship Standardization Engineer, 2020, 53(03): 55-58.

[11] Zhang Qiuping, Jin Tingyu, Yao Wen, et al. Statistical Analysis of Principal Dimension Elements of Asphalt Carriers [J]. China Ship Repair, 2022, 35(05): 59-62, 72.

[12] Guan Guan, Zheng Mengtian, Ji Zhuoshang. Research on the Application of Big Data Technology in Determining the Principal Dimensions of Ships [J]. Applied Science and Technology, 2018, 45(02): 1-5.

[13] Breiman L. Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)[J]. Statistical Science, Institute of Mathematical Statistics, 2001, 16(3).

[14] H. Rong and A.P. Teixeira and C. Guedes Soares. A framework for ship abnormal behaviour detection and classification using AIS data[J]. Reliability Engineering and System Safety, 2024, 247 : 110-105.

[15] Ran X L ,Qiu T L ,Ping Z W .Rapid prediction of damaged ship roll motion responses in beam waves based on stacking algorithm[J].Journal of Hydrodynamics,2024,36(2):394-405.

[16] Zhou Yi et al. Predicting ship fuel consumption using a combination of metocean and on-board data[J]. Ocean Engineering, 2023, 285(P2)

[17] N. Li et al. SHIP DETECTION BASED ON MULTIPLE FEATURES IN RANDOM FOREST MODEL FOR HYPERSPECTRAL IMAGES[J]. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2018, XLII-3 : 891-895.

[18] Zhang Mingxia, Zhao Tongming, Wang Siyi. Application Research of Random Forest Method in Selection of Prototype Ship Types [J]. Applied Science and Technology, 2023, 50(05): 126-132, 174.

[19] Jiefang Jiang and Xianyong Zhang and Zhong Yuan. Feature selection for classification with Spearman’s rank correlation coefficient-based self-information in divergence-based fuzzy rough sets[J]. Expert Systems With Applications, 2024, 249(PB) : 123633-

[20] Guanqiao Wang and Heng Zhou and Bohang Lin. Evaluation of Carbon Emissions Redcution Performance Based on TOPSIS and K-Means Clustering Algorithm[J]. Academic Journal of Computing & Information Science, 2023, 6(7)