Date of Award


Degree Type

Open Access Dissertation

Degree Name

Engineering and Industrial Applied Mathematics Joint PhD with California State University Long Beach, PhD


Institute of Mathematical Sciences

Advisor/Supervisor/Committee Chair

Tang-Hung Nguyen

Dissertation or Thesis Committee Member

Marina Chugunova

Dissertation or Thesis Committee Member

Elhami Nasr

Dissertation or Thesis Committee Member

Ali Nadim

Terms of Use & License Information

Terms of Use for work posted in Scholarship@Claremont.

Rights Information

© 2019 Abdulrahman M Alansari


case based reasoning, marine construction projects, risk assessment, risk factors

Subject Categories



Marine-construction projects are becoming increasingly important for the development of the maritime industry. However, such increases are hampered by various risks that can significantly impact growth. Natural forces, political events, administrative and operational mistakes, equipment failures, external attacks such as arson, and economic events are some of the major risks faced by firms in this industry. Researchers have paid little attention on marine- construction risk assessment, despite the importance of such research.

This study sought to develop a generic risk-levels predictor framework, using the integrated definition function model (IDEF0) and the case-based reasoning approach (CBR), to predict levels of risk associated with a new marine-construction project. This framework can be developed through the following three phases: (a) Cases collection: previous marine-construction projects (cases) were investigated for identification, classification, and evaluation of risk factors and triggers, (b) Cases classification: the cases were organized and stored in a marine construction database (MCDB) and compiled into risk-triggers and risk-levels data for each case, (c) Cases reasoning: using the information from previous phases, when risk-triggers data for a new case is entered into a system knowledge database (i.e., a temporary database that keeps the new risks triggers and proposes prediction data for further knowledge and validation) looking for risk-levels prediction, the system searches into the MCDB for known risk-triggers that are similar to the new case. The similar cases are retrieved, and their risk-levels data are used to propose a risk -levels prediction for the new case. Finally, when the proposed prediction is revised and approved by users, the risk-triggers and risk-levels prediction data for the new case are stored in the system knowledge database for further learning. The implementation of the proposed risk-level predictor framework (RLPF) was tested in this study on 10 hypothetical marine construction projects conducted in Saudi Arabia.

The automated systematic approach—the RLPF proposed in this study—can address specific and time-urgent decisions invariably and accurately. Future researchers should use the RLPF to gain knowledge on risk aspects in marine construction projects.



Included in

Engineering Commons