Decision Making for Improving Maritime Traffic Safety Using Constraint Programming

Authors: Saumya Bhatnagar, Akshat Kumar, Hoong Chuin Lau

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct a thorough evaluation on key performance indicators using real world data, and demonstrate the effectiveness of our approach in mitigating high-risk situations.
Researcher Affiliation Collaboration School of Information Systems, Singapore Management University {saumyab, akshatkumar, hclau}@smu.edu.sg; This research is supported by the Agency for Science, Technology and Research (A*STAR), Fujitsu Limited and the National Research Foundation Singapore as part of the A*STAR-Fujitsu SMU Urban Computing and Engineering Centre of Excellence.
Pseudocode No Not found. The paper describes its CP model using mathematical formulations and constraints in Table 2, but does not present pseudocode or a distinct algorithm block.
Open Source Code No Not found. The paper provides a link to supplemental material for parameters and DCPA computation but does not state that the source code for their methodology is publicly available.
Open Datasets No We use a 4-month vessel dataset of Singapore Straits and Port Waters. Each file contains information of 2700-3500 unique vessels and around 16 million records on average.
Dataset Splits No Not found. The paper describes its evaluation on 64 instances but does not provide details on training, validation, or test dataset splits in the context of model development.
Hardware Specification No Not found. The paper mentions using 'IBM ILOG CP Optimizer' but does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No Not found. The paper mentions 'IBM ILOG CP Optimizer' but does not provide a specific version number for this or any other software dependency.
Experiment Setup Yes Configurable hyperparameters. We set different configurable parameters of our model (used in Table 2) after analyzing the data. More details about them are in the supplemental material. We set CP optimizer s maximum allowed runtime to 10 minutes.