A close contact identification algorithm using kernel density estimation for the ship passenger health

Area of Science:

• Epidemiology
• Data Science
• Maritime Health

Background:

• Global spread of COVID-19 presents unique challenges in ship environments.
• Effective containment relies on identifying and isolating close contacts.
• Existing contact tracing methods may be insufficient in confined spaces.

Purpose of the Study:

• To propose a novel algorithm for identifying close contacts in ship environments.
• To enhance the accuracy of contact tracing for infectious disease control on vessels.
• To leverage location data for improved public health interventions in maritime settings.

Main Methods:

• Development of the Close Contact Identification Algorithm (CCIA).
• Utilizing Kernel Density Estimation (KDE) to calculate location point probability density.
• Employing maximum Euclidean distance for cluster merging and analysis.

Main Results:

• CCIA demonstrates superior clustering accuracy compared to Kmeans, Hierarchical, and DBSCAN.
• The algorithm effectively identifies close contacts by analyzing probability density of location points.
• CCIA enhances the capability of user devices for COVID-19 mitigation on ships.

Conclusions:

• CCIA offers a more accurate method for close contact identification in ship environments.
• The algorithm's unique approach using probability density improves upon traditional clustering methods.
• CCIA can significantly contribute to mitigating the spread of COVID-19 in maritime settings.