Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Lower-neck involvement and post-concurrent chemoradiotherapy response predict distant metastasis in head and neck cancer.

Radiation oncology journal·2026

Same author

Generation of Functional Oligodendrocyte Progenitor Cells Through Serial Replating of iPSC-Derived NPC Spheres.

Cells·2026

Same author

Habitual Ultra-processed Food Intake Is Associated with Gut Dysbiosis and Pro-inflammatory Metabolite Profiles in Korean Patients with IBD.

Digestive diseases and sciences·2026

Same author

Population Pharmacokinetics and Model-Informed Precision Dosing of Lenalidomide Incorporating Total and Unbound Plasma Concentrations in Renally Impaired Patients with Multiple Myeloma.

Drug design, development and therapy·2026

Same author

Advancing Small-Molecule Immunotherapy Through Polymeric Micelle Delivery.

Pharmaceutics·2026

Same author

Korean Medical Consultation With Open-Weight Large Language Models: Pilot Comparative Evaluation of Retrieval-Augmented Generation With Metadata Filtering.

JMIR formative research·2026

Search research articles

Related Experiment Video

Updated: Oct 25, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

Explainable Anomaly Detection Framework for Maritime Main Engine Sensor Data.

Donghyun Kim¹, Gian Antariksa², Melia Putri Handayani²

¹Korea Marine Equipment Research Institute, Busan 49111, Korea.

Sensors (Basel, Switzerland)

|August 10, 2021

Summary

This summary is machine-generated.

This study introduces an explainable AI approach for marine engine condition monitoring. By using Shapley Additive exPlanations (SHAP), it clarifies the causes of detected anomalies, improving upon existing methods.

Keywords:

SHAP Shapley Additive exPlanations anomaly detection clustering explainable AI isolation forest marine engine onboard sensors

More Related Videos

A Cross-Disciplinary and Multi-Modal Experimental Design for Studying Near-Real-Time Authentic Examination Experiences

A Cross-Disciplinary and Multi-Modal Experimental Design for Studying Near-Real-Time Authentic Examination Experiences

Published on: September 4, 2019

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

Related Experiment Videos

Last Updated: Oct 25, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

A Cross-Disciplinary and Multi-Modal Experimental Design for Studying Near-Real-Time Authentic Examination Experiences

A Cross-Disciplinary and Multi-Modal Experimental Design for Studying Near-Real-Time Authentic Examination Experiences

Published on: September 4, 2019

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

Area of Science:

Marine Engineering
Artificial Intelligence
Data Science

Background:

Unsupervised anomaly detection in marine engines lacks interpretability.
Existing methods cannot explain why specific data points are flagged as anomalies.
Interpreting anomalies is crucial for effective condition monitoring.

Purpose of the Study:

To develop a data-driven approach for marine engine condition monitoring.
To integrate explainable AI (XAI) with anomaly detection for enhanced interpretability.
To address the limitation of unexplained anomalies in current maritime industry methods.

Main Methods:

Proposed a novel framework combining anomaly detection with explainable AI (XAI).
Utilized Shapley Additive exPlanations (SHAP) for quantifying sensor variable contributions to anomalies.
Applied hierarchical clustering on transformed SHAP values to identify and group anomaly patterns.

Main Results:

Demonstrated that SHAP values effectively identify specific sensor variables responsible for anomalies.
Successfully interpreted and segmented common anomaly patterns using SHAP-based hierarchical clustering.
Showcased superior anomaly interpretation and segmentation compared to non-SHAP methods.

Conclusions:

The proposed SHAP-integrated framework significantly enhances the interpretability of marine engine condition monitoring.
Explainable AI provides actionable insights into anomaly causes, enabling better maintenance decisions.
This approach offers a more transparent and reliable method for detecting and understanding engine anomalies.