Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation
Ensuring the normal operation of mechanical equipment is crucial in marine transportation, as data anomalies in these systems can lead to serious safety incidents, environmental pollution, and economic losses. To improve the accuracy and efficiency of anomaly detection in ship equipment data, a long...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10856011/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859645288022016 |
|---|---|
| author | Zhan Wang Mwamba Kasongo Dahouda Hyoseong Hwang Inwhee Joe |
| author_facet | Zhan Wang Mwamba Kasongo Dahouda Hyoseong Hwang Inwhee Joe |
| author_sort | Zhan Wang |
| collection | DOAJ |
| description | Ensuring the normal operation of mechanical equipment is crucial in marine transportation, as data anomalies in these systems can lead to serious safety incidents, environmental pollution, and economic losses. To improve the accuracy and efficiency of anomaly detection in ship equipment data, a long-short-term memory auto-encoder model (LSTM-AE) has been developed, tailored for time-series anomaly detection. The normal behavior patterns of key metrics, such as temperature, pressure, and rotational speed, are learned and captured by this model, enabling abnormal states in these metrics to be accurately identified. The approach is based on the encoder in the long-short-term memory (LSTM) network, where input time-series data is converted into a lower-dimensional, implicit representation, and an attempt is made to reconstruct the original input data via a decoder. Trained exclusively on anomaly-free data, the model ensures a low reconstruction error on normal data. However, when input data that significantly deviates from the training set is encountered, a high reconstruction error is produced, thereby allowing potential anomalies to be flagged. To enhance the interpretability of the results, explainable artificial intelligence (XAI) techniques are incorporated, specifically shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME), to identify which features have the most impact on detected anomalies. The LSTM-AE model shows superior performance compared to other data generation models such as GAN and diffusion models, which have accuracy issues and require high computational cost. In addition, the integration of XAI methods has advantages in the interpretation of the results, solving the problem that these existing methods often lack transparency. |
| format | Article |
| id | doaj-art-cfa9ac394c9f4552b843c9bdbbd44972 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-cfa9ac394c9f4552b843c9bdbbd449722025-02-11T00:00:51ZengIEEEIEEE Access2169-35362025-01-0113231952320810.1109/ACCESS.2025.353569510856011Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine TransportationZhan Wang0https://orcid.org/0000-0002-3193-8208Mwamba Kasongo Dahouda1Hyoseong Hwang2https://orcid.org/0009-0002-9201-6159Inwhee Joe3https://orcid.org/0000-0002-8435-0395Department of Computer Science, Hanyang University, Seoul, South KoreaDepartment of Computer Science, Hanyang University, Seoul, South KoreaHyundai Company, Seoul, South KoreaDepartment of Computer Science, Hanyang University, Seoul, South KoreaEnsuring the normal operation of mechanical equipment is crucial in marine transportation, as data anomalies in these systems can lead to serious safety incidents, environmental pollution, and economic losses. To improve the accuracy and efficiency of anomaly detection in ship equipment data, a long-short-term memory auto-encoder model (LSTM-AE) has been developed, tailored for time-series anomaly detection. The normal behavior patterns of key metrics, such as temperature, pressure, and rotational speed, are learned and captured by this model, enabling abnormal states in these metrics to be accurately identified. The approach is based on the encoder in the long-short-term memory (LSTM) network, where input time-series data is converted into a lower-dimensional, implicit representation, and an attempt is made to reconstruct the original input data via a decoder. Trained exclusively on anomaly-free data, the model ensures a low reconstruction error on normal data. However, when input data that significantly deviates from the training set is encountered, a high reconstruction error is produced, thereby allowing potential anomalies to be flagged. To enhance the interpretability of the results, explainable artificial intelligence (XAI) techniques are incorporated, specifically shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME), to identify which features have the most impact on detected anomalies. The LSTM-AE model shows superior performance compared to other data generation models such as GAN and diffusion models, which have accuracy issues and require high computational cost. In addition, the integration of XAI methods has advantages in the interpretation of the results, solving the problem that these existing methods often lack transparency.https://ieeexplore.ieee.org/document/10856011/Long short-term memory auto-encoderanomaly detectiontime series datainterpretation |
| spellingShingle | Zhan Wang Mwamba Kasongo Dahouda Hyoseong Hwang Inwhee Joe Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation IEEE Access Long short-term memory auto-encoder anomaly detection time series data interpretation |
| title | Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation |
| title_full | Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation |
| title_fullStr | Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation |
| title_full_unstemmed | Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation |
| title_short | Explanatory LSTM-AE-Based Anomaly Detection for Time Series Data in Marine Transportation |
| title_sort | explanatory lstm ae based anomaly detection for time series data in marine transportation |
| topic | Long short-term memory auto-encoder anomaly detection time series data interpretation |
| url | https://ieeexplore.ieee.org/document/10856011/ |
| work_keys_str_mv | AT zhanwang explanatorylstmaebasedanomalydetectionfortimeseriesdatainmarinetransportation AT mwambakasongodahouda explanatorylstmaebasedanomalydetectionfortimeseriesdatainmarinetransportation AT hyoseonghwang explanatorylstmaebasedanomalydetectionfortimeseriesdatainmarinetransportation AT inwheejoe explanatorylstmaebasedanomalydetectionfortimeseriesdatainmarinetransportation |