Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling
This research develops and validates a novel impact detection system for container monitoring using autoencoders embedded within an edge computing unit. This solution addresses common limitations in current container tracking systems, such as a lack of real-time processing and reliance on cloud conn...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/13/7/1231 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849418110162960384 |
|---|---|
| author | Sergej Jakovlev Tomas Eglynas Edvinas Pocevicius Miroslav Voznak Gediminas Gricius Valdas Jankunas Mindaugas Jusis |
| author_facet | Sergej Jakovlev Tomas Eglynas Edvinas Pocevicius Miroslav Voznak Gediminas Gricius Valdas Jankunas Mindaugas Jusis |
| author_sort | Sergej Jakovlev |
| collection | DOAJ |
| description | This research develops and validates a novel impact detection system for container monitoring using autoencoders embedded within an edge computing unit. This solution addresses common limitations in current container tracking systems, such as a lack of real-time processing and reliance on cloud connectivity, by enabling local, on-device anomaly detection. We compare the performance of Recurrent Autoencoders (RAEs) and Temporal Convolutional Autoencoders (TCAEs) using acceleration data collected during quay crane handling. Experimental results show that the RAE framework outperforms TCAEs, achieving a precision of 91.3%, a recall of 87.6%, and an F1-score of 89.4% for impact detection while also demonstrating lower reconstruction loss and improved detection of sequential anomalies. The system accurately identifies impact events with minimal computational overhead, proving its viability for real-time deployment in port environments. Our findings suggest that time-series autoencoder architectures, particularly RAEs, are effective for detecting mechanical impacts in resource-constrained edge devices, offering a robust alternative to traditional cloud-based solutions. |
| format | Article |
| id | doaj-art-18502f1e95f9462895ee2e34c01eef84 |
| institution | Kabale University |
| issn | 2077-1312 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj-art-18502f1e95f9462895ee2e34c01eef842025-08-20T03:32:32ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-06-01137123110.3390/jmse13071231Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane HandlingSergej Jakovlev0Tomas Eglynas1Edvinas Pocevicius2Miroslav Voznak3Gediminas Gricius4Valdas Jankunas5Mindaugas Jusis6Department of Telecommunications, VŠB-Technical University of Ostrava, 17. Listopadu 2172/15, 708 00 Ostrava, Czech RepublicMarine Research Institute, Klaipeda University, Universiteto al. 17, 92295 Klaipeda, LithuaniaDepartment of Marine Engineering, Klaipeda University, Bijunu Str. 17, 91225 Klaipeda, LithuaniaDepartment of Telecommunications, VŠB-Technical University of Ostrava, 17. Listopadu 2172/15, 708 00 Ostrava, Czech RepublicDepartment of Informatics and Statistics, Klaipeda University, Bijunu Str. 17, 91225 Klaipeda, LithuaniaMarine Research Institute, Klaipeda University, Universiteto al. 17, 92295 Klaipeda, LithuaniaDepartment of Informatics and Statistics, Klaipeda University, Bijunu Str. 17, 91225 Klaipeda, LithuaniaThis research develops and validates a novel impact detection system for container monitoring using autoencoders embedded within an edge computing unit. This solution addresses common limitations in current container tracking systems, such as a lack of real-time processing and reliance on cloud connectivity, by enabling local, on-device anomaly detection. We compare the performance of Recurrent Autoencoders (RAEs) and Temporal Convolutional Autoencoders (TCAEs) using acceleration data collected during quay crane handling. Experimental results show that the RAE framework outperforms TCAEs, achieving a precision of 91.3%, a recall of 87.6%, and an F1-score of 89.4% for impact detection while also demonstrating lower reconstruction loss and improved detection of sequential anomalies. The system accurately identifies impact events with minimal computational overhead, proving its viability for real-time deployment in port environments. Our findings suggest that time-series autoencoder architectures, particularly RAEs, are effective for detecting mechanical impacts in resource-constrained edge devices, offering a robust alternative to traditional cloud-based solutions.https://www.mdpi.com/2077-1312/13/7/1231autoencoderimpact detectionaccelerator |
| spellingShingle | Sergej Jakovlev Tomas Eglynas Edvinas Pocevicius Miroslav Voznak Gediminas Gricius Valdas Jankunas Mindaugas Jusis Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling Journal of Marine Science and Engineering autoencoder impact detection accelerator |
| title | Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling |
| title_full | Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling |
| title_fullStr | Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling |
| title_full_unstemmed | Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling |
| title_short | Comparative Analysis of Recurrent vs. Temporal Convolutional Autoencoders for Detecting Container Impacts During Quay Crane Handling |
| title_sort | comparative analysis of recurrent vs temporal convolutional autoencoders for detecting container impacts during quay crane handling |
| topic | autoencoder impact detection accelerator |
| url | https://www.mdpi.com/2077-1312/13/7/1231 |
| work_keys_str_mv | AT sergejjakovlev comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling AT tomaseglynas comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling AT edvinaspocevicius comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling AT miroslavvoznak comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling AT gediminasgricius comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling AT valdasjankunas comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling AT mindaugasjusis comparativeanalysisofrecurrentvstemporalconvolutionalautoencodersfordetectingcontainerimpactsduringquaycranehandling |