A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE
This paper proposes a unified deep-learning framework for fault and performance prediction in communication equipment by utilizing spatiotemporal geometric features. The core methodology, Spatio-Temporal Slope Feature Extraction (STSFE), transforms irregular time-series data into slope-, area-, and...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11084782/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849254354991710208 |
|---|---|
| author | Dong-Hyun Kang A-Youn Yang Jong-Min Lee Jong-Gu Lee |
| author_facet | Dong-Hyun Kang A-Youn Yang Jong-Min Lee Jong-Gu Lee |
| author_sort | Dong-Hyun Kang |
| collection | DOAJ |
| description | This paper proposes a unified deep-learning framework for fault and performance prediction in communication equipment by utilizing spatiotemporal geometric features. The core methodology, Spatio-Temporal Slope Feature Extraction (STSFE), transforms irregular time-series data into slope-, area-, and volume-based representations, capturing both temporal dynamics and spatial correlations. We develop three distinct yet structurally aligned prediction models: 1) passive MUX fault classification, 2) SFP port-level fault detection, and 3) regression-based forecasting of Rx signal degradation. All models employ a multi-branch neural architecture that integrates MLP, CNN, and attention mechanisms, along with customized loss functions designed to enhance sensitivity to tail-zone deviations. To evaluate the generalization capability of the proposed framework, we conduct a comparative analysis using the NASA Battery dataset, which is reshaped via STSFE to emulate industrial signal characteristics. Experimental results demonstrate that our models outperform existing approaches in terms of classification accuracy, mean absolute error, and tail prediction performance. This research provides a flexible and robust methodology for predictive maintenance across diverse time-series domains in industrial communication networks. |
| format | Article |
| id | doaj-art-229d4a13c83b4e13bceea4f0450487f8 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-229d4a13c83b4e13bceea4f0450487f82025-08-20T03:56:04ZengIEEEIEEE Access2169-35362025-01-011312940012941810.1109/ACCESS.2025.359039311084782A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFEDong-Hyun Kang0https://orcid.org/0000-0001-9711-655XA-Youn Yang1Jong-Min Lee2https://orcid.org/0009-0001-6250-4314Jong-Gu Lee3https://orcid.org/0009-0004-4320-4617HFR, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of KoreaHFR, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of KoreaHFR, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of KoreaHFR, Bundang-gu, Seongnam-si, Gyeonggi-do, Republic of KoreaThis paper proposes a unified deep-learning framework for fault and performance prediction in communication equipment by utilizing spatiotemporal geometric features. The core methodology, Spatio-Temporal Slope Feature Extraction (STSFE), transforms irregular time-series data into slope-, area-, and volume-based representations, capturing both temporal dynamics and spatial correlations. We develop three distinct yet structurally aligned prediction models: 1) passive MUX fault classification, 2) SFP port-level fault detection, and 3) regression-based forecasting of Rx signal degradation. All models employ a multi-branch neural architecture that integrates MLP, CNN, and attention mechanisms, along with customized loss functions designed to enhance sensitivity to tail-zone deviations. To evaluate the generalization capability of the proposed framework, we conduct a comparative analysis using the NASA Battery dataset, which is reshaped via STSFE to emulate industrial signal characteristics. Experimental results demonstrate that our models outperform existing approaches in terms of classification accuracy, mean absolute error, and tail prediction performance. This research provides a flexible and robust methodology for predictive maintenance across diverse time-series domains in industrial communication networks.https://ieeexplore.ieee.org/document/11084782/Spatio-temporal slope feature extraction (STSFE)geometric features of time-seriesMUX and SFP modulesunified deep learning framework |
| spellingShingle | Dong-Hyun Kang A-Youn Yang Jong-Min Lee Jong-Gu Lee A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE IEEE Access Spatio-temporal slope feature extraction (STSFE) geometric features of time-series MUX and SFP modules unified deep learning framework |
| title | A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE |
| title_full | A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE |
| title_fullStr | A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE |
| title_full_unstemmed | A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE |
| title_short | A Unified Framework for Fault and Performance Prediction Using Spatio-Temporal Geometric Features Based on STSFE |
| title_sort | unified framework for fault and performance prediction using spatio temporal geometric features based on stsfe |
| topic | Spatio-temporal slope feature extraction (STSFE) geometric features of time-series MUX and SFP modules unified deep learning framework |
| url | https://ieeexplore.ieee.org/document/11084782/ |
| work_keys_str_mv | AT donghyunkang aunifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT ayounyang aunifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT jongminlee aunifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT jonggulee aunifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT donghyunkang unifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT ayounyang unifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT jongminlee unifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe AT jonggulee unifiedframeworkforfaultandperformancepredictionusingspatiotemporalgeometricfeaturesbasedonstsfe |