This Author published in this journals
All Journal Jurnal JEETech
Ahmad Musyafa
Universitas Pamulang, South Tangerang, Indonesia

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Cross-Layer Seismic Data Gap Detection Using Bi-GRU Autoencoder and Hybrid CNN-BiGRU Aziz Setiawan; Ahmad Musyafa; Makhsun; Ceppy Multi Anggara
Jurnal JEETech Vol. 7 No. 2 (2026): Nomor 2 November (In Progress)
Publisher : Universitas Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32492/jeetech.v7i2.7204

Abstract

Continuous seismic waveform transmission is essential to the Indonesia Tsunami Early Warning System (InaTEWS), yet transmission gaps may originate from either communication-network degradation or disruption in the SeedLink application stream. This study develops an unsupervised cross-layer anomaly-detection framework for the TEBBI seismic site and compares a Bidirectional Gated Recurrent Unit (BiGRU) autoencoder with a Hybrid CNN-BiGRU model. Integrated Layer-3 PRTG and Layer-7 SeedLink logs from October 2025 to March 2026 produced 262,080 one-minute records with six operational features. Domain-aware missing-value treatment, fixed-range normalization, 30-minute sliding windows, chronological 80:10:10 partitioning, and one-class training on normal windows were applied. Validation reconstruction errors were converted into model-specific F1-max thresholds. The hybrid model achieved MAE 0.016637, RMSE 0.051577, F1-score 0.8737, and AUC-ROC 0.9595, compared with 0.016806, 0.051810, 0.8728, and 0.9590 for BiGRU. Cross-layer diagnosis separated normal operation, Layer-3 failure, Layer-7 blind spots, and systemic disruption; Layer-7 or systemic states represented 10.27% and 10.08% of test windows for the hybrid and BiGRU models, respectively. Inter-model diagnostic agreement reached 97.70%. The principal contribution is source-oriented, site-specific diagnosis that supports more targeted seismic-transmission troubleshooting at TEBBI