Büyük Sismik Veriler Üzerinde Zaman ve Frekans Tabanlı Özniteliklerin Gerçek Deprem Verilerinin Tespitindeki Etkisi

Year 2025, Volume: 15 Issue: 3, 95 - 107, 19.11.2025

Yunus Emre Erdoğan , Ali Narin

https://doi.org/10.7212/karaelmasfen.1706849

Abstract

Depremler, yer kabuğundaki ani hareketler sonucu meydana gelen doğal afetlerdir. Bu olayların hızlı bir şekilde tespit edilmesi can ve mal kaybının en aza indirilmesi açısından hayati öneme sahiptir. Erken ve doğru tespit, acil müdahale ekiplerinin olay yerine zamanında ulaşmasını sağlayarak halkın güvenliğini artıran önlemlerin hızla alınmasına olanak tanır. Bu çalışmada, sismik sinyaller üzerinden elde edilen özniteliklerin kullanımıyla deprem ve çevresel gürültülerin otomatik olarak ayrıştırılması hedeflenmiştir. Böylece gerçek deprem sinyallerinin tespit süreci hızlandırılmakta ve müdahale süresi kısaltılmaktadır. Sinyaller z-skor normalizasyon yöntemiyle ölçeklendirilmiş ve ardından zaman ve frekans alanlarına ait çeşitli öznitelikler çıkarılmıştır. Zaman alanında ortalama, standart sapma, maksimum, minimum, varyans, çarpıklık ve basıklık gibi öznitelikler kullanılmıştır. Frekans alanında ise tepe frekansı ve ortalama frekans öznitelikleri çıkarılmıştır. Bu öznitelikler sinyallerin daha doğru ve güvenilir şekilde sınıflandırılmasını sağlamaktadır. Çalışmada k-en yakın komşu (k-NN), karar ağaçları (DT) ve toplu torbalanmış karar ağaçları (EBT) algoritmaları kullanılarak sınıflandırma işlemleri gerçekleştirilmiştir. Elde edilen sonuçlara göre k-NN algoritması ile %94,2, DT algoritması ile %94,7 ve EBT algoritması ile %95,6 doğruluk değerleri elde edilmiştir. Bu bulgular deprem sinyallerinin yüksek doğrulukla tespit edilebileceğini göstermektedir. Sunulan çalışma hem akademik araştırmalar hem de pratik uygulamalar açısından önemli bir kaynak olma potansiyeline sahiptir ve depremlerin etkilerinin azaltılmasına yönelik gelecekteki çalışmalara katkı sağlamayı amaçlamaktadır.

Keywords

Deprem Tespiti , Öznitelik Çıkarma , Karar Ağaçları , Toplu Torbalanmış Karar Ağaçları , K en yakın Komşu.

The Effect of Time and Frequency Based Features on Large Seismic Data in Detecting Real Earthquake Data

Abstract

Earthquakes are natural disasters that occur as a result of sudden movements in the Earth’s crust. Rapid detection of these events is of vital importance for minimizing loss of life and property. Early and accurate identification enables emergency response teams to arrive on scene in a timely manner and implement measures that enhance public safety. In this study, we aim to automatically distinguish real earthquake signals from environmental noise by using features extracted from seismic recordings, thereby accelerating the detection process and reducing response time. Signals were first scaled using z-score normalization, and then a variety of time- and frequency-domain features were computed. In the time domain, we extracted statistics such as mean, standard deviation, maximum, minimum, variance, skewness, and kurtosis. In the frequency domain, we derived peak frequency and average frequency features. These features improve the accuracy and reliability of signal classification. Classification was performed using k-nearest neighbors (k-NN), decision trees (DT), and ensemble bagged trees (EBT) algorithms. The results show accuracy rates of 94.2 % for k-NN, 94.7 % for DT, and 95.6 % for EBT. These findings demonstrate that earthquake signals can be detected with high accuracy. The presented work has the potential to serve both academic research and practical applications, and aims to contribute to future efforts in mitigating the impacts of earthquakes.

Keywords

Earthquake Detection , Feature Extraction , Decision Trees , Ensemble Bagged Trees , k-Nearest Neighbors.

References

• Ali, HA., Mohamed, C., Abdelhamid, B., Ourdani, N., El Alami, T. 2022. A comparative evaluation use bagging and boosting ensemble classifiers. 2022 International Conference on Intelligent Systems and Computer Vision (ISCV), 1-6. IEEE. DOI: 10.1109/ISCV54655.2022.9806080
• Avcil, F., Işık, E., İzol, R., Büyüksaraç, A., Arkan, E., Arslan, MH., ... Harirchian, E. 2024. Effects of the February 6, 2023, Kahramanmaraş earthquake on structures in Kahramanmaraş city. Natural Hazards, 120(3), 2953-2991. DOI: 10.1007/s11069-023-06314-1
• Bai, R., Meng, Z., Xu, Q., Fan, F. 2023. Fractional Fourier and time domain recurrence plot fusion combining convolutional neural network for bearing fault diagnosis under variable working conditions. Reliability Engineering & System Safety, 232, 109076. DOI: 10.1016/j.ress.2022.109076
• Bansal, M., Goyal, A., Choudhary, A. 2022. A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning. Decision Analytics Journal, 3, 100071. DOI: 10.1016/j.dajour.2022.100071
• Bhatia, M., Ahanger, TA., Manocha, A. 2023. Artificial intelligence based real-time earthquake prediction. Engineering Applications of Artificial Intelligence, 120, 105856. DOI: 10.1016/j.engappai.2023.105856
• Cai, S., Zhou, J., Pan, J. 2021. Estimating the sample mean and standard deviation from order statistics and sample size in meta-analysis. Statistical Methods in Medical Research, 30(12), 2701-2719. DOI: 10.1177/09622802211047
• Delastrada, DP., Steffi, S., Hoendarto, G., Tjen, J. 2024. Random Forest Analysis for Predicting the Probability of Earthquake in Indonesia. Social Science and Humanities Journal, 9(1), 6295–6304. DOI:10.18535/sshj.v9i01.1574
• Erdoğan, YE., Narin, A. 2021. COVID-19 detection with traditional and deep features on cough acoustic signals. Computers in Biology and Medicine, 136, 104765. DOI: 10.1016/j.compbiomed.2021.104765.
• Erdoğan, YE., Narin, A. 2022. Elektrokardiyografi Yardımıyla Hipertansiyonun Otomatik Belirlenmesinde Ampirik Kip Ayrışımının Gürültülü ve Gürültüsüz Sinyaller Üzerindeki Performansının Karşılaştırılması. El-Cezeri, 9(2), 788-800. DOI: 10.31202/ecjse.1009456
• Essam, Y., Kumar, P., Ahmed, AN., Murti, MA., El-Shafie, A. 2021. Exploring the reliability of different artificial intelligence techniques in predicting earthquake for Malaysia. Soil Dynamics and Earthquake Engineering, 147, 106826. DOI: 10.1016/j.soildyn.2021.106826
• Giarno, G., Hadi, MP., Suprayogi, S., Murti, SH. 2020. Suitable proportion sample of holdout validation for spatial rainfall interpolation in surrounding the Makassar Strait. Forum Geografi, 33(2), 219-232. DOI:10.23917/forgeo.v33i2.8351
• Gonzalez, E., Alvarez, L., Mazorra, L. 2012. Normalization and feature extraction on ear images. 2012 IEEE International Carnahan Conference on Security Technology (ICCST), 97-104. IEEE. DOI:10.1109/CCST.2012.6393543
• Haraguchi, T., Emoto, T., Hirayama, T., Imai, Y., Kato, M., Hirano, T. 2023. Peak-Frequency Histogram Similarity of Bowel Sounds for the Evaluation of Intestinal Conditions. Applied Sciences, 13(3), 1405. DOI:10.3390/app13031405
• Hearn, EH., Bürgmann, R., Reilinger, RE. 2002. Dynamics of Izmit earthquake postseismic deformation and loading of the Duzce earthquake hypocenter. Bulletin of the Seismological Society of America, 92(1), 172-193. DOI:10.1785/0120000832
• Jiao, P., Alavi, AH. 2020. Artificial intelligence in seismology: advent, performance and future trends. Geoscience Frontiers, 11(3), 739-744. DOI: 10.1016/j.gsf.2019.10.004
• Kaliappan, J., Bagepalli, AR., Almal, S., Mishra, R., Hu, YC., Srinivasan, K. 2023. Impact of Cross-validation on Machine Learning models for early detection of intrauterine fetal demise. Diagnostics, 13(10), 1692. DOI:10.3390/diagnostics13101692
• Kaur, R., GholamHosseini, H., Sinha, R., Lindén, M. 2022. Melanoma classification using a novel deep convolutional neural network with dermoscopic images. Sensors, 22(3), 1134. DOI: 10.3390/s22031134
• Kelter, R. 2021. Bayesian model selection in the M-open setting—Approximate posterior inference and subsampling for efficient large-scale leave-one-out cross-validation via the difference estimator. Journal of Mathematical Psychology, 100, 102474. DOI: 10.1016/j.jmp.2020.102474
• Kennett, BLN., Engdahl, ER. 1991. Traveltimes for global earthquake location and phase identification. Geophysical Journal International, 105(2), 429-465. DOI: 10.1111/j.1365-246X.1991.tb06724.x
• Liu, C., Fang, D., Zhao, L. 2021. Reflection on earthquake damage of buildings in 2015 Nepal earthquake and seismic measures for post-earthquake reconstruction. Structures, 30, 647-658. Elsevier. DOI: 10.1016/j.istruc.2020.12.089
• Liu, R., Liu, Q., Shi, J., Yu, W., Gong, X., Chen, N., ... Wang, Z. 2021. Application of a feature extraction and normalization method to improve research evaluation across clinical disciplines. Annals of Translational Medicine, 9(20). DOI: 10.21037/atm-21-5046
• Magrini, F., Jozinović, D., Cammarano, F., Michelini, A., Boschi, L. 2020. Local earthquakes detection: A benchmark dataset of 3-component seismograms built on a global scale. Artificial Intelligence in Geosciences, 1, 1-10. DOI: 10.1016/j.aiig.2020.04.001
• Majstorović, J., Giffard‐Roisin, S., Poli, P. 2021. Designing convolutional neural network pipeline for near‐fault earthquake catalog extension using single‐station waveforms. Journal of Geophysical Research: Solid Earth, 126(7), e2020JB021566. DOI:10.1029/2020JB021566
• Ozkaya, SG., Baygin, M., Barua, PD., Tuncer, T., Dogan, S., Chakraborty, S., Acharya, UR. 2024. An automated earthquake classification model based on a new butterfly pattern using seismic signals. Expert Systems with Applications, 238, 122079. DOI: 10.1016/j.eswa.2023.122079
• Shaheed, K., Mao, A., Qureshi, I., Kumar, M., Hussain, S., Ullah, I., Zhang, X. 2022. DS-CNN: A pre-trained Xception model based on depth-wise separable convolutional neural network for finger vein recognition. Expert Systems with Applications, 191, 116288. DOI: 10.1016/j.eswa.2021.116288
• Sholeh, M., Nurnawati, EK. 2024. Comparison of Z-score, min-max, and no normalization methods using support vector machine algorithm to predict student’s timely graduation. AIP Conference Proceedings, 3077(1). AIP Publishing. DOI:10.1063/5.0202505
• Singh, AK., Krishnan, S. 2023. ECG signal feature extraction trends in methods and applications. BioMedical Engineering OnLine, 22(1), 22. DOI:10.1186/s12938-023-01075-1
• Tam, A., Barker, J., Rubin, D. 2016. A method for normalizing pathology images to improve feature extraction for quantitative pathology. Medical Physics, 43(1), 528-537. DOI:10.1118/1.4939130
• Tasci, E., Zhuge, Y., Kaur, H., Camphausen, K., Krauze, AV. 2022. Hierarchical voting-based feature selection and ensemble learning model scheme for glioma grading with clinical and molecular characteristics. International Journal of Molecular Sciences, 23(22), 14155. DOI:10.3390/ijms232214155 Yetkın, M. 2024. 6 Şubat 2023 Depremleri İçin Kirsaldaki Yiğma Yapilarin Performanslari Üzerine Bir Saha Araştirmasi: Nurdaği/Gaziantep Örneği. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 27(3), 821-837. DOI: 10.17780/ksujes.1430177
• Yapıcı, İŞ., Arslan, RU., Erkaymaz, O. 2024. Kalp yetmezliği tanılı hastaların hayatta kalma tahmininde topluluk makine öğrenme yöntemlerinin performans analizi. Karaelmas Fen ve Mühendislik Dergisi, 14(1), 59-69. DOI: 10.7212/karaelmasfen.1429458
• Zhang, Y., Li, H., Du, J., Qin, J., Wang, T., Chen, Y., ... Lei, B. 2021. 3D multi-attention guided multi-task learning network for automatic gastric tumor segmentation and lymph node classification. IEEE Transactions on Medical Imaging, 40(6), 1618-1631. DOI: 10.1109/TMI.2021.3062902