苗栗鹿場崩塌邊坡上堆積大量碎屑岩塊，因此持續發生落石事件，影響邊坡下方道路之安全。若能有效地偵測由落石引致的地表振動，讓邊坡下方用路人能在最短時間內獲知落石發生資訊，便能發展為落石災害警報的工具之一。
本研究利用2019年開始安裝於鹿場邊坡周圍的4個地震站紀錄，以人工辨識方式挑選落石、地震，以及車輛等三種地動訊號，透過分析三種地動訊號在時間域與頻率域之特徵，萃取合適的訊號特徵值建立監督式機器學習分類器，並探討分類器使用之特徵值的意義，同時也嘗試對落石訊號進行簡易定位，以及觀察每日落石事件數量與日降雨量之關聯性。其中，以隨機森林演算法所建構之分類器準確度為92.7%，以支援向量機演算法所建構之分類器準確度為90.4%，表示兩種分類器皆能有效地辨別三種地動訊號的差異。緊接著將所建立之地動訊號分類器運用於2020年6月至8月間的連續地動觀測紀錄，分類結果顯示兩個分類器之車輛和地震訊號的敏感度皆下降，而落石訊號雖然僅4個，有3個被正確分類，但依舊維持不錯的分類效果。最後，本研究提出以多站特徵值加權平均的方法建立訊號分類器，將原本的4個分類結果減少至單一分類結果，使分析人員更容易直接判斷為何種地動事件。特徵值加權平均後的隨機森林分類器之準確度為88.3%，特徵值加權平均後的支援向量機分類器之準確度為84.0%，特徵值加權平均後所建立之分類器準確度略為下降，但仍有助於提高辨識效率。

Rockfall events occur intermittently on the slope filled with landsliding debris at Luchang in Miaoli Country, affecting the life and property of road users. If the ground motion caused by rockfalls can be detected effectively, it will become a useful tool to warn passersby of rockfall disasters.
Since 2009, four seismic stations were installed around the collapsed slope at Luchang. In the study, three types of ground motion signals, including rockfalls, earthquake and cars, were selected by manual identification from the records of these four stations. By analyzing the characteristics of ground motion signals, the suitable features for discriminating three event signals were extracted in the time domain and frequency domain. Using random forest and support vector machine algorithm, two kinds of automatic classifiers were create and used to explore the meaning of the features. Besides, the rockfall ground-motions were used to locate the possible runout path and to investigate the relationship between the number of rockfall event and daily rainfall. Then, the built signal classifiers were operated for continuous seismic records from June to August in 2020. Finally, a weighted average method was proposed to build signal classifiers, which would reduce the confusion of different classification results shown in four station signals for researchers.

中文部分
王豐仁(1994)。玉山國家公園新中橫公路段之落石邊坡調查研究。國立成功大學地球科學系碩士論文，台南市。取自：https://hdl.handle.net/11296/rbxm7s
李準勝(2008)。苗栗鹿場地區地質環境特性與邊坡穩定敏感度分析之研究。國立中興大學水土保持學系所碩士論文，台中市。取自：https://hdl.handle.net/11296/8hzg55
彭永光(2013)。山區道路崩塌風險潛勢探討-以苗21線鹿場部落聯絡道為例。國立中興大學水土保持學系所碩士論文，台中市。取自：https://hdl.handle.net/11296/9w3683
陳時仲(2015)。隨機森林模型效力評估。國立交通大學統計學研究所碩士論文，新竹市。取自：https://hdl.handle.net/11296/vxx439
伊凡歹木(2019年5月24日):〈動態時報〉〔動態貼文〕。Facebook。取自：https://www.facebook.com/permalink.php?story_fbid=2336208403327543&id=100008152173609
張簡意逢(2019)。藉由機器學習演算法及地動訊號特徵值進行崩塌事件的自動判釋。國立成功大學地球科學系碩士論文，台南市。取自：https://hdl.handle.net/11296/b579y8
莊昀叡(2020)。雷達影像時間序列分析於崩塌地監測之探討。行政院農業委員會水土保持局(計畫編號：SWCB-109-267)，未出版。

英文部分
Bramer, M. (2007). Avoiding overfitting of decision trees. Principles of data mining, 119-134.
Breiman, L. (1996a). Bagging predictors. Machine learning, 24(2), 123-140.
Breiman, L. (1996b). Out-of-bag estimation.
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Chapelle, O., Scholkopf, B., & Zien, A. (2009). Semi-supervised learning (chapelle, o. et al., eds.; 2006)[book reviews]. IEEE Transactions on Neural Networks, 20(3), 542-542.
Chau, K. T., Wong, R. H. C., Liu, J., & Lee, C. F. (2003). Rockfall hazard analysis for Hong Kong based on rockfall inventory. Rock Mechanics and Rock Engineering, 36(5), 383-408.
Chen, C. H., Chao, W. A., Wu, Y. M., Zhao, L., Chen, Y. G., Ho, W. Y., Lin, T. L., Kuo, K. H., & Chang, J. M. (2013). A seismological study of landquakes using a real-time broad-band seismic network. Geophysical Journal International, 194(2), 885-898
Chen, C. S., Chen, Y. L., Liu, C. L., Lin, P. L., & Chen, W. C. (2007). Statistics of heavy rainfall occurrences in Taiwan. Weather and Forecasting, 22(5), 981-1002.
Curilem, G., Vergara, J., Fuentealba, G., Acuña, G., & Chacón, M. (2009). Classification of seismic signals at Villarrica volcano (Chile) using neural networks and genetic algorithms. Journal of Volcanology and Geothermal Research, 180(1), 1-8.
Dammeier, F., Moore, J. R., Haslinger, F., & Loew, S. (2011). Characterization of alpine rockslides using statistical analysis of seismic signals. Journal of Geophysical Research: Earth Surface, 116(F4).
Debnath, R., Takahide, N., & Takahashi, H. (2004). A decision based one-against-one method for multi-class support vector machine. Pattern Analysis and Applications, 7(2), 164-175.
Dietze, M., Mohadjer, S., Turowski, J. M., Ehlers, T. A., & Hovius, N. (2017). Seismic monitoring of small alpine rockfalls–validity, precision and limitations. Earth Surface Dynamics, 5(4), 653-668.
Dorren, L. K. (2003). A review of rockfall mechanics and modelling approaches. Progress in Physical Geography, 27(1), 69-87.
Feng, L., Pazzi, V., Intrieri, E., Gracchi, T., & Gigli, G. (2019). Rockfall seismic features analysis based on in situ tests: frequency, amplitude, and duration. Journal of Mountain Science, 16(5), 955-970.
Greene, D., Cunningham, P., & Mayer, R. (2008). Unsupervised learning and clustering. In Machine learning techniques for multimedia (pp. 51-90). Springer, Berlin, Heidelberg.
Hibert, C., Provost, F., Malet, J. P., Maggi, A., Stumpf, A., & Ferrazzini, V. (2017). Automatic identification of rockfalls and volcano-tectonic earthquakes at the Piton de la Fournaise volcano using a Random Forest algorithm. Journal of Volcanology and Geothermal Research, 340, 130-142.
Ho, M. C., Shaw, D., Lin, S., & Chiu, Y. C. (2008). How do disaster characteristics influence risk perception?. Risk Analysis: An International Journal, 28(3), 635-643.
Hongjun, S., Hiroyuki, F., & Masato, N. (2019). Variation Of Density Functions For The Distribution Of Residuals Between GMPE And Observation Data Based On The NGA-W2 Database.
Hsu, C. W., & Lin, C. J. (2002). A comparison of methods for multiclass support vector machines. IEEE transactions on Neural Networks, 13(2), 415-425.
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996). Reinforcement learning: A survey. Journal of artificial intelligence research, 4, 237-285.
Kao, H., Thompson, P. J., Rogers, G., Dragert, H., & Spence, G. (2007). Automatic detection and characterization of seismic tremors in northern Cascadia. Geophysical research letters, 34(16).
Kohavi, R. (1995, August). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Ijcai (Vol. 14, No. 2, pp. 1137-1145).
Kortström, J., Uski, M., & Tiira, T. (2016). Automatic classification of seismic events within a regional seismograph network. Computers & Geosciences, 87, 22-30.
Langer, H., Falsaperla, S., Powell, T., & Thompson, G. (2006). Automatic classification and a-posteriori analysis of seismic event identification at Soufrière Hills volcano, Montserrat. Journal of Volcanology and Geothermal Research, 153(1-2), 1-10.
Lee, C. S., Huang, L. R., Shen, H. S., & Wang, S. T. (2006). A climatology model for forecasting typhoon rainfall in Taiwan. Natural Hazards, 37(1-2), 87-105.
Liu, Z. (2011). A method of SVM with normalization in intrusion detection. Procedia Environmental Sciences, 11, 256-262.
Ma, K. F., Lee, C. T., Tsai, Y. B., Shin, T. C., & Mori, J. (1999). The Chi‐Chi, Taiwan earthquake: Large surface displacements on an inland thrust fault. Eos, Transactions American Geophysical Union, 80(50), 605-611.
Malfante, M., Dalla Mura, M., Mars, J. I., Métaxian, J. P., Macedo, O., & Inza, A. (2018). Automatic classification of volcano seismic signatures. Journal of Geophysical Research: Solid Earth, 123(12), 10-645.
Melillo, M., Gariano, S. L., Peruccacci, S., Sarro, R., Mateos, R. M., & Brunetti, M. T. (2020). Rainfall and rockfalls in the Canary Islands: assessing a seasonal link. Natural Hazards and Earth System Sciences, 20(8), 2307-2317.
Milgram, J., Cheriet, M., & Sabourin, R. (2006, October). “One against one” or “one against all”: Which one is better for handwriting recognition with SVMs?. In tenth international workshop on Frontiers in handwriting recognition. Suvisoft.
Noble, W. S. (2006). What is a support vector machine? Nature biotechnology, 24(12), 1565-1567.
Norris, R. D. (1994). Seismicity of rockfalls and avalanches at three Cascade Range volcanoes: Implications for seismic detection of hazardous mass movements. Bulletin of the Seismological Society of America, 84(6), 1925-1939.
Ongsulee, P. (2017, November). Artificial intelligence, machine learning and deep learning. In 2017 15th International Conference on ICT and Knowledge Engineering (ICT&KE) (pp. 1-6). IEEE.
Oshiro, T. M., Perez, P. S., & Baranauskas, J. A. (2012, July). How many trees in a random forest?. In International workshop on machine learning and data mining in pattern recognition (pp. 154-168). Springer, Berlin, Heidelberg.
Parihar, D. S., Ghosh, R., Akula, A., Kumar, S., & Sardana, H. K. (2018). Machine Learning Based Comparative Analysis for the Classification of Earthquake Signals. In Proceedings of the International Conference on Computing and Communication Systems (pp. 369-376). Springer, Singapore.
Provost, F., Hibert, C., & Malet, J. P. (2017). Automatic classification of endogenous landslide seismicity using the Random Forest supervised classifier. Geophysical Research Letters, 44(1), 113-120.
Quang, P. B., Gaillard, P., Cano, Y., & Ulzibat, M. (2015). Detection and classification of seismic events with progressive multi-channel correlation and hidden Markov models. Computers & Geosciences, 83, 110-119.
Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1(1), 81-106.
Scarpetta, S., Giudicepietro, F., Ezin, E. C., Petrosino, S., Del Pezzo, E., Martini, M., & Marinaro, M. (2005). Automatic classification of seismic signals at Mt. Vesuvius volcano, Italy, using neural networks. Bulletin of the Seismological Society of America, 95(1), 185-196.
Shin, T. C., & Teng, T. L. (2001). An overview of the 1999 Chi-Chi, Taiwan, earthquake. Bulletin of the Seismological Society of America, 91(5), 895-913.
Su, S. H., Kuo, H. C., Hsu, L. H., & Yang, Y. T. (2012). Temporal and spatial characteristics of typhoon extreme rainfall in Taiwan. Journal of the Meteorological Society of Japan. Ser. II, 90(5), 721-736.
Suriñach, E., Vilajosana, I., Khazaradze, G., Biescas, B., Furdada, G., & Vilaplana, J. M. (2005). Seismic detection and characterization of landslides and other mass movements. Natural Hazards and Earth System Sciences, 5(6), 791-798.
Vapnik, V. (2013). The nature of statistical learning theory. Springer science & business media.