查詢結果分析
相關文獻
- 道路落石坍方危險度分級準則之探討
- 地理資訊系統及類神經網路應用於土石流危險溪流危險度判定
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
- 以性能及機率為基礎的撒水設備設計
頁籤選單縮合
題名 | 道路落石坍方危險度分級準則之探討=On the Criteria of Hazardous Degree of Rock-falls and Landslides of Roadways |
---|---|
作者 | 吳傳威; 魏鎮東; 鄭大偉; 王玉瑞; | 書刊名 | 臺北科技大學學報 |
卷期 | 34:2 2001.09[民90.09] |
頁次 | 頁37-54 |
分類號 | 442.11 |
關鍵詞 | 落石坍方; 危險度; 分級準則; 類神經網路; Rock-falls; Landslides; Hazardous degree; Neural network; |
語文 | 中文(Chinese) |
中文摘要 | 本研究針對南橫公路,進行蒐集資料及現場調查,首先使用傳統型式道路落石坍方危險度評估準則評分,並評定危險度等級。再採用類神經網路之分析模組來替代傳統之權值計算方式,以實際觀測數值來取代影響因子之分級評分,進行資料之分析與歸納,完成路段邊坡落石坍方發生機率之預測,其中68組輸出的推論值錯誤率在4.5%以下。最後再與傳統型式危險度準則評分的結果相互比較之後,據其結果提出對傳統型式準則氣象因子以加成方式處理之修訂方案,並証明其效果。類神經網路除了可有助於對傳統型式準則的修訂,在另一方面亦可考慮獨立應用,兩者相輔相成,以增進道路落石坍方危險度判定之準確性,提供道路維護與災害防治之正確資訊。 |
英文摘要 | The present research first used a traditional type of criteria to assessing hazardous degree of rock-falls and landslides after a fully site investigation and information collection on the southern transversal highway. Then, neural network analyzed modules were applied to substitute the traditional weighting calculation. The assessed factors was replaced by actually collected data to study the probability of the occurrence of rock-falls and landslides to the same. It is found that the error rate of 68 groups output is under 4.5%. Finally, after comparing the results with those obtained from traditional criteria, a modified suggestion with respect to the weather factor was proposed. It is seen that neural network analysis not only could help in amending the traditional criteria, but also could be used independently to predict the occurrence of rock-falls and landslides or roadways. Both together would very much helpful in improving the accuracy of the assessment to the hazardous degree of road ways, and providing an useful information for maintenance and disaster prevention of roadways in Taiwan. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。