應用決策樹分析重大職業災害統計資料-以建築工程為例

Analysis of Occupational Accident for Construction Industry by Using Decision Tree

陳俊廷(Chun-Ting Chen)

指導教授 ： 王亦凡

國立臺北商業大學/管理學院/資訊與決策科學研究所/碩士(2018年)

摘要

建築工程一直以來都被公認為高風險及高職災率的行業，根據政府公開資料的統計建築工程為營造業中重大職業災害發生頻率最高的，政府在保障勞工工作權益與預防職業災害上有安全衛生相關法律讓工程單位落實相關規定，但根據統計顯示發生職災的工程單位對於落實相關規定是消極的，職業災害的預防除了法律規定與內部管理外政府單位在稽查與輔導方面扮演了重要角色。
　　本研究由政府稽查的角度出發運用決策樹探勘2004-2014年重大職業災害統計資料以工程單位相關資料作為輸入變數，預防職業災害態度作為輸出類別產生CHAID分類決策樹模型提取決策規則，這些規則可以用於製定優先輔導或稽查的條件。研究結果一共產生了11個決策法則其中有7個決策規則顯示為預防職業災害態度消極，可以依照此7個決策規則確定優先被稽查與輔導的工程單位。

關鍵字

政府公開資料 ； 職業災害 ； 資料探勘 ； 決策樹

並列摘要

The construction industry is considered as a high-risk industry. According to the statistics, the number of occupational disasters in construction industry is significantly higher than that of other types of industry. In this study, we analyzed the statistical data of occupational disasters in construction disasters. In this study we used the engineering related information as input variables and occupational hazards prevention attitude as the output variable. A CHAID (Chi-Square Automatic Interaction Detector) classification decision tree model was chosen to established the decision rules.
Those rules determine the priority consultation consider in the construction industry. Decision tree model has produced a total output of 11 decision rules, This study use these decision rules to determine the priority of construction engineering.

並列關鍵字

Open data ； Occupational hazards ； Data mining ； Decision tree

參考文獻

1. Heinrich, H. W., Petersen, D. C., Roos, N. R., & Hazlett, S. (1980). Industrial accident prevention: A safety management approach. McGraw-Hill Companies.

2. Kim, Y. S. (2008). Comparison of the decision tree, artificial neural network, andlinear regression methods based on the number and types of independentvariables and sample size. Expert Systems with Applications, 34, 1227–1234.

3. Frawley, W. J.， Shapiro, G. P.， & Mathews, C. J. (1992)，Knowledge discovery in databases: An overview，AI Magazine， Vol.13， No.3.

4. Grupe, F. H.， & Owrang, M. M.， (1995)， DataBase Mining DiscoveringNew Knowledge And Cooperative Advantage ， Information Systems Management，Vol.12，No.4,26-31

5. Fayyad, U.，Shapiro, G. P.， & Smyth, P. (1996)， From Data Mining to Knowledge Discovery in Database，AI Magazine， Vol.17，37-54