Abstract
A reasonable assessment of overall effective levels, incorporating dimensions such as risks, durations, and costs, will be salutary for the rational planning and better selection of optional transmission corridor mechanized construction schemes. With this motivation, this paper establishes an ensemble to address the issue of effective level diagnoses, and thus the hidden patterns and regularities between scheme features and effective levels can be explored. Based on the complex characteristics of input data, the Pearson correlation coefficient is deployed to handle the multidimensional data from multiple sources, and K-means clustering is then employed to classify scheme indicators into classes. The Weighted Itemset Mining (W-IM) model is proposed to identify the underlying key factors, to cope with the frequent omission of High Impact Low Probability (HILP) factors during the qualitative analysis stage. Next, the Factor Criticality Analysis (FCA) model is built to quantify the specific impact levels of these distinguished key elements. Finally, the significance proportion of individual features to the overall effectiveness can be determined and optimized according to the Entropy Impact Model (EIM) model. An empirical case study indicates that the proposed ensemble in this paper exhibits higher predictive accuracy along with better flexibility and comprehensiveness.