Planningof Deep Foundation Construction Technical Specifications Using ImprovedCase-Based Reasoning with Weighted k-Nearest Neighbors

YongchengZhang¹; Lieyun Ding²; and Peter E. D. Love³

Abstract:Planning of construction technical specifications (CTS) for deep foundations iscritical for ensuring works performed safely.k-nearest neighbors (kNN) isregarded as a practical algorithm for case retrieval in a case-based reasoning(CBR) cycle to search for past similar plans for new plan making. The parameterk and neighbors’ weights affect the performance of the CBR cycle deeply but kNNneglects the weights’ effect on case retrieval. The massive and multisourcedata of CTS of deep foundations presents a challenge for retaining case data ina database and for decision making due to an inefficient data process of thetraditional tool. This paper presents a new framework to integrate weightedk-nearest neighbors (kkNN) to improve the performance of a CBR system fortechnical planning of deep foundations.It contains two parts: (1) a process todeal with a large amount of data derived from CTS; and (2) kkNN to obtainsimilar cases considering k and the weights of neighbors’. The feasibility ofthe proposed approach is validated through a case study and the evaluationresult shows that the approach enhances the performance of the CBR cycle increating construction technical specifications in deep foundation projects.

下载地址：

http://ascelibrary.org/doi/abs/10.1061/%28ASCE%29CP.1943-5487.0000682