基于LVQ神经网络的建筑学专业研究生科研潜力评估  

Evaluation on the Research Capability of Architectural Graduates Based on LVQ Neural Network

作　　者：吴蔚[1] 吴农[2] Wu Wei;Wu Nong(School of Architecture and Urban Planning,Nanjing University,Nanjing Jiangsu 210093,China;School of Mechanics,Civil Engineering and Architecture,Northwestern Polytechnical University,Xi'an Shaanxi 710000,China)

机构地区：[1]南京大学建筑与城市规划学院,江苏南京210093 [2]西北工业大学力学与土木建筑学院,陕西西安710000

出　　处：《城市建筑》2021年第7期32-34,100,共4页Urbanism and Architecture

基　　金：江苏省研究生教育教学改革课题(JGLX19-006)。

摘　　要：对高校研究生科研能力的培养,是衡量一所高校综合实力的一项重要指标。建筑学研究生受专业影响,其整体科研能力偏弱。随着新工科建设的开展,如何提高建筑学专业研究生的科研能力已成为刻不容缓的问题。本文选用一款学习向量量化(LVQ)人工神经网络,尝试建构建筑学专业研究生的科研能力评估模型,并对网络模型进行训练和泛化能力测试。研究显示LVQ模型较为简洁易用,评价结果也较为客观准确。Research capability of graduate students is an important indicator to measure comprehensive strength of a university.The overall research capability of architectural graduates is weak due to their majors.With the development of Emerging Engineering Education,how to improve the research ability of architectural graduates has become an urgent issue.An artificial neural network,Learning Vector Quantization(LVQ)is selected to build an evaluation model to study the research capabilities of architectural graduates in this paper.This capability test of the network model is trained and generalized.The simulation results show that LVQ model is simple and easy to use,and its evaluation results are objective and accurate relatively.

关 键 词：研究生 建筑教育 LVQ神经网络 科研能力 评估 

分 类 号：G712[文化科学—职业技术教育学]