Research Article
An Empirical Study on Entrepreneurial Education Competency of Young College Teachers Based on K-means Clustering Algorithm
@INPROCEEDINGS{10.1007/978-3-030-87900-6_3, author={Xuemei Hu}, title={An Empirical Study on Entrepreneurial Education Competency of Young College Teachers Based on K-means Clustering Algorithm}, proceedings={Application of Big Data, Blockchain, and Internet of Things for Education Informatization. First EAI International Conference, BigIoT-EDU 2021, Virtual Event, August 1--3, 2021, Proceedings, Part I}, proceedings_a={BIGIOT-EDU}, year={2021}, month={10}, keywords={K-means Innovation and entrepreneurship education Teacher competency Structural model}, doi={10.1007/978-3-030-87900-6_3} }- Xuemei Hu
Year: 2021
An Empirical Study on Entrepreneurial Education Competency of Young College Teachers Based on K-means Clustering Algorithm
BIGIOT-EDU
Springer
DOI: 10.1007/978-3-030-87900-6_3
Abstract
Innovation and entrepreneurship education is an important part of activating students’ innovative thinking and helping them successfully implement entrepreneurial behavior. In order to implement and promote the reform of innovation and entrepreneurship education in Colleges and universities, it is necessary to study the competency of innovation and entrepreneurship education teachers. This study uses the literature research method to sort out the research status of innovation and entrepreneurship education teachers at home and abroad. This paper takes the innovative and entrepreneurial teachers in Hebei Province as the research object, analyzes the composition, current situation and existing problems of the competency of innovative and entrepreneurial teachers in Hebei Province from the theoretical and empirical levels, and puts forward some countermeasures and suggestions to improve the competitiveness of teachers. Firstly, the samples in the dataset sample space are regarded as k-nearest neighbors, and the samples in each neighborhood space are averaged to replace the original samples to form a new feature space. At the same time, after the formation of a new feature space, in order to increase the discrimination between samples, K-means clustering is used in the original feature space, the clustering center of each sample is merged into the new feature space, and the elbow method is used to determine the K value in the k-means.
