Research on innovation and development of university instructional administration informatization in IoT and big data environment

被引:0
|
作者
Wu, Shengnan [1 ]
机构
[1] Beijing Inst Econ & Management, Beijing 100102, Peoples R China
关键词
Instructional management; IoT devices security; Big data; Informatization; K-means algorithm; Informatization of instructional management;
D O I
10.1007/s00500-023-09311-5
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Because of the advent of new technologies like machine learning (ML), the Internet of Things (IoT), and big data, nearly every electronic device in the modern era of digitization is now capable of making intelligent decisions. To transform instructional management in the big data and educational informatization era, institutions are using digital technologies. Though there has been significant progress in this area, there are still numerous issues with the informatization of instructional management in universities, which have an impact on both the quality of construction and the effectiveness of the application. To improve effectiveness, efficiency, and data security, we investigated in this study how to integrate IoT devices and big data analytics methods into university instructional management systems. Universities can handle security and data integrity concerns while extracting insights from complex data streams by utilizing IoT devices with big data analytics. To achieve the stated goal, we first carefully examined the current university instructional management system to identify its shortcomings. After that, we presented our proposal for an instructional management system for universities that collects data using IoT devices, and it undergoes preprocessing to get it ready for big data analytics. Some of the data mining and big data analytics algorithms such as K-mean clustering, PCA, and Apriori algorithms were applied to get a thorough insight from the collected data. Students were grouped according to their academic activities using the K-mean clustering algorithm. By lowering the dimensionality, the principal component analysis (PCA) algorithm is utilized to determine the relationship between a student's library visit and their final grade. The result of our proposed system is carefully analyzed to display the various levels of student interaction, their study habits, and their final grade.
引用
收藏
页码:19075 / 19094
页数:20
相关论文
共 50 条