Student Learner Characteristics and Adoption of M-learning: Are We Effectively Supporting Students?

Hanbidge, Alice Schmidt; Tin, Tony; Sanderson, Nicole

doi:10.1007/978-981-10-6144-8_18

Cited by 1 publication

(1 citation statement)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Intelligence refers to the ability of people to recognize and understand objective things and use knowledge and experience to solve problems, such as memory, observation, imagination, thinking, and judgment. Intelligence mainly includes intelligence and five components of Professor Hanbidge [15] (observation, memory, imagination, thinking, and attention). Intelligence includes language intelligence, mathematical logic intelligence, etc.…”

Section: Learner Characteristicsmentioning

confidence: 99%

Research on the Characteristic Model of Learners in Modern Distance Music Classroom Based on Big Data

Wang¹,

Liu²

2022

Scientific Programming

View full text Add to dashboard Cite

This paper makes in-depth research on data mining, especially association rule mining, improves the FP-tree algorithm in both the algorithm itself and the data source, and finds out a mining algorithm suitable for learner characteristics. Association rule algorithm for actor feature model mining. By establishing the characteristic model of learners in modern distance music classroom, simulation experiments are carried out on FP-tree and three improved algorithms. This paper improves the FP-tree algorithm. Firstly, we improve the algorithm itself; aiming at the problem of too many frequent itemsets, an improved key item extraction algorithm KEFP-growth based on FP-growth is proposed, which ignores the frequent itemsets that are not concerned in the analysis. Then, improvements were made in terms of data sources. In view of the problem that the data source is too large, the mining efficiency is low, and the FP-tree cannot be loaded in memory, this paper proposes a data projection algorithm, which adopts the idea of divide and conquer, divides the frequent 1-itemsets of the database into database subsets of each frequent 1-itemsets, and then mines the database subsets separately and then merges them. Finally, the KEFP-growth algorithm and the projection algorithm are combined, which can not only eliminate the mining of meaningless frequent items but also divide the data when there is a large amount of data. This paper also compares the performance of the three improved algorithms and the original FP-tree algorithm through experiments. The experiments show that the combination of the KEFP-growth algorithm and the database projection algorithm is the most suitable one for the learner feature mining of the adaptive learning system. (1) The KEFP-growth algorithm reduces the number of frequent items output by the original FP-tree algorithm by about 50%, and the mining time is reduced by 50%. (2) The data projection algorithm is more suitable for data mining with less support. When the support is 10%, the mining time of the data projection algorithm is reduced by 80% compared with the FP-tree algorithm. (3) When the support degree is 10%, the running time of the hybrid algorithm is reduced by 10% compared with the KEFP-growth algorithm and the data projection algorithm.

show abstract

Section: Learner Characteristicsmentioning

confidence: 99%