Intelligent approach to automated star-schema construction using a knowledge base

Sanprasit, Non; Jampachaisri, Katechan; Titijaroonroj, Taravichet; Kesorn, Kraisak

doi:10.1016/j.eswa.2021.115226

Cited by 7 publications

(2 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6. Using a spacy large English model for semantic comparison [25]. It can be further improved by training a model for computer terminologies.…”

Section: ) Compare Syllabuses Semantically and Find The Semantic Simi...mentioning

confidence: 99%

Text Analyzing Tool for Simplifying the Syllabus Creation Process

Sodhi¹,

Choudhary²

2023

IJIET

View full text Add to dashboard Cite

In curriculum development, syllabus creation is an important activity. The need for a syllabus repository and data extraction is essential for creating a new syllabus. Faculties do this job manually by adding topics from their intelligence as well as analyzing syllabuses of the same course available on the search engine. Because it is a time-consuming job, this research aims to propose and implement a text-analyzing tool. The methodology is used, first to create a syllabus repository of computer science courses, do data extraction & normalization, analyzes the contents of different syllabuses, and suggests the contents to the faculties. This tool is experimented on the sample for creating the syllabus of C Programming. The result of the tool is that it suggests the topics that can be included in the syllabus to the faculties. The time and effort required to create a syllabus are reduced by using this tool. In the future weightage to the syllabuses can be given for classification that will give more accurate results while analyzing syllabuses. This tool can be improved by using machine learning algorithms for creating syllabus repositories and data extraction. Semantic comparison can give more accurate results by creating a specific model for computer terminologies.

show abstract

“…6. Using a spacy large English model for semantic comparison [25]. It can be further improved by training a model for computer terminologies.…”

Section: ) Compare Syllabuses Semantically and Find The Semantic Simi...mentioning

confidence: 99%

Text Analyzing Tool for Simplifying the Syllabus Creation Process

Sodhi¹,

Choudhary²

2023

IJIET

View full text Add to dashboard Cite

show abstract

“…Another trend is using knowledge-based methods for automatic DW design [28]. Key information on measures and dimensions are extracted through a Natural Language Processing (NLP) model based on sentences from the business requirements.…”

Section: Related Workmentioning

confidence: 99%

Automatic Machine Learning-Based OLAP Measure Detection for Tabular Data

Yang

Abdelhédi²,

Darmont

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

zhang2011handling combining naive bayes and em, li2015trip combining dependencies and web information, zhang2019learning combining KNN and Regression, song2020imputing combining KNN and likelihood maximization, chhabra2018missing combining k-means and association rules, aydilek2013hybrid combining fuzzy c-means, support vector regression and genetic algorithm, etc. There are also hybrid approaches which use techniques of the same category like latifi2012evaluation combining knn and random forest and wang2017cosset combining crowdsourcing and knowledge base, etc. Nowadays, it is difficult for companies and organisations without Business Intelligence (BI) experts to carry out data analyses. Existing automatic data warehouse design methods cannot treat with tabular data commonly defined without schema. Dimensions and hierarchies can still be deduced by detecting functional dependencies, but the detection of measures remains a challenge. To solve this issue, we propose a machine learning-based method to detect measures by defining three categories of features for numerical columns. The method is tested on real-world datasets and with various machine learning algorithms, concluding that random forest performs best for measure detection.

show abstract