Teaching undergraduates data mining in engineering programs

2008

This paper describes the activities of a Computer Science doctoral student and a Secondary Education masters student in the design, development, and implementation of a lesson for a high school science class. The graduate students, called Fellows, worked in secondary classrooms in the Cincinnati Public School District as a part of Project STEP at the University of Cincinnati, which is funded by the National Science Foundation GK-12 Program. The Fellows formed partnerships with secondary math and science teachers to generate new lessons, activities, and resources to enhance the STEM skills of high school students. Additionally, the Fellows used their engineering expertise to bring authentic, inquiry-based learning experiences into the classroom and introduced engineering concepts to underserved student populations. This paper highlights a lesson that integrates data mining and software engineering into a physical science lesson that focuses on the periodic table. Included in the paper are techniques used by the Fellows, reactions and feedback from the students, and observations and reflections by the Fellows regarding aspects of the activity that had the most impact on student learning.

2012 Federated Conference on Computer Science and Information Systems (FedCSIS), 2012

Data mining is recognized as an important field where one has the possibility to become accustomed both with analysis techniques and methods and with a state of mind. By means of data mining it is possible to develop critical skills that are essential in today's information technology. We present our experience in teaching a data mining module, within an Information System course, centered around a few key aspects: a convergence of theoretical Information Systems aspects and computing skills through programming a complete data mining analysis in Matlab; a project centered learning experience; a sharing of resources that are commented on both by the teacher and by peers facilitating the flow of information and the development of critical skills; a guided inquiry process where the students, when needed, are guided through appropriate questions in the right direction; and finally special attention to requiring motivation of each decision and step undertaken. As a case study we pres...

Computer Applications in Engineering Education

In recent years, there has been an increasing amount of theoretical and applied research that has focused on educational data mining. The learning analytics is a discipline that uses techniques, methods and algorithms that allow the user to discover and extract patterns in stored educational data, with the purpose of improving the teaching-learning process. However, there are many requirements related to the use of new technologies in teaching-learning processes that are practically unaddressed from the learning analytics. In an analysis of the literature, the existence of a systematic revision of the application of learning analytics in the field of engineering education is not evident. The study described in this article provides researchers with an overview of the progress made to date and identifies areas in which research is missing. To this end, a systematic mapping study has been carried out, oriented towards the classification of publications that focus on the type of research and the type of contribution. The results show a trend towards case study research that is mainly directed at software and computer science engineering. Furthermore, trends in the application of learning analytics are highlighted in the topics, such as student retention or dropout prediction, analysis of academic student data, student learning assessment and student behavior analysis. Although this systematic mapping study has focused on the application of learning analytics in engineering education, some of the results can also be applied to other educational areas.

Proceedings of the Canadian Engineering Education Association Annual Conference, Kelowna, BC. , 2023

We extended our earlier student data analytics work [1] to further analysis of 10 years of 11,000+ engineering undergraduates 'academic records in the Faculty of Applied Science and Engineering at the University of Toronto to uncover underlying factors impacting students 'academic performance upon graduation. We explored the potential of using supervised and non-supervised machine learning algorithms to select the key features that strongly correlate with the identified students' academic performance. K-means clustering method was used to study math competency on academic performance and the findings indicate factors other than math can significantly influence student performance. We also applied Association Rule Mining to study lifelong learning attributes based on the completion of minors and certificates. From the results, we noticed that technical minors choices correlated strongly with specific core engineering programs and there are also marked differences in terms of gender, legal status and Professional Engineering Year/COOP completion. Various visualization graphical methods including Heatmap, Pie Char, Sanky Diagrams were applied to aid the analysis. The power of data analysis enables a better understanding of our engineering students' experiences and informs evidence-based decision-making in our school. .

The growing use of technology in education generates massive amounts of data every day, attracting scholars worldwide. Educational data mining is growing quickly and may use cuttingedge machine learning and data mining methods and approaches. Advanced data mining techniques can help understand students, particularly computer science students, and their learning environments, as well as extract unique, captivating, and meaningful insights from educational data. EDM may be used to identify at-risk students, prioritize different student groups, raise graduation rates, evaluate institutional performance, optimize campus resources, and improve topic curricula. A comprehensive assessment of EDM studies showed its widespread use and effect. This research investigated the methods and data utilized in numerous studies and identified the most popular and promising EDM applications.