Modelling for understanding AND for prediction/classification - the power of neural networks in research
30 Jan 2015-Vol. 2, Iss: 5, pp 67-81
TL;DR: Two articles, Edelsbrunner and, Schneider (2013), and Nokelainen and Silander (2014) comment on Musso, Kyndt, Cascallar, and Dochy, with a perspective on its place among other predictive approaches.
Abstract: Two articles, Edelsbrunner and, Schneider (2013), and Nokelainen and Silander (2014) comment on Musso, Kyndt, Cascallar, and Dochy (2013). Several relevant issues are raised and some important clarifications are made in response to both commentaries. Predictive systems based on artificial neural networks continue to be the focus of current research and several advances have improved the model building and the interpretation of the resulting neural network models. What is needed is the courage and open-mindedness to actually explore new paths and rigorously apply new methodologies which can perhaps, sometimes unexpectedly, provide new conceptualisations and tools for theoretical advancement and practical applied research. This is particularly true in the fields of educational science and social sciences, where the complexity of the problems to be solved requires the exploration of proven methods and new methods, the latter usually not among the common arsenal of tools of neither practitioners nor researchers in these fields. This response will enrich the understanding of the predictive systems methodology proposed by the authors and clarify the application of the procedure, as well as give a perspective on its place among other predictive approaches.
Citations
More filters
TL;DR: In this paper, a mixed-methods systematic literature review of 42 studies has been carried out to investigate the relationship between socio-economic status (SES) and academic performance in higher education, finding that SES is measured through education, occupation, income, household resources, and neighborhood resources, while academic performance was measured through achievement, competencies, and persistence.
67 citations
01 Jan 2021
TL;DR: Artificial neural networks outperform other machine-learning algorithms in evaluation metrics such as the recall and the F1 score and it is found that prior academic achievement, socioeconomic conditions, and high school characteristics are important predictors of students’ academic performance in higher education.
Abstract: The applications of artificial intelligence in education have increased in recent years. However, further conceptual and methodological understanding is needed to advance the systematic implementation of these approaches. The first objective of this study is to test a systematic procedure for implementing artificial neural networks to predict academic performance in higher education. The second objective is to analyze the importance of several well-known predictors of academic performance in higher education. The sample included 162,030 students of both genders from private and public universities in Colombia. The findings suggest that it is possible to systematically implement artificial neural networks to classify students’ academic performance as either high (accuracy of 82%) or low (accuracy of 71%). Artificial neural networks outperform other machine-learning algorithms in evaluation metrics such as the recall and the F1 score. Furthermore, it is found that prior academic achievement, socioeconomic conditions, and high school characteristics are important predictors of students’ academic performance in higher education. Finally, this study discusses recommendations for implementing artificial neural networks and several considerations for the analysis of academic performance in higher education.
28 citations
TL;DR: In this article, a longitudinal analysis is carried out on the cohort of first-year students enrolled in the academic year 2015-2016, searching for a predictive model of their performance given some explicative variables.
Abstract: Following the introduction of performance management in Italian universities, Business intelligence has become a strategical means to use administrative data in support of governance and decision-making processes. The aim of this paper is to show the important role played by a decision support system inside an organization by evaluating the outcomes of the fair tuition fee policy of the University of Bari, in favour of low-income students, stated as a priority in its mission. A longitudinal analysis is carried out on the cohort of first-year students enrolled in the academic year 2015–2016, searching for a predictive model of their performance given some explicative variables. The usefulness of adopting a periodic monitoring system, investigating data by means of suitable statistical techniques (logistic regression, survival analysis, Cox regression model), allows to early detect those factors to be modified in order to achieve optimal results with respect to student expectations and quality of higher education.
3 citations
TL;DR: In this article , a machine learning approach was used to analyze the interactions among activated domain-specific information, context-sensitive appraisals, and emotions, and their impact on task engagement as well as task satisfaction and attribution of the perceived learning outcome.
Abstract: The learning research literature has identified the complex and multidimensional nature of learning tasks, involving not only (meta) cognitive processes but also affective, linguistic, and behavioral contextualized aspects. The present study aims to analyze the interactions among activated domain-specific information, context-sensitive appraisals, and emotions, and their impact on task engagement as well as task satisfaction and attribution of the perceived learning outcome, using a machine learning approach. Data was collected from 1130 vocational high-school students of both genders, between 15 and 20 years of age. Prospective questionnaires were used to collect information about the students’ home environment and domain-specific variables. Motivation processes activated during the learning episode were measured with Boekaerts’ on-line motivation questionnaire. The traces that students left behind were also inspected (e.g., time spent, use of provided tools, content, and technical aspects of writing). Artificial neural networks (ANN) were used to provide information on the multiple interactions between the measured domain-specific variables, situation-specific appraisals and emotions, trace data, and background variables. ANN could identify with high precision students who used a writing skill, affect, and self-regulation strategies attribution on the basis of domain variables, appraisals, emotions, and performance indicators. ANN detected important differences in the factors that seem to underlie the students’ causal attributions.
1 citations
TL;DR: In this paper , the authors explored the influence of genetic variables on individual differences in susceptibility to intervention and developed robust predictive models of the gains in working memory and fluid intelligence following executive attention training in children.
Abstract: The objective of this research was to develop robust predictive models of the gains in working memory (WM) and fluid intelligence (Gf) following executive attention training in children, using genetic markers, gender, and age variables. We explore the influence of genetic variables on individual differences in susceptibility to intervention. Sixty-six children (males: 54.2%) aged 50.9–75.9 months participated in a four-weeks computerized training program. Information on genes involved in the regulation of dopamine, serotonin, norepinephrine, and acetylcholine was collected. The standardized pre- to post-training gains of two dependent measures were considered: WM Span backwards condition (WISC-III) and the IQ-f factor from the Kaufman Brief Intelligence Test (K-BIT). A machine-learning methodology was implemented utilizing multilayer perceptron artificial neural networks (ANN) with a backpropagation algorithm. Both ANN models reached high overall accuracy in their predictive classification. Variations in genes involved in dopamine and norepinephrine neurotransmission affect children's susceptibility to benefit from executive attention training, a pattern that is consistent with previous studies.
1 citations
References
More filters
Book•
16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
Abstract: From the Publisher:
This book represents the most comprehensive treatment available of neural networks from an engineering perspective. Thorough, well-organized, and completely up to date, it examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks. Written in a concise and fluid manner, by a foremost engineering textbook author, to make the material more accessible, this book is ideal for professional engineers and graduate students entering this exciting field. Computer experiments, problems, worked examples, a bibliography, photographs, and illustrations reinforce key concepts.
29,130 citations
TL;DR: A new latent variable modeling approach is provided that can give more accurate estimates of interaction effects by accounting for the measurement error that attenuates the estimated relationships.
Abstract: The ability to detect and accurately estimate the strength of interaction effects are critical issues that are fundamental to social science research in general and IS research in particular. Within the IS discipline, a significant percentage of research has been devoted to examining the conditions and contexts under which relationships may vary, often under the general umbrella of contingency theory (cf. McKeen et al. 1994, Weill and Olson 1989). In our survey of such studies, the majority failed to either detect or provide an estimate of the effect size. In cases where effect sizes are estimated, the numbers are generally small. These results have led some researchers to question both the usefulness of contingency theory and the need to detect interaction effects (e.g., Weill and Olson 1989). This paper addresses this issue by providing a new latent variable modeling approach that can give more accurate estimates of interaction effects by accounting for the measurement error that attenuates the estimated relationships. The capacity of this approach at recovering true effects in comparison to summated regression is demonstrated in a Monte Carlo study that creates a simulated data set in which the underlying true effects are known. Analysis of a second, empirical data set is included to demonstrate the technique's use within IS theory. In this second analysis, substantial direct and interaction effects of enjoyment on electronic-mail adoption are shown to exist.
5,639 citations
Book•
01 Jan 1996TL;DR: Professor Ripley brings together two crucial ideas in pattern recognition; statistical methods and machine learning via neural networks in this self-contained account.
Abstract: From the Publisher:
Pattern recognition has long been studied in relation to many different (and mainly unrelated) applications, such as remote sensing, computer vision, space research, and medical imaging. In this book Professor Ripley brings together two crucial ideas in pattern recognition; statistical methods and machine learning via neural networks. Unifying principles are brought to the fore, and the author gives an overview of the state of the subject. Many examples are included to illustrate real problems in pattern recognition and how to overcome them.This is a self-contained account, ideal both as an introduction for non-specialists readers, and also as a handbook for the more expert reader.
5,632 citations
Posted Content•
01 Jan 2001
TL;DR: This paper gives a lightning overview of data mining and its relation to statistics, with particular emphasis on tools for the detection of adverse drug reactions.
Abstract: The growing interest in data mining is motivated by a common problem across disciplines: how does one store, access, model, and ultimately describe and understand very large data sets? Historically, different aspects of data mining have been addressed independently by different disciplines. This is the first truly interdisciplinary text on data mining, blending the contributions of information science, computer science, and statistics. The book consists of three sections. The first, foundations, provides a tutorial overview of the principles underlying data mining algorithms and their application. The presentation emphasizes intuition rather than rigor. The second section, data mining algorithms, shows how algorithms are constructed to solve specific problems in a principled manner. The algorithms covered include trees and rules for classification and regression, association rules, belief networks, classical statistical models, nonlinear models such as neural networks, and local "memory-based" models. The third section shows how all of the preceding analysis fits together when applied to real-world data mining problems. Topics include the role of metadata, how to handle missing data, and data preprocessing.
3,765 citations
01 Jan 1995
TL;DR: Title Type pattern recognition with neural networks in c++ PDF pattern recognition and neural networks PDF Neural networks for pattern recognition advanced texts in econometrics PDF neural networks for applied sciences and engineering from fundamentals to complex pattern recognition PDF
Abstract: Title Type pattern recognition with neural networks in c++ PDF pattern recognition and neural networks PDF neural networks for pattern recognition advanced texts in econometrics PDF neural networks for applied sciences and engineering from fundamentals to complex pattern recognition PDF an introduction to biological and artificial neural networks for pattern recognition spie tutorial text vol tt04 tutorial texts in optical engineering PDF
3,328 citations
Additional excerpts
...…“so that they can no longer be considered as black boxes” (Benitez et al., 1997, p. 1156), while retaining all the advantages and power of the ANNs as very efficient computing representations as automated knowledge acquisition procedure models, and as universal approximators (Ripley, 1996)....
[...]