On the use of conventional and statistical-learning techniques for the analysis of PISA results in Spain

Gorostiaga, Arantza; Rojo-Álvarez, José Luis

doi:10.1016/j.neucom.2015.07.001

Cited by 29 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then RFE-CV was applied to identify the accuracy scores of different feature sets. According to the study by Gorostiaga and Rojo-Álvarez (2016), around 20 features can compose the best set in PISA studies. Therefore, the following 4 feature sets of top 10, top 15, top 20 and top 25 features were adopted in the SVM model to calculate their mean accuracy score.…”

Section: Resultsmentioning

confidence: 99%

“…During this process, raw data were firstly preprocessed by deleting some (N = 20) samples with missing values in more than half columns. Then data imputation was dealt with using the mean value of nearest-neighbor (Gorostiaga & Rojo-Álvarez, 2016). After that, variables in student-level and school-level were integrated according to student ID.…”

Section: Data Analysis Proceduresmentioning

confidence: 99%

“…In addition to the overall effect of socioeconomic status, parents' education levels were associated with children's academic performance, since well-educated parents were role models for their children and they could offer children more resources and instructions (Burhan et al, 2017;Epstein, 2018). What's more, parents' occupational status could affect students' academic performance and abilities (Gorostiaga & Rojo-Álvarez, 2016). It has been found that in families where parents have accepted good education and with relatively high occupational status, children are likely to get similar achievement (Hertz et al, 2008).…”

Section: Family-level Factors Related To Students' Reading Literacymentioning

confidence: 99%

See 2 more Smart Citations

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

Dong¹,

Hu²

2019

IJEL

View full text Add to dashboard Cite

This study identified the contextual factors which differentiated 15-year-old students with high- and low-achieving reading literacy in Singapore based on Program for International Student Assessment (PISA) 2015. 4,015 students from Singapore were collected from the public dataset of PISA 2015, with 2,646 high-achieving students and 1,369 low-achieving students in PISA reading literacy test. The impact of the overall 49 contextual factors on reading literacy was analyzed in three levels: student level, family level and school level. Support vector machine (SVM), a machine learning approach, was applied to analyze these contextual features. It indicated that SVM could effectively distinguish these two cohorts of readers with an accuracy score of 0.78. SVM-based recursive feature elimination (SVM-RFE), another machine learning approach, was then applied to rank these selected features. These features were outputted in descending order with regard to the degree of their significance to the differentiation. At last, an optimal set with 15 contextual factors was selected by RFE-CV (cross validation), which collectively affected the differentiation of students with high- and low-level of reading literacy. Based on the analysis, implications to further improving students’ reading literacy can be achieved.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Data Analysis Proceduresmentioning

confidence: 99%

Section: Family-level Factors Related To Students' Reading Literacymentioning

confidence: 99%

See 1 more Smart Citation

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

Dong¹,

Hu²

2019

IJEL

View full text Add to dashboard Cite

show abstract

“…In the statistical classification, classification and regression trees (CART) and SVM are two symbolic supervised learning methods of data classification and pattern recognition; however, data analysis in CART is a logic-based analysis, whereas SVM is a rule-based data analysis. CART has been successfully used to analyze PIRLS datasets (Alivernini, 2013), and SVM has recently been effectively utilized in analyzing mathematics literacy in another international benchmark of Program for International Students Assessment (Gorostiaga & Rojo-Álvarez, 2015). CART offers the advantage of providing a straightforward illustration of the correlation…”

Section: Reason For Selecting Svmmentioning

confidence: 99%

Assessment of Optimal Pedagogical Factors for Canadian ESL Learners’ Reading Literacy Through Artificial Intelligence Algorithms

Xiao¹,

Hu²

2019

IJEL

View full text Add to dashboard Cite

The current study explored the effective pedagogical factors that distinguish high-achieving from low-achieving ESL (English as a second language) primary school learners in reading literacy in Canada. In total, 203 samples (167 high-achieving learners and 36 low-achieving learners from 128 primary schools) in the 4th grade were drawn from the public database of Progress in International Reading Literacy Study (PIRLS) 2016, which is the benchmark for large-scale assessments of reading literacy targeting fourth-grade students. For the first time in the ESL-related research, this study applied an artificial intelligence approach, support vector machine (SVM), to concurrently analyze 41 pedagogical factors associated with reading materials, classroom organization, reading strategies, in-class reading activities and post-reading activities. The overall 41 factors collectively distinguished the high-achieving readers from the low-achieving readers with a high accuracy score (0.793) via SVM. Then, these 41 factors were ranked according to their contribution to the SVM model through SVM-based recursive feature elimination (SVM-RFE). Eventually, an optimal factor set was selected by the SVM-RFE cross validation, which contained 10 effective pedagogical factors centered on reading materials, reading strategies and in-class reading activities for fourth-grade high-achieving ESL learners in reading literacy. Suggestions based on solid data analysis would facilitate infrastructural and pedagogical improvements in ESL reading education.

show abstract

“…Nevertheless, a criterion is further needed to establish the relevance of the reduced set of directions obtained from PCA. For this purpose, we used two linear classifiers, following a similar methodology to the one proposed in [ 21 ]. The use of linear classifiers with the PCA projected signals allows us to determine the relevance of each projection direction by scrutinizing their weights.…”

Section: Methodsmentioning

confidence: 99%

Force Trends and Pulsatility for Catheter Contact Identification in Intracardiac Electrograms during Arrhythmia Ablation

Rivas

Muñoz-Romero

Huerta

et al. 2018

Sensors

View full text Add to dashboard Cite

The intracardiac electrical activation maps are commonly used as a guide in the ablation of cardiac arrhythmias. The use of catheters with force sensors has been proposed in order to know if the electrode is in contact with the tissue during the registration of intracardiac electrograms (EGM). Although threshold criteria on force signals are often used to determine the catheter contact, this may be a limited criterion due to the complexity of the heart dynamics and cardiac vorticity. The present paper is devoted to determining the criteria and force signal profiles that guarantee the contact of the electrode with the tissue. In this study, we analyzed 1391 force signals and their associated EGM recorded during 2 and 8 s, respectively, in 17 patients (82 ± 60 points per patient). We aimed to establish a contact pattern by first visually examining and classifying the signals, according to their likely-contact joint profile and following the suggestions from experts in the doubtful cases. First, we used Principal Component Analysis to scrutinize the force signal dynamics by analyzing the main eigen-directions, first globally and then grouped according to the certainty of their tissue-catheter contact. Second, we used two different linear classifiers (Fisher discriminant and support vector machines) to identify the most relevant components of the previous signal models. We obtained three main types of eigenvectors, namely, pulsatile relevant, non-pulsatile relevant, and irrelevant components. The classifiers reached a moderate to sufficient discrimination capacity (areas under the curve between 0.84 and 0.95 depending on the contact certainty and on the classifier), which allowed us to analyze the relevant properties in the force signals. We conclude that the catheter-tissue contact profiles in force recordings are complex and do not depend only on the signal intensity being above a threshold at a single time instant, but also on time pulsatility and trends. These findings pave the way towards a subsystem which can be included in current intracardiac navigation systems assisted by force contact sensors, and it can provide the clinician with an estimate of the reliability on the tissue-catheter contact in the point-by-point EGM acquisition procedure.

show abstract

On the use of conventional and statistical-learning techniques for the analysis of PISA results in Spain

Cited by 29 publications

References 24 publications

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

An Exploration of Impact Factors Influencing Students’ Reading Literacy in Singapore with Machine Learning Approaches

Assessment of Optimal Pedagogical Factors for Canadian ESL Learners’ Reading Literacy Through Artificial Intelligence Algorithms

Force Trends and Pulsatility for Catheter Contact Identification in Intracardiac Electrograms during Arrhythmia Ablation

Contact Info

Product

Resources

About