Complex artificial intelligence models for energy sustainability in educational buildings.

Energy consumption of constructed educational facilities significantly impacts economic, social and environment sustainable development. It contributes to approximately 37% of the carbon dioxide emissions associated with energy use and procedures. This paper aims to introduce a study that investigates several artificial intelligence-based models to predict the energy consumption of the most important educational buildings; schools. These models include decision trees, K-nearest neighbors, gradient boosting, and long-term memory networks. The research also investigates the relationship between the input parameters and the yearly energy usage of educational buildings. It has been discovered that the school sizes and AC capacities are the most impact variable associated with higher energy consumption. While 'Type of School' is less direct or weaker correlation with 'Annual Consumption'. The four developed models were evaluated and compared in training and testing stages. The Decision Tree model demonstrates strong performance on the training data with an average prediction error of about 3.58%. The K-Nearest Neighbors model has significantly higher errors, with RMSE on training data as high as 38,429.4, which may be indicative of overfitting. In contrast, Gradient Boosting can almost perfectly predict the variations within the training dataset. The performance metrics suggest that some models manage this variability better than others, with Gradient Boosting and LSTM standing out in terms of their ability to handle diverse data ranges, from the minimum consumption of approximately 99,274.95 to the maximum of 683,191.8. This research underscores the importance of sustainable educational buildings not only as physical learning spaces but also as dynamic environments that contribute to informal educational processes. Sustainable buildings serve as real-world examples of environmental stewardship, teaching students about energy efficiency and sustainability through their design and operation. By incorporating advanced AI-driven tools to optimize energy consumption, educational facilities can become interactive learning hubs that encourage students to engage with concepts of sustainability in their everyday surroundings.

Predicting open education competency level: A machine learning approach.

This article aims to study open education competency data through machine learning models to determine whether models can be built on decision rules using the features from the students' perceptions and classify them by the level of competency. Data was collected from a convenience sample of 326 students from 26 countries using the eOpen instrument. Based on a quantitative research approach, we analyzed the eOpen data using two machine learning models considering these findings: 1) derivation of decision rules from students' perceptions of knowledge, skills, and attitudes or values related to open education to predict their competence level using Decision Trees and Random Forests models, 2) analysis of the prediction errors in the machine learning models to find bias, and 3) description of decision trees from the machine learning models to understand the choices that both models made to predict the competency levels. The results confirmed our hypothesis that the students' perceptions of their knowledge, skills, and attitudes or values related to open education and its sub-competencies produced satisfactory data for building machine learning models to predict the participants' competency levels.

The impact of national culture in the development of complexity reasoning skills: An international comparison.

There is a clear inequality in gender distribution for the STEM areas (Science, Technology, Engineering, and Mathematics). Furthermore, there is a noticeable lack of diversity and a socio-economic gap that requires actionable solutions. To explore potential factors that affect the participation of women in STEM, this paper reviews two possible groups of determinants: national culture and complexity thinking. A survey with 684 respondents from higher education institutions in Chile, Ecuador, Mexico, and Spain was undertaken. The instrument measured four components of complexity thinking namely critical, scientific, innovative, and systemic). Using analysis of variance between two groups and between multiple groups, differences were observed between the countries' samples and between genders. Once the significance was confirmed, boxplots for each dimension were elaborated to facilitate the visualization of the distributions. The scores were compared with the national culture values to seek possible behavioral patterns in the data. The results reveal two groups between the observed countries. Also, there are clear indications of a relationship between the national culture dimensions and the complex thinking components.

Traits of Complex Thinking: A Bibliometric Review of a Disruptive Construct in Education.

The purpose of this research is to contextualize the behavior of publications on complex thinking in education. A total of 428 documents compiled in Scopus from 1937 to 2022 were analyzed with a bibliometric study considering criteria such as "complex thinking", "complex thought", and "reasoning for complexity", all combined with education. The results show 153, 47, and 5 publications for each criterion with their related disciplines, citations, types of documents, universities, prominent authors, researching countries, and the general diachronic evolution of the subject, this allows to establish an idea about the implications of the present study according to one of the most important databases in the world. It is concluded that complex thinking and its relationship with education awakens a greater interest in the academy, not only because of its incidence in diverse fields that are nourished by it for the generation of new multidisciplinary knowledge but also because of the published research that demonstrates its transcendence.

Academic literacy among the university students in Mexico and Spain: A holistic perspective.

Introduction: Currently, young people have access to a large amount of information, so they must have the ability to critically analyze the texts they are exposed to in order to choose those that are useful for their training or research process, as well as to have the necessary skills to interact efficiently with the texts, especially with those specialized documents corresponding to their area of study. In this regard, this article aims to identify how cognitive, emotional, attitudinal, digital and personality aspects influence the development of academic literacy skills in university students. Method: Research was conducted with the mixed method, in which quantitative instruments were applied and analyzed: a Likert scale questionnaire to measure the perceived level of mastery of academic literacy skills, which was applied to a sample of 595 students from higher education institutions in Mexico and Spain. In addition, a test was applied to identify personality type. For the qualitative part, the case study was chosen and the qualitative instruments applied were interviews with a teacher and a student and a focus group with five students. Results: The findings identified were as follows: (a) the cognitive aspect of academic literacy is the one with the lowest perceived mastery by students, (b) having a positive attitude favors the development of academic literacy, (c) by knowing the aspects of their personality that can favor the development of academic literacy, students can seek strategies to improve that competency, (d) the emotional part has repercussions in the process of developing the competence of academic literacy, (e) students prefer to interact with texts in digital spaces and therefore must learn to interact critically in virtual environments, (f) Mexican students perceive themselves to have a higher level of mastery of the academic literacy competency than Spanish students. Conclusion: The literature review and the mixed methods study allowed identifying the relevance of approaching academic literacy in university environments in a holistic manner through the analysis of the influence of cognitive, attitudinal, emotional, digital and personality aspects.

Technological Ecosystems That Support People With Disabilities: Multiple Case Studies.

Advances in technology, research development, and teaching practices have brought improvements in the training, levels of autonomy, and quality of life of people who need support and resources appropriate to their circumstances of disability. This article focuses on empirically analyzing the usefulness of treatments that have been supported by technology to answer the question "How do technological ecosystems being used help people with special educational needs?" The multiple case study methodology was used to address six categories of analysis: project data, objectives, processes, outputs and outcomes, technologies, and impact. The processes, open in communication, were characterized as transversal, ethical, and sustainable. The results yielded various technological ecosystems that support people with disabilities, deliver the help they need to improve their health, and provide enjoyable user experiences. At the same time, they promote the training and improvement of teaching methodologies and involve families in order to improve their knowledge, attitudes, and care of children, young people, and adults with functional diversity.

Mexican and Spanish university students' Internet addiction and academic procrastination: Correlation and potential factors.

The 21st-century problem of Internet addiction is increasing globally, but especially among university students. Not surprisingly, then, problematic Internet use is associated with university students' academic procrastination. Because studies are scarce in Mexico and Spain has one of the highest rates of Internet addiction in Europe, this paper (i) analyzed the presence and degree of Internet addiction among university students in Mexico and Spain, (ii) determined potential sociodemographic factors influencing Internet addiction, and (iii) established the type of correlation between Internet addiction and academic procrastination. The cross-sectional study design used an online questionnaire to measure problematic Internet use and academic procrastination through convenience sampling at one university in Mexico and one in Spain. The questionnaire contained three sections: participants' sociodemographic data, the Internet Addiction Test, and the Academic Procrastination Scale. The final sample comprised 758 university students, 387 from Mexico, and 371 from Spain, aged from 18 to 35 (M = 20.08, SD = 3.16). Results revealed similar prevalence rates of problematic and daily Internet use for leisure, potentially influencing Internet addiction in all three models (i.e., Mexico, Spain, and Total). Additionally, significant positive correlation was revealed between problematic Internet use and academic procrastination (p < .001). Finally, findings showed relevant data on Internet addiction's prevalence in Mexican and Spanish university contexts, along with its influential sociodemographic factors.