The COVID-19 pandemic has changed our common habits and lifestyle. Occupancy information is valued more now due to the restrictions put in place to reduce the spread of the virus. Over the years, ...several authors have developed methods and algorithms to detect/estimate occupancy in enclosed spaces. Similarly, different types of sensors have been installed in the places to allow this measurement. However, new researchers and practitioners often find it difficult to estimate the number of sensors to collect the data, the time needed to sense, and technical information related to sensor deployment. Therefore, this systematic review provides an overview of the type of environmental sensors used to detect/estimate occupancy, the places that have been selected to carry out experiments, details about the placement of the sensors, characteristics of datasets, and models/algorithms developed. Furthermore, with the information extracted from three selected studies, a technique to calculate the number of environmental sensors to be deployed is proposed.
The understanding of occupancy patterns has been identified as a key contributor to achieve improvements in energy efficiency in buildings since occupancy information can benefit different systems, ...such as HVAC (Heating, Ventilation, and Air Conditioners), lighting, security, and emergency. This has meant that in the past decade, researchers have focused on improving the precision of occupancy estimation in enclosed spaces. Although several works have been done, one of the less addressed issues, regarding occupancy research, has been the availability of data for contrasting experimental results. Therefore, the main contributions of this work are: (1) the generation of two robust datasets gathered in enclosed spaces (a fitness gym and a living room) labeled with occupancy levels, and (2) the evaluation of three Machine Learning algorithms using different temporal resolutions. The results show that the prediction of 3-4 occupancy levels using the temperature, humidity, and pressure values provides an accuracy of at least 97%.
Early dropout of students is one of the bigger problems that universities face currently. Several machine learning techniques have been used for detecting students at risk of dropout. By using ...sociodemographic data and qualifications of the previous level, the accuracy of these predictive models is good enough for implementing retention programs. In addition, by using grades of the first semesters, the accuracy of these models increases. Nevertheless, the classification errors produced by these models cause undetected students to be discarded from the retention programs, whereas students with no actual risk consume additional resources. In order to provide more accurate models, we propose the use of a stacking ensemble technique to obtain an improved combined dropout model, while using relatively few variables. The model results show values on the expected ranges for an early dropout model, but with considerably fewer features and historical information, and we show that deploying the models would be cost-efficient for the institution if applied towards an intervention program.
Scientometrics is the field of study and evaluation of scientific measures such as the impact of research papers and academic journals. It is an important field because nowadays different rankings ...use key indicators for university rankings and universities themselves use them as Key Performance Indicators (KPI). The purpose of this work is to propose a semantic modeling of scientometric indicators using the ontology Statistical Data and Metadata Exchange (SDMX). We develop a case study at Tecnologico de Monterrey following the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology. We evaluate the benefits of storing and querying scientometric indicators using linked data as a mean for providing flexible and quick access knowledge representation that supports indicator discovery, enquiring and composition. The semi-automatic generation and further storage of this linked data in the Neo4j graph database enabled an updatable and quick access model.
Learning analytics (LA) is a key research domain within educational technology. This field harnesses data analysis, unlocking tangible advantages for educators and learners. Despite extensive ...research, geographical disparities in adoption remain, with certain regions still in developing stages. Within this scenario, Latin America has been adopting LA to address specific educational challenges, including reducing quality disparities and dropout rates. However, the region confronts limitations for adoption, such as infrastructure, a lack of widespread data literacy, and regulatory constraints, all of which impede broader implementation. In this context, this special issue, titled “Applications of Learning Analytics in Latin America,” intends to present a comprehensive perspective on LA’s deployment across the continent, highlighting its current state and potential growth. In this editorial, we curate a selection of relevant papers, each delving into diverse facets of LA’s application within Latin American contexts. These papers exemplify practical implementations and discuss the implications and possible future trajectories for LA research, especially tailored for the Latin American academic community.
This research article presents a study to compare the teaching performance of teaching-only versus teaching-and-research professors at higher education institutions. It is a common belief that, ...generally, teaching professors outperform research professors in teaching-and-research universities according to student perceptions reflected in student surveys. This case study presents experimental evidence that shows this is not always the case and that, under certain circumstances, it can be the contrary. The case study is from Tecnologico de Monterrey (Tec), a teaching-and-research, private university in Mexico that has developed a research profile during the last two decades using a mix of teaching-only and teaching-and-research faculty members; during this time period, the university has had a growing ascendancy in world university rankings. Data from an institutional student survey called the ECOA was used. The data set contains more than 118,000 graduate and undergraduate courses for 5 semesters (January 2017 to May 2019). The results presented were derived from statistical to data mining methods, including Analysis of Variance and Logistic Regression, that were applied to this data set of more than nine thousand professors who taught those courses. The results show that teaching-and-research professors perform better or at least the same as teaching-only professors. The differences found in teaching with respect to attributes like professors’ gender, age, and research level are also presented.
A case study for impelling university research productivity and impact through collaboration is presented. Scientometric results support the hypothesis that a knowledge management model increased ...research collaboration and thereby boosted a university's number of publications and citations. Results come from fifteen years of data at a Mexican university with 2400 researchers who produced 24,000 works in fifteen research disciplines. These data are treated with social network visualizations and algorithms to identify patterns of collaboration and clustering, as well as with normalizations to make disciplines comparable and to verify increasing citation impact. The knowledge management model implemented in the study may be a cost-effective way for universities to intensify collaboration and improve research performance.
To understand and approach the spread of the SARS-CoV-2 epidemic, machine learning offers fundamental tools. This study presents the use of machine learning techniques for projecting COVID-19 ...infections and deaths in Mexico. The research has three main objectives: first, to identify which function adjusts the best to the infected population growth in Mexico; second, to determine the feature importance of climate and mobility; third, to compare the results of a traditional time series statistical model with a modern approach in machine learning. The motivation for this work is to support health care providers in their preparation and planning. The methods compared are linear, polynomial, and generalized logistic regression models to describe the growth of COVID-19 incidents in Mexico. Additionally, machine learning and time series techniques are used to identify feature importance and perform forecasting for daily cases and fatalities. The study uses the publicly available data sets from the John Hopkins University of Medicine in conjunction with the mobility rates obtained from Google’s Mobility Reports and climate variables acquired from the Weather Online API. The results suggest that the logistic growth model fits best the pandemic’s behavior, that there is enough correlation of climate and mobility variables with the disease numbers, and that the Long short-term memory network can be exploited for predicting daily cases. Given this, we propose a model to predict daily cases and fatalities for SARS-CoV-2 using time series data, mobility, and weather variables.
The estimation of occupancy is a crucial contribution to achieve improvements in energy efficiency. The drawback of data or incomplete data related to occupancy in enclosed spaces makes it ...challenging to develop new models focused on estimating occupancy with high accuracy. Furthermore, considerable variation in the monitored spaces also makes it difficult to compare the results of different approaches. This dataset comprises the indoor environmental information (pressure, altitude, humidity, and temperature) and the corresponding occupancy level for two different rooms: (1) a fitness gym and (2) a living room. The fitness gym data were collected for six days between 18 September and 2 October 2019, obtaining 10,125 objects with a 1 s resolution according to the following occupancy levels: low (2442 objects), medium (5325 objects), and high (2358 objects). The living room data were collected for 11 days between 14 May and 4 June 2020, obtaining 295,823 objects with a 1 s resolution, according to the following occupancy levels: empty (50,978 objects), low (202,613 objects), medium (35,410 objects), and high (6822 objects). Additionally, the number of fans turned on is provided for the living room data. The data are publicly available in the Mendeley Data repository. This dataset can be used to train and compare different machine learning, deep learning, and physical models for estimating occupancy at enclosed spaces.
The factors that foster successful scientific collaboration and teamwork have been studied extensively. However, these factors have been studied in isolation and it is not clear to what extent one ...factor is more relevant than other in the formation of research groups. In this work we propose a new methodology based on network analysis to simultaneously evaluate multiple factors considered relevant in the conformation of formal research groups. Our methodology is supported on structural, statistical, and correlation analysis. In addition to validating our methodology with a case study at a research-teaching university, we introduce a new network to represent the success of scientific collaboration that produces the best prediction in group formation. Our methodology and the results obtained can be used for organising researchers in a university that seeks to strengthen its research strategy.