Predicting students’ performance in e-learning using learning process and behaviour data

E-learning is achieved by the deep integration of modern education and information technology, and plays an important role in promoting educational equity. With the continuous expansion of user groups and application areas, it has become increasingly important to effectively ensure the quality of e-learning. Currently, one of the methods to ensure the quality of e-learning is to use mutually independent e-learning behaviour data to build a learning performance predictor to achieve real-time supervision and feedback during the learning process. However, this method ignores the inherent correlation between e-learning behaviours. Therefore, we propose the behaviour classification-based e-learning performance (BCEP) prediction framework, which selects the features of e-learning behaviours, uses feature fusion with behaviour data according to the behaviour classification model to obtain the category feature values of each type of behaviour, and finally builds a learning performance predictor based on machine learning. In addition, because existing e-learning behaviour classification methods do not fully consider the process of learning, we also propose an online behaviour classification model based on the e-learning process called the process-behaviour classification (PBC) model. Experimental results with the Open University Learning Analytics Dataset (OULAD) show that the learning performance predictor based on the BCEP prediction framework has a good prediction effect, and the performance of the PBC model in learning performance prediction is better than traditional classification methods. We construct an e-learning performance predictor from a new perspective and provide a new solution for the quantitative evaluation of e-learning classification methods.

Evaluation of Road Safety Performance Based on Self-Reported Behaviour Data Set

Self-reported behavioural data, being often linguistic variables that represent a qualitative measure of respondents’ opinions/attitudes, are vague, uncertain, and fuzzy in nature. A road safety performance index, based on these fuzzy data, should consider this uncertainty. In this study, fuzzy numbers were used to describe self-reported behaviour on Montenegrin roads, which was further integrated into the data envelopment analysis (DEA), a technique for measuring the relative performance of decision-making units (DMUs). The vagueness of the performance scores obtained in this way was treated with grey relational analysis (GRA). GRA was applied to the cross-efficiency (CE) matrix constructed by the DEA to distinguish Montenegrin municipalities’ performance, with the main goal of describing road safety in the observed territories in the environment of uncertain/grey data. It is concluded that the proposed DEA–GRA model, based on fuzzy data, provides a more reasonable and encompassing measure of performance, and with which the overall ranking position of municipalities can be obtained.

The Seismic Shock Prediction Algorithm based on the Rock Mass behaviour data

KGHM S.A. exploits copper ore deposits in underground mining facilities. As a result of this operation the seismic activity of the rock mass is induced. One of the symptoms of seismic activity of the rock mass is the occurrence of high energy seismic shocks. These phenomena can lead to severe destructions in mine workings. Resulting from that is a threat to work safety in the area of seismic shock occurrence and risk of damage to mine's property. Particularly strong seismic shocks may also pose a threat to objects on the surface. The level of seismic activity of the rock mass depends on many factors that can be divided into factors related to the environment in which the operation is carried out and factors related to methods of conducting the operation. In the report authors propose an algorithm for prediction of the occurrence of seismic shocks with a given energy.

Personalized Drug-Disease prediction using Multiple Linear Regression with ReLU

Predicting models for personalized Drugs related to specific disease are essential, as traditional methods are expensive and time consuming. The most challenging task in personalized medicine is predicting the status of disease from high dimensionality data. In the biomedical domain the association between drugs and disease plays a vital role as the same drug may treat similar diseases. For the good adaptability to complex and nonlinear behaviour data, Multiple Linear Regression method with ReLU Activation function is used for calculation and to fit the model with Drug –Disease dataset. Based on the results the drug or combination of drugs that treat a specific disease is predicted efficiently.

Georeferencing Oblique Aerial Wildfire Photographs: An Untapped Source of Fire Behaviour Data

In this study, we investigate a novel application of the photogrammetric monoplotting technique for assessing wildfires. We demonstrate the use of the software program WSL Monoplotting Tool (MPT) to georeference operational oblique aerial wildfire photographs taken during airtanker response in the early stages of fire growth. We located the position of the fire front in georeferenced pairs of photos from five fires taken 31–118 min apart, and calculated the head fire spread distance and head fire rate of spread (HROS). Our example photos were taken 0.7 to 4.7 km from fire fronts, with camera angles of incidence from −19 to −50° to image centre. Using high quality images with detailed landscape features, it is possible to identify fire front positions with high precision; in our example data, the mean 3D error was 0.533 m and the maximum 3D error for individual fire runs was less than 3 m. This resulted in a maximum HROS error due to monoplotting of only ~0.5%. We then compared HROS estimates with predictions from the Canadian Fire Behavior Prediction System, with differences mainly attributed to model error or uncertainty in weather and fuel inputs. This method can be used to obtain observations to validate fire spread models or create new empirical relationships where databases of such wildfire photos exist. Our initial work suggests that monophotogrammetry can provide reproducible estimates of fire front position, spread distance and rate of spread with high accuracy, and could potentially be used to characterize other fire features such as flame and smoke plume dimensions and spotting.

Time spent playing video games is unlikely to impact well-being

Video games are a massively popular form of entertainment, socialising, cooperation, and competition. Games’ ubiquity fuels fears that they cause poor mental health, and major health bodies and national governments have made far-reaching policy decisions to address games’ potential risks, despite lacking adequate supporting data. The concern-evidence mismatch underscores that we know too little about games’ impacts on well-being. We addressed this disconnect by linking six weeks of 38,030 players’ objective game-behaviour data, provided by six global game publishers, with three waves of their self-reported well-being that we collected. We found little to no evidence for a causal connection between gameplay and well-being. However, results suggested that motivations play a role in players’ well- being. For good or ill, the average effects of time spent playing video games on players’ well-being are likely very small, and further industry data are required to determine potential risks and supportive factors to health.

Animal Linguistics: A Primer

The evolution of language is investigated by various research communities (including biologists and linguists) which engage in comparative works to highlight similar linguistic capacities across species. So far though, no consensus exists on linguistic capacities of nonhuman species. Rather, vivid debates have emerged, mostly fuelled by misuses of linguistic terminology, irrelevance of analysis methods and inappropriate behavioural data collection. The field of ‘animal linguistics’ has recently emerged to overcome these difficulties, notably by increasing exchanges and collaborations across disciplines, in an attempt to reach unique methods and terminology.This primer on ‘animal linguistics’ is a tutorial review on the study of animal communication using both linguistic and biological methods, aimed at both the linguistic and biology communities. Specifically, it aims at accompanying researchers from either of these fields to collect data, run analyses and draw conclusions step by step, and in a way that could satisfy the other research community. To this end, it first exposes the linguistic theoretical concepts of semantics, pragmatics and syntax, and proposes the minimal criteria that are to be fulfilled to claim that a given species displays one – or several – linguistic capacities. Second, it reviews relevant methods successfully applied to the study of animal data. Third, it proposes guidelines to detect and overcome major pitfalls commonly observed in the collection of animal behaviour data. As observed in the past history of science, research traditions can be fragile if not sustained by collaborative communities. We believe this article to represent a milestone towards mutual understanding and fruitful collaborations between linguists and biologists.

934Prevalence by proxy: Estimating youth smoking prevalence using nationally representative household surveys

Background Reducing youth (15-17 years) smoking uptake is critical to tobacco control; accordingly, youth smoking prevalence is a key monitoring and evaluation outcome. Many nationally representative surveys collect youth smoking behaviour data from, or in the presence of, the youth’s parent or caregiver. We aimed to quantify the potential bias conferred by this. Methods We compared youth smoking prevalence when reported by parent proxy, with parent present or by private self-report, in Australian Bureau of Statistics Health Surveys. National youth current smoking prevalence if all data were collected by youth self-report was estimated. Results Smoking behaviour data for over 75% of youth participants in the health survey were collected by proxy or with parent present. Ever-smoking prevalence using private self-report versus report by proxy was 1.29 (95%CI:0.96-1.73) to 1.99 (1.39-2.85) times as high in Aboriginal and Torres Strait Islander youth, and 1.83 (0.92-2.63) to 2.72 (1.68-4.41) times as high in total population youth. Predicted national current smoking prevalence if all youth were to self-report alone was substantively higher than the estimated national prevalence based on actual responses, but still reveals a decline over time. Conclusions Youth smoking estimates drawn from data collected by proxy/with parent present are unlikely to be accurate. Increased youth self-report is crucial to ensure data accuracy to inform effective tobacco control. Key messages The accuracy of youth smoking data collected by proxy/with parent present should be further scrutinised before it is used to inform assessment of national prevalence and trends.