The current study is an approximate replication of Gray and DiLoreto’s (2016) study, which proposed a model predicting that course structure, learner interaction and instructor presence would influence students’ perceived learning and satisfaction in online learning, with student engagement acting as a mediator between two of the predictors and the outcome variables. Using mixed methods, the current study investigated whether Gray and DiLoreto’s model would be able to explain the relationships among the same variables in a computer-assisted language learning environment. A mediation analysis was conducted using survey responses from a sample of 215 college-level students, and qualitative analysis was conducted on the survey responses from a subsample of 50 students. Similar to Gray and DiLoreto’s study, positive correlational relationships emerged between the variables. However, the model proposed by Gray and DiLoreto did not fit our data well, leading us to suggest alternative path-analytic models with both student engagement and learner interaction as mediators. These models showed that the role of course organization and instructor presence were pivotal in explaining the variation in students’ perceived learning and satisfaction both directly and indirectly via student engagement and learner interaction. Moreover, qualitative analysis of students’ responses to open-ended questions suggested that from students’ perspectives, course structure was the most salient factor affecting their experiences within online language learning contexts, followed by learner interaction, and then by instructor presence.

Two-part framework and the Tweedie generalized linear model (GLM) have traditionally been used to model loss costs for short-term insurance contracts. For most portfolios of insurance claims, there is typically a large proportion of zero claims that leads to imbalances, resulting in lower prediction accuracy of these traditional approaches. In this article, we propose the use of tree-based methods with a hybrid structure that involves a two-step algorithm as an alternative approach. For example, the first step is the construction of a classification tree to build the probability model for claim frequency. The second step is the application of elastic net regression models at each terminal node from the classification tree to build the distribution models for claim severity. This hybrid structure captures the benefits of tuning hyperparameters at each step of the algorithm; this allows for improved prediction accuracy, and tuning can be performed to meet specific business objectives. An obvious major advantage of this hybrid structure is improved model interpretability. We examine and compare the predictive performance of this hybrid structure relative to the traditional Tweedie GLM using both simulated and real datasets. Our empirical results show that these hybrid tree-based methods produce more accurate and informative predictions.

Multilayer networks are in the focus of the current complex network study. In such networks, multiple types of links may exist as well as many attributes for nodes. To fully use multilayer—and other types of complex networks in applications, the merging of various data with topological information renders a powerful analysis. First, we suggest a simple way of representing network data in a data matrix where rows correspond to the nodes and columns correspond to the data items. The number of columns is allowed to be arbitrary, so that the data matrix can be easily expanded by adding columns. The data matrix can be chosen according to targets of the analysis and may vary a lot from case to case. Next, we partition the rows of the data matrix into communities using a method which allows maximal compression of the data matrix. For compressing a data matrix, we suggest to extend so-called regular decomposition method for non-square matrices. We illustrate our method for several types of data matrices, in particular, distance matrices, and matrices obtained by augmenting a distance matrix by a column of node degrees, or by concatenating several distance matrices corresponding to layers of a multilayer network. We illustrate our method with synthetic power-law graphs and two real networks: an Internet autonomous systems graph and a world airline graph. We compare the outputs of different community recovery methods on these graphs and discuss how incorporating node degrees as a separate column to the data matrix leads our method to identify community structures well-aligned with tiered hierarchical structures commonly encountered in complex scale-free networks.

We investigate artificial intelligence and machine learning methods for optimizing the adversarial behavior of agents in cybersecurity simulations. Our cybersecurity simulations integrate the modeling of agents launching Advanced Persistent Threats (APTs) with the modeling of agents using detection and mitigation mechanisms against APTs. This simulates the phenomenon of how attacks and defenses coevolve. The simulations and machine learning are used to search for optimal agent behaviors. The central question is: under what circumstances, is one training method more advantageous than another? We adapt and compare a variety of deep reinforcement learning (DRL), evolutionary strategies (ES) and Monte Carlo Tree Search methods within Connect 4, a baseline game environment, and on both a simulation supporting a simple APT threat model, SNAPT, as well as CyberBattleSim, an open-source cybersecurity simulation. Our results show that when attackers are trained by DRL and ES algorithms, as well as when they are trained with both algorithms being used in alternation, they are able to effectively choose complex exploits that thwart a defense. The algorithm that combines DRL and ES achieves the best comparative performance when attackers and defenders are simultaneously trained, rather than when each is trained against its non-learning counterpart.

In this paper, we present a model of the spread of the COVID-19 pandemic simulated by a multi-agent system (MAS) based on demographic data and medical knowledge. Demographic data are linked to the distribution of the population according to age and to an index of socioeconomic fragility with regard to the elderly. Medical knowledge are related to two risk factors: age and obesity. The contributions of this approach are as follows. Firstly, the two aggravating risk factors are introduced into the MAS using fuzzy sets. Secondly, the worsening of disease caused by these risk factors is modeled by fuzzy aggregation operators. The appearance of virus variants is also introduced into the simulation through a simplified modeling of their contagiousness. Using real data from inhabitants of an island in the Antilles (Guadeloupe, FWI), we model the rate of the population at risk which could be critical cases, if neither social distancing nor barrier gestures are respected by the entire population. The results show that hospital capacities are exceeded. The results show that hospital capacities are exceeded. The socioeconomic fragility index is used to assess mortality and also shows that the number of deaths can be significant.