Explore the vast range of titles available.

Over the past four decades, e-learning has experienced rapid global growth, revolutionizing higher education. In Vietnam, universities have increasingly turned their attention and resources toward e-learning development, adapting to specific contexts and needs. This study investigates the drivers of e-learning choice within the framework of the demand-driven learning model (DDLM), with a primary focus on three core factors: quality content, delivery, and service. Employing a quantitative approach and the PLS-SEM technique, this research uncovers significant findings. The results of the study highlight the pivotal role of quality content, which exerts the most potent influence on e-learning choice, evidenced by a robust path coefficient of 0.400. Service and delivery, with direct path coefficients of 0.183 and 0.173, respectively, also play substantial roles in shaping e-learning decisions. Moreover, mediate role of delivery in the the e-learning choice model has been confirmed. Quality content leads to delivery, and delivery, in turn, leads to e-learning choice. Similar pathway has been found with service. A higher level of service increases delivery, which positively impacts on e-learning choice. These findings hold critical implications for the formulation of e-learning development policies in Vietnam’s higher education institutions. Universities should prioritize the continuous development of high-quality, engaging, and up-to-date educational content that aligns with industry needs and student interests. Additionally, emphasis should be placed on providing a supportive e-learning experience, characterized by responsive customer service, accessible technical support, and efficient issue resolution mechanisms. Moreover, universities should consider the implementation of user-friendly and interactive content delivery platforms and methods that actively engage learners. In essence, this research serves as a guide for universities in Vietnam, enabling them to enhance their e-learning offerings by ensuring the content quality, support services, and delivery methods, ultimately fostering a dynamic and accessible learning environment that meets the evolving needs of their students and the demands of the modern educational landscape.

Many science fiction conventions host interactive sessions and activities related to science fiction, fantasy, and popular culture media for the public. Specialized sessions known as science tracks are spaces where science professionals and conference attendees discuss and question the science embedded within science fiction fandoms. The present study focused on science, technology, engineering, and mathematics (STEM) identity formation among science track attendees identifying with an underrepresented group in STEM. As such, six science fiction convention attendees were interviewed to explore their life histories, interests in science, STEM, and science fiction, to illuminate factors that influenced their STEM identity development, broadening insight into free-choice, adult, STEM learning environments. Narrative inquiry captured and examined participants’ stories utilizing subsequent inductive and deductive coding to explore attributes of STEM identity. Findings suggest sampled attendees had rich and varied stories regarding their STEM identity formation over their lifespan; common threads of childhood experiences and recognition from others, such as friends, family members, and other science fiction convention attendees, shaped their interest and identities. Attendees noted the science tracks were safe places to participate in questioning and communication with science experts regarding their science fiction fandom interest. Yet, their interest in science or STEM, from these experiences highlight the lack of access to quality STEM programming and mentors perceived to be similar to themselves. Overall, science fiction conventions can provide STEM programming that is accessible and welcoming to a diverse community connecting the public’s interest in science fiction fandoms to science.

Free-choice learning occurs when individuals have autonomy in what and how they learn, and often takes place in informal settings such as zoos. To describe goal-setting and -achievement of biology undergraduates at a regional zoo, we primarily asked: (1) What types of learning goals do students set for themselves for a trip to the zoo?; and (2) What activities do students intend to engage in on a zoo trip? Participating students completed the first portion of a goal-setting assessment prior to entering the zoo, which asked students to develop learning and activity goals for themselves. At the conclusion of the zoo trip, students completed the second portion of this survey, which asked whether students achieved their goals, and if not, why. We found that most students devised learning goals related to gaining knowledge and identified passive interactions with animals as activities they hoped to engage in during their trip.

Spiking neural networks (SNNs) are inspired by information processing in biology, where sparse and asynchronous binary signals are communicated and processed in a massively parallel fashion. SNNs on neuromorphic hardware exhibit favorable properties such as low power consumption, fast inference, and event-driven information processing. This makes them interesting candidates for the efficient implementation of deep neural networks, the method of choice for many machine learning tasks. In this review, we address the opportunities that deep spiking networks offer and investigate in detail the challenges associated with training SNNs in a way that makes them competitive with conventional deep learning, but simultaneously allows for efficient mapping to hardware. A wide range of training methods for SNNs is presented, ranging from the conversion of conventional deep networks into SNNs, constrained training before conversion, spiking variants of backpropagation, and biologically motivated variants of STDP. The goal of our review is to define a categorization of SNN training methods, and summarize their advantages and drawbacks. We further discuss relationships between SNNs and binary networks, which are becoming popular for efficient digital hardware implementation. Neuromorphic hardware platforms have great potential to enable deep spiking networks in real-world applications. We compare the suitability of various neuromorphic systems that have been developed over the past years, and investigate potential use cases. Neuromorphic approaches and conventional machine learning should not be considered simply two solutions to the same classes of problems, instead it is possible to identify and exploit their task-specific advantages. Deep SNNs offer great opportunities to work with new types of event-based sensors, exploit temporal codes and local on-chip learning, and we have so far just scratched the surface of realizing these advantages in practical applications.

Neoadjuvant chemo-radiotherapy (CRT) followed by total mesorectal excision (TME) represents the standard treatment for patients with locally advanced (≥ T3 or N+) rectal cancer (LARC). Approximately 15% of patients with LARC shows a complete response after CRT. The use of pre-treatment MRI as predictive biomarker could help to increase the chance of organ preservation by tailoring the neoadjuvant treatment. We present a novel machine learning model combining pre-treatment MRI-based clinical and radiomic features for the early prediction of treatment response in LARC patients. MRI scans (3.0 T, T2-weighted) of 72 patients with LARC were included. Two readers independently segmented each tumor. Radiomic features were extracted from both the “tumor core” (TC) and the “tumor border” (TB). Partial least square (PLS) regression was used as the multivariate, machine learning, algorithm of choice and leave-one-out nested cross-validation was used to optimize hyperparameters of the PLS. The MRI-Based “clinical-radiomic” machine learning model properly predicted the treatment response (AUC = 0.793, p  = 5.6 × 10 –5 ). Importantly, the prediction improved when combining MRI-based clinical features and radiomic features, the latter extracted from both TC and TB. Prospective validation studies in randomized clinical trials are warranted to better define the role of radiomics in the development of rectal cancer precision medicine.

Multiple treatments are effective for major depressive disorder (MDD), but the outcomes of each treatment vary broadly among individuals. Accurate prediction of outcomes is needed to help select a treatment that is likely to work for a given person. We aim to examine the performance of machine learning methods in delivering replicable predictions of treatment outcomes. Of 7732 non-duplicate records identified through literature search, we retained 59 eligible reports and extracted data on sample, treatment, predictors, machine learning method, and treatment outcome prediction. A minimum sample size of 100 and an adequate validation method were used to identify adequate-quality studies. The effects of study features on prediction accuracy were tested with mixed-effects models. Fifty-four of the studies provided accuracy estimates or other estimates that allowed calculation of balanced accuracy of predicting outcomes of treatment. Eight adequate-quality studies reported a mean accuracy of 0.63 [95% confidence interval (CI) 0.56-0.71], which was significantly lower than a mean accuracy of 0.75 (95% CI 0.72-0.78) in the other 46 studies. Among the adequate-quality studies, accuracies were higher when predicting treatment resistance (0.69) and lower when predicting remission (0.60) or response (0.56). The choice of machine learning method, feature selection, and the ratio of features to individuals were not associated with reported accuracy. The negative relationship between study quality and prediction accuracy, combined with a lack of independent replication, invites caution when evaluating the potential of machine learning applications for personalizing the treatment of depression.

Modern societies are exposed to a myriad of risks ranging from disease to natural hazards and technological disruptions. Exploring how the awareness of risk spreads and how it triggers a diffusion of coping strategies is prominent in the research agenda of various domains. It requires a deep understanding of how individuals perceive risks and communicate about the effectiveness of protective measures, highlighting learning and social interaction as the core mechanisms driving such processes. Methodological approaches that range from purely physics-based diffusion models to data-driven environmental methods rely on agent-based modeling to accommodate context-dependent learning and social interactions in a diffusion process. Mixing agent-based modeling with data-driven machine learning has become popularity. However, little attention has been paid to the role of intelligent learning in risk appraisal and protective decisions, whether used in an individual or a collective process. The differences between collective learning and individual learning have not been sufficiently explored in diffusion modeling in general and in agent-based models of socio-environmental systems in particular. To address this research gap, we explored the implications of intelligent learning on the gradient from individual to collective learning, using an agent-based model enhanced by machine learning. Our simulation experiments showed that individual intelligent judgement about risks and the selection of coping strategies by groups with majority votes were outperformed by leader-based groups and even individuals deciding alone. Social interactions appeared essential for both individual learning and group learning. The choice of how to represent social learning in an agent-based model could be driven by existing cultural and social norms prevalent in a modeled society.

Machine learning methods are widely used within the medical field. However, the reliability and efficacy of these models is difficult to assess, making it difficult for researchers to identify which machine-learning model to apply to their dataset. We assessed whether variance calculations of model metrics (e.g., AUROC, Sensitivity, Specificity) through bootstrap simulation and SHapely Additive exPlanations (SHAP) could increase model transparency and improve model selection. Data from the England National Health Services Heart Disease Prediction Cohort was used. After comparison of model metrics for XGBoost, Random Forest, Artificial Neural Network, and Adaptive Boosting, XGBoost was used as the machine-learning model of choice in this study. Boost-strap simulation (N = 10,000) was used to empirically derive the distribution of model metrics and covariate Gain statistics. SHapely Additive exPlanations (SHAP) to provide explanations to machine-learning output and simulation to evaluate the variance of model accuracy metrics. For the XGBoost modeling method, we observed (through 10,000 completed simulations) that the AUROC ranged from 0.771 to 0.947, a difference of 0.176, the balanced accuracy ranged from 0.688 to 0.894, a 0.205 difference, the sensitivity ranged from 0.632 to 0.939, a 0.307 difference, and the specificity ranged from 0.595 to 0.944, a 0.394 difference. Among 10,000 simulations completed, we observed that the gain for Angina ranged from 0.225 to 0.456, a difference of 0.231, for Cholesterol ranged from 0.148 to 0.326, a difference of 0.178, for maximum heart rate (MaxHR) ranged from 0.081 to 0.200, a range of 0.119, and for Age ranged from 0.059 to 0.157, difference of 0.098. Use of simulations to empirically evaluate the variability of model metrics and explanatory algorithms to observe if covariates match the literature are necessary for increased transparency, reliability, and utility of machine learning methods. These variance statistics, combined with model accuracy statistics can help researchers identify the best model for a given dataset.

The choice of the optimal printing setup for Fused Deposition Modeling (FDM) 3D-printing technology is challenging due to complex interactions between process parameters and mechanical properties. This especially affects engineering applications where the maximum performance is required. To address this challenge, this study explores the influence of main controllable printing parameters including layer thickness, extrusion temperature, printing speed and deposition patterns, on the mechanical properties of FDM-printed ABS specimens using the Design-of-Experiments (DoE) approach by a 3 4 full factorial design. Main-effects and Interaction-effects on tensile strength, elastic modulus, and strain at maximum stress are investigated via ANOVA analysis, providing interesting hints to evaluate at the design stage. Given the complexity of these effects, a deeper investigation is conducted with a quadratic regression model of the Response Surface Method and the Random Forest regressor, with the latter enhancing the predictive capability ( R 2 ) on test data by more than 40% for all the mechanical properties. Eventually, a Genetic Algorithm (NSGA-II) is integrated to estimate the optimal parameter set for multiple responses. Overall results indicate that the deposition strategy is the parameter affecting the most the overall mechanical response, with “Lines” pattern providing the best balanced results in maximizing the elastic modulus and the tensile strength, respectively 1381 MPa and 33.3 MPa. Testing of a set of specimens printed with the found optimal parameters confirm the model’s prediction.

Punishment involves learning about the relationship between behavior and its adverse consequences. Punishment is fundamental to reinforcement learning, decision-making and choice, and is disrupted in psychiatric disorders such as addiction, depression, and psychopathy. However, little is known about the brain mechanisms of punishment and much of what is known is derived from study of superficially similar, but fundamentally distinct, forms of aversive learning such as fear conditioning and avoidance learning. Here we outline the unique conditions that support punishment, the contents of its learning, and its behavioral consequences. We consider evidence implicating GABA and monoamine neurotransmitter systems, as well as corticostriatal, amygdala, and dopamine circuits in punishment. We show how maladaptive punishment processes are implicated in addictions, impulse control disorders, psychopathy, anxiety, and depression and argue that a better understanding of the cellular, circuit, and cognitive mechanisms of punishment will make important contributions to next generation therapeutic approaches.