Learning Performance Research Articles

Improving Low‐Cloud Fraction Prediction Through Machine Learning

AbstractIn this study, we evaluated the performance of machine learning (ML) models (XGBoost) in predicting low‐cloud fraction (LCF), compared to two generations of the community atmospheric model (CAM5 and CAM6) and ERA5 reanalysis data, each having a different cloud scheme. ML models show a substantial enhancement in predicting LCF regarding root mean squared errors and correlation coefficients. The good performance is consistent across the full spectrums of atmospheric stability and large‐scale vertical velocity. Employing an explainable ML approach, we revealed the importance of including the amount of available moisture in ML models for representing spatiotemporal variations in LCF in the midlatitudes. Also, ML models demonstrated marked improvement in capturing the LCF variations during the stratocumulus‐to‐cumulus transition (SCT). This study suggests ML models' great potential to address the longstanding issues of “too few” low clouds and “too rapid” SCT in global climate models.

Multifaceted Strategy That Improves Students’ Achievement of Entrustable Professional Activities Across Advanced Pharmacy Practice Experiences

ObjectiveTo outline an approach to help students achieve Entrustable Professional Activities (EPAs) entrustment during a sequence of Advanced Pharmacy Practice Experiences (APPEs) by implementing longitudinal monitoring and individualized intervention and remediation strategies. MethodsUsing the recommended EPAs within the core APPEs (acute care, ambulatory care, community, institutional), students were expected to achieve entrustment on all EPAs by graduation. A longitudinal monitoring approach, using an “EPA report card,” was implemented to continuously identify students at risk of not meeting the EPA requirement of “Level 3” entrustment (perform with reactive supervision). Individualized interventions, including proactive outreach and in-sequence remediation, were incorporated into the APPE core and elective sequence to help ensure all students were entrusted by the end of APPEs without requiring further end-of-year remediation to graduate. ResultsFor the graduating classes of 2023 and 2024, 12% (8 of 69) and 16% (12 of 75) students, respectively, were identified as at risk of not meeting EPA entrustment. Proactive outreach, in-sequence remediation, or a combination of both strategies, were used to enhance learning and EPA performance. As a result, all students achieved “Level 3” entrustment on the deficient EPA(s) by the end of the APPE sequence. No student required further end-of-year remediation to graduate. ConclusionUtilizing a multifaceted strategy provided timely, real-world practice opportunities to improve the students’ achievement of EPAs across the APPE curriculum and decreased the need for end-of-year remediation and potential graduation delays.

Coupled Conditional Neural Movement Primitives

Learning sensorimotor trajectories through flexible neural representations is fundamental for robots as it facilitates the building of motor skills as well as equipping them with the ability to represent the world as predictable temporal events. Recent advances in deep learning led to the development of powerful learning from demonstration (LfD) systems such as Conditional Neural Movement Primitives (CNMPs). CNMPs can robustly represent skills as movement distributions and allow them to be ‘recalled’ by conditioning the movement on a few observation points. In this study, we focus on improving CNMPs to achieve a higher resource economy by adopting a divide-and-conquer approach. We propose a novel neural architecture called Coupled CNMP (C-CNMP), that couples the latent spaces of a pair of CNMPs that splits a given sensorimotor trajectory into segments whose learning is undertaken by smaller sub-networks. Therefore, each sub-network needs to deal with a less complex trajectory making the learning less resource-hungry. With systematic simulations on a controlled trajectory data set, we show that the overhead brought by the coupling introduced in our model is well offset by the resource and performance gain obtained. To be specific, with CNMP model as the baseline, it is shown that the proposed model is able to learn to generate trajectories in the data set with a lower trajectory error measured as the mean absolute difference between the generated trajectory and the ground truth. Importantly, our model can perform well with relatively limited resources, i.e., with less number of neural network parameters compared to the baseline. To show that the findings from the controlled data set well-transfer to robot data, we use robot joint data in an LfD setting and compare the learning performance of the proposed model with the baseline model at equal complexity levels. The simulation experiments show that with also the robot joint data, the proposed model, C-CNMP, learns to generate the joint trajectories with significantly less error than the baseline model. Overall, our study improves the state of the art in sensorimotor trajectory learning and exemplifies how divide-and-conquer approaches can benefit deep learning architectures for resource economy.

Translanguaged practice in listening assessment: L1 vs. L2 responses in recall tasks

ABSTRACT Listening recall tasks, where test takers write L2 responses based on audio content, often inadvertently measure L2 writing skills, potentially compromising the accuracy of listening assessment. To address this concern, the present study draws inspiration from translanguaging, and employs a mixed-methods approach to investigate the potential of using L1 responses into recall tasks to mitigate the impact of L2 writing proficiency on task outcomes, thus enhancing task validity. Specifically, a listening recall task requiring L1 responses was developed and administered to 102 L2 learners in low and intermediate English proficiency. Their performance on this task was compared to a control task that required L2 responses. Follow-up interviews were also conducted. The results indicated that allowing L1 responses in the recall task led to better performance for intermediate-level L2 learners, enhanced representation of the listening construct, and garnered participants’ preference as a listening assessment approach. This suggests that utilising L1 responses has the potential to improve the construct and face validity of recall tasks, addressing the initial validity concern. Consequently, this investigation contributes to the refinement of listening task development and advocates for the application of translanguaged practices in language assessment, advancing the broader concept of translanguaging in language education.

Accuracy versus precision in boosted top tagging with the ATLAS detector

Abstract The identification of top quark decays where the top quark has a large momentum transverse to the beam axis, known as top tagging, is a crucial component in many measurements of Standard Model processes and searches for beyond the Standard Model physics at the Large Hadron Collider. Machine learning techniques have improved the performance of top tagging algorithms, but the size of the systematic uncertainties for all proposed algorithms has not been systematically studied. This paper presents the performance of several machine learning based top tagging algorithms on a dataset constructed from simulated proton-proton collision events measured with the ATLAS detector at √ s = 13 TeV. The systematic uncertainties associated with these algorithms are estimated through an approximate procedure that is not meant to be used in a physics analysis, but is appropriate for the level of precision required for this study. The most performant algorithms are found to have the largest uncertainties, motivating the development of methods to reduce these uncertainties without compromising performance. To enable such efforts in the wider scientific community, the datasets used in this paper are made publicly available.

Effects of game-based learning on academic outcomes: A study of technology acceptance and self-regulation in college students

ObjectiveThis study investigates the interplay between the Technology Acceptance Model (TAM), self-regulation strategies, and academic self-efficacy, and their collective impact on academic performance and perceived learning among college students engaged in remote education. MethodsA sample of 872 university students from Southern China participated in this study. Structural Equation Modeling (SEM) was employed to analyze the theoretical relationships among the variables. The research focused on two primary areas: the connection between academic self-efficacy and gameful self-regulation strategies within the framework of TAM, and the influence of TAM's three dimensions on students' perceived learning and academic performance. ResultsFindings highlight self-efficacy and gameful self-regulation strategies, in enhancing technology acceptance. Improved acceptance of technology is shown to positively affect academic performance and the perceived learning experience of students in classes using game-based online resources. ConclusionThe study emphasizes the significance of self-efficacy and gameful self-regulation strategies in shaping students' perceptions and attitudes towards technology. These factors are found to be key determinants of both perceived learning and academic achievement in the context of game-based online resource classes.

Exploring the Relationship between Online Learning, Student Health, and Academic Performance: Insights from Postgraduate Education in Egypt

Exploring the Relationship between Online Learning, Student Health, and Academic Performance: Insights from Postgraduate Education in Egypt

Entrepreneurial Learning, Digital Capabilities and Inclusive Entrepreneurial Performance

Entrepreneurial Learning, Digital Capabilities and Inclusive Entrepreneurial Performance

Network-Based Entrepreneurial Learning and Business Performance

Network-Based Entrepreneurial Learning and Business Performance

Examining students' self‐regulated learning processes and performance in an immersive virtual environment

Examining students' self‐regulated learning processes and performance in an immersive virtual environment

Nanoemulsion of Ethanolic Extract of Centella asiatica (NanoSECA)Ameliorates Learning and Memory Performance by EnhancingCholinergic Activities, Increasing Antioxidative Levels, and AttenuatingOxidative Stress Markers in Adult Rats.

Centella asiatica (C. asiatica) has long been traditionally used as a memory enhancer. Nanoemulsion of ethanolic extract C. asiatica (NanoSECA) has been developed to improve brain functions. However, the effect of NanoSECA on enhancing memory and cognitive functions remains unexplored. This research aimed to investigate the potential of NanoSECA on cognitive tasks and memory enhancement pathways in a normal adult rat model. Thirty male Sprague Dawley rats (7-8 weeks old) were randomly subjected to five groups (n=six per group). Treatment groups were supplemented with NanoSECA and ethanolic extract of C. asiatica (SECA) for 28 days by oral gavages. Different brain sections were isolated, homogenized, and tested for acetylcholinesterase, antioxidants (glutathione and malondialdehyde), and anti-inflammatory agents (nitric oxide, tumour necrosis factor-α, and prostaglandin E2). NanoSECA supplementation markedly enhanced the acetylcholine, glutathione levels and reduced a distinct diminution in plasma activities of acetylcholinesterase, malondialdehyde, nitric oxide, prostaglandin E, and tumor necrosis factor-α levels. NanoSECA can be used as a memory enhancer through enhanced cholinergic activity, increased antioxidant level, and reduced oxidative stress.

The use of genetic algorithm and particle swarm optimization on tiered feature selection method in machine learning-based coronary heart disease diagnosis system

Coronary heart disease (CHD) is a leading global cause of death. Early detection is the right step to reduce mortality rates and treatment costs. Early detection can be developed using machine learning by utilizing patient medical record datasets. Unfortunately, this dataset has excessive features which can reduce machine learning performance. For this reason, it is necessary to reduce the number of redundant features and irrelevant data to improve machine learning performance. Therefore, this research proposes a tiered of feature selection model with genetic algorithm (GA) and particle swarm optimization (PSO) to improve the performance of the diagnosis model. The feature selection model is evaluated using parameters derived from the confusion matrix and using the CatBoost machine learning algorithm. Model testing uses z-Alizadeh Sani, Cleveland, Statlog, and Hungarian datasets. The best results for this model were obtained on the z-Alizadeh Sani dataset with 6 selected features from 54 features and the resulting performance for accuracy parameters was 99.32%, specificity 98.57%, sensitivity 100.00%, area under the curve (AUC) 99.28%, and F1-Score 99.37%. The proposed feature selection model is able to provide machine learning performance in the very good category. The diagnostic model proposed is of excellent standard.

Detecting accelerated long-term forgetting remotely in a community sample of people with epilepsy: Evidence from the Crimes and Four Doors tests

People with epilepsy often report experiencing memory problems though these are not always detectable using standard neuropsychological measures. One form of difficulty that may be relatively prevalent in epilepsy is termed accelerated long-term forgetting (ALF), typically described as relatively greater loss of memory over days or weeks following initial encoding. The current study used remote assessment to examine memory and forgetting over one week in a broad community sample of people with epilepsy and healthy control participants, using two recently developed tests, one verbal (the Crimes test) and one visual (the Four Doors test). These were administered as part of a short battery of cognitive measures, run remotely with participants over Zoom. Across this community-derived sample, people with epilepsy reported more memory complaints and demonstrated significantly faster forgetting on both the verbal and visual tests. This difference was not attributable to level of initial learning performance and was not detectable through delayed recall on a standard existing test. Our results suggests that ALF may be more common than suspected in people with epilepsy, leading to a potentially important source of memory problems that are currently undetected by standard memory tests.

A data augmentation procedure to improve detection of spike ripples in brain voltage recordings

Epilepsy is a major neurological disorder characterized by recurrent, spontaneous seizures. For patients with drug-resistant epilepsy, treatments include neurostimulation or surgical removal of the epileptogenic zone (EZ), the brain region responsible for seizure generation. Precise targeting of the EZ requires reliable biomarkers. Spike ripples - high-frequency oscillations that co-occur with large amplitude epileptic discharges - have gained prominence as a candidate biomarker. However, spike ripple detection remains a challenge. The gold-standard approach requires an expert manually visualize and interpret brain voltage recordings, which limits reproducibility and high-throughput analysis. Addressing these limitations requires more objective, efficient, and automated methods for spike ripple detection, including approaches that utilize deep neural networks. Despite advancements, dataset heterogeneity and scarcity severely limit machine learning performance. Our study explores long-short term memory (LSTM) neural network architectures for spike ripple detection, leveraging data augmentation to improve classifier performance. We highlight the potential of combining training on augmented and in vivo data for enhanced spike ripple detection and ultimately improving diagnostic accuracy in epilepsy treatment.

Differential online and offline effects of theta-tACS on memory encoding and retrieval

Theta oscillations support memory formation, but their exact contribution to the communication between prefrontal cortex (PFC) and the hippocampus is unknown. We tested the functional relevance of theta oscillations as a communication link between both areas for memory formation using transcranial alternating current stimulation (tACS). Healthy, young participants learned two lists of Dutch-German word pairs and retrieved them immediately and with a 30-min delay. In the encoding group (N = 30), tACS was applied during the encoding of list 1. List 2 was used to test stimulation aftereffects. In the retrieval group (N = 23), we stimulated during the delayed recall. In both groups, we applied tACS bilaterally at prefrontal and tempo-parietal sites, using either individualized theta frequency or 15 Hz (as control), according to a within-subject design. Stimulation with theta-tACS did not alter overall learning performance. An exploratory analysis revealed that immediate recall improved when word-pairs were learned after theta-tACS (list 2). Applying theta-tACS during retrieval had detrimental effects on memory. No changes in the power of the respective frequency bands were observed. Our results do not support the notion that impacting the communication between PFC and the hippocampus during a task by bilateral tACS improves memory. However, we do find evidence that direct stimulation had a trend for negatively interfering effects during immediate and delayed recall. Hints for beneficial effects on memory only occurred with aftereffects of the stimulation. Future studies need to further examine the effects during and after stimulation on memory formation.

The Effect of Implementing Google Classroom-Based Learning Innovations and Technology Support on Learning Performance of Economics Faculty Students at Medan State University

This study aims to analyze the influence of the implementation of Google Classroom-based learning innovation and technological support on student learning performance in the Faculty of Economics, Universitas Negeri Medan. The research method used was a quantitative approach with a sample of students from the Faculty of Economics, Universitas Negeri Medan. The results show that the implementation of Google Classroom-based learning innovation and technological support have a positive and significant effect on student learning performance. These findings indicate that the use of online learning platforms such as Google Classroom, supported by the availability of adequate technology, can improve students' academic performance. The implication of this research is the need to improve lecturers' ability to utilize learning technologies, as well as the provision of adequate facilities and infrastructure to support online learning at the Faculty of Economics, Universitas Negeri Medan. This study provides insights for educational institutions in developing effective learning strategies through the integration of digital technology.

Enriching Students’ Vocabulary through Quizlet in Reading Class

This study explored teaching media “Quizlet” to enrich students’ vocabulary in reading class. This study aimed to analyze the students’ perceptions on the use of Quizlet as teaching media in reading class. This qualitative case study research was conducted in one of an Islamic Senior High School in Ciamis. This study involved a tenth- grade consisted of seventeen students which were chosen purposively as the sample of the study. The data were collected by using questionnaire. The results of this study indicate that students have positive perceptions about using Quizlet as a learning media to enrich their vocabulary. Students agreed that the Quizlet application motivated them to learn English vocabulary and improved their learning performance. It can be concluded that the Quizlet application is considered as a useful and fun learning media to enrich students' vocabulary. Furthermore, the researcher recommends that further researchers investigate the use of Quizlet at various levels of education to get more in- depth and specific results regarding the use of Quizlet media in learning vocabulary.

A two-stream decision fusion network for cervical pap-smear image classification tasks

Deep learning, especially Convolution Neural Networks (CNNs), has demonstrated superior performance in image recognition and classification tasks. They make complex pattern recognition possible by extracting image features through layers of abstraction. However, despite the excellent performance of deep learning in general image classification, its limitations are becoming apparent in specific domains such as cervical cell medical image classification. This is because although the morphology of cervical cells varies between normal, diseased and cancerous, these differences are sometimes very small and difficult to capture. To solve this problem, we propose a two-stream feature fusion model comprising a manual feature branch, a deep feature branch, and a decision fusion module. Specifically, We process cervical cells through a modified DarkNet backbone network to extract deep features. In order to enhance the learning of deep features, we have devised scale convolution blocks to substitute the original convolution, termed Basic convolution blocks. The manual feature branch comprises a range of traditional features and is linked to a multilayer perceptron. Additionally, we design three decision feature channels trained from both manual and deep features to enhance the model performance in cervical cell classification. Our proposed model demonstrates superior performance when compared to state-of-the-art cervical cell classification models. We establish a 15-category 148762 cervical cytopathology image dataset (CCID). In addition, we additionally conducted experiments on the SIPaKMeD dataset. Numerous experiments show that our proposed model performs excellently compared to state-of-the-art classification models. The outcomes illustrate that our approach can significantly aid pathologists in accurately evaluating cervical smears.

Enhancing Second Language Speech: The Roles Of Task Repetition And Planning In Improving L2 English Production

This paper explores the impact of task repetition and planning conditions on the complexity, accuracy, and fluency (CAF) of second language (L2) speech production. By conducting a case study on an L2 English learner, the study investigates how the learner's speech performance is characterized under the CAF construct and how it is affected by task repetition, the absence of pre-task planning, and the presence of unpressured within-task planning. The study employs various measures to assess lexical and grammatical complexity, accuracy, and fluency. The findings suggest that while the lack of pre-task planning did not completely compromise complexity, accuracy remained low despite the unpressured within-task planning condition, and fluency was negatively impacted. However, task repetition led to improvements in all three dimensions of CAF. The paper concludes with pedagogical implications for L2 instruction, highlighting the importance of strategic and guided pre-task planning, multiple-task repetitions, and learner self-evaluation to enhance CAF in L2 speech production.

Design and Research of an Intelligent Learning System for University Physics

In order to break through the limitations of traditional teaching, realize the integration of online and offline teaching, and optimize the intelligent learning experience of university physics, this paper proposes the design of an intelligent learning system for university physics based on cloud computing platforms, and applies this system to teaching environment of university physics. It successfully integrates emerging technologies such as cloud computing, machine learning, and situational awareness, integrates learning context awareness, intelligent recording and broadcasting, resource sharing, learning performance prediction, and content planning and recommendation, and comprehensively improves the quality of university physics teaching. It can optimize the teaching process and deepen intelligent teaching reform, aiming at providing references for the teaching practice of university physics.