Learning Performance Research Articles

Empowering voices: A deep dive into translanguaging perceptions among Turkish high school and university language learners

This study explores the perceptions of translanguaging among high school and university foreign language students in Turkey using a mixed-methods research design. 325 participants, comprising 155 high school and 170 university students, were surveyed to understand how translanguaging practices impact language learning, cultural integration, and academic performance. The study is grounded in Translanguaging Theory, Sociocultural Theory, and Pedagogical Translanguaging, emphasizing the fluid use of students' linguistic repertoires in language education. The findings reveal significant differences in perceptions based on gender, educational level, and age, highlighting the need for tailored translanguaging strategies to support diverse learner needs. This research contributes to the growing body of literature on translanguaging by providing empirical evidence from the Turkish educational context, offering insights into optimizing language teaching practices in multilingual settings.

Parents’ Perception of In-Person Classes, Parental Support, and Academic Performance of Learners: Basis for a Sustainable Parental Support Program

Parents’ Perception of In-Person Classes, Parental Support, and Academic Performance of Learners: Basis for a Sustainable Parental Support Program

Online / Distance Learning – Feedbacks A Priority!

A matter of current interest in recent times has been the noticeable growth experienced in the field of online higher education (OHE) and worldwide expansion, with higher educational institutions (HEI’s) offering a variety of programs. This phenomenal growth is mainly attributed to rapid digital transformations and a considerably improved demand for lifelong learning! It is preferred by a segment of the diaspora who have opted for higher education much later in life or would have faced obstacles as economic constraints, or failure in adjusting to work schedules, geographical and social barriers. Flexibility and access without time or geographical restrictions have been the most common reasons for preferring this mode of study. Feedback is a necessary skill for online instructors. Feedback is an important intervention for the online educator because it is an opportunity to develop the instructor-learner relationship, improve academic performance, and enhance learning. Effective online feedback from educators to learners is able to guide learners toward positive learning outcomes. An estimated 5.5 to 7.1 million students take at least one online course in the US according to the US Education Department and Babson Survey Research Group as reported by Kolowich (2014). India in recent years has found increased acceptance of the online education system, and students and working professionals have taken to different e-learning platforms in order to enhance their skills. A report released by KPMG India and Google indicates (Online Education in India: 2021), “the market for online education in India was expected to witness a magnificent growth of eight times in three years, i.e., from USD 247 million in 2016 to USD 1.96 billion in 2021”. This market is expected to grow multiple-folds in the next few years. An implication of providing effective online feedback is the positive impact for online learner performance.

The neuropsychological impacts of COVID-19 in non-hospitalized patients with long COVID and brain fog.

Coronavirus disease 2019 (COVID-19) causes persistent symptoms, including brain fog. Based on limited research on the long-term consequences of mild COVID-19, which has yielded inconsistent results, we investigated which cognitive functions were most affected by COVID-19 in non-hospitalized Asian patients with long-term COVID and subjective cognitive complaints. Fifty-five non-hospitalized patients with long COVID and brain fog (24 males and 31 females, mean age: 45.6 ± 14.6 years, mean duration of education: 14.4 ± 3.0 years) were recruited. Neuropsychological assessments included screening tests for overall cognition, and comprehensive tests for memory, executive function, processing speed, and subjective emotional and disease symptoms. Cognitive test scores were converted into Z-scores. Moreover, principal component analysis (PCA) was employed to define cognitive domains across subtest scores. Comprehensive assessments revealed cognitive impairment in 69.1% of patients (<1.5 standard deviation in at least one test). The processing speed (27.3%), memory recall (21.8%), memory learning (20.0%), and inhibitory control (18.2%) were the most affected areas. Self-reported anxiety and depression were observed in 35% and 33% of patients, respectively. Furthermore, the degree of self-anxiety can be used to predict learning performance. Nearly 70% of patients with subjective cognitive complaints and long COVID had objective cognitive impairments. A comprehensive evaluation is essential for patients with long COVID and brain fog, including those with mild symptoms.

Bayesian-Learning-Based Diffusion Least Mean Square Algorithms Over Networks.

To improve the learning performance of the conventional diffusion least mean square (DLMS) algorithms, this article proposes Bayesian-learning-based DLMS (BL-DLMS) algorithms. First, the proposed BL-DLMS algorithms are inferred from a Gaussian state-space model-based Bayesian learning perspective. By performing Bayesian inference in the given Gaussian state-space model, a variable step-size and an estimation of the uncertainty of information of interest at each node are obtained for the proposed BL-DLMS algorithms. Next, a control method at each node is designed to improve the tracking performance of the proposed BL-DLMS algorithms in the sudden change scenario. Then, a lower bound on the variable step-size of each node of the proposed BL-DLMS algorithms is derived to maintain the optimal steady-state performance in the nonstationary scenario (unknown parameter vector of interest is time-varying). Afterward, the mean stability and the transient and steady-state mean square performance of the proposed BL-DLMS algorithms are analyzed in the nonstationary scenario. In addition, two Bayesian-learning-based diffusion bias-compensated LMS algorithms are proposed to handle the noisy inputs. Finally, the superior learning performance of the proposed learning algorithms is verified by numerical simulations, and the simulated results are in good agreement with the theoretical results.

Explainable artificial intelligence for the interpretation of ensemble learning performance in algal bloom estimation.

Chlorophyll-a (Chl-a) concentrations, a key indicator of algal blooms, were estimated using the XGBoost machine learning model with 23 variables, including water quality and meteorological factors. The model performance was evaluated using three indices: root mean square error (RMSE), RMSE-observation standard deviation ratio (RSR), and Nash-Sutcliffe efficiency. Nine datasets were created by averaging 1hour data to cover time frequencies ranging from 1hour to 1month. The dataset with relatively high observation frequencies (1-24 h) maintained stability, with an RSR ranging between 0.61 and 0.65. However, the model's performance declined significantly for datasets with weekly and monthly intervals. The Shapley value (SHAP) analysis, an explainable artificial intelligence method, was further applied to provide a quantitative understanding of how environmental factors in the watershed impact the model's performance and is also utilized to enhance the practical applicability of the model in the field. The number of input variables for model construction increased sequentially from 1 to 23, starting from the variable with the highest SHAP value to that with the lowest. The model's performance plateaued after considering five or more variables, demonstrating that stable performance could be achieved using only a small number of variables, including relatively easily measured data collected by real-time sensors, such as pH, dissolved oxygen, and turbidity. This result highlights the practicality of employing machine learning models and real-time sensor-based measurements for effective on-site water quality management. PRACTITIONER POINTS: XAI quantifies the effects of environmental factors on algal bloom prediction models The effects of input variable frequency and seasonality were analyzed using XAI XAI analysis on key variables ensures cost-effective model development.

Introducing a novel dataset for facial emotion recognition and demonstrating significant enhancements in deep learning performance through pre-processing techniques

Facial expression recognition (FER) plays a pivotal role in various applications, ranging from human-computer interaction to psychoanalysis. To improve the accuracy of facial emotion recognition (FER) models, this study focuses on enhancing and augmenting FER datasets. It comprehensively analyzes the Facial Emotion Recognition dataset (FER13) to identify defects and correct misclassifications. The FER13 dataset represents a crucial resource for researchers developing Deep Learning (DL) models aimed at recognizing emotions based on facial features. Subsequently, this article develops a new facial dataset by expanding upon the original FER13 dataset. Similar to the FER + dataset, the expanded dataset incorporates a wider range of emotions while maintaining data accuracy. To further improve the dataset, it will be integrated with the extended Cohn-Kanade (CK+) dataset.This paper investigates the application of modern DL models to enhance emotion recognition in human faces. By training a new dataset, the study demonstrates significant performance gains compared with its counterparts. Furthermore, the article examines recent advances in FER technology and identifies critical requirements for DL models to overcome the inherent challenges of this task effectively. The study explores several DL architectures for emotion recognition in facial image datasets, with a particular focus on convolutional neural networks (CNNs). Our findings indicate that complex architecture, such as EfficientNetB7, outperforms other DL architectures, achieving a test accuracy of 78.9 %. Notably, the model surpassed the EfficientNet-XGBoost model, especially when used with the new dataset. Our approach leverages EfficientNetB7 as a backbone to build a model capable of efficiently recognizing emotions from facial images. Our proposed model, EfficientNetB7-CNN, achieved a peak accuracy of 81 % on the test set despite facing challenges such as GPU memory limitations. This demonstrates the model's robustness in handling complex facial expressions. Furthermore, to enhance feature extraction and attention mechanisms, we propose a new hybrid model, CBAM-4CNN, which integrates the convolutional block attention module (CBAM) with a custom 4-layer CNN architecture. The results showed that the CBAM-4CNN model outperformed existing models, achieving higher accuracy, precision, and recall metrics across multiple emotion classes. The results highlight the critical role of comprehensive and diverse data in enhancing model performance for facial emotion recognition.

The Analysis of Learning Performance from STEM Robotic Game with Design Thinking

The Analysis of Learning Performance from STEM Robotic Game with Design Thinking

Adaptive Synaptic Adjustment Mechanism to Improve Learning Performances of Spiking Neural Networks

ABSTRACTSpiking Neural Networks (SNNs) are currently attracting researchers' attention due to their efficiencies in various tasks. Spike‐timing‐dependent plasticity (STDP) is an unsupervised learning process that utilizes bio‐plausibility based on the relative timing of pre/post‐synaptic spikes of neurons. Integrated with STDP, SNNs perform well consuming less energy. However, it is hard to ensure that synaptic weights always converge to values guaranteeing accurate prediction because STDP does not change synaptic weights with supervision. To address this limitation, researchers have proposed mechanisms for inducing STDP to converge synaptic weights on the proper values referring to current synaptic weights. Thus, if the current weights fail to describe proper synaptic connections, they cannot induce STDP to update synaptic weights properly. To solve this problem, we propose an adaptive mechanism that helps STDP to converge synaptic weights directly based on input data features: Adaptive synaptic template (AST). AST leads synaptic weights to describe synaptic connections according to the data features. It prevents STDP from changing synaptic weights based on abnormal weights that fail to describe the proper synaptic connections. This is because it does not use the current synaptic weights that can disturb proper weight convergence. We integrate AST with an SNN and conduct experiments to compare it with a baseline (the SNN without AST) and benchmarks (previous works to improve STDP). Our experimental results show that the SNN using AST classifies various data sets with 6%–39% higher accuracy than the baseline and benchmarks.

DeepMarkerNet: Leveraging supervision from the Duchenne Marker for spontaneous smile recognition

Distinguishing between spontaneous and posed smiles from videos poses a significant challenge in pattern classification literature. Researchers have developed feature-based and deep learning-based solutions for this problem. To this end, deep learning outperforms feature-based methods. However, certain aspects of feature-based methods could improve deep learning methods. For example, previous research has shown that Duchenne Marker (or D-Marker) features from the face play a vital role in spontaneous smiles, which can be useful to improve deep learning performances. In this study, we propose a deep learning solution that leverages D-Marker features to improve performance further. Our multi-task learning framework, named DeepMarkerNet, integrates a transformer network with the utilization of facial D-Markers for accurate smile classification. Unlike past methods, our approach simultaneously predicts the class of the smile and associated facial D-Markers using two different feed-forward neural networks, thus creating a symbiotic relationship that enriches the learning process. The novelty of our approach lies in incorporating supervisory signals from the pre-calculated D-Markers (instead of as input in previous works), harmonizing the loss functions through a weighted average. In this way, our training utilizes the benefits of D-Markers, but the inference does not require computing the D-Marker. We validate our model’s effectiveness on four well-known smile datasets: UvA-NEMO, BBC, MMI facial expression, and SPOS datasets, and achieve state-of-the-art results.

CONTRIBUTION OF INCLUSIVE EDUCATION ON PERFORMANCE OF LEARNERS WITH LEARNING DIFFICULTIES IN PUBLIC PRIMARY SCHOOLS OF RWANDA A CASE OF KICUKIRO DISTRICT

Background: Inclusive Education is problematic in several countries including Rwanda and has been held back by a number of factors including negative attitudes towards people with disabilities. School administrators and teachers have not sufficient skills so that they can manage inclusive schools and it requires several and regular training to be equipped with necessary knowledge and get sensitized on how to introduce inclusive practices. The study examined the contribution of inclusive education on performance of learners with learning difficulties in Rwandan public primary schools especially in Kicukiro District. To examine the level of implementation of inclusive education to the performance of learners with learning difficulties in public primary schools, to assess the performance of learners with learning difficulties in public primary schools in general education, to establish the relationship between inclusive education and the performance of learners with learning difficulties in public primary schools. The target population of this research was 240 population, from which a sample size of 148 respondents chosen as the participants of the study were 70 parents of learners with disabilities from public primary schools selected 69 teachers, 6 head teachers and 3 sector educational inspectors of 3 sectors of Kicukiro District. Nine respondents (6 HTs and 3 SEIs) were sampled using a purposive sampling technique, while 148 respondents (69 teachers and 70 parents of learners with disabilities) were selected using a simple random sampling. Methods and Methodology: This study used a survey research design with questionnaires as instruments of data collection and guided interview. The SPSS version 2.0, Logical analysis and Microsoft Excel 2010 was used in description and interpretation of results via tables, chart and figures. The researcher provided recommendations and conclusions depending on the findings of the research. Results: The findings showed that the effort put in the implementation of inclusive education practices and their relationship between inclusive education and performance contributed to the learners achievement as 95% of teachers and 89% of the head teachers with SEIs, they assumed there was a close relationship between inclusive education and learners performance because one affected the other one. Conclusion: It is recommended to the ministry of education of Rwanda (MINEDUC), to include the contents and strategies that facilitate teaching and learning processes for learners with learning difficulties at all level of education. The further research should consider collecting data via observational methods, fieldwork, and classroom visits to check if the competencies that this study identified are indeed being applied in Rwandas classrooms.

Impact of Teacher’s Effectiveness on the Acquisition of Skills in Early Childhood Education (ECE)

The study was conducted to explore teacher effectiveness in the development of skills in early childhood education (ECE). The aim of this research work was to know to what extent the teacher is effective in the development of skills in early childhood students. Thus, the performance of learners was evaluated based on the impact of ECE resource rooms on the skills development of learners from the teacher's perception. A total of 170 teachers were chosen from elementary and secondary schools as a sample of this study. The effectiveness of the teachers in early childhood education (ECE) was evaluated using a self-created questionnaire. Data entry and subsequent statistical analysis were conducted using the Social Sciences Statistical Package (SPSS 21). The results revealed that male and female teacher perceptions about utilizing ECE resource rooms were different among student skills and competency development. It was concluded that a healthy learning environment is considered to be supportive in augmenting the development of the brain, as well as social and physical. The resource rooms should be established to boost prospective teachers' imagination and enable them to create stories. Teachers should be encouraged to raise discussions among students to gain their attention and support the learning process.

Assessing the Intersectionality of Language Anxiety and Outcomes for African Learners Writing Examinations in English

This study investigated the intersectionality of language anxiety, writing examinations in English, and outcomes for non-English mother-tongue learners in South Africa. The study focused on the impact of these three factors on learner performance and delved into this intersectionality by reviewing the literature on anxiety stemming from writing examinations and the impact of the language medium used in assessing learners. Qualitative document analysis was used to collect and analyse the data for this study. It involved gathering literature from psychology, education, and language studies to reveal a correlation between anxiety, writing examinations, and the Language of Learning and Teaching (LOLT). The study concluded that using English as a medium for examinations can have a negative impact on learners who may not be linguistically competent to express themselves effectively in English, even if they were taught using translanguaging pedagogies. It argued that the true potential and outcomes of learners will only be fully realised through the exam process if they are allowed to write examinations in their mother tongues; and recommended that the Department of Basic Education (DBE) should allow for examinations to be conducted in all official languages for all grades and encourage learners to write examinations in their mother tongues. The only examinations they should be required to write in English are those for English Additional Language, like Afrikaans mother tongue speakers who can write all their examinations in Afrikaans except for English as a subject. Keywords: Anxiety, English Hegemony, Examinations, Language of Learning and Teaching, Linguistic Injustice

A Self-Driven Ga2O3 Memristor Synapse for Humanoid Robot Learning.

In recent years, the rapid development of brain-inspired neuromorphic systems has created an imperative demand for artificial photonic synapses that operate with low power consumption. In this study, a self-driven memristor synapse based on gallium oxide (Ga2O3) nanowires is proposed and demonstrated successfully. This memristor synapse is capable of emulating a range of functionalities of biological synapses when exposed to 255nm light stimulation. These functionalities encompass peak time-dependent plasticity, pulse facilitation, and memory learning capabilities. It exhibits an ultrahigh paired-pulse facilitation index of 158, indicating exceptional learning performance. The transition from short-term memory to long-term memory can be attributed to the remarkable relearning capabilities. Furthermore, the potential applications of the memristor synapse is showcased through the successful manipulation of a humanoid intelligent robot. Upon establishing artificial intelligence (AI) systems, the control commands originating from the synaptic device can drive the humanoid robot to perform various actions. Based on the memristor synapses, the autonomous feedback system of the humanoid robot facilitates a good collaboration between robotic actions and bio-inspired light perception. Therefore, this research opens up an effective way to advance the development of neuromorphic computing technologies, AI systems, and intelligent robots that demand ultra-low energy consumption.

Improving Elementary Students’ Computational Thinking Skills through an Educational Robot Intervention: A Quasi-Experimental Study

Globally, many educational institutions recognize the importance of computational thinking and have begun incorporating it into primary education. Educators cultivate students’ computational thinking skills through block-based programming; however, a lack of digital learning tools that offer real interaction may negatively impact students’ computational thinking learning performances. This study proposes a cost-effective, block-based, programmable computational thinking educational robot developed using the open-source Arduino platform, combined with Android application development. This robot is specifically designed for use in elementary computational thinking education. To assess the impact of the proposed approach on elementary students’ learning achievement, motivation, and attitudes towards computational thinking education, a quasi-experimental design with control and experimental groups was implemented in the computational thinking curriculum at an elementary school. The experiment was conducted over a period of three weeks and involved two classes of students and one teacher. The control group engaged in computational thinking learning activities using computers, while the experimental group completed computational thinking learning activities using the computational thinking educational robot and application developed in this study. Data were collected through prior knowledge tests of computational thinking, learning motivation and attitude questionnaires, and computational thinking achievement tests completed by the students. The results indicate that the experimental group outperformed the control group in learning achievement, motivation, and attitudes, demonstrating that physical interaction in learning can effectively enhance learning performances.

THE DEVELOPMENT OF CHINESE VOCABULARY SKILL USING THE TASK BASED TEACHING METHOD OF GRADE 5 THAI STUDENTS

This study aimed to compare the learning performance of grade 5 Thai students in Chinese vocabulary skills before and after using a task-based teaching method, as well as their satisfaction. We collected the quantitative data through teaching, Chinese vocabulary skill tests (pre-test and post-test), and student satisfaction questionnaires. For the first research objective, we analyzed the data using a paired sample t-test, while the second objective relied on mean, standard deviation (SD), and thematic analysis. The study's findings demonstrated a significant improvement in Chinese vocabulary skills learning performance. All participants had high scores on the students' satisfaction questionnaires. It indicated a statistically significant improvement in Chinese vocabulary skills and students' satisfaction. This study clearly showed that students were very supportive of the task-based teaching method, which can improve Chinese vocabulary skills and students' satisfaction.

Cloud Computing Performance Evaluation Model for Open and Distance Learners in Nigeria

The increasing need for fast, secure and dynamic processing of information has necessitated the wide scale adoption of cloud computing. The educational sector especially the open and distance learning institutions are not left out of the need for distributed technology. This study presented a model that provided insight into the pre and post usage adoption variables associated with cloud computing adoption and performance in open and distance learning (ODL) setting. Partial Least Square (PLS) was adapted to test seven hypotheses on the causal relationship between the variables. Five out of the seven hypotheses were supported. The pre-usage and satisfaction oriented constructs showed more significant contributions in determining performance impact than the task technology fit oriented constructs. The study also provided insights on user preferences for decision making by educational institutions, service providers, business owners and government. Keywords: Cloud Computing, TUSPEM, Performance, Utilization, Cost, Ease Of Use

Comparative Analysis of Machine Learning Models and Hybrid Ensemble Approach’s for Landslide Prediction

The NH-44 Jammu Srinagar National Highway in India is susceptible to landslides, rock falls and shooting stones due to its geological characteristics and steep slopes. This study aims to compare the performance of various Machine Learning (ML) algorithms and hybrid models in predicting landslides using historical data. Seven optimized ML approaches Support Vector Classifier (SVC), Logistic Regression (LR), Decision Tree (DT), K Nearest Classifier (KNC), Random Forest (RF), GaussianNB (GNB) and AdaBoost Classifier (ABC) are used. Additionally, two Hybrid Ensemble methods, the Voting Hybrid Model (VHM) and Stacking Hybrid Model (SHM), are introduced. The performance of each model is evaluated using accuracy, precision, recall, F1-score and AUC metrics. Results indicate that all the models performed well, with hybrid ensemble models surpassing all individual algorithms. The Stacking Hybrid Model (SHM) excels achieving 99.4% accuracy and 98.5% AUC, outperforming the Voting Hybrid Model (VHM). Hybrid models consistently outperform individual models in accuracy and AUC. These proposed methods exhibit robustness and enhanced results in addressing this issue. This framework can help to predict the landslides with high accuracy which can save the lives through timely evacuations from high-risk areas.

The Role of Growth Mindset on the Relationships between Students’ Perceptions of English Language Teachers’ Feedback and Their ESL Learning Performance

The importance of growth mindset and teachers’ feedback has been widely recognised to improve the English language performance of students; however, the impact of growth mindset as a mediator is least explored. Therefore, the study aimed to empirically analyse the interrelationships between growth mindset and teachers’ feedback levels on secondary school students’ English as a Second Language (ESL) performance and to study the mediation effects of growth mindset in the relationships. The research model examined growth mindset along with four types of feedback. The levels of feedback include task, process, self-regulation and self-based feedback that teachers provide to improve the ESL performance of students. Survey questionnaires were administered to 301 secondary school students in Class 9 from two private schools in India. The data were analysed using PLS-SEM 4.0 software. The results indicated that the direct effect of feedback that emphasised process and self-regulation fosters a growth mindset in ESL students. Feedback levels focused on task, process, self-regulation, and growth mindset significantly impact ESL performance. Moreover, growth mindset mediated the relationships between process and self-regulation-focused feedback and ESL performance. However, no evidence supports the relationship between self-focused feedback, growth mindset, and ESL performance. The study concludes with implications and directions for future research.

Implementation Of Education Quality Assurance (PMP) In The Context Of Improving PAI Learning Performance

This study aims to describe the implementation of education quality assurance in improving PAI learning at MA At-tadzkir Kaliaren Grobogan. This research uses a type of descriptive qualitative research. Data collection techniques using interviews, observations, and document reviews. While data analysis is used, interactive analysis models include data reduction, data delivery, and conclusions. Based on the results of the study, the quality mapping carried out by the madrasah to improve PAI learning, in general, has been carried out well. The preparation of quality fulfillment plans carried out by the madrasah is quite good. The implementation of quality fulfillment carried out by madrasah to improve PAI learning is quite good, meaning that 8 national standards of education have been fulfilled in the implementation of madrasah, namely fulfillment of content standards, fulfillment of process standards, fulfillment of graduate competency standards, fulfillment of standards of educators and educational personnel, fulfillment of standards of facilities and infrastructure, fulfillment of management standards, fulfillment of financing standards and fulfillment of educational assessment standards. The quality evaluation/audit conducted by the madrasah to improve PAI learning is quite good, shown by the implementation of formative evaluation referring to process indicators, summative evaluation referring to indicators of output, outcome, and impact, and auditing the SNP fulfillment process according to a previously set plan