Assisted Learning Research Articles

Learning Assistance Program through puzzles to Improve Students' Arabic Language Skills

Learning Assistance Program through puzzles to Improve Students' Arabic Language Skills

From cognitive coach to social architect: shifts in learning assistants’ valued practices

BackgroundLearning assistants (LAs) are undergraduate students who serve as instructional assistants in STEM classrooms. In addition to engaging in active practice, they take a pedagogy seminar and regularly meet with a content instructor. While aspects of LAs’ pedagogical beliefs and actions have been investigated, there remains a gap in understanding how LAs make sense of their new instructional roles and how they negotiate between their experiences as students and their responsibilities as instructors. This study uses a sequential, exploratory mixed-methods approach, which includes constant comparative open-coding, thematic analysis, and epistemic network analysis, to analyze 178 reflections written by 89 LAs across five terms at two institutions. Here, we identify each LA’s expressed goals and intended actions at the start and the end of their first term as an LA. Using a community of practice framework, we seek to explicate the shifts in these LAs’ values as they become more central members of the LA community.ResultsLAs’ expressed roles shift from being cognitive coaches, where they focus on student thinking, sense-making, and understanding of disciplinary concepts, to being social architects, where their focus shifts to attending to the aspects of the environment that can support productive interactions for learning. A social architect prioritizes goals related to mutual trust, respect, & approachability, understanding and learning about students, and creating a sense of belonging. Similarly, their intended actions emphasize compassion, understanding, and facilitating group discussion. While all LAs studied exhibited this shift, it manifested in different ways and to different extents, as illustrated in detail by four selected cases. These cases illustrate how the shifts coupled to a change in language around teaching, becoming more specific and contextual.ConclusionsLAs express a shift in their valued practices over their first term as LAs related to their instructional role. The goal of student-centered instructional practice is often framed as becoming a better cognitive coach; however, this orientation does not foreground ideas around teaching practice that aim to foster engagement, belonging, and student agency. Implications for both the LA model and, more generally, for postsecondary STEM instructors are discussed.

Utilisation of ChatGPT and other Artificial Intelligence tools among medical faculty in Uganda: a cross-sectional study

Background ChatGPT is an open-source large language model that uses deep learning techniques to generate human-like texts. ChatGPT has the potential to revolutionize medical education as it acts as an interactive virtual tutor and personalized learning assistant. We assessed the use of ChatGPT and other Artificial Intelligence (AI) tools among medical faculty in Uganda. Methods We conducted a descriptive cross-sectional study among medical faculty at four public universities in Uganda from November to December 2023. Participants were recruited consecutively. We used a semi-structured questionnaire to collect data on participants’ socio-demographics and the use of AI tools such as ChatGPT. Our outcome variable was the use of ChatGPT and other AI tools. Data were analyzed in Stata version 17.0. Results We recruited 224 medical faculty, majority [75% (167/224)] were male. The median age (interquartile range) was 41 years (34–50). Almost all medical faculty [90% (202/224)] had ever heard of AI tools such as ChatGPT. Over 63% (120/224) of faculty had ever used AI tools. The most commonly used AI tools were ChatGPT (56.3%) and Quill Bot (7.1%). Fifty-six faculty use AI tools for research writing, 37 for summarizing information, 28 for proofreading work, and 28 for setting exams or assignments. Forty faculty use AI tools for non-academic purposes like recreation and learning new skills. Faculty older than 50 years were 40% less likely to use AI tools compared to those aged 24 to 35 years (Adjusted Prevalence Ratio (aPR):0.60; 95% Confidence Interval (CI): [0.45, 0.80]). Conclusion The use of ChatGPT and other AI tools was high among medical faculty in Uganda. Older faculty (>50 years) were less likely to use AI tools compared to younger faculty. Training on AI use in education, formal policies, and guidelines are needed to adequately prepare medical faculty for the integration of AI in medical education.

Clinical Utility of Deep Learning Assistance for Detecting Various Abnormal Findings in Color Retinal Fundus Images: A Reader Study.

To evaluate the clinical usefulness of a deep learning-based detection device for multiple abnormal findings on retinal fundus photographs for readers with varying expertise. Fourteen ophthalmologists (six residents, eight specialists) assessed 399 fundus images with respect to 12 major ophthalmologic findings, with or without the assistance of a deep learning algorithm, in two separate reading sessions. Sensitivity, specificity, and reading time per image were compared. With algorithmic assistance, readers significantly improved in sensitivity for all 12 findings (P < 0.05) but tended to be less specific (P < 0.05) for hemorrhage, drusen, membrane, and vascular abnormality, more profoundly so in residents. Sensitivity without algorithmic assistance was significantly lower in residents (23.1%∼75.8%) compared to specialists (55.1%∼97.1%) in nine findings, but it improved to similar levels with algorithmic assistance (67.8%∼99.4% in residents, 83.2%∼99.5% in specialists) with only hemorrhage remaining statistically significantly lower. Variances in sensitivity were significantly reduced for all findings. Reading time per image decreased in images with fewer than three findings per image, more profoundly in residents. When simulated based on images acquired from a health screening center, average reading time was estimated to be reduced by 25.9% (from 16.4 seconds to 12.1 seconds per image) for residents, and by 2.0% (from 9.6 seconds to 9.4 seconds) for specialists. Deep learning-based computer-assisted detection devices increase sensitivity, reduce inter-reader variance in sensitivity, and reduce reading time in less complicated images. This study evaluated the influence that algorithmic assistance in detecting abnormal findings on retinal fundus photographs has on clinicians, possibly predicting its influence on clinical application.

The Development of Free-Response Questions to Assess Learning Assistants’ Pedagogical Content Knowledge

The Development of Free-Response Questions to Assess Learning Assistants’ Pedagogical Content Knowledge

Building pedagogical partnerships

Engaging students as pedagogical partners in teaching and learning in higher education is becoming increasingly prevalent. However, developing and sustaining such partnerships can be challenging. The present study highlights the potential of utilizing work-integrated learning (WIL) students as partners. Semi-structured interviews were conducted with 18 university instructors to explore how access to an online learning assistant (OLA) program helped them navigate remote instruction challenges. The OLA program was a novel WIL initiative providing co-operative (co-op) education students with full-time, paid work to assist instructors transitioning to remote learning. Unexpectedly, our findings demonstrate that pedagogical partnerships emerged in the context of this WIL program, leading to teaching and learning benefits. Online learning assistants were able to assist instructors with many of the difficulties they faced, although some program challenges also emerged. Our findings suggest that full-time, paid co-op student positions offer a unique program structure that make them ideal for the development and ongoing success of pedagogical partnerships.

Deep learning assists early-detection of hypertension-mediated heart change on ECG signals.

Arterial hypertension is a major risk factor for cardiovascular diseases. While cardiac ultrasound is a typical way to diagnose hypertension-mediated heart change, it often fails to detect early subtle structural changes. Electrocardiogram(ECG) represents electrical activity of heart muscle, affected by the changes in heart's structure. It is crucial to explore whether ECG can capture slight signals of hypertension-mediated heart change. However, reading ECG records is complex and some signals are too subtle to be captured by cardiologist's visual inspection. In this study, we designed a deep learning model to predict hypertension on ECG signals and then to identify hypertension-associated ECG segments. From The First Affiliated Hospital of Xiamen University, we collected 210,120 10-s 12-lead ECGs using the FX-8322 manufactured by FUKUDA and 812 ECGs using the RAGE-12 manufactured by NALONG. We proposed a deep learning framework, including MML-Net, a multi-branch, multi-scale LSTM neural network to evaluate the potential of ECG signals to detect hypertension, and ECG-XAI, an ECG-oriented wave-alignment AI explanation pipeline to identify hypertension-associated ECG segments. MML-Net achieved an 82% recall and an 87% precision in the testing, and an 80% recall and an 82% precision in the independent testing. In contrast, experienced clinical cardiologists typically attain recall rates ranging from 30 to 50% by visual inspection. The experiments demonstrate that ECG signals are sensitive to slight changes in heart structure caused by hypertension. ECG-XAI detects that R-wave and P-wave are the hypertension-associated ECG segments. The proposed framework has the potential to facilitate early diagnosis of heart change.

Machine Learning Algorithm for Enhanced Cybersecurity: Identification and Mitigation of Emerging Threats

Machine learning (ML) methodologies have significantly transformed cybersecurity by offering sophisticated instruments that not only identify but also avert and alleviate cyber threats. This research study seeks to examine the convergence of machine learning and cybersecurity, focusing on diverse methodologies and their use in enhancing cybersecurity measures. The study examines several machines learning methods, including Graph Neural Networks, Adversarial Learning, Federated Learning, Explainable AI, and Reinforcement Learning. Every algorithm is essential for enhancing the identification and mitigation of cyber assaults. Graph Neural Networks facilitate the modelling of intricate linkages within cybersecurity data. It aids not just in forecasting future events but also in identifying anomalies and analyzing network traffic. Adversarial Learning assists in training machine learning models to address the difficulty of producing misleading input data that can deceive any model, hence enhancing their efficacy. Federated Learning is examined as a method for training machine learning models across decentralized networks while preserving data privacy and enhancing model accuracy. Explainable AI methodologies primarily offer transparency and interpretability in machine learning-driven cybersecurity decisions, which are crucial for comprehension and confidence in automated security systems. Reinforcement Learning is focused on a trial-and-error methodology, wherein the model acquires new tasks through a system of rewards and penalties. These sophisticated algorithms jointly improve the effectiveness, precision, and clarity of cybersecurity protocols, offering strong protection against emerging cyber threats.

Meningkatkan Hasil Belajar Dan Bernalar Kritis Pakbp Melalui Model PBL Berbantuan Wayang Kardus Fase B Kelas IV

Nowadays, Critical Thinking plays a significant role and totally needed because it is closely related to the improvement of Profile Pelajar Pancasila as one of the Indonesian educational goals. It helps students to understand and prefer to be a selective person in giving and taking information, and it also makes the students become wiser in taking a decision based on Pancasila values. In fact, it is still found that there are many elementary school students' critical thinking abilities are still low. The purpose in doing this research is in order to know the effect of the Problem Based Learning (PBL) method to assisted cardboard puppet learning media on the result of learning and critical thinking skills in the subject of Catholic Religious Education and Character (PAKBP) about "The Ten Commandments of God as a Guide to Life" for grade 4th students, Phase B at Panggung Lor Elementary School, Semarang City. The method used in this research is Classroom Action Research (CAR). The population in this research is 12 students grade IV at Panggung Lor Elementary School, Semarang City, in the 1st semester academic year of 2024-2025.In analyzing the data, the researcher used descriptive analysis. It includes the results of observations of students' critical thinking skill in the PAKBP learning process using the PBL method of assisted cardboard puppet learning media and test data result of students' learning.The results of observations of student activities are analyzed descriptively using percentage statistics. The results of the research show that the application of the Problem Based Learning (PBL) with the help of cardboard puppets can improve learning outcomes and critical thinking abilities of students in the subject of Catholic Religious Education and Character Class IV, Phase B at Panggung Lor State Elementary School, Semarang City.

YOLOv7-KDT: An ensemble model for pomelo counting in complex environment

Pomelo counting recognition in complex environments faces many difficulties, mainly including changes in illumination, occlusion, and complex backgrounds. These factors contribute to the poor recognition performance of early models such as Faster R-CNN, SSD, and Efficientdet. This study optimized the YOLOv7 object detection network through several strategies for this issue. The main optimization strategies are: (1) Introducing the SEAM module to improve the detection ability for occluded objects; (2) Using the AIFI attention mechanism to enhance the network’s recognition of small objects; (3) Adopting the LAMP pruning technique to reduce model complexity; (4) Utilizing multi-teacher knowledge distillation for model compression and performance enhancement. The results show that under the assisted learning of the student module by the multi-teacher module distillation, the proposed method improves mAP by more than 1.9% compared to the aforementioned early models and other networks. After LAMP pruning, the model size is reduced by at least 93.6%. After knowledge distillation processing, its mAP is increased from 84.2% to 91.1%, achieving high-precision pomelo counting recognition. This study effectively solves automatic pomelo recognition and counting in complex environments. The method can be generalized to other agricultural product detection and statistics scenarios, having broad application prospects.

Tajweed Learning Education and Al-Qur'an Reading Assistance with the Ummi Method for 'Aisyiyah Jiken Branch Mothers

This community service activity aims to improve the ability of Aisyiyah mothers at the Al-Jihad Jiken Tulangan mosque to read the Qur'an correctly according to the rules of tajwid through the Ummi method with the Quran Explore method. The Ummi method was chosen because of its simplicity and effectiveness in teaching tajwid to adults. This activity was carried out through several stages, namely the introduction of the Ummi method, learning the theory of tajwid, application in reading the Qur'an, and group incentive assistance. The implementation of the activity was carried out in 4 meetings, with an evaluation carried out at the end of the program. The results obtained after the tajwid learning assistance program for the mothers of the 'Aisiyah Jiken branch leaders showed significant results, where students were able to read more fluently by understanding the basic science of tajwid. This assistance program succeeded in motivating students to continue learning and practicing independently. With this activity, it is hoped that it can be sustainable as a routine program to improve reading the Qur'an among the community.

Performance of ChatGPT on Nursing Licensure Examinations in the United States and China: Cross-Sectional Study.

The creation of large language models (LLMs) such as ChatGPT is an important step in the development of artificial intelligence, which shows great potential in medical education due to its powerful language understanding and generative capabilities. The purpose of this study was to quantitatively evaluate and comprehensively analyze ChatGPT's performance in handling questions for the National Nursing Licensure Examination (NNLE) in China and the United States, including the National Council Licensure Examination for Registered Nurses (NCLEX-RN) and the NNLE. This study aims to examine how well LLMs respond to the NCLEX-RN and the NNLE multiple-choice questions (MCQs) in various language inputs. To evaluate whether LLMs can be used as multilingual learning assistance for nursing, and to assess whether they possess a repository of professional knowledge applicable to clinical nursing practice. First, we compiled 150 NCLEX-RN Practical MCQs, 240 NNLE Theoretical MCQs, and 240 NNLE Practical MCQs. Then, the translation function of ChatGPT 3.5 was used to translate NCLEX-RN questions from English to Chinese and NNLE questions from Chinese to English. Finally, the original version and the translated version of the MCQs were inputted into ChatGPT 4.0, ChatGPT 3.5, and Google Bard. Different LLMs were compared according to the accuracy rate, and the differences between different language inputs were compared. The accuracy rates of ChatGPT 4.0 for NCLEX-RN practical questions and Chinese-translated NCLEX-RN practical questions were 88.7% (133/150) and 79.3% (119/150), respectively. Despite the statistical significance of the difference (P=.03), the correct rate was generally satisfactory. Around 71.9% (169/235) of NNLE Theoretical MCQs and 69.1% (161/233) of NNLE Practical MCQs were correctly answered by ChatGPT 4.0. The accuracy of ChatGPT 4.0 in processing NNLE Theoretical MCQs and NNLE Practical MCQs translated into English was 71.5% (168/235; P=.92) and 67.8% (158/233; P=.77), respectively, and there was no statistically significant difference between the results of text input in different languages. ChatGPT 3.5 (NCLEX-RN P=.003, NNLE Theoretical P<.001, NNLE Practical P=.12) and Google Bard (NCLEX-RN P<.001, NNLE Theoretical P<.001, NNLE Practical P<.001) had lower accuracy rates for nursing-related MCQs than ChatGPT 4.0 in English input. English accuracy was higher when compared with ChatGPT 3.5's Chinese input, and the difference was statistically significant (NCLEX-RN P=.02, NNLE Practical P=.02). Whether submitted in Chinese or English, the MCQs from the NCLEX-RN and NNLE demonstrated that ChatGPT 4.0 had the highest number of unique correct responses and the lowest number of unique incorrect responses among the 3 LLMs. This study, focusing on 618 nursing MCQs including NCLEX-RN and NNLE exams, found that ChatGPT 4.0 outperformed ChatGPT 3.5 and Google Bard in accuracy. It excelled in processing English and Chinese inputs, underscoring its potential as a valuable tool in nursing education and clinical decision-making.

Can I Collaborate with You? An Investigation of Trust in Generative AI

ABSTRACTThis study investigates the role of trust in human‐AI collaboration in K‐12 education, focusing on generative AI. Using a two‐factor experimental design (n = 26), we examined attitudes toward AI and creativity level as independent variables and assessed cognitive trust, affective trust, perceptions of usability, and continuance intention to use generative AI tools in text‐to‐text (ChatGPT) and text‐to‐image (Canva) tasks. The results is analyzed with two‐way ANOVA, we find that: (1) text‐to‐text human‐AI collaboration tends to foster higher emotional engagement and trust compared to text‐to‐image human‐AI collaboration; (2) perceptions of usability and continuance intention to use are slightly higher in text‐to‐text interactions, suggesting a preference for text‐based generative AI tools; (3) significant interactive effects between attitudes toward AI and creativity were observed across all measured variables, highlighting the importance of considering both factors in understanding and improving human‐AI collaboration in educational settings, contributing to research on generative AI for learning assistance.

Unveiling the influence of pedagogical content knowledge in questioning on college students’ conceptual learning of introductory physics

Learning assistants (LAs) play a pivotal role in transforming traditional physics instruction toward a more inquiry-oriented approach. While empirical evidence supports the effectiveness of LA-involved physics instruction, there is a research gap regarding the specific competencies of LAs that contribute to improved conceptual understanding. One conjectured reason is LAs’ inquiry-oriented pedagogical skills, like questioning, which engender more effective interactions with students at points of instructional needs. This study addresses the gap by constructing a model delineating the contribution of LAs’ competencies of questioning, referred to as pedagogical content knowledge in questioning (PCK-Q), to students’ conceptual learning in introductory classical mechanics and electromagnetism. The participants included an instructional team comprising instructors, graduate teaching assistants, and LAs, and students from two sections over two semesters. PCK-Q was measured using a prevalidated instrument of free-response questions from our previous study, which could predict LAs’ questioning practices. Employing a pre-post design, students’ learning gain in conceptual understanding and critical thinking was assessed, and separate models were constructed to explore the relationship between LAs’ PCK-Q and students’ learning gain. Findings suggest that LAs’ PCK-Q has a significant but slight impact on students’ conceptual learning, with little impact on critical thinking. Furthermore, we developed Likert-scale questions, derived equations to quantify PCK-Q from Likert-scale ratings, verified the feasibility of this streamlined approach in measuring LAs’ PCK-Q, and discussed its limitations. The implications of the research findings are discussed in the context of physics instruction and LA preparation. Published by the American Physical Society 2024

Student voice and choice in the virtual classroom: engagement strategies

The coronavirus pandemic has compelled a transition to distance and online education, requiring instructors and students to adjust swiftly. During this transition period, it became crucial to prioritize comprehending students’ perspectives and decision-making within virtual educational environments. The present study investigates the strategies a GPCOM (Purposive Communication) instructor employs at a premier university to enhance student autonomy and decision-making through student voice and choice in the online learning environment. Data were collected via a survey comprising Likert scale items and open-ended questions from the 335 participants who participated in the study. The study results indicate that educators significantly facilitate student engagement in expressing their thoughts and ideas, promoting self-discovery, critical thinking, and collaborative problem-solving. Student preferences noted that active learning, utilization of technology, and engagement in class discussions were prominent options. Several strategies were employed to promote student engagement, such as fostering cooperation, implementing interactive gamification techniques, establishing real-life linkages, facilitating class debates, and encouraging self-directed learning. This study emphasizes the crucial role of instructor assistance in virtual learning while recognizing and integrating student preferences. Doing so aims to create a well-rounded and captivating virtual learning experience.

Undergraduate Teaching and Learning Assistants Provide Feedback as Part of a Formative Assessment System

Undergraduate Teaching and Learning Assistants Provide Feedback as Part of a Formative Assessment System

Learning assistance for students with special needs at SLB Kirana Hati Bunda, Tamiajeng Village, Trawas District

The purpose of this community service is to help provide learning assistance to students at SLB Kirana Hati Bunda Tamiajeng Village. The service activities carried out at Kirana Hati Bunda SLB use a hands-on method. This activity was carried out well and smoothly. With this service activity, it provides a more enjoyable and effective learning experience and can provide additional support for students.

Based on Medicine, The Now and Future of Large Language Models.

This review explores the potential applications of large language models (LLMs) such as ChatGPT, GPT-3.5, and GPT-4 in the medical field, aiming to encourage their prudent use, provide professional support, and develop accessible medical AI tools that adhere to healthcare standards. This paper examines the impact of technologies such as OpenAI's Generative Pre-trained Transformers (GPT) series, including GPT-3.5 and GPT-4, and other large language models (LLMs) in medical education, scientific research, clinical practice, and nursing. Specifically, it includes supporting curriculum design, acting as personalized learning assistants, creating standardized simulated patient scenarios in education; assisting with writing papers, data analysis, and optimizing experimental designs in scientific research; aiding in medical imaging analysis, decision-making, patient education, and communication in clinical practice; and reducing repetitive tasks, promoting personalized care and self-care, providing psychological support, and enhancing management efficiency in nursing. LLMs, including ChatGPT, have demonstrated significant potential and effectiveness in the aforementioned areas, yet their deployment in healthcare settings is fraught with ethical complexities, potential lack of empathy, and risks of biased responses. Despite these challenges, significant medical advancements can be expected through the proper use of LLMs and appropriate policy guidance. Future research should focus on overcoming these barriers to ensure the effective and ethical application of LLMs in the medical field.

It’s Personal and Pedagogical: Peer Learning Assistants Use Multiple Strategies to Support Student Learning in College Biology Courses

It’s Personal and Pedagogical: Peer Learning Assistants Use Multiple Strategies to Support Student Learning in College Biology Courses

Fatigue Crack Detection Based on Semantic Segmentation Using DeepLabV3+ for Steel Girder Bridges

Artificial intelligence technology is receiving more and more attention in structural health monitoring. Fatigue crack detection in steel box girders in long-span bridges is an important and challenging task. This paper presents a semantic segmentation network model for this task based on DeepLabv3+, ResNet50, and active learning. Specifically, the classification network ResNet50 is re-tuned using the crack image dataset. Secondly, with the re-tuned ResNet50 as the backbone network, a crack semantic segmentation network was constructed based on DeepLabv3+, which was trained with the assistance of active learning. Finally, optimization for the probability threshold of the pixel category was performed to improve the pixel-level detection accuracy. Tests show that, compared with the crack detection network based on conventional ResNet50, this model can improve MIoU from 0.6181 to 0.7241.