Active Learning Strategies Research Articles

Hyperactive learning for data-driven interatomic potentials

Data-driven interatomic potentials have emerged as a powerful tool for approximating ab initio potential energy surfaces. The most time-consuming step in creating these interatomic potentials is typically the generation of a suitable training database. To aid this process hyperactive learning (HAL), an accelerated active learning scheme, is presented as a method for rapid automated training database assembly. HAL adds a biasing term to a physically motivated sampler (e.g. molecular dynamics) driving atomic structures towards uncertainty in turn generating unseen or valuable training configurations. The proposed HAL framework is used to develop atomic cluster expansion (ACE) interatomic potentials for the AlSi10 alloy and polyethylene glycol (PEG) polymer starting from roughly a dozen initial configurations. The HAL generated ACE potentials are shown to be able to determine macroscopic properties, such as melting temperature and density, with close to experimental accuracy.

One Class One Click: Quasi scene-level weakly supervised point cloud semantic segmentation with active learning

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed and contribute to attaining competitive results under weak supervision strategy. Revisiting current weak label forms, we introduce One Class One Click (OCOC), a low cost yet informative quasi scene-level label, which encapsulates both point-level and scene-level annotations. An active weakly supervised framework is proposed to leverage scarce labels by involving weak supervision from both global and local perspectives. Contextual constraints are imposed by an auxiliary scene classification task, respectively based on global feature embedding and point-wise prediction aggregation, which restricts the model prediction merely to OCOC labels within a sub-cloud. Furthermore, we design a context-aware pseudo labeling strategy, which effectively supplement point-level supervisory signals subject to OCOC labels. Finally, an active learning scheme with a uncertainty measure — temporal output discrepancy is integrated to examine informative samples and provides guidance on sub-clouds query, which is conducive to quickly attaining desirable OCOC annotations and reduces the labeling cost to an extremely low extent. Extensive experimental analysis using three LiDAR benchmarks respectively collected from airborne, mobile and ground platforms demonstrates that our proposed method achieves very promising results though subject to scarce labels. It considerably outperforms genuine scene-level weakly supervised methods by up to 25% in terms of average F1 score and achieves competitive results against full supervision schemes. On terrestrial LiDAR dataset — Semantics3D, using approximately 2‱ of labels, our method achieves an average F1 score of 85.2%, which increases by 11.58% compared to the baseline model. Codes are publicly available at https://github.com/PuzoW/One-Class-One-Click.

A multiscale computational framework using active learning to model complex suspension flows

We devise a novel computational framework to achieve efficient multiscale modeling for suspension flows. The modeling framework comprises a particle-resolving direct numerical simulation for microscopic computation, a single-fluid continuum model to capture the bulk flow behavior at the macroscale, and a Gaussian process regression that connects the two modeling components. The microscopic calculation simulates detailed flow fields around individual suspended particles. Along with a coarse-grained method, we are able to obtain the mean volume fractions and stresses for discrete particles, which are then further used to calculate the rheological properties of the bulk flow fields at the macroscale under specific forcing conditions. Using Gaussian process regression, a few data points from the microscopic calculations can be further interpolated/extrapolated to form complete constitutive relationships that cover the whole forcing range in macroscopic calculations (i.e., continuum modeling). Moreover, via the uncertainties returned from the Gaussian process regression, the resulting active learning strategy using the Gaussian process regression automatically decides on the required the microscopic calculations given by a specified tolerance. As a result, complex suspension problems can be efficiently solved by the macroscopic continuum model to the desired accuracy with the minimum computational effort (i.e., minimum number of microscopic runs). Four examples are demonstrated, among which two examples involve particle migration as a function of the particle stress, and the resulting nonuniform distribution of particles. This demands a multivariate Gaussian process regression, which is found to be particularly effective in achieving high computational efficiency compared with the off-line cases, i.e., a large number of off-line microscopic calculations to obtain the prescribed constitutive relationships.

The Assembly of a New Human Osteological Collection: The XXI CEIC as a Forensic Pedagogical Tool

This technical note aims to characterize and contextualize the creation of a new collection of identified skeletons stored in the University Institute of Health Sciences—CESPU. This project presents unique and innovative pedagogical opportunities, with students actively involved in the cleaning and processing of the bones and antemortem/postmortem information gathering, as well as in anthropology research projects. This XXI Century Identified Skeletal Collection is composed of 98 complete adult skeletons of both sexes and is still expanding, being the 10th contemporary collection available in Portugal. The skeletons consist exclusively of Portuguese nationals who died between 1946 and 2007, and the 42% that have been processed so far are in good preservation. Comparative learning outcomes after implementing this active learning strategy are not yet available. Improvements are expected since more participation and enthusiasm in classes and research were perceived.

Predicting academic performance of learners with the three domains of learning data using neuro-fuzzy model and machine learning algorithms

In recent days, learners faced difficulties learning programming courses. This research study will help the learners learn complex concepts quickly with different activities like flipped classrooms, online quizzes, learning by doing, and a virtual laboratory. This research is carried out to address the difficulties of learners and cover all the domains of learning, including knowledge, Skill, and Attitude. The fuzzy logic method has recently been applied in education to overcome these restrictions. While employing the fuzzy logic approach to evaluate student achievement, qualifications are assessed qualitatively rather than quantitatively. This research study applies Fuzzy Logic in the first stage, Factor Analysis (FA), and Machine Learning (ML) techniques in the second stage to discover essential factors associated with the effective use of Active Learning Strategies (ALS) in the Learning Management System (LMS) of information technology course learners. Fuzzy logic and neural network topology can be coupled using ANFIS, an adaptable network. FA is performed to find the critical factors for successful learners. The study compares the performance of five supervised machine learning algorithms: K-Nearest Neighbor, Decision Tree, Naive Bayes, Discriminant Analysis, and Support Vector Machine. These classifiers are evaluated to determine their suitability and model fit in the context of the research. In this study, real-time data is collected from B.Tech Information Technology learners. The following prediction models achieved high accuracy before FA analysis: Naive Bayes (90 %), Support Vector Machine (89 %), Discriminant Analysis (88 %), Decision Tree (86 %), and K-Nearest Neighbors (82 %). Naive Bayes gives the best accuracy, with 90 %. Following factor analysis (FA), the accuracy achieved by various classifiers is as follows: Naive Bayes - 92 %, K-Nearest Neighbors - 92 %, Support Vector Machine - 90 %, Discriminant Analysis - 89 %, and Decision Tree - 88 %. Among these, Naive Bayes and K-Nearest Neighbors exhibit the highest accuracy of 92 %.

An Exploratory Study of Learners’ Perceptions About the Effectiveness of Active Learning Approaches

This study reports on the results of a mixed-methods study conducted at Sultan Qaboos University, Oman, which aimed at exploring students’ overall perspectives and their perceptions of the benefits and challenges involved in active learning approaches, namely flipped instruction, problem-based learning, Socratic questioning and critical thinking, and reflective writing, employed in an English language and skills course. Results revealed that overall students valued the active learning strategies adopted in the course. More specifically, developing learners’ language, academic, and 21st century skills (analysis, critical thinking and evaluation, problem solving, and synthesis), fostering learners’ autonomy and metacognitive skills, and enhancing learners’ motivation and engagement in the learning process were considered the main benefits of these active learning strategies. The study also indicated that novelty of active learning strategies to learners, the heavy workload, learners’ inadequate academic skills, poor collaboration and communication skills in team-based tasks, and limited linguistic and technological abilities constituted the major challenges associated with these strategies. The study contributes to the English as a Foreign Language (EFL) knowledge base and has implications for the teaching and learning of EFL in the context of Oman and similar educational settings.

A feature-based physics-constrained active dictionary learning scheme for image-based additive manufacturing process monitoring

Compressed sensing is a new technique for data acquisition, which reconstructs the original signal from a small number of measurements. The performance of compressed sensing depends on the design of measurement and basis matrices. To improve the reconstruction accuracy, dictionary learning methods have been developed to customize basis matrices for specific signals. However, it may be difficult to obtain the theoretically optimal results because of the restrictions in physical realization such as the sensor placement and accessibility in the working environment. In this paper, a feature-based physics-constrained active dictionary learning (FB-PCADL) framework is proposed to solve the compression and classification problems simultaneously for image-based additive manufacturing process monitoring. A new active dictionary learning strategy is developed to optimize the measurement matrix, where the reconstruction errors are gradually reduced with the new measurements taken adaptively at the positions where the largest reconstruction errors occur. In addition, important features in images are identified and used to enhance the classification accuracy. The FB-PCADL framework is demonstrated with thermal images in monitoring fused filament fabrication process and optical images in monitoring laser powder bed fusion process.

The Design of an ICT Enabled Active Teaching and Learning Model for Use in Teacher Training Institutions in Uganda

In this paper, the author describes the theories behind the model that was designed in a study that was conducted in Eastern Region, Uganda. The paper provides examples of the teaching model based upon the model and illustrates the support systems required to facilitate the implementation of the model. The e-Model for Active Teaching and Learning to enhance the teaching and learning process utilizing technologies as a result of the growing use of technology over the past 10 years has been designed. The e-Model targets the teachers in a bid to improve the learning outcomes. The study design was a mixed method which employed qualitative and quantitative approaches and was conducted in the Eastern Uganda with a total population of 313 participants from the 6 participating teacher training colleges. The findings demonstrated a substantial link between teaching methodologies, ICT tools, and tools for active learning. Using the data collected on the relationship between aspects an e-Model for Active Teaching and Learning (e-MATL), to support teacher educators in effective use of technology to enhance active learning strategies.

Knowledge and Use of Active Learning Strategies Among Lecturers at the College of Health Technology Calabar, Cross River State, Nigeria

Knowledge and Use of Active Learning Strategies Among Lecturers at the College of Health Technology Calabar, Cross River State, Nigeria

Digital storytelling: A relational pedagogic approach to rebuilding hybrid places for creativity, equity and community building in a crisis

The COVID-19 pandemic had an impact on human flourishing worldwide as in-person teaching and learning provision within universities and schools rapidly shifted online. This exposed challenges as staff and students worked from home. Digital competences in online pedagogy differed across teaching teams, access to digital equipment, technical and social infrastructure was limited, specific fields of study had different requirements, and physical distancing measures heightened social isolation. ‘The Ship of Theseus’ is a thought experiment that poses the question: if every part of a ship is replaced, is it still the same ship? The authors apply the Ship of Theseus to reflect on experiences of rebuilding and reimagining teaching and learning online in a crisis. This intergenerational, practice-informed case study considers a strategic role for digital storytelling on the Digital Media and Communications BSc (DMC) at Manchester Metropolitan University (MMU) during the COVID-19 pandemic. A student-led component was supported by two research internships as part of MMU’s extracurricular programme, Rise. Catering specifically for students with culturally diverse backgrounds, Rise enables students to enhance their degree profile through activities such as volunteering, self-study on other learning platforms, work experience or research projects. The two student co-authors cooperated as peers, and as part of the research team in order to critique and reimagine curriculum content delivery in a crisis. This was informed by the literature and student co-authors’ critical reflections on their lived experience of pandemic online teaching and learning and prototyping an equitable alternative to build a creative community that co-imagines different desires and visions of the future from an inequitable present. In applying the Ship of Theseus to the use of digital storytelling to support online teaching and learning, we offer active learning strategies to reinvigorate relational pedagogic approaches that position online learning within wider debates to transform higher education. The authors suggest that digital storytelling can rebuild social connections and transform online spaces into hybrid places where meaningful and creative playfulness can become anchored within practice. We conclude that designing for equity by extending digital storytelling communities of practice beyond university learning environments provides alternative spaces that potentially transform how learners respond equitably to global crises together. While new forms of digital storytelling, cooperation, co-learning and community building are invaluable, the rapid convergence of digital technologies and media by industry warrants active stewarding to address emergent digital media ethical challenges, including accessibility, privacy and equity.

From provider to professor: Supporting nurse practitioner faculty through NONPF's Faculty Institute.

Over the past 15 years, the number of practicing nurse practitioners (NPs) has increased exponentially. This growth has been sustained by an increase in the number of schools offering NP preparation. Experienced NPs have assumed faculty positions in these schools. Although educational curricula prepare NPs to deliver high-quality patient care, it does not prepare graduates for academic roles in teaching, dissemination of scholarship, or service leadership to advance the profession. To address these gaps in NP faculty preparation, faculty development resources specific to NP education are needed. The National Organization of Nurse Practitioner Faculties (NONPF) has stepped forward to fill this gap. The NONPF Faculty Institute was created in 2017, and it includes the annual Fall Conference, the Faculty Leadership Mentoring Program, the Webinar Series, and, most recently, the joint NPACE/NONPF New Faculty Development Program. This comprehensive focus on faculty development aligns with NONPF's mission to promote excellence in NP education and advance the NP role in health care. Programs in the NONPF Faculty Institute are specifically designed to address the distinct learning needs of NP faculty. They use "just in time" presentations and active learning strategies to provide NP faculty with easily accessible and targeted content and opportunities for direct application of new skills. The Institute's goal is to provide NP faculty opportunities to prepare themselves to meet the teaching, scholarship and service leadership expectations of academia, the learning needs of students, and advance the impact of NP practice on patient and health care system outcomes.

Experimental Ni3TeO6 synthesis condition exploration accelerated by active learning

Material synthesis is time- and chemicals-consuming due to the traditional (“brute force”) methodology. For instance, Ni3TeO6 (NTO) is a multiferroic material relevant in different applications. Herein, we used an active learning scheme to explore the different phases obtained using a complex hydrothermal synthesis procedure instead of a solid-state methodology. Different from conventional ML prediction requiring a large dataset, we show that with only 9 data points obtained through experimental endeavor, 87% of the experimental condition space is predicted. The predicted phase configuration is verified with the sample in a new synthetic work. Beside exploring the NTO species, scheme developed herein constitute a powerful tool for experimental condition optimization.

The Infusion of Gamification in Promoting Chemical Engineering Laboratory Classes

Active learning strategies are increasingly implemented in chemical engineering education, yet challenges persist in stimulating student participation and motivation. The rigorous demands placed on students in this field, from complex practical requirements to extensive programming and computational skills, underscore the need for innovative educational tools. Gamification emerges as a pivotal instrument in this context, fostering active student engagement, enhancing practical application of knowledge, increasing motivation, and providing a more precise assessment of student comprehension. These educational games serve as a powerful adjunct to traditional teaching strategies, equipping students with necessary skills for their future careers in the field. These games include laboratory course games, process simulators, games used in foundational courses, and those centered around reaction kinetics. This entry primarily investigates the various games employed to bolster student learning during chemical engineering laboratory courses. A thorough analysis is conducted on the survey of existing games used specifically in chemical engineering labs. The gamut of games discussed includes escape games, along with Virtual Reality (VR) and Augmented Reality (AR) games, all aiming to enhance laboratory experiences in areas such as fluid mechanics, organic reactions, and process control. This entry concludes by examining the prospective trajectory of gamification in chemical engineering labs, offering insights into future potential and advancements in this innovative educational approach.

The Effectiveness of Using Some Active Learning Strategies in the Developing of Rhetorical Skills Among First Grade Secondary Students in the Republic of Yemen

هدفت الدراسة إلى معرفة أثر استخدام بعض استراتيجيات التعلم النشط في تنمية المهارات البلاغية لدى طلبة الصف الأول الثانوي في الجمهورية اليمنية، ولتحقيق هذا الهدف استخدم الباحث المنهجين الوصفي وشبه التجريبي، وأعدَّ قائمة بالمهارات البلاغيَّة، واختبارًا تحصيليًّا، وبرنامجًا تعليميًّا وفق استراتيجيات التَّعلُّم النَّشط، وتكونت عينة البحث من (111). طالبًا وطالبة من طلبة الصف الأول الثانوي بأمانة العاصمة، تم اختيارها بطريقة قصدية، وقسمت إلى مجموعتين: الأولى تجريبية درست باستخدام البرنامج القائم على التعلم النشط، والثانية ضابطة درست باستخدام الطريقة الاعتيادية، وتوصَّلت الدراسة إلى النتائج الآتية: - وجود فروق دالة إحصائيًّا عند مستوى الدلالة (0.05). بين متوسطي درجات طلبة المجموعتين التجريبيَّة والضابطة في التطبيق البعدي لاختبار المهارات البلاغيَّة لصالح المجموعة التجريبيّة. - وجود فروق دالة إحصائيًّا عند مستوى الدلالة (0.05). بين متوسطي درجات طلبة المجموعة التجريبيَّة في التطبيقين القبلي والبعدي لاختبار المهارات البلاغيَّة لصالح التطبيق البعدي. - وجود فروق ذات دالة إحصائيًّا عند مستوى الدلالة (0.05). بين متوسطي درجات طلبة المجموعة التجريبيَّة (الذكور والإناث). في التطبيق البعدي لاختبار المهارات البلاغيَّة لصالح الإناث.

Model update for intrusion detection: Analyzing the performance of delayed labeling and active learning strategies

Intrusion Detection Systems (IDS) help protect computer networks by identifying and detecting attempts to obtain unauthorized access to data via computer networks by inspecting packets separately or in the context of flows. Intrusion detection is a classification task performed on continuously generated packets with a non-stationary distribution (data stream). As such, the decision models used for Intrusion Detection must be constantly updated to account for changes in what constitutes normal traffic of a network and correctly identify attacks. This work evaluates two approaches concerning label availability to update the intrusion detection classifier. First, we analyze the impact of delayed labeling of samples on the classifiers' performance, and second, we evaluate the impact of using active learning strategies on the classifiers. Our experimental evaluation uses two datasets (CIC-IDS2017 and CSE-CIC-IDS2018) to compare different data stream classification algorithms under different evaluation measures. Based on comparison results, we studied different active learning techniques to estimate the impact of delayed labeling on packet-based IDS. We found that the performance of the classifiers is inversely proportional to the label delivery rate. Besides, the active learning strategies helped keep the performance compatible with the baselines, even with a small set of labeled instances.

Assessment of clustering techniques to support the analyses of soybean seed vigor.

Soy is the main product of Brazilian agriculture and the fourth most cultivated bean globally. Since soy cultivation tends to increase and due to this large market, the guarantee of product quality is an indispensable factor for enterprises to stay competitive. Industries perform vigor tests to acquire information and evaluate the quality of soy planting. The tetrazolium test, for example, provides information about moisture damage, bedbugs, or mechanical damage. However, the verification of the damage reason and its severity are done by an analyst, one by one. Since this is massive and exhausting work, it is susceptible to mistakes. Proposals involving different supervised learning approaches, including active learning strategies, have already been used, and have brought significant results. Therefore, this paper analyzes the performance of non-supervised techniques for classifying soybeans. An extensive experimental evaluation was performed, considering (9) different clustering algorithms (partitional, hierarchical, and density-based) applied to 5 image datasets of soybean seeds submitted to the tetrazolium test, including different damages and/or their levels. To describe those images, we considered 18 extractors of traditional features. We also considered four metrics (accuracy, FOWLKES, DAVIES, and CALINSKI) and two-dimensionality reduction techniques (principal component analysis and t-distributed stochastic neighbor embedding) for validation. Results show that this paper presents essential contributions since it makes it possible to identify descriptors and clustering algorithms that shall be used as preprocessing in other learning processes, accelerating and improving the classification process of key agricultural problems.

Pengaruh Strategi Critical Incident terhadap Hasil Belajar Menulis Karangan Narasi Siswa Kelas V SDN 19 Malela Kecamatan Suli

The aim of this study was to determine the effect of the critical incident strategy on learning outcomes in writing narrative essays. This research is a descriptive type. The population of this study were fifth grade students at SDN 19 Malela for the 2022/2023 academic year, consisting of one class. The sample in this study were all Class V students at SDN 19 Malela, Suli District, totaling 27 students. Sampling used a total sampling technique. Data collection techniques used in this study were tests (pre-test and post-test), observation and documentation. Learning outcomes after applying active learning strategies based on calculations with 26 degrees of freedom, produce t-count = 5.0144 and t-table = 2.056. The results of these calculations show that t count ≥ t table (5.0144 ≥ 2.056). It can be concluded that the use of active learning strategies in critical incidents has an impact on the learning outcomes of fifth grade students at SDN 19 Malela, Suli District, Luwu Regency.

Students’ Perceptions of Crossword Puzzles to Enhance Learning in Social Studies 10

Extensive scholarly investigation in social studies education has led to a significant shift in the prevailing paradigm, moving away from conventional lecture-based teaching methods and towards adopting novel and student-centric instructional approaches. The utilization of crossword puzzles is a straightforward and innovative strategy for integrating active learning in the field of social studies. This subject area is an introduction for students to gain a fundamental comprehension of current circumstances, employing contemporary terminology and concepts that diverge significantly from their preexisting knowledge. This study aimed to evaluate students’ perspectives on crossword puzzles as a viable strategy for reinforcing essential concepts related to contemporary subjects. The study was carried out at Bagong Nayon II National High School. The study population comprised 60 tenth-grade students from the cohort of 2022-2023. After attending instructional lectures on the subject matter, the students were allocated 40 minutes to solve the puzzle using a freely available online puzzle generator. An eight-item survey instrument questionnaire was utilized to examine students’ perceptions of crossword puzzles. Many learners perceived using the crossword puzzles as an innovative pedagogical strategy, as indicated by most of their positive evaluations. Using crossword puzzles as an active learning strategy offers a unique, creative, and straightforward approach to enhance the retrieval and preservation of information. Consequently, the study demonstrated that appropriately using crossword puzzles increased student involvement. This instructional tool can serve as a means of formative evaluation and offers a cost-effective alternative to the constraints of didactic teaching.

Upaya Guru Pendidikan Agama Islam Dalam Meningkatkan Kemampuan Berkomunikasi Dalam Pembelajaran di SD Negeri No. 104274 Pematang Kasih Kecamatan Pantai Cermin Kabupatan Serdang Berdagai

In the learning process is not only related to knowledge but communication in the world of education is also very important. Every learning activity is synonymous with communicating, therefore a teacher has an important role in developing students' communication skills in learning. So there needs to be an effort made by PAI teachers at SD Negeri No. 104274 Pematang Kasih to improve students' communication skills to make it easier for students to understand the learning material delivered. The efforts made are in the form of providing good communication examples, guiding students when asking questions, making presentations in discussion activities, using question and answer methods, using active learning strategies and doing habituation. This research uses qualitative methods with a phenomenological approach. The purpose of the efforts made is to create effective communication and a pleasant learning atmosphere.

Incorporating Collaborative and Active Learning Strategies in the Design and Deployment of a Master Course on Computer-Assisted Scientific Translation

This research aims to address the current gaps in computer-assisted translation (CAT) courses offered in bachelor’s and master’s programmes in scientific and technical translation (STT). A multi-framework course design methodology is proposed to support CAT teachers from the computer engineering field, improve student engagement, and promote computer-supported education, together with a balanced coverage of the most relevant topics in the CAT domain. STT is currently in high demand in many fields, requiring translators with sector-specific language skills and considerable computer literacy in order to manage translation projects with complex structures, and format heterogeneity. However, many STT curricula often lag behind current market demands, focusing primarily on language and translation theory, with less emphasis on CAT technologies and tools. Moreover, the lack of shared course design guidelines hinders the introduction of innovative teaching approaches based on collaborative learning. A novel multi-framework CAT course design methodology, named CATDeM, is proposed, based on the integration between an official European translation competence framework, real-life-mimicking laboratorial activities, and computer-supported collaborative learning, enriched with discussion case studies and role-playing experiences. A real-life case study is examined to illustrate and evaluate the implementation of CATDeM in two consecutive editions (2020/2021 and 2021/2022) of a one-semester compulsory CAT course in a M.A. degree in STT at the University of Salento (Italy). Students’ perceptions of translation technology and role-plays, as well as their attitudes towards the proposed CAT course are evaluated through a post-grading self-assessment questionnaire. Achieved results indicated successful student engagement and self-assessed improvement in translation, technical, and interpersonal skills. The importance given by students to role-playing experiences mimicking professional scenarios was also highlighted, paving the way for CATDeM to be adopted in similar contexts.