Application Of Active Learning Research Articles

The search for sparse data in molecular datasets: Application of active learning to identify extremely low volatile organic compounds

The formation of aerosol particles in the atmosphere is driven by the gas to particle conversion of extremely low volatile organic compounds (ELVOC), organic compounds with a particularly low saturation vapor pressure (pSat). Identifying ELVOCs and their chemical structures is both experimentally and theoretically challenging: Measuring the very low pSat of ELVOCs is extremely difficult, and computing pSat for these often large molecules is computationally costly. Moreover, ELVOCs are underrepresented in available datasets of atmospheric organic species, which reduces the value of statistical models built on such data. We propose an active learning (AL) approach to efficiently identify ELVOCs in a data pool of atmospheric organic species with initially unknown pSat. We assess the performance of our AL approach by comparing it to traditional machine learning regression methods, as well as ELVOC classification based on molecular properties. AL proves to be a highly efficient method for ELVOC identification with limitations on the type of ELVOC it can identify. We also show that traditional machine learning or molecular property-based methods can be adequate tools depending on the available data and desired degree of efficiency.

Active Learning on Students 'Interpersonal Skills Impact: An Online Theater Approach

This study aims to examine the improvement of interpersonal skills through the application of active learning in the teaching and learning of art education. The approach used is the theatre-play approach. Theatre games are used as a fresh and appropriate approach to learning art education subjects through various types of games that are applied with various theatre techniques, including improvisation, role playing, physical exercise, and voice acting. The subject of art education is a theoretical and practical one that requires high focus during learning. Therefore, theatre games are applied to encourage active learning and prevent students from getting bored when learning is conducted online. Students play, act, improvise, and sing while learning. This qualitative study involved eight Form 5 students at the Malaysian Art School using observation and interview methods. The study applies social learning theory and constructivist learning theory. The data was thematically analysed using Nvivo software. Findings found that active learning takes place in learning through the application of a theatre game approach and highlights the interpersonal skills of students. Two-way communication occurs in every activity because the activity is carried out in groups. Studies on the learning of art subjects that apply this active learning through theatre games are believed to promote confidence and stimulate students to improve their interpersonal skills without realising it.

Learning From Incorrectness: Active Learning With Negative Pre-Training and Curriculum Querying for Histological Tissue Classification.

Patch-level histological tissue classification is an effective pre-processing method for histological slide analysis. However, the classification of tissue with deep learning requires expensive annotation costs. To alleviate the limitations of annotation budgets, the application of active learning (AL) to histological tissue classification is a promising solution. Nevertheless, there is a large imbalance in performance between categories during application, and the tissue corresponding to the categories with relatively insufficient performance are equally important for cancer diagnosis. In this paper, we propose an active learning framework called ICAL, which contains Incorrectness Negative Pre-training (INP) and Category-wise Curriculum Querying (CCQ) to address the above problem from the perspective of category-to-category and from the perspective of categories themselves, respectively. In particular, INP incorporates the unique mechanism of active learning to treat the incorrect prediction results that obtained from CCQ as complementary labels for negative pre-training, in order to better distinguish similar categories during the training process. CCQ adjusts the query weights based on the learning status on each category by the model trained by INP, and utilizes uncertainty to evaluate and compensate for query bias caused by inadequate category performance. Experimental results on two histological tissue classification datasets demonstrate that ICAL achieves performance approaching that of fully supervised learning with less than 16% of the labeled data. In comparison to the state-of-the-art active learning algorithms, ICAL achieved better and more balanced performance in all categories and maintained robustness with extremely low annotation budgets. The source code will be released at https://github.com/LactorHwt/ICAL.

Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis

The empirical aspect of descriptor design in catalyst informatics, particularly when confronted with limited data, necessitates adequate prior knowledge for delving into unknown territories, thus presenting a logical contradiction. This study introduces a technique for automatic feature engineering (AFE) that works on small catalyst datasets, without reliance on specific assumptions or pre-existing knowledge about the target catalysis when designing descriptors and building machine-learning models. This technique generates numerous features through mathematical operations on general physicochemical features of catalytic components and extracts relevant features for the desired catalysis, essentially screening numerous hypotheses on a machine. AFE yields reasonable regression results for three types of heterogeneous catalysis: oxidative coupling of methane (OCM), conversion of ethanol to butadiene, and three-way catalysis, where only the training set is swapped. Moreover, through the application of active learning that combines AFE and high-throughput experimentation for OCM, we successfully visualize the machine’s process of acquiring precise recognition of the catalyst design. Thus, AFE is a versatile technique for data-driven catalysis research and a key step towards fully automated catalyst discoveries.

Discovery-Based Approach Combined with Active Learning to Improve Student Learning Experiences for STEM Students

A survey is administered to understand the application of active learning in undergraduate STEM courses. The findings observed over an academic year reflect current trends in the use of active learning. A combination of discovery-based learning and Pro-Con Grids is then used to improve long-term retention among STEM students. Students in a STEM course were provided with a course lecture prior to in-class sessions. A quiz was used for each lecture to gain insight into students’ understanding and to evaluate the effectiveness of the learning method. To measure the effectiveness of the proposed discovery-based learning two categories of metrics are used: learners' outcomes (grades) and survey (process measure) with 64 participants. The responses from the students show that discovery-based learning convinced students to find and use information rather than memorizing and repeating concepts and facilitate effective group work. In addition, the grade comparisons for three semesters indicate that the higher the use of discovery learning during the course the higher the course grades are found to be.

Active Learning and Professional Development: A Case of Thai Chinese Teachers

While Chinese has been taught as a school subject outside of China for decades, there is little research on how Chinese subjects are taught in secondary schools outside of China’s mainland with regard to the use of active learning and the impact of professional development events on teachers’ professional growth in classroom Chinese teaching. This article explored Thai Chinese teachers’ use of active learning methods at public and private secondary schools in the south of Thailand. It also examined the impact of a government-administered Chinese teaching seminar on their professional development. A sequential mixed-methods explanatory design was employed, involving focus group interviews and pre- and post-tests. The phenomenological approach with thematic analysis was used to analyze the qualitative data from the focus group interviews, while the Wilcoxon test was run to compare the pre- and post-test data. Findings revealed the application of active learning with discussion and role-playing activities involving audio-visual materials. The pedagogy of Thai Chinese secondary schools has shifted from knowledge transmission through lectures to knowledge generation and transformation via dynamic learning activities. After attending the seminar, teachers’ comprehension of active learning methods increased considerably (Z = 3.740, p < 0.001). However, teachers expressed concerns over the lack of innovative teaching techniques for teaching Chinese characters and the problems encountered by both students and teachers during the teaching and learning process. This study recommends that Hanban and the Thai Ministry of Education plan their seminars and workshops in a way that allows Thai Chinese instructors to continuously address their students’ and their own deficiencies while they are engaged in active learning activities, and it calls for additional research on the use of active CFL methods in secondary schools outside of China.

Flexibility of Virtual Team-based Learning in Teaching Medical Genetics

Team-based Learning (TBL) is a global education strategy designed to inculcate self-directed and active learning. The fallout is a new breed of students who are exposed to restricted and compromised teaching and learning methods via online platforms amidst this COVID -19 pandemic. Therefore, this innovation aims to explore the application of active learning among undergraduate medical students through virtual TBL. In this pilot study, the concept of medical genetics is introduced virtually through utilizing online platforms, Microsoft TeamsTM and Universiti Kebangsaan Malaysia (UKM) Learning Management System (UKMFolioTM), while maintaining the principles of TBL. Emphasis is placed on applied learning to apply the fundamental knowledge learnt during the preparation phase through team discussions and subsequent pitching presentations. Our study indicates no significant difference (p=0.404) in the mean score of students who participated in conventional face-to-face TBL sessions and virtual TBL. This suggests that active and self-directed learning can be integrated through virtual means with reproducible excellent results as with conventional face-to-face TBL. Nonetheless, issues related to Internet stability and insufficient content experts must be addressed if we are to tackle successful virtual teaching and learning.

Teaching of Magnetism Unit Topics Via Active Learning Applications

The aim of this study is to investigate the effect of active learning on students’ achievement in the unit of magnetism. It is important to create proper teaching environments in order to ensure the active participation of students in learning processes. Many different methods and techniques may be used for active participation. Detailed information should be provided for the teachers on how these methods and techniques can be implemented. For this reason, an active learning environment was created in the present study by way of using worksheets accompanied by experiments, simulations, modelling, garden activity and games. It was explained how these activities are implemented for each of the acquisitions related with the magnetism unit topics. The study employed sequential explanatory mixed design. The subject of this study consisted of 98 eleventh grade students in a high school in Türkiye. The data were acquired via an open ended and multiple-choice conceptual achievement test, observation forms and interviews. The findings obtained illustrated that active learning applications increase academic achievements of students at a statistically significant level. In addition, it was concluded that active learning applications make a positive impact on the interest, attitude and motivations of the students towards the physics course. The results show that magnetism unit topics are effective in providing a conceptual change. It is suggested to use the applications shared in the present study for the teaching of abstract subjects such as magnetism. In this way, it may be possible to create learning environments that will enable instructors to reach the desired goals.

On the application of active learning for efficient and effective IoT botnet detection

The active learning approach for machine learning can greatly benefit those environments where a wealth of unlabeled data is available, and the labeling cost of the data can be restrictive. In this regard, security operations centers (SOCs) can take advantage of the human expertise available to improve machine learning-based detection models using the active learning approach. In the context of SOC operations and IoT botnet detection, our study provides a thorough benchmarking of the application of different active learning approaches within the framework of pool-based sampling. The selection of the optimal query instance for learning is evaluated using uncertainty sampling, ranked batch-mode sampling, and query by committee strategies. Our results show that the active learning approach can help to generate better detection models using all the active learning query strategies tested in our benchmarking setup. Leveraging the human–machine interaction can produce high-performance models in the context of IoT botnet detection using significantly less data than the passive approaches traditionally used for the generation of machine learning-based detection systems. Additionally, the impact of wrong-labeled data in the active learning implementation is explored.

IMPLEMENTASI PEMBELAJARAN AKTIF DALAM HABITUASI HARI BERBAHASA ARAB JURUSAN KEAGAMAAN DI MA DARUL ULUM PURWOGONDO KALINYAMATAN JEPARA

The application of active learning in learning Arabic at MA Darul Ulum Purwogondo Kalinyamatan Jepara. The implementation of active learning is learning that is made so that students can take part in learning actively and fun. So that students have many roles in participating when the learning process takes place in order to improve the quality and satisfactory results. This study aims to determine the level of interest of students in Arabic subjects at MA Darul Ulum Purwogondo Kalinyamatan Jepara. This research is a qualitative research. Data collection techniques using the method of observation, interviews, and documentation. Research on the implementation of active learning in Arabic subjects majoring in religion at MA Darul Ulum Purwogondo Kalinyamatan Jepara has been going well by emphasizing Arabic-language students majoring in religion with the concept of an Arabic day every Sunday. In the process of implementing active learning for Arabic subjects, the teacher provided a stimulus or stimulus that aims to be motivated and understand what the learning objectives are to be studied. Active learning is carried out after the educator delivers the material by asking questions to students individually or in groups (if forming groups). Educators also give awards or rewards to groups that can answer questions from educators based on teams that work together correctly and well.

Large deviations of semisupervised learning in the stochastic block model.

In semisupervised community detection, the membership of a set of revealed nodes is known in addition to the graph structure and can be leveraged to achieve better inference accuracies. While previous works investigated the case where the revealed nodes are selected at random, this paper focuses on correlated subsets leading to atypically high accuracies. In the framework of the dense stochastic block model, we employ statistical physics methods to derive a large deviation analysis of the number of these rare subsets, as characterized by their free energy. We find theoretical evidence of a nonmonotonic relationship between reconstruction accuracy and the free energy associated to the posterior measure of the inference problem. We further discuss possible implications for active learning applications in community detection.

On the Application of Active Learning for Efficient and Effective Iot Botnet Detection

On the Application of Active Learning for Efficient and Effective Iot Botnet Detection

The Reality of Active Learning Application in Jeddah Schools by English Teachers

This study explored the extent to which teachers of English as a Foreign Language (EFL) adopt and implement active learning strategies in their classrooms. The study, also, examined the obstacles encountering high school teachers to use active learning and it delved further into exploring the participants’ recommendations to mitigate these obstacles. The study followed a quantitative methodology. Sixty-six EFL teachers (Male n=22 and Female n=44) from Jeddah in the Kingdom of Saudi Arabia participated in this study. The researchers used an electronic custom-designed, 19-items rated on a five-point Likert scale questionnaire, for ease of dissemination and data collection. The findings revealed that the degree of employing active learning was medium (54.8%). However, 55% of the participants responded that they encountered some acute obstacles to implementing active learning in their classrooms. The findings showed no statistically significant differences attributed to gender, experience, and training about using active learning, obstacles, and recommendations to overcome the obstacles. The study discusses some of the obstacles to implementing active learning and concludes with some recommendations to the Ministry of Education to reinforce active learning in the education system of EFL contexts.

Reclaiming agency: skills, academics and students in the Social Sciences

The adoption of active learning pedagogy and, later, the institution of the employability agenda in Higher Education have resulted in a severe loss of agency for academics and students in the Social Sciences. In this article, we reflect on our experiences of applying active learning methods. We argue that we have been part of a change that has occasioned a loss of key skills development, especially those associated with traditional learning and academic thinking. An overly headlong rush to implement the “new” over the “old” saw the discarding of certain skills central to the active learning agenda. Further, the emphasis on student satisfaction, professionalisation and quality assurance pushed the academic to the sidelines, to the detriment of Higher Education. We, therefore, first critique the skills debate and identify shortcomings in the active learning application that emerged from that debate. We focus on the skills emphasised in practice, how they are portrayed in opposition (instead of complementarity) to academic skills, and how they undermine the agency academics and students really require. Next, we propose a reconsideration of necessary but undervalued skills like reading, listening and note-taking.

Active Learning for Efficient Segmentation of Liver with Convolutional Neural Network-Corrected Labeling in Magnetic Resonance Imaging-Derived Proton Density Fat Fraction.

This study aimed to propose an efficient method for self-automated segmentation of the liver using magnetic resonance imaging-derived proton density fat fraction (MRI-PDFF) through deep active learning. We developed an active learning framework for liver segmentation using labeled and unlabeled data in MRI-PDFF. A total of 77 liver samples on MRI-PDFF were obtained from patients with nonalcoholic fatty liver disease. For the training, tuning, and testing of the liver segmentation, the ground truth of 71 (internal) and 6 (external) MRI-PDFF scans for training and testing were verified by an expert reviewer. For 100 randomly selected slices, manual and deep learning (DL) segmentations for visual assessments were classified, ranging from very accurate to mostly accurate. The dice similarity coefficients for each step were 0.69 ± 0.21, 0.85 ± 0.12, and 0.94 ± 0.01, respectively (p-value = 0.1389 between the first step and the second step or p-value = 0.0144 between the first step and the third step for paired t-test), indicating that active learning provides superior performance compared with non-active learning. The biases in the Bland-Altman plots for each step were - 24.22% (from - 82.76 to - 2.70), - 21.29% (from - 59.52 to 3.06), and - 0.67% (from - 10.43 to 4.06). Additionally, there was a fivefold reduction in the required annotation time after the application of active learning (2 min with, and 13 min without, active learning in the first step). The number of very accurate slices for DL (46 slices) was greater than that for manual segmentations (6 slices). Deep active learning enables efficient learning for liver segmentation on a limited MRI-PDFF.

Penerapan Active Learning dan Penggunaan Media Berbasis Komputer untuk Meningkatkan Prestasi Belajar Siswa pada Pembelajaran IPA

This study aims to analyze the effectiveness of the application of active learning in increasing interest, attention, and activity, as well as students' learning achievements in science lessons. The subject of the study was a grade VI student of MI Negeri 1 Yogyakarta. This study uses methods of action through the process of incugate. The results showed that the application of active learning through inkuiri method can train students to discover for themselves various concepts learned, foster the ability to think, work, and be scientific and can improve and expand the mastery of skills in the process of acquiring cognitive students.

Active learning application in engineering education: effect on student performance using repeated measures experimental design

ABSTRACT The purpose of this article is to present the methodology and the results of active learning application in an Engineering Education institution in Brazil, using repeated measures experimental design. It involved taking course samples from 7 engineering programs, providing 6 classes, 202 participant students and 296 class-hours. The design had a strict implementation plan where each course content was taught in two subsequent stages using traditional and active learning approaches respectively. Similar grade assessments were applied to both stages. The classes were observed using a classroom observation protocol, to check for the profile change from passive to active in-class behaviours. The consolidated results demonstrated that student performance in the second assessment was 14% better, after the application of active learning techniques (~40% of the grades standard deviation). The article aims to contribute to current research and inform future studies about the effectiveness of active learning methods in Engineering Education.

Active learning strategy for high fidelity short-term data-driven building energy forecasting

The quality of a data-driven model is heavily dependent on the quality of data. Data from building operation often have data bias problems, which means that the data sample is collected in a way that some members of the intended data population are less likely to be included than others. Data-driven energy forecasting models built on such data hence are biased and could lead to large forecasting errors. Active learning— an effective method to defying data bias—is rarely studied or applied in the area of data-driven building energy forecasting modeling. This paper attempts to fill this gap and explores the application of active learning in data-driven building energy forecasting.The developed strategy in this paper efficiently generate informative training data within a time budget and uses block design to passively consider weather disturbances. The developed active learning strategy is applied and evaluated in both virtual and real-building testbeds against traditional data-driven methods. Via these virtual and real-building evaluation cases, we have demonstrated that the data bias problem typically exists in building operation data is resolved by applying the developed active learning strategy. Building energy forecasting models trained from data generated from the active learning strategy have shown improved performances in both model accuracy and model extendibility perspectives. The effectiveness of the block design module is also validated to effectively consider the impact of weather conditions on active learning design.

Application of active learning in DNA microarray data for cancerous gene identification

Microarray technology has an important role in evaluating gene expression data with unique patterns into existence. In gene-expression based experiments, the expression level of the gene is constantly monitored in order to classify a tissue sample. In microarray technology, the expressions of the genes are altered with respect to pathogenes. The altered expression values can be identified by analyzing the genes of the tissue/cell that are affected along with the tissues/cells that are unaffected are termed as biomarkers. In the current paper, we have developed an Active Learning (AL) model by using Support Vector Machine (SVM) in association with feature-selection (FS) algorithm; called Symmetrical Uncertainty (SU) for the prediction of cancer. The effectiveness of the proposed AL and SU combination is manifested and the biomarkers or cancerous genes identified by the proposed method on four gene-expression data sets are reported. In addition, the biological significance tests are performed for the cancer biomarkers obtained from the data sets.

Active learning in Japan: Breaking barriers at individual, institutional, and policy levels

Active learning has emerged as a means of developing generic employability skills that enable students to prepare for an uncertain future. In this context, many universities have encouraged their instructors to practice active learning. While some scholars indicate challenges with adopting this approach, few empirical studies have examined perceptions of instructors related to its application. This current study addresses this research gap—how instructors perceive the issues regarding the application of active learning—by surveying 157 instructors from across numerous institutions in Japan. Identifying issues at the individual level is important because it can provide guidance for institutional managers and policymakers on the strategies necessary for effective implementation of active learning. While the findings of this study largely confirm those of the extant literature, they also revealed which issues are more pertinent than others. Japanese instructors did not adopt active learning because they were indifferent and reluctant toward active learning and prioritized students’ knowledge acquisition over application. We conclude with a discussion of the findings and suggestions to address the perceived issues in implementing active learning at all levels, using the theory of planned behavior.