Design Of Learning Model Research Articles

A Learning Model for Explanation Text Literacy Using Flipbook Applications in SMP/MTS

This research aims to develop an explanatory text literacy learning model using the flipbook application as media in SMP/MTS. The background to this problem 1) How is the planning for an explanatory text literacy learning model using the flipbook application as a medium in class VIII SMP/MTS? 2) How to implement an explanatory text literacy learning model using the flipbook application as a medium in class VIII SMP/MTS? 3) What is the effectiveness of the explanatory text literacy learning model using the flipbook application as a medium in class VIII SMP/MTS? This research uses the Research and Development (R&D) research and development method with the ADDIE (Analyze, Design, Development, Implementation, and Evaluation) model. The steps of this research consist of, needs analysis, learning model design, learning model development, implementation of learning model products, evaluation of learning model products. Data collection in this research was by collecting data from the results of expert validation questionnaires and questionnaires from student assessments. The data obtained was analyzed descriptively using a Likert scale. The results of the validation test by media experts obtained a score of 77.94%, the validation test by language experts obtained a score of 81.25%, the Indonesian language teacher's response score obtained a score of 97.33%, and the average student response obtained a score of 82.13%. The conclusion of this research is that the explanatory text literacy learning model using the flipbook application media in SMP/MTS meets the appropriate criteria to be used as a learning model by students or teachers in Indonesian language subjects with explanatory text material in class VIII SMP/ MTS students.

Instructional Design of Problem-Based Learning Models: A Strategy for Improving Students' Critical Thinking Abilities in Learning News Texts

Instructional Design of Problem-Based Learning Models: A Strategy for Improving Students' Critical Thinking Abilities in Learning News Texts

When Co-Generative Learning Met Co-Production and Co-Creation - On How Three Different Concepts Shaped “Samskaping”

AbstractThe Norwegian/Danish word «samskaping” is today one of the most frequently used terms or concepts in the public discourse of development and change. Scholars familiar with the work of Morten Levin and Max Elden will recognize “samskaping” as a short translation of their model of “cogenerative learning”, originating from the discussion in the 80’s and 90’ on participative action research processes. However, there is no simple line of transfer of ideas from “cogenerative learning” in action research to “samskaping” in public sector today. Rather, three concepts from different disciplines all ended up being translated into or strongly associated with the newly constructed and popular Norwegian word “samskaping”, and Morten Levin’s “cogenerative learning” is one of the three. The two others are co-production and co-creation, which originates from fields of innovation research in private and public sector. Seen from the position of action research and the heritage from Morten Levin, this means that although his (and Max Eldens) concept (in the Norwegian translation) appears to have gained a strong impact Norway the last decade, the meaning and importance of the concept is partially lost to many of its later users. This article will track the main roots of “samskaping” as it has found its way in the everyday language of change and development in Norway, and will in particular try to reclaim for the term or concept, some of the main themes that shaped the discussion and the design of the co-generative learning model in PAR, in particular participation, power and social change.

Lived Experiences and Support Needs of Students with Disabilities: A Phenomenological Approach to Achieving SDGs 3,4, 10, and 11

Introduction: This study investigates the experiences, challenges, and needs of students with special needs and disabilities, aiming to create accessible facilities that support their educational requirements. Anchored in the Universal Learning Design and Social Model of Disability frameworks, it explores inclusive practices that promote equitable access. Employing a phenomenological qualitative approach, the research gathered data through semi-structured interviews with 16 students diagnosed with disabilities. The thematic analysis revealed three key areas of concern: infrastructure and facilities, physical education courses, and student support services. The identified needs include accessible infrastructure, assistive technology, and tailored academic accommodations, integrated into the concept of a "HUB." The study’s implications underscore the importance of inclusive learning environments, aligning with Sustainable Development Goals (SDGs) related to quality education, well-being, and reduced inequalities. The originality lies in contextualizing the experiences of these students, with findings that could inform institutional policies and enhance support for diverse student populations. Objective: The objective of this study is to investigate the experiences, challenges, and needs of students with special needs and disabilities to create a learning hub where they can feel supported in all aspects of their educational needs. Theoretical Framework: The study is anchored on the frameworks of Universal Learning Design and the Social Model of Disability. These frameworks focus on creating inclusive educational practices and systems that provide equitable access and opportunities for students with disabilities. Method: This study employs a phenomenological qualitative approach, as outlined by Creswell (2013), to explore the lived experiences of students with special needs and disabilities in higher education. It involved sixteen (16) student participants who were all medically diagnosed as people with a disability. Data was collected through semi-structured interviews, which allowed for flexibility while ensuring that key topics related to the participants' experiences were covered. Each interview lasted for approximately 45-60 minutes and took place in a comfortable setting, both in-person or via a virtual platform. Results and Discussion: The interviews were transcribed and manually coded with three emerging themes under the experiences and challenges, these being: infrastructure and facilities, physical education courses, and student support services. Emerging themes from specific support services they need are accessible facilities and infrastructure, assistive technology and academic accommodations, and dedicated support services & counseling. Research Implications: The practical and theoretical implications of this research are discussed, providing insights into how the results can be applied or influence practices in the field of inclusive and equitable quality education. These implications could encompass SDG 4 Quality Education, SDG 3 Good Health and Well-Being, SDG 10 Reduced Inequalities, and SDG 11 Sustainable Cities and Communities. Originality/Value: This study contributes to the literature by highlighting the contextualized experiences, challenges, and needs of students with special needs and disabilities in higher education. The relevance and value of this research are evidenced by its potential to inform institutional policies and practices that address the unique needs of students with special needs and disabilities. By identifying key challenges and support mechanisms, the study contributes to creating a more inclusive academic environment, promoting equity, and ensuring that all students have access to quality education. Additionally, the findings can help guide the development of accessible facilities, tailored support services, and academic accommodations, further enhancing the university’s capacity to meet diverse student needs.

A parallel recursive framework for modelling time series

Abstract Time series modelling is of significance to several scientific fields. Several approaches based on statistics, machine learning or combinations have been utilized. In order to model and forecast time series a novel parallel framework based on recursive pseudoinverse matrices is proposed. This framework enables the design of arbitrary statistical and machine learning models, adaptively, from a set of potential basis functions. This unification enables compact definition of existing and new models as well as easy implementation for new massively parallel architectures. The choice of appropriate basis functions is analysed and the fitting accuracy, termination criteria and model update operations are presented. A block variant for multivariate time series is also proposed. Parallel GPU implementation and performance optimization of the framework are provided, based on mixed precision arithmetic and matrix operations. The use of different basis functions is showcased with respect to various model univariate and multivariate time series for applications such as regression, frequency estimation and automatic trend detection. Discussions on limitations and future directions of research are also provided.

Design and Development of Machine Learning Model for Antibody Design: Rituximab a Case Study

Design and Development of Machine Learning Model for Antibody Design: Rituximab a Case Study

Integrating machine learning model and computer-aided molecular design toward rational ionic liquid selection for separating fluorinated refrigerants

To reduce emissions and facilitate the reclamation of hydrofluorocarbons (HFCs), which are potent greenhouse gases, ionic liquid (ILs)-based absorption separation of HFCs from fluorinated refrigerant (FR) blends is considered as an effective approach. In this work, computer-aided ionic liquid design (CAILD) is carried out to rationally design ILs for separating FR blends, with the near-azeotropic R-32/R-125 system as an illustrative case study. Firstly, the machine learning algorithm, namely artificial neural network (ANN), is employed to develop a group contribution (GC) model for accurate prediction of FR-in-IL solubility. Then, a mixed-integer nonlinear programming (MINLP) problem is formulated and solved by integrating the ANN-GC model with two available GC models for predicting the melting point and viscosity of ILs. Consequently, the optimal three ILs including [C1C10Im][dca], [C1C11Im][dca], and [C1C12Im][dca] are identified. Finally, quantum chemistry calculations are conducted to disclose the separation mechanism from molecular perspective, further validating the reliability of the CAILD results.

Educational Revolution : Digital Project-Based Rotation Learning (DPBRL) Model to Improve Students' Critical Thinking Skills

The research aimed to develop and assess the effectiveness of the Digital Project-Based Rotation Learning (DPBRL) model in enhancing students' critical thinking skills. The study employed a research and development method, using a non-equivalent control group design during the pilot phase, a research method used to describe and measure the characteristics of populations or phenomena systematically using numerical data, involving 83 undergraduate students from Mulawarman University Guidance and Counseling Study Program, divided into two heterogeneous classes. Validation of the DPBRL model was conducted by experts in learning model design, materials, and media, with data collected through validation sheets, interviews, document analysis, questionnaires, observation, and documentation. The data was analyzed using descriptive technique and Independent Samples t-test. The results demonstrated that the DPBRL model effectively improved students' critical thinking skills and digital literacy, particularly through the use of digital modules with Flipbook Maker. The model’s rotation structure and presentation stage provided a structured learning approach, highlighting the importance of feedback. The study concluded that integrating technology and collaboration in project-based learning through the DPBRL model significantly benefited students’ critical thinking, digital literacy, and teamwork, offering a comprehensive and effective learning experience.

Problem-Based Learning Model Assisted by Graphic Media in Poetry Text Learning for Fourth Grade Elementary School Students

This research aims to explain the problem-based learning model assisted by graphic media in learning poetry texts for fourth-grade elementary school students, as well as the process of implementing it in learning. The research was conducted in the 2022/2023 Academic Year, Even Semester, at Madrasah Ibtidaiyah Al-Zaytun, Sandrem Village, Gantar District, Indramayu Regency, with fourth-grade students in West Java Province. This research uses the Research and Development (R&D) method. The research design used is research and development (Research and Development) with the ADDIE model. The steps/phases of development include: Analysis, Design, Development or Production, Implementation or Delivery, and Evaluation. Data collection methods include interviews, questionnaires, observations, written tests, and performance assessments. The results of the research show that the design of a problem-based learning model assisted by graphic media in learning poetry texts for fourth-grade elementary school students is a new learning model developed from a problem-based learning model associated with graphic media, making learning more meaningful. The assessment results of the learning model design and media use were 70.5%, categorized as suitable for use. The learning media expert assessment results of 80% indicate that the learning media is suitable for use. Meanwhile, based on the results of the implementation of the problem-based learning model assisted by graphic media in learning poetry texts, the assessment results were 38 out of 44, or 86.4%, indicating that the implementation of the learning model was very suitable for use. Based on the data above, it is evident that a problem-based learning model assisted by graphic media in learning poetry texts for fourth-grade elementary school students is highly needed.

THIẾT KẾ HOẠT ĐỘNG HỌC TẬP MÔN TIN HỌC CHO HỌC SINH TIỂU HỌC SỬ DỤNG MÔ HÌNH 21CLD ĐỂ PHÁT TRIỂN NĂNG LỰC GIAO TIẾP VÀ HỢP TÁC

Communication and collaboration competency is one of three core general competencies specified in the 2018 Vietnam General Education Curriculum. However, teachers encounter difficulties in designing appropriate learning activities and assessing the development of communication and collaboration skills to cultivate this competency. The 21st Century Learning Design (21CLD) model, proposed by Microsoft, is a teaching framework aimed at developing essential skills in students, including communication and collaboration. This study compared the 21CLD model with the common and core competency framework specified in Vietnam's 2018 General Education Curriculum and found similarities between the two assessment frameworks. Therefore, this article will present Microsoft's 21CLD model, detailing assessment levels according to specific criteria for each skill, and propose a process for applying this model to develop learning activities for Informatics at the elementary level to enhance students' communication and collaboration competency. Keywords: 21CLD; learning design; communication and collaboration; teaching Informatics; primary education.

PENGEMBANGAN MEDIA PEMBELAJARAN BERBASIS ISPRING SUITE PADA MATERI BANGUN RUANG SISI DATAR

This research aims to develop ispring suite-based learning media on flat side space building materials reviewed from the aspects of feasibility, practicality and effectiveness. The research uses the R&D method, namely (Research and Development), and uses the ADDIE learning design model (Analysis, Design, Development, Implementation and Evaluation). The media developed uses ispring suite software, which is software used to create interactive learning media in the form of material presentations, material videos, practice questions, and quizzes. The test subjects in this study used individual and small group trials. The individual trial was 3 students of class VIII Madrasah Tsanawiyah and for the small group trial, namely 13 students of class VIII Madrasah Tsanawiyah. The results of this study, according to the assessment of media experts and material experts, show that ispring suite-based learning media obtained criteria suitable for use with an average score of 4.1. The results of the trials conducted on individual trials and small group trials showed that the ispring suite-based learning media obtained very practical criteria with an average score of 4.3. The ispring suite-based learning media also obtained very effective criteria with an average N-gain score of 0.87 based on the results of individual trial tests and small group trial test results.

Enhancing schizophrenia phenotype prediction from genotype data through knowledge-driven deep neural network models

This article explores deep learning model design, drawing inspiration from the omnigenic model and genetic heterogeneity concepts, to improve schizophrenia prediction using genotype data. It introduces an innovative three-step approach leveraging neural networks' capabilities to efficiently handle genetic interactions. A locally connected network initially routes input data from variants to their corresponding genes. The second step employs an Encoder-Decoder to capture relationships among identified genes. The final model integrates knowledge from the first two and incorporates a parallel component to consider the effects of additional genes. This expansion enhances prediction scores by considering a larger number of genes. Trained models achieved an average AUC of 0.83, surpassing other genotype-trained models and matching gene expression dataset-based approaches. Additionally, tests on held-out sets reported an average sensitivity of 0.72 and an accuracy of 0.76, aligning with schizophrenia heritability predictions. Moreover, the study addresses genetic heterogeneity challenges by considering diverse population subsets.

Sustainable Learning Design

This article presents the results of a case study of eight undergraduate science modules on factors for sustainable Learning Design interventions. Using a mixed-methods approach involving educator interviews, statistical data, screening of learning designs based on a furthered learning design model (STREAM), student surveys, and an efficiency assessment based on the concept of Efficient Learning Design, a total of six factors for sustainable Learning Design in the context of science higher education related to the educator perspective and the actualised learning designs are identified. The article concludes that in addition to the direct factors such as the number of enrolled students and repetition of modules, the educators’ consideration for the institutional cost-benefit perspective, their perceived usefulness of technology-enhanced learning and buy-in of its related pedagogy, the students buy-in of technology-enhanced learning, and a consistent structure with online activities, reflection exercises, and feedback are significant underlying factors for efficient and sustainable Learning Design.

A New Fingerprint and Graph Hybrid Neural Network for Predicting Molecular Properties.

Machine learning plays a role in accelerating drug discovery, and the design of effective machine learning models is crucial for accurately predicting molecular properties. Characterizing molecules typically involves the use of molecular fingerprints and molecular graphs. These are input into a multilayer perceptron (MLP) and variants of graph neural networks, such as graph attention networks (GATs). Due to the diverse types and large dimension of fingerprints, models may contain many features that are relatively irrelevant or redundant; meanwhile, although the GAT excels in handling heterogeneous graph tasks, it lacks the ability to extract collaborative information from neighboring nodes, which is crucial in scenarios where it cannot capture the joint influence of adjacent groups on atoms. To overcome these challenges, we introduce a hybrid model, combining improved GAT and MLP. In GAT, the recurrent neural network is employed to capture collaborative information. To address the dimensionality issue, we propose a feature selection algorithm, which is based on the principle of maximizing relevance while minimizing redundancy. Through experiments on 13 public data sets and 14 breast cell lines, our model demonstrates superior performance compared to state-of-the-art deep learning and traditional machine learning algorithms. Additionally, a series of ablation experiments were conducted to demonstrate the advantages of our improved version, as well as its antinoise capability and interpretability. These results indicate that our model holds promising prospects for practical applications.

A scalable adaptive sampling approach for surrogate modeling of rigid pavements using machine learning

Rigid pavement design is a high-dimensional optimization problem, involving several variables and design considerations. The existing machine learning (ML) design models are either low-dimensional or less accurate than computational simulations. Surrogate modeling is a powerful tool for approximating the results of high-fidelity computational simulations, which is commonly used to approximate the results of these simulations by sampling their solutions to train models. However, conventional and adaptive sampling methods face the challenge of “curse of dimensionality”, due to the exponential increase in required sample size and computations with the number of variables. To overcome this, we propose a scalable adaptive sampling (SAS) method that uses random samples for testing the model's performance but generates new training samples as a subset of a full factorial design of experiments (DoE). The factorial level increases with each iteration, allowing the algorithm to sample training data at a progressively finer scale, and updating the ML models each time adaptively. The proposed method was tested on several 2D benchmark examples, as well as practical pavement design problems. Our results demonstrate that the proposed technique can develop accurate surrogate models for both low- and high-dimensional inference spaces. For a 4D inference space, the surrogate models derived from the proposed method had an order of magnitude lower error than those derived from “one-shot” conventional sampling with the same sample size. For a 6D inference space, the sample size required by the proposed method was only 5 % of that required by conventional sampling for comparable performance.

Intersections and Interactions in Student Experiences

This piece is an invited commentary responding to the student roundtable on experiential learning (see ELTHE 7.2 Discussion Roundtable: Student Panel). Framing the essay around how students respond to experiential learning as significant learning experiences, the challenge for educators is to harness these learning experiences intentionally. Fink's integrated course design model and taxonomy of learning is introduced and remixed in this essay. Rooted in practitioner-scholar inquiry, this essay anchors practitioner research as the theoretical foundation to explore the students’ experience, emerging from experiential education practice and leading to broad inquiry focused on the learning that arises (Green, 2023). In the end, a new taxonomy of experiential learning is proposed, based on student responses to experiential learning as featured in the roundtable discussion.

Granular transfer learning

Transfer learning is aimed at supporting the design of machine learning models in the target domain Dt, given that the knowledge (model) has already been constructed in the source domain Ds. The domains Dt and Ds (as well as the corresponding tasks Ts and Tt) are similar, yet not identical. As a result, the model transferred from Ds to Dt in this new environment exhibits its relevance (credibility) only to some limited extent. In this study, we develop an original approach, where we advocate that the knowledge transfer (model transfer) gives rise to a granular model where the level of information granularity associated with the produced results quantifies the relevance (quality or credibility) of the transferred model. In other words, we stress that the quality of knowledge transferred to Dt becomes captured through a granular generalization of the original numeric model. The overall systematic design process is elaborated on by focusing on the development process of granular neural networks carried out on a basis of the numeric neural networks coming from Ds. The key aspect of the design is to elevate the existing numeric neural network to its granular counterpart by admitting that the connections of the developed model come in the form of information granules, in particular intervals and fuzzy sets. The optimization process is guided by adjusting (optimizing) the level of information granularity being regarded as an essential design asset. The optimized performance index builds upon the descriptors of information granules commonly encountered in Granular Computing. In particular, coverage and specificity measures are treated as sound performance indicators of the quality of knowledge transfer (viz. the performance of the granular neural network expressed in the target domain). Several illustrative examples are provided to visualize the performance of the established design environment.

Designing a Project-Based Learning (PjBL) Model on Multiculturalism in History

The purpose of writing this article is to design a multiculturalism approach to teaching history; analyze opportunities and challenges regarding teaching history through a multicultural lens; and prepare a project-based learning model design with the theme of multiculturalism with material on the Cultural History of West Kalimantan. This research method is a literature review. This research uses library insights to examine 20 journal articles related to the content of the article topic. Articles are written based on secondary data sources. The data used was obtained based on research reports, books, and appropriate articles. The data collection method was carried out through a process of in-depth study and analysis of literature on multiculturalism in the history of education in Indonesia. The data analysis technique used in writing articles is qualitative analysis. This article provides insight into the multiculturalism approach to cultural history in the West Kalimantan region. The project-based learning (PjBL) learning model can be an example for teachers in designing learning models that suit the environment and conditions of students. The aim of learning with a multiculturalism approach is expected to provide good historical awareness for students to care for Indonesia's diversity and the variety of cultures that exist. In practice, students can instill an attitude of tolerant and respectful civic life, have empathy for others to create a just Indonesian nation, and uphold democratic values ​​in life.

A Comprehensive Survey on Machine Learning and Deep Learning Techniques for Crop Disease Prediction in Smart Agriculture

Diseases caused by bacteria, fungi, and viruses are a problem for many crops. Farmers have challenges when trying to evaluate their crops daily by manual inspection across all forms of agriculture. Also, it is difficult to assess the crops since they are affected by various environmental factors and predators. These challenges can be addressed by employing crop disease detection approaches using artificial intelligence-based machine learning and deep learning techniques. This paper provides a comprehensive survey of various techniques utilized for crop disease prediction based on machine learning and deep learning approaches. This literature review summarises the contributions of a wide range of research works to the field of crop disease prediction, highlighting their commonalities and differences, parameters, and performance indicators. Further, to evaluate, a case study has been presented on how the paradigm shift will lead us to the design of an efficient learning model for crop disease prediction. It also identifies the gaps in knowledge that are supposed to be addressed to forge a path forward in research. From the survey conducted, it is apparent that the deep learning technique shows high efficiency over the machine learning approaches, thereby preventing crop loss.

Enhancing traffic flow monitoring with machine learning integration on cloud data warehousing

With urbanization and rising vehicle ownership rates, global traffic congestion and accidents have become pressing issues. This paper delves into leveraging cloud data warehousing and machine learning to tackle traffic flow monitoring and prediction, along with their potential in intelligent transportation systems. Through comprehensive analysis and case studies, it highlights how modern technology can enhance urban traffic management and services. Initially, the paper underscores the importance of traffic monitoring and prediction, identifying shortcomings in traditional approaches and advocating for machine learning solutions. It then reviews traditional traffic monitoring methods and explores machine learning's role in traffic flow prediction, illustrating its widespread application and evolving trends. Subsequently, the paper delves into the pivotal role of data warehousing in machine learning, encompassing data integration, management, cleaning, and multidimensional analysis. Additionally, it discusses the significance of relation matrices in graph convolution and presents experimental designs and model results for traffic flow prediction. Finally, the paper summarizes research findings, emphasizing the significance and future prospects of machine learning model design and cloud data warehousing in intelligent transportation systems.