Innovative Learning Methods Research Articles

Strengthening Student Nationalism Through Civic Education at Timor University

This research aims to (1) Describe the strengthening of student nationalism through civic education at Timor University, (2) Analyze the obstacles and challenges in strengthening student nationalism through civic education at Timor University, (3) Analyze the efforts made in facing challenges and obstacles in strengthening student nationalism through civic education at Timor University. This research uses a case study method with a qualitative approach. Determination of research data sources using purposive techniques, namely: Civics lecturers, and Civics class students. Data collection techniques using observation, interviews and documentation techniques. Data analysis uses the Miles, Huberman, and Saldana model with three stages, namely: data condensation, data presentation and conclusion drawing. The results of this study indicate that (1) strengthening student nationalism through civic education is carried out by applying innovative and interactive learning methods, namely, lectures, discussions, and hands-on learning. (2) challenges and obstacles in strengthening student nationalism in the border region of Indonesia and Timor Leste are the complexity of cultural identity, limited facilities in learning, and technological developments. (3) efforts made in overcoming challenges and obstacles in strengthening student nationalism through civic education in the border areas of Indonesia and Timor Leste are carried out with several activities, namely the development of more interactive learning methods such as project-based learning, empowerment programs for nationalism values

Enhancing Reusability Practices in Massive Online Open Courses

Over the past decade, the emergence of Massive Online Open Courses (MOOCs) has profoundly transformed the distance learning landscape, capturing the attention of both higher education and professional institutions. This surge of interest has not only spurred the development of innovative teaching and learning methods but has also led to a re-evaluation of content production and reuse strategies. In fact, when producing MOOCs, multiple resources and efforts are dedicated to creating a considerable amount of learning material. This is often housed within the learning environment, which serves as a sort of repository and it is accessible by learners throughout the course. However, due to a lack of management support or internal organisational structure, the use of this material sometimes remains limited to the existence of the MOOC, causing it not to be actively employed and exploited after the course has ended. Lately, issues regarding MOOCs’ content management have raised critical questions about the long-term sustainability, reusability and management of the created online learning material even after the end of the online course. By using as a case study the three interlinked MOOCs on European History, Law and Governance developed in the framework of the KU Leuven programme in European Studies and the effort invested in both the planning and afterlife of the MOOC, this paper provides an overview of the formulas adopted to enhance learning content reusability. Drawing from KU Leuven’s extensive experience in creating humanities-focused MOOCs, this collection of interconnected online courses represents a novel attempt at offering a series of educational courses that are designed to complement each other not only in terms of content but also in terms of content management. Also, by contributing to the discussion on MOOCs' reusability this paper intends to emphasise the importance of establishing clear guidelines to enhance educational content reuse, ultimately contributing to the long-term educational value of MOOCs.

Advanced deep learning strategies for breast cancer image analysis

One of the leading causes of cancer-related deaths in women is breast cancer (BC). Patients' chances of survival are improved when this ailment is diagnosed in a timely manner and suitable treatments are prescribed. Thus, the chance of survival increases with the early detection of BC. Deep learning neural networks have garnered significant attention in recent years for use in BC screening, identification, and classification. Even though some encouraging results have surfaced, more improvement and confirmation are necessary. In this regard, the creation and comparison of many deep learning approaches for the early identification and classification of BC from mammography pictures is the main focus of our research. In this study, Innovative deep learning methods are developed by freezing the first 40 layers an dropping the 43 layers of MobileNetV2, InceptionV3 and DenseNet121 pretrained models, this approach was reinforced by using Data augmentation techniques. Our suggested methodologies are tested through simulations on MIAS dataset and SA private dataset. The three modified models achieved very high classification accuracies, specifically the modified DenseNet121 model, which reached 99,1% on MIAS dataset and 98,8% on SA dataset.

Sub‐Pixel Displacement Estimation With Deep Learning: Application to Optical Satellite Images Containing Sharp Displacements

AbstractOptical image correlation is a powerful method for remotely constraining ground movement from optical satellite imagery related to natural disasters (e.g., earthquakes, volcanoes, landslides). This approach enables the characterization, and identification of the causal factors and mechanisms underlying such processes. By employing sub‐pixel correlation algorithms, one can obtain highly accurate (m‐to‐cm level) displacement fields at high spatial resolution (dm‐to‐cm) by comparing satellite images acquired before and after a period of movement. However, this method generally assumes a homogeneous translation of all pixels within a given correlation window, which will lead to biased estimates of ground displacement if the real case is not well represented by such a simplification, especially when resolving ground displacements next to sharp gradients in displacement, such as those found in the near‐field of earthquake surface ruptures. In this paper, we present an innovative deep learning method estimating sub‐pixel displacement maps from optical satellite images for the retrieval of ground displacement. From the generation of a realistic simulated database, comprising Landsat‐8 satellite image pairs containing simulated sub‐pixel shifts and sharp discontinuities, we develop a Convolutional Neural Network able to retrieve sub‐pixel displacements. The comparison to state‐of‐the‐art correlation methods shows that our pipeline significantly reduces by 32% the estimation bias around fault ruptures, leading to more accurate characterization of the near‐field strain in surface rupturing earthquakes. Application of our model to the 2019 Ridgecrest earthquake demonstrates the ability of our model to accurately and quickly resolve ground displacement using real satellite images. Code is made available at https://gricad‐gitlab.univ‐grenoble‐alpes.fr/montagtr/cnn4l‐discontinuities.

LightDPH: Lightweight Dual-Projection-Head Hierarchical Contrastive Learning for Skin Lesion Classification

Effective skin cancer detection is crucial for early intervention and improved treatment outcomes. Previous studies have primarily focused on enhancing the performance of skin lesion classification models. However, there is a growing need to consider the practical requirements of real-world scenarios, such as portable applications that require lightweight models embedded in devices. Therefore, this study aims to propose a novel method that can address the major-type misclassification problem with a lightweight model. This study proposes an innovative Lightweight Dual Projection-Head Hierarchical contrastive learning (LightDPH) method. We introduce a dual projection-head mechanism to a contrastive learning framework. This mechanism is utilized to train a model with our proposed multi-level contrastive loss (MultiCon Loss), which can effectively learn hierarchical information from samples. Meanwhile, we present a distance-based weight (DBW) function to adjust losses based on hierarchical levels. This unique combination of MultiCon Loss and DBW function in LightDPH tackles the problem of major-type misclassification with lightweight models and enhances the model’s sensitivity in skin lesion classification. The experimental results demonstrate that LightDPH significantly reduces the number of parameters by 52.6% and computational complexity by 29.9% in GFLOPs while maintaining high classification performance comparable to state-of-the-art methods. This study also presented a novel evaluation metric, model efficiency score (MES), to evaluate the cost-effectiveness of models with scaling and classification performance. The proposed LightDPH effectively mitigates major-type misclassification and works in a resource-efficient manner, making it highly suitable for clinical applications in resource-constrained environments. To the best of our knowledge, this is the first work that develops an effective lightweight hierarchical classification model for skin lesion detection.

The Transformation of Social Media in Arabic Language Learning: Opportunities and Risks in the Indonesian Context

This research examines the possibilities and dangers associated with using social media for learning Arabic in Indonesia. This work aims to address research difficulties by utilising library-based research methods, which involve analysing data obtained from various sources such as publications, papers, journals, scientific articles, and related books. Next, we will examine the potential and concerns associated with the evolution of social media in the context of Arabic language acquisition. The findings revealed that educational opportunities encompassed convenient access to information and learning resources, widespread availability of global connectivity and language exchange, innovative learning methods, global reach and interactive teaching, and enhanced ease and effectiveness of student-Arabic-teacher interaction. The risks associated with using social media in education include distractions from irrelevant content, exposure to inappropriate material that can have a negative impact on students, technical issues such as unstable internet connections, and high data costs, particularly in remote areas.

Integration of Pancasila and Islamic values in Indonesia's futuristic education transformation: Multicultural analysis

This research aims to analyze the integration of Pancasila and Islamic values in the context of futuristic educational transformation in Indonesia with a multicultural approach. Facing the era of industrial revolution 4.0 and society 5.0, Indonesian education needs to transform without losing the roots of the nation's noble values. The research method used is descriptive qualitative with a literature study approach. The research results show that there is harmony between the values of Pancasila and Islamic teachings which can be integrated into futuristic education. Soft skills development based on these two value systems is very important in preparing future generations. The integration model can be implemented through the development of an integrated curriculum and innovative learning methods such as project-and role-based learning, and the formation of cross-cultural communities. This multicultural approach in the integration process strengthens understanding of diversity while maintaining unity. Although there are challenges in implementation, strategies such as intensive teacher training and multi-stakeholder collaboration can be a solution. This research contributes to the development of an educational model that integrates national and religious values to face the challenges of the digital era in Indonesia.

Andragogy and Edutainment Approach: A Cross-Generational Solution for Improved Worship Practices

This research is a Participatory Action Research (PAR) that aims to improve the understanding and practice of ibadah in the Kampung Batu Dalam, Solok district community. Research is carried out through several cycles of planning, action, observation, and reflection. In Cycle 1, diagnosis of problems is carried out through initial observation, identification of problems, analysis of root problems, and consultation with stakeholders. The lecture and learning methods were chosen as the initial action. Cycle 2 focuses on religious learning activities such as worship, sanctification, and sacrament and is taught to the community and children. The methods used include routine learning, competition, and active involvement of the community and children. Evaluations at Cycle 3 show success in raising children's spirits, but the main challenge is the difficulty of reaching older people who are still tied to the old tradition. The main findings of this study were the importance of combining an andragogic approach for the elderly and innovative game-based learning methods for children. Combining these two approaches is a creative and replicable solution to address similar problems in other societies with different characteristics.

PEMBUATAN BONEKA HORTA SEBAGAI PEMANFAATAN LIMBAH SERBUK KAYU DAN PEMBELAJARAN PERAWATAN TANAMAN DI SDN 2 GUMUKREJO

Horta Doll program explores the application of innovative learning methods at SDN 2 Gumukrejo as an effort to cultivate students' environmental awareness and creativity. Horta dolls, which are planting media shaped like dolls made from organic materials with plant seeds inside, are used to introduce the concept of plant growth in a direct and enjoyable way. The demonstration method is applied in this workshop to provide an interactive experience that engages students in creating and caring for Horta dolls. The results show high enthusiasm from students, as well as an increase in environmental awareness and creativity. This environment-based learning proves effective in teaching students about plant growth and care for the environment practically..

Real-time prediction of river ice breakup phenomena: A jittered genetic programming model and wavelet analysis integrating remotely sensed imagery and machine learning

Forecasting the timing of breakup ice jams in rivers is crucial for early flood warning and effective management in cold regions where rising river flows can lead to significant damage. However, this task is hindered by insufficient data and the complex dynamics of river ice. These obstacles pose challenges in developing precise forecasting models. This study aimed to address the data scarcity issue by introducing innovative machine learning methods, focusing on classification and jittering (J), binary genetic programming (BGP), and wavelet transform (WT) for river ice forecasting (WT-JBGP) in the Tornio River, situated between Finland and Sweden. By considering time scales ranging from 2 to 32 days and time lags of 1 to 3 days, this method was applied to enhance the predictive capabilities of predictors. The findings reveal that certain predictors, with specific time scales and time lags, significantly influence the timing of breakup events. These include the 8-day temperature and 32-day discharge, both with a 2-day lag time, as well as the 4-day precipitation, approximation of albedo, and 16-day atmospheric pressure at ground level, all with a 1-day lag obtained from ERA5 and recorded data. Additionally, we conducted a quantitative evaluation of the effectiveness of the proposed model and contrasted its efficacy with that of BGP, WT-BGP, and advanced J-BGP techniques. The WT-JBGP model attains the highest overall classification accuracy of approximately 0.91, alongside a Heidke Skill Score exceeding 0.78, and a Positive Predictive Value surpassing 0.85, thereby demonstrating its superiority over competing methodologies. In summation, this study offers a promising approach to overcoming observed data scarcity in breakup date prediction, providing valuable insights into river ice dynamics.

Swimtrans Net: a multimodal robotic system for swimming action recognition driven via Swin-Transformer.

Currently, using machine learning methods for precise analysis and improvement of swimming techniques holds significant research value and application prospects. The existing machine learning methods have improved the accuracy of action recognition to some extent. However, they still face several challenges such as insufficient data feature extraction, limited model generalization ability, and poor real-time performance. To address these issues, this paper proposes an innovative approach called Swimtrans Net: A multimodal robotic system for swimming action recognition driven via Swin-Transformer. By leveraging the powerful visual data feature extraction capabilities of Swin-Transformer, Swimtrans Net effectively extracts swimming image information. Additionally, to meet the requirements of multimodal tasks, we integrate the CLIP model into the system. Swin-Transformer serves as the image encoder for CLIP, and through fine-tuning the CLIP model, it becomes capable of understanding and interpreting swimming action data, learning relevant features and patterns associated with swimming. Finally, we introduce transfer learning for pre-training to reduce training time and lower computational resources, thereby providing real-time feedback to swimmers. Experimental results show that Swimtrans Net has achieved a 2.94% improvement over the current state-of-the-art methods in swimming motion analysis and prediction, making significant progress. This study introduces an innovative machine learning method that can help coaches and swimmers better understand and improve swimming techniques, ultimately improving swimming performance.

Deskripsi Pembelajaran IPAS dalam Kurikulum Merdeka Kelas IV di SD Negeri 01 Anjongan

The Independent Curriculum was introduced as a response to the need for a more flexible and relevant education to global developments. Science and Technology learning integrates scientific and social elements to provide a holistic understanding to students. This study aims to describe the implementation of Natural and Social Sciences (IPAS) learning in the Independent Curriculum in grade IV of SD Negeri 01 Anjongan. The research method used is qualitative descriptive, with direct observation as the main data collection technique. Data analysis is carried out qualitatively with the stages of data reduction, data presentation, and conclusion drawing. The results of the study show that social science learning in grade IV of SD Negeri 01 Anjongan has been carried out well, with teachers successfully linking learning materials with daily life and practicing process skills effectively. However, challenges are still encountered in terms of providing resources and developing innovative learning methods. This research provides important insights for the development of educational practices that are more in line with the goals of the Independent Curriculum, especially in the context of basic education. It is hoped that the results of this study can be a reference for teachers and other schools in implementing science and technology learning optimally.

The Impact of Innovative Learning Methods on Self-Efficacy: The Lived Experiences of High School Students and Educators

The Impact of Innovative Learning Methods on Self-Efficacy: The Lived Experiences of High School Students and Educators

Distributed Learning in Intelligent Transportation Systems: A Survey

The development of artificial intelligence (AI) and self-driving technology is expected to enhance intelligent transportation systems (ITSs) by improving road safety and mobility, increasing traffic flow, and reducing vehicle emissions in the near future. In an ITS, each autonomous vehicle acts as a node with its own local machine learning models, which can be updated using locally collected data. However, for autonomous vehicles to learn effective models, they must be able to learn from data sources provided by other vehicles and infrastructure, utilizing innovative learning methods to adapt to various autonomous driving scenarios. Distributed learning plays a crucial role in implementing these learning tasks in an ITS. This review provides a systematic overview of distributed learning in the field of ITSs. Within an ITS, vehicles can engage in distributed learning by interacting with peers through opportunistic encounters and clustering. This study examines the challenges associated with distributed learning, focusing on issues related to privacy and security in data intelligence sharing, communication quality and speed, and trust. Through a thorough analysis of these challenges, this study presents potential research avenues to address these issues, including the utilization of incentive mechanisms that rely on reputation, the adoption of rapid convergence techniques, and the integration of opportunistic federated learning with blockchain technology.

Student involvement and innovative teaching methods in a biophilic design education pilot elective course in interior architecture

Biophilic design has gained popularity in interior design areas owing to its numerous advantages. Nevertheless, globally, Interior Architecture/Interior Architecture and Environmental Design departments lack adequate biophilic design courses in their curricula. This research investigates the impact of involving students in syllabus design and applying innovative teaching methods in a pilot elective course focused on biophilic design in interior spaces on student engagement and course sustainability. A new pilot elective course was introduced in the 2022–2023 Spring Semester at the Interior Architecture Department, Faculty of Architecture, Near East University, aiming to establish an enduring and captivating learning environment for students. Initially, a focus group study was conducted to measure students’ awareness of biophilic design and integrate their ideas regarding innovative learning methods into the syllabus for an engaging elective course. Strategies like interactive learning tools, group tasks, and peer assessments were incorporated throughout the course to enhance engagement. Analysis of end-of-course surveys and student observations revealed an augmented awareness of biophilic design among students and a positive influence of innovative learning methods on course sustainability. Thus, the study suggests that an elective course offers the potential to mitigate the deficiency of biophilic design integration in undergraduate programs, augmenting students’ awareness in this field. Moreover, new elective courses could deliver more sustainable and engaging learning experiences for enrolled students when structured through student involvement and innovative learning methods.

Paradigma dan Tantangan Pendidikan Seni dalam Mengintegrasikan Akhlaq, Teknologi, dan Multikulturalisme

Art education faces various paradigms and challenges in the modern era, where the integration of moral values, technological development, and multiculturalism is increasingly important. This study aims to examine the challenges and opportunities in integrating moral values, technology, and multiculturalism into art education. This research uses Creswell's naturalistic qualitative method. The results of this study include: First, moral values encompassing ethics, morality, and character are outlined as fundamental foundations in shaping students' personalities. Second, rapid technological development provides both opportunities and challenges in adapting innovative and interactive art learning methods. Third, multiculturalism and cultural diversity are important elements in enriching artistic perspectives and promoting inclusivity. Through this approach, it is hoped that art education can produce creative, critical, and character-driven individuals who are ready to face the ever-changing global dynamics.

Data-driven void growth prediction of aluminum under monotonic tension using deep learning

Void growth plays a significant role in ductile fracture prediction of aluminum. This study proposes 2 deep learning models to address this issue. For voids that retain their ellipsoidal characteristics during growth, the ellipsoidal void Semiaxes Long Short-Term Memory (SLSTM) method is proposed, using the 3 principal features of the ellipsoid to represent the voids. For voids that undergo arbitrary shape changes during growth, an innovative deep learning method called Voronoi tessellation-assisted LSTM (VLSTM) is proposed. This method uses the Voronoi algorithm to standardize data features and employs Principal Component Analysis (PCA) to perform data compression before neural network training. This new method combines the Voronoi algorithm, LSTM neural networks, and PCA algorithms, and is termed as VLSTM-PCA. In this study the deep learning-based SLSTM surrogate models and VLSTM-PCA surrogate models run approximately 514 and 537 times faster than ABAQUS finite element simulations, significantly enhancing efficiency while maintaining high prediction accuracy. Finally, growth patterns of ellipsoidal voids under different stress triaxialities are analyzed.

Development of teaching materials for writing short stories based on multi-modal through the Glide Apps platform

Developing a multimodal short story writing application is an innovative step in improving students' understanding and ability to write short stories. This study aims to develop and test the effectiveness of an application for learning to write short stories through the Glide Apps platform. This study adopts a research and development (R&D) method to develop multimodal short story writing teaching materials through the Glide Apps platform by integrating qualitative and quantitative approaches. The effectiveness test was conducted using a pseudo-experimental method for students of Kuningan University taking the anatomy of fictional prose course through a one-group pretest-posttest design to evaluate the impact of the application. The results of the effectiveness test provide a positive picture of the potential of this application as an effective tool in improving short story writing skills as a whole. This application presents various learning methods, theories, and exercises that gadgets can access flexibly. This application also provides short story writing assignment facilities via email. The results of this study have positive implications, especially in developing innovative learning methods that can improve students' literacy and creativity in writing short stories.

Fostering Mental-Wellbeing and Health Behavior through Online learning Measures and Cyber Resilience

Objective: Online learning tools and updated cyber-information can lead to improve overall health behavior and offer solutions for learners' mental well-being. A major role is played by digital technology in collaborating with innovative methods of learning to foster healthy behavior. This study attempted to examine how online learning techniques such as flipped learning and E-learning can help learners enhance cyber resilience and build a Metaverse, the online universe; and how this cyber resilience can further enhance students' health behaviors and mental-wellbeing. Method: A qualitative research design was adopted; data was collected through semi-structured interviews from a sample of 10 students, randomly identified from higher educational institutions in Turkey. Results: The content analysis of interview transcripts yielded the following results: that the metaverse integration of flipped learning and e-learning has proven to be a significant educational technique; that Cyber Resilience in digital settings plays a pivotal role in generating good learning experiences; that technological advancements in learning contexts express the interdependence of health behavior and mental health on technology; and that when e-learning and flipped learning incorporate with the metaverse, they demonstrate their potential for boosting health behavior and mental well-being. Findings: These findings will encourage policymakers and technology experts to emphasize the importance of creating secure digital environments, assisted by technology. Finally, this research sheds light on the complex interaction between education, technology, and well-being in the ever-changing metaverse context.

OnsitNet: A memory-capable online time series forecasting model incorporating a self-attention mechanism

Traditional time series (TS) forecasting models are based on fixed, static datasets and lack scalability when faced with the continuous influx of data in real-world scenarios. Real-time online learning of data streams is crucial for improving forecasting efficiency. However, few studies focus on online TS forecasting, and existing approaches have several limitations. Most current online TS forecasting models merely train on data streams and are ineffective in handling concept drift scenarios. Furthermore, they often fail to adequately consider dependencies between variables and do not leverage the robust modeling capabilities of offline models. Therefore, we propose an innovative online learning method called OnsitNet. It consists of multiple learning modules that progressively expand the receptive field of convolutional kernels within the learning modules using an exponentially growing dilation factor, aiding in the capture of multi-scale data features. Within the learning modules, we propose an online learning strategy focusing on memorizing concept drift scenarios, with a fast learner, memorizer, and Pearson trigger. The Pearson trigger activates dynamic interaction between the fast learner and memorizer by detecting new data patterns, facilitating online rapid learning of data streams. To capture the dependencies between variables, we propose a new model, SITransformer, which is a streamlined version of the offline model ITransformer. Unlike the traditional Transformer, it reverses the roles of the feed-forward network and the attention mechanism. This inverted architecture is more effective at learning the correlations between variables. Experimental results on five real-world datasets show OnsitNet achieves lower online prediction errors, enabling timely and effective forecasting of future trends in TS data.