Innovative Learning Research Articles

Perceived Enablers of and Barriers to Serious Game as Oral Histology Learning Strategy for Undergraduate Dental Students.

Previously, we reported the serious game HistoRM as an innovative learning approach for an oral histology course. This study aimed to examine the impact of HistoRM on summative assessment and the enablers and barriers factors affecting HistoRM as an interactive learning strategy in an oral histology course. A crossover randomized controlled trial was performed. Study participants were first-year dental students at the Universitas Indonesia. The average final grades of students who participated in HistoRM serious game were significantly higher than those of students who did not participate in this trial (p < 0.001). Positive responses of HistoRM were observed in the learning content, games and learning experience domains. The enabler factors most recognized by the students were the game method, which helped students to understand the learning materials; the immediate feedback provided following each gameplay; as well as the fun and interesting gameplay. The barrier factors most recognized by the students were some challenges of the gameplay, which resulted in a longer time needed to study. While the HistoRM serious game can stimulate student motivation and engagement in learning oral histology, overcoming the barriers is essential for the implementation of serious games as a complementary learning approach in the dental curriculum.

Optimization of Digital Media Utilization for Anti-Bullying Campaigns Among Generation Z

Digital learning media based on applications are rarely found in anti-bullying education, yet the impact of using such learning tools cannot be underestimated. Therefore, this study aims to develop a digital learning media product based on an application to promote anti-bullying among Generation Z in junior high schools. This research adopts a Research and Development (R&amp;D) approach using the ADDIE model, focusing on the process of producing application-based digital learning media suitable for educational purposes. The research subjects consist of media experts, content experts, and the director of the Children's Care Foundation (KAKAK) in Surakarta. Data collection techniques involved media validation questionnaires, which were then analyzed using percentages and described to provide an overview of the suitability level of this media. The research results show that the average validation results were 88%, while the average results from content were 87%. After validation, this digital media fall into the 'Very Good' qualification. Therefore, based on assessments from media experts, content experts, and the director of the KAKAK Foundation, it is concluded that this application-based digital learning media product is categorized as 'feasible' for use as an alternative learning medium in promoting anti-bullying in junior high schools. The existence of this media is evidently an innovative learning tool that enriches the process of anti-bullying education.

Development of Mobile Learning NARACY (Financial Literacy) as a Learning Media for Social Studies Subjects in Junior High School

The industrial revolution 4.0 is characterized by technological disruption that affects the education system. One of the implementations of technology orientation in the learning process facilitated by teachers is through learning resources. Therefore, this study aims to produce a mobile learning product, NARACY, as a learning media to support financial literacy material activities for grade IX junior high school students. This research uses the Research &amp; Development (R&amp;D) method with the ADDIE model. This research and development showed a total percentage of material validators of 91.6% and media validators of 95%. At the same time, the trial results on grade IX students obtained an average percentage score of 93%. Based on these results, the NARACY application is very feasible to use as a medium for learning social studies in grade IX junior high school. This research and development is expected to be an innovative learning support media that can be used by teachers and students and is expected to facilitate diverse student learning styles. Suggestions for further research include testing the product's effectiveness by conducting experimental activities in the classroom and providing various themed features on the product. They can be disseminated through the Google PlayStore platform.

Development of Learning E-Modules Based on Contextual Teaching and Learning on the Material of Changing the Form of Energy to Improve Students' Science Literacy

The low science literacy of students is caused by the lack of utilization of technology in learning activities such as the use of teaching materials. One way to improve students' science literacy is to develop innovative learning materials such as learning e-modules. This study aims to produce contextual teaching and learning-based learning e-modules on IPAS Phase B learning, material for changing the form of energy to improve the science literacy of students in elementary school. This research is a type of Research and Development (R&amp;D) research, the development was carried out referring to the Borg &amp; Gall theory. Data collection tools use valid and reliable test instruments. Based on the results of the material, media and language expert validation test of the validity of the contextual teaching and learning-based learning e-module product obtained an average value of 0.813 with decent criteria. Furthermore, the results of the educator's response test to the contextual teaching and learning-based learning e-module users obtained 86.88 with very practical criteria, while the response of students obtained an average value of 97.59 with very practical criteria. Then the results of the data effectiveness test using the paired t-test with the calculation result of 0.000 &lt; 005 means that there is a significant difference between before being given treatment with contextual teaching and learning-based learning e-modules and after being given the treatment. Based on the data obtained from the results of the study, it can be concluded that the contextual teaching and learning-based learning e-module on the material of changing the form of energy is valid, practical, and effective to improve the science literacy of students in elementary schools

Advances in Cybersecurity and AI: Integrating Machine Learning, IoT, and Smart Systems for Resilience and Innovation Across Domains

Artificial Intelligence (AI) is revolutionizing cybersecurity by offering enhanced threat detection, predictive analytics, and automated responses. However, AI also introduces significant challenges, including bias, lack of transparency, and vulnerability to adversarial attacks. This paper examines the dual role of AI in cybersecurity, providing a comprehensive analysis of its benefits and drawbacks, and discussing the future of AI in securing digital environments.

The Utilization of Google Sites Media in Writing Skills in the 5.0 Era

High school teachers in Tegal City have difficulty realizing professionalism in managing meaningful learning. One of the reasons is that teachers are not used to using google sites learning media which includes innovative, efficient, and effective learning materials and media and are student-oriented in the 5.0 era. The solution to overcome this problem is to empower the Indonesian Subject Teacher Conference (MGMP) through the development of google sites media in writing skills in the field of Indonesian studies to improve meaningful learning in the 5.0 era for high school teachers in Tegal City. The goal is to maximize the MGMP program and foster teacher professionalism and optimize the ability of educators to carry out learning. The methods used are training methods and guidance methods. The training method is used to teach google sites media content and the guidance method is used in the practice of designing google sites media in writing skills using Canva, the preparation of teaching modules, learning materials, and learning models. With these two methods, it is hoped that the target audience for the application of science and technology can increase professionalism for teachers to improve the quality of learning.

Revolutionizing Network Intelligence: Innovative Data Mining and Learning Approaches for Knowledge Management in Next-Generation Networks

The Information and Communication (ICT) industry, a global giant among service sectors, is known for both its massive scale and its unforgiving demands. Here, downtime is unacceptable, requiring constant high availability – often at the stringent Sigma Six standard. Redundancy is a common solution, but it comes at a cost. To meet these demands proactively, the ability to predict load and growth becomes crucial. This project aims to develop a prototype, or proof of concept, that utilizes data mining to provide early warnings and growth forecasts for the ICT industry with good accuracy. Big data is key to making discoveries in any data analysis project. Normally, this data comes from real-time system logs. However, for this initial test, I used a dataset called MIT Reality Mining. This dataset is useful because real-world companies, especially in the tech industry (ICT), are often hesitant to share their current information. By using MIT Reality Mining, I could still find trends and potential reasons behind them in the ICT industry. It's important to remember that this is a limited functionality prototype. While it can serve as a guideline for Telcos looking to implement data warehouses, the actual implementation details will need to adapt to the specific needs of each industry.

Peningkatan Hasil Belajar Peserta Didik Pada Pembelajaran IPAS Dengan Menggunakan Model Discovery Learning di Kelas IV SDN 15 Tabing Kecamatan Bonjol

This research is based on the low learning outcomes of students, this is because teachers have not used innovative learning models that can attract students' attention. The purpose of this study is to describe the improvement of social science learning outcomes by using the Discovery Learning model in Class IV SDN 15 Tabing, Bonjol District. This research is a classroom action research (PTK) that uses qualitative and quantitative approaches. It is carried out in two cycles, namely cycle I consists of 2 meetings and cycle II consists of 1 meeting. Each cycle includes four stages, namely planning, implementation, observation, and reflection. The subjects of this study are teachers and students of grade IV of SDN 15 Tabing with a total of 30 students, 10 male students and 20 female students. Data collection techniques are in the form of observation, test, and non-test. The results of this study are guided by the recapitulation table of the results of the first cycle and the second cycle of research that have been presented in the discussion section, the results of this study show an increase in: a) the teaching module of the first cycle with an average of 81.81% qualification (good) and increased in the second cycle to 97.72% with qualification (very good), b) the implementation in the aspect of the teacher of the first cycle with an average of 82.8% qualification (good) and increased in the second cycle to 93.5% with qualifications (very good), in the aspect of students in the first cycle with an average of 82.8% of qualifications (good), and increased in the second cycle to 93.5% with qualifications (very good), c) the learning outcomes of students in the first cycle with an average of 76.78 with qualifications (adequate) and increased in the second cycle to 87.96 with qualifications (good). Based on these results, it can be concluded that using the Discovery Learning model can improve the learning outcomes of science and technology in students.

Exploring the individual adoption of human resource analytics: Behavioural beliefs and the role of machine learning characteristics

The technological capabilities of Human Resource Analytics (HRA), enhanced by recent innovations in Machine Learning (ML), offer exciting opportunities. However, organisations often fail to realise these potentials because of a limited understanding of why individuals choose to adopt or disregard respective tools. Prior research on innovation adoption offers preliminary insights but fails to aggregate the determinants of individual adoption into actionable suggestions for decisions in the ML adoption process. Our study applies focused interviews to examine non-ML experts' reasoning for using a specific tool tailored to a public sector organisation, which corresponds to the usual end-user perspective of ML-based HRA adoption. By drawing from the HRA adoption framework, provided by Vargas et al. (2018), we contribute to the literature by identifying relevant beliefs and experiences influencing one's intention to adopt ML-based HRA and by qualitatively linking these beliefs to ML characteristics such as transparency, automation and fairness. For practitioners, we provide actionable guidance emphasising the need to ensure fairness proactively, as interviewees do not consider this aspect when deciding to adopt ML-based HRA.

PAI Teachers' Strategies In Improving Students' Learning Activity In PAI Subjects In Elementary Schools (Case Study Research at SDN 2 Parakan Garokgek, Purwakarta Regency)

This study was motivated by observations showing low interest and activeness of students in participating in Islamic Religious Education (PAI) learning, which has implications for the achievement of learning objectives that are not optimal. This study explores the strategies Islamic Religious Education (PAI) teachers to improve student learning activeness in Elementary Schools. This study uses a qualitative approach with a case study method—data collection techniques through observation, interviews, and documentation studies. Research participants consisted of Islamic Religious Education (PAI) teachers, principals, and homeroom teachers at the school. Data analysis was carried out descriptively and qualitatively to understand the strategies applied by teachers in planning and implementing learning and the factors that influence its success. The study results showed that Islamic Religious Education (PAI) teachers used various innovative and creative learning strategies to improve student learning activeness, such as discussion methods, group work, and interactive learning media. In addition, this study identified factors that influence the success of learning strategies, including active student involvement, support from the school environment, and teacher competence and creativity in teaching. This study provides theoretical contributions in the form of new knowledge and insights regarding Islamic Religious Education learning strategies in elementary schools and practical benefits for teachers, schools, and educational institutions to improve the quality of learning and student learning activity.

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.

Breast lesions segmentation from ultrasound images using DeepLabV3 + model with channel and spatial attention mechanism

Segmenting breast tumors in ultrasound images is pivotal for computer-aided diagnosis (CAD) systems aimed at detecting breast cancer. This research contributes directly to the Sustainable Development Goal (SDG), good health and well-being by leveraging innovative deep learning technique to boost the accuracy of breast tumor segmentation. Achieving accurate segmentation is crucial for precise tumor size, shape, and location determination, which in turn facilitates subsequent tumor quantification and classification. However, this task presents challenges, particularly when dealing with small tumors. The complexity arises from factors such as speckle noise, variations in tumor shapes and sizes across patients, and the presence of tumor-like regions in the images. Although deep learning-based methods have shown remarkable success in biomedical image analysis, the current state-of-the-art approaches still struggle to achieve satisfactory performance in segmenting small breast tumors. In this paper, BUS (Breast Ultrasound) dataset was initially applied on state of-the art DeepLabV3 + architecture for the segmentation of breast lesions in ultrasound images. After that to focus on more informative features, a modified DeepLabV3 + has been proposed by integrating a CBAM module in encoder as well as decoder. At the end, comparative analysis of state-of-art DeepLabV3 + model and proposed modified DeepLabV3 + has also been presented in terms of performance metrics like Dice Coefficient, Intersection over Union, Precision, Recall and Specificity. The proposed model demonstrates outstanding performance across different evaluation metrics achieving precision, recall, specificity, dice coefficient and Intersection over Union (IoU) values of 0.974, 0.933, 0.997, 0.951, and 0.933. respectively.

Economical hybrid novelty detection leveraging global aleatoric semantic uncertainty for enhanced MRI-based ACL tear diagnosis

This study presents an innovative hybrid deep learning (DL) framework that reformulates the sagittal MRI-based anterior cruciate ligament (ACL) tear classification task as a novelty detection problem to tackle class imbalance. We introduce a highly discriminative novelty score, which leverages the aleatoric semantic uncertainty as this is modeled in the class scores outputted by the YOLOv5-nano object detection (OD) model. To account for tissue continuity, we propose using the global scores (probability vector) when the model is applied to the entire sagittal sequence. The second module of the proposed pipeline constitutes the MINIROCKET timeseries classification model for determining whether a knee has an ACL tear. To better evaluate the generalization capabilities of our approach, we also carry out cross-database testing involving two public databases (KneeMRI and MRNet) and a validation-only database from University General Hospital of Larissa, Greece. Our method consistently outperformed (p-value<0.05) the state-of-the-art (SOTA) approaches on the KneeMRI dataset and achieved better accuracy and sensitivity on the MRNet dataset. It also generalized remarkably good, especially when the model had been trained on KneeMRI. The presented framework generated at least 2.1 times less carbon emissions and consumed at least 2.6 times less energy, when compared with SOTA. The integration of aleatoric semantic uncertainty-based scores into a novelty detection framework, when combined with the use of lightweight OD and timeseries classification models, have the potential to revolutionize the MRI-based injury detection by setting a new precedent in diagnostic precision, speed and environmental sustainability. Our resource-efficient framework offers potential for widespread application.

How to Better Qualify ICT Graduates to Support Digital Education: A contribution from CALOHEE Tuning project qualifications framework

The Information and Communications Technology subject area is a broad multidisciplinary field of academic research and professional practice covering many topics ranging from electronics to system and network administration, to software development, cyber security, VR, AR, IoT and AI. Due to its nature, it cooperates closely with diverse areas, most notably eLearning and digital education. As contemporary educational institutions undergo a digital transformation, by which its processes are reengineered to take most of the possibilities offered by the emerging technologies, the contribution of the ICT field has become transversal and consequently of critical importance. The term ICT which refers to this wide multidisciplinary field differentiates from IT, which applies specifically to the management and use of computer systems to store, retrieve, transmit, and manipulate data. The continuous expansion of the field to new territories of practice such as education is requiring additional knowledge, skills and wider competences acquisition. In addition, high volatility of the job market creates the need for very adaptable professional profiles. As a result, there is a pressure from the job market for shorter and more job-oriented programmes, but also for competence frameworks which may serve as references for quality higher education and training. In this paper we present the Tuning Quality Reference Framework (QRF) for ICT which was developed as part of the CALOHEE Erasmus+ funded project. A multidisciplinary team with experts from 12 different countries (Portugal, Lithuania, Germany, Italy, Spain, Austria, Belgium, Greece, Turkey, Finland, Ireland and Romania) took part in the task. The QRF is built in a way to flexibly address all the mentioned complexity and continuously emerging new requirements including educational institutions and non-formal education organisations. The approach used also supports innovation in learning, teaching and assessment practices in ICT degrees, fostering open and digital education.

Abnormal low-magnitude seismicity preceding large-magnitude earthquakes

Unraveling the precursory signals of potentially destructive earthquakes is crucial to understand the Earth’s crust dynamics and to provide reliable seismic warnings. Earthquake precursors are ambiguous, but recent experimental studies suggest that robust warning signs may precede large seismic events in the short (day-to-months) term. Here, we show that the M6.4-M7.1 2019 Ridgecrest sequence (California) and the M7.1 2018 Anchorage earthquake (Alaska) were preceded by up to ~3 months of tectonic unrest on regional scales, as evidenced by abnormal low-magnitude seismicity spreading over the ~15-25% of Southern California and Southcentral Alaska. This precursory unrest has been discovered with an algorithm that integrates an innovative random forest machine learning approach and statistical features built from earthquake catalogs. Supported by a novel suite of finite element solid mechanics models, we propose that precursory, abnormal, low-magnitude seismicity arises if the pore fluid pressure within large fault segments escalates significantly as they approach failure, which leads to major uneven changes in the regional stress field. Our findings and method may open up new perspectives for surveillance agencies to anticipate when a region approaches an earthquake of great magnitude weeks to months before it occurs.

AI-Driven IoT Healthcare System for Real-Time ECG Analysis and Comprehensive Patient Monitoring

This study explores the integration of deep learning and Internet of Things (IoT) technologies to enhance healthcare delivery, with a primary focus on improving electrocardiogram (ECG) analysis and real-time patient monitoring systems. The research presents the development of two innovative deep learning models based on the MIT-BIH dataset, enabling highly accurate ECG analysis. One model is trained for precise R-R peak detection, while the other performs effective classification of ECG signals into five distinct disease categories. The study also introduces an integrated healthcare system that seamlessly captures patients' real-time physiological data, including ECG, SpO2, and temperature, using an ESP32 microcontroller and Raspberry Pi. An IoT infrastructure with Node-RED IBM Platform and Message Queuing Telemetry Transport (MQTT) securely transmits the ECG data to the advanced analysis algorithms. The user interface displays patients' vital signs, including heart rate, oxygen saturation, and temperature, providing healthcare professionals with comprehensive real-time insights. By integrating the deep learning models, which achieve approximately 99% accuracy, alongside robust sensor technology and an IoT architecture, this system aims to transform healthcare by enabling highly precise ECG analysis and remote patient monitoring. The findings of this study underscore the potential of the synergistic convergence of deep learning, sensor technology, and IoT to advance healthcare delivery and improve patient outcomes.

Technology Enhanced Assessment in Higher Education

Research indicates that assessment of learning and assessment of learning outcomes are the biggest challenges that teachers in higher education (HE) face. Traditional assessment practices do not work when learning and teaching is supported with technologies, which is inevitable in HE today. Teachers lack digital competence in designing assessment strategies and applying digital technologies for assessment of learning process and learning outcomes. DIGI-PROF project aims to address these challenges by introducing innovative learning and teaching practices that promote transparent technology enhanced assessment for online learning. This paper seeks to identify how teachers have progressed with application of digital technologies to support technology enhanced assessment of learning process and learning outcomes. The research revealed which technologies teachers apply for technology enhanced assessment of learning process (voice/video/text communication channels, file-sharing services, emails, and online quizzes), and how teachers use these technologies to facilitate learning process (providing feedback, applying technologies for peer assessment, and monitoring of students’ learning). The study opened perspectives for further investigation on the use of learning analytics data to monitor and track students' learning progress.

PENGARUH PENYULUHAN METODE SOKRATIK DAN DIDAKTIK DENGAN MEDIA FRUVEBLE CARD TERHADAP PENGETAHUAN DAN SIKAP KONSUMSI BUAH DAN SAYUR PADA ANAK

Obesity and the incidence of fruit and vegetable consumption are experienced by many elementary school children. The lack of consumption of fruits and vegetables is related to the poor metabolic processes in the body, causing obesity and even obesity in children. The purpose of this study was to determine the consumption of fruits and vegetables in elementary school children, the influence of socratic and didactic methods using fruveble card media on knowledge and attitudes about fruit and vegetable consumption in elementary school children. This study used an experimental design with a two-group pre-test post-test research design. The population was 178,196 people with the intervention group of SDN 18 totaling 33 people and the control group of SDN 34 totaling 33 people. Sampling using the total sampling technique. Analyzed through wilcoxon and mann whitney tests. The results of this study also showed that there was an influence on increasing the knowledge score and attitudes of students who were given socratic and didactic method counseling with p value = 0.000 &lt; 0.05. It is hoped that this research can be developed again with a combination of innovative learning methods that arouse more interest in learning so that the knowledge and attitudes of elementary school children about fruit and vegetable consumption can increase. Keywords: Socratic &amp; Didactic, Consumption, Knowledge, Attitude, Fruveble Card

Building an Innovative Learning Ecosystem: A Model for Secondary Schools in Hanoi, Vietnam

In an era characterized by rapid technological advancements and evolving educational needs, the development of innovative learning ecosystems is crucial for fostering creativity and critical thinking among students. This study investigates the components and characteristics of such an ecosystem tailored for secondary schools in Hanoi, Vietnam, a city recognized as a UNESCO Creative City. Grounded in theories of system, ecology, connection, and creativity, the proposed model emphasizes the integration of technology and creative teaching methods. The research identifies five primary elements of the innovative learning ecosystem: creative learning individuals; creative knowledge; smart technology; creative context; and cultures, innovative institutions, strategies. Each primary element includes secondary components with distinct characteristics, providing a comprehensive framework for schools to develop their specific ecosystems. Grounded in theories of systems, ecology, connection, and creativity, the research highlights the importance of technology and creative teaching methods in fostering a holistic and sustainable educational environment. The proposed model facilitates interactions at multiple levels, encompassing schools, families, and society, aiming to enhance academic outcomes, holistic development, and contributions to economic and cultural growth. The study identifies the necessity of a supportive policy framework, investment in teacher training, and active stakeholder engagement for the successful implementation and sustainability of the innovative learning ecosystem. This research contributes to the broader understanding of educational innovation, underscoring the significance of creativity in addressing global challenges and promoting economic development.

The Development of English Learning Video to Enhance Students’ Reading Comprehension Skill

Developing innovative learning media is needed at school nowadays, with learning media the learning goal will be easier to achieve. The aim of this research is to prove whether there is an enhancement in students’ scores in reading comprehension test after being treated by using learning video in learning process. This research is Research and Development using the model of ADDIE and data analysis of the products using likert scale. Data collection methods using questionnaires and test. Data processing was completed by using SPSS. The study participants were IPS students in the 10th grade from SMAN 2 Pekanbaru. The enhancement testing was done on students to calculate the rise in student scores after using learning video. The results of the validity of learning videos from media expert is 96% which categorized “very good”, the scores form material expert is 92,5% which also categorized “very good”. To ascertain the enhance in students' reading comprehension skill, the statistical analysis tests were carried out namely the mean and paired sample t-test. The significance value is 0.00, which means it fewer than 0.05, it might be ascertained that there is a significant influence among the results of the students' pre-test and post-test. The result shows that any enhancement of using learning video toward students’ reading comprehension skill.