Publication Search

Amyotrophic Lateral Sclerosis (ALS) is a progressive neurodegenerative disorder that presents significant diagnostic challenges due to its heterogeneous clinical manifestations and symptom overlap with other neurological conditions. Early and accurate diagnosis is critical for initiating timely interventions and improving patient outcomes. Traditional diagnostic approaches rely heavily on clinical expertise and manual interpretation of neuroimaging data, such as structural MRI, Diffusion Tensor Imaging (DTI), and functional MRI (fMRI), which are inherently time-consuming and prone to interobserver variability. Recent advances in Artificial Intelligence (AI) and Deep Learning (DL) have demonstrated potential for automating neuroimaging analysis, yet existing models often suffer from limited generalizability across modalities and datasets. To address these limitations, we propose a Transformer-augmented deep learning ensemble framework for automated ALS diagnosis using multi-modal neuroimaging data. The proposed architecture integrates Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Vision Transformers (ViTs) to leverage the complementary strengths of spatial, temporal, and global contextual feature representations. An adaptive weighting-based fusion mechanism dynamically integrates modality-specific outputs, enhancing the robustness and reliability of the final diagnosis. Comprehensive preprocessing steps, including intensity normalization, motion correction, and modality-specific data augmentation, are employed to ensure cross-modality consistency. Evaluation using 5-fold cross-validation on a curated multi-modal ALS neuroimaging dataset demon-strates the superior performance of the proposed model, achieving a mean classification accuracy of 94.5% ± 0.7%, precision of 93.9% ± 0.8%, recall of 92.9% ± 0.9%, F1-score of 93.4% ± 0.7%, spec-ificity of 97.4% ± 0.6%, and AUC-ROC of 0.968 ± 0.004. These results significantly outperform baseline CNN models and highlight the potential of transformer-augmented ensembles in complex neurodiagnostic applications. This framework offers a promising tool for clinicians, supporting early and precise ALS detection and enabling more personalized and effective patient management strategies.

Conflict is an inevitable phenomenon in organizational dynamics, whether in the education sector, social sector, or wider society. Conflicts that are not managed properly can lead to disintegration, but if handled appropriately, they can become a means of learning and innovation. This literature review aims to identify sources of conflict, resolution strategies used, and their impact on organizational performance. The research questions asked are: (1) What are the main factors causing conflict in educational and social organizations? (2) What are the most effective conflict resolution strategies according to the context? This research method uses a literature review approach by searching articles through Google Scholar and Publish or Perish (PoP) using the keywords “sources AND levels of conflict.” A total of 20 articles were selected from the period 2021–2025, with a final result of five valid articles that were analyzed thematically. The review results show three main themes: (1) sources of conflict include differences in vision, interests, and resource distribution; (2) conflict resolution strategies vary, ranging from mediation, negotiation, to religious and cultural-based approaches; (3) the impact of conflict is ambivalent, it can decrease performance but also encourage positive change.The conclusion of this study emphasizes the importance of contextual conflict management and opens up opportunities for further research to develop more adaptive resolution models based on local values.

Chronic diseases such as chronic kidney disease (CKD), diabetes, and heart disease remain major causes of mortality worldwide, highlighting the need for accurate and interpretable diagnostic models. However, conventional machine learning methods often face challenges of limited generalization, feature redundancy, and class imbalance in medical datasets. This study proposes an integrated classification framework that unifies three complementary feature paradigms: classical tabular attributes, deep latent features extracted through an unsupervised Long Short-Term Memory (LSTM) encoder, and quantum-inspired features derived from a five-qubit circuit implemented in PennyLane. These heterogeneous features are fused using a feature-wise attention mechanism combined with an AdaBoost classifier to dynamically weight feature contributions and enhance decision boundaries. Experiments were conducted on three benchmark medical datasets—CKD, early-stage diabetes, and heart disease—under both balanced and imbalanced configurations using stratified five-fold cross-validation. All preprocessing and feature extraction steps were carefully isolated within each fold to ensure fair evaluation. The proposed hybrid model consistently outperformed conventional and ensemble baselines, achieving peak accuracies of 99.75% (CKD), 96.73% (diabetes), and 91.40% (heart disease) with corresponding ROC AUCs up to 1.00. Ablation analyses confirmed that attention-based fusion substantially improved both accuracy and recall, particularly under imbalanced conditions, while SMOTE contributed minimally once feature-level optimization was applied. Overall, the attention-guided AdaBoost framework provides a robust and interpretable approach for clinical risk prediction, demonstrating that integrating diverse quantum, deep, and classical representations can significantly enhance feature discriminability and model reliability in structured medical data.

JakLingko is a digital-based public transportation integration system developed to facilitate access to various transportation modes in Jakarta. Along with the increasing number of users, reviews on the JakLingko application reflect user experiences and perceptions. This study aims to analyze the sentiment of user reviews on the Google Play Store using the Naïve Bayes method. Data collection was conducted through web scraping, resulting in 3,260 reviews. The data were preprocessed, sentiment-labeled, and classified using Orange Data Mining. The research applied a quantitative experimental approach with a machine learning framework. The classification results showed that neutral sentiment dominated user reviews, followed by negative and positive sentiments. The Naïve Bayes model achieved 100% accuracy based on the confusion matrix and other evaluation metrics such as precision, recall, and F1-score. The findings highlight that Naïve Bayes can be a reliable approach for analyzing public opinion and serve as a reference for evaluating and improving digital service applications.

This research is motivated by the low cognitive abilities of students in science learning in elementary schools, which is largely caused by conventional teaching methods that do not actively involve students. To overcome this problem, the Team Assisted Individually (TAI) learning model is used, which combines a cooperative approach and individual learning to improve the understanding of science concepts more effectively. The purpose of this study is to determine the effect of the TAI model on the cognitive abilities of fifth-grade students of SD Islam Baitul Salam Ciledug on natural phenomena material. This study uses a quantitative approach with a quasi-experimental design and a pretest-posttest control group design technique. The sample consists of two classes, namely the experimental class that uses the TAI model and the control class that uses conventional learning methods. The results of the study show that there is a significant increase in the cognitive learning outcomes of students who participate in learning with the TAI model compared to the conventional method. Therefore, this study is expected to provide an alternative effective learning model for teachers, as well as improve the quality of the process and student learning outcomes, especially in science learning.  

This study aims to develop an interactive learning medium on the Gimkit platform with the topic of modal verbs at the A1 level. The research method applies a qualitative approach using the model of Richey & Klein (2017), which consists of three stages: (1) planning, (2) development, and (3) evaluation. The data source of this study is the book Grammatik aktiv A1–B1 by Friederike Jin and Ute Voß (2014), Chapter 5, pages 16–18, focusing on the topics: (1) conjugation of modal verbs in the present tense, (2) conjugation of modal verbs in the past tense, and (3) comparison of modal verbs in the present and past tenses. The learning medium was validated by a material expert with a score of 95 and by a media expert with a score of 90; both results fall into the category “very good.” Based on these results, the Gimkit learning medium on the topic of modal verbs is considered suitable and effective for teaching German at the A1 level in senior high schools, both for independent learning and for classroom instruction.

This study aims to analyze the role of Kajian Kalam at Gedung Dakwah Kalasan, Sleman, as a community-based Qur’anic literacy practice. The study is motivated by the phenomenon that, although many people in Indonesia are proficient in reading the Qur’an, their understanding of its meaning remains limited. Kajian Kalam addresses this gap through a contextual and participatory tafsir approach, actively involving participants in discussion and reflection. This research employs a qualitative case study method, using direct observation, interviews with the study leader, and documentation of the study activities as data sources. The findings indicate that Kajian Kalam enhances Qur’anic literacy on three levels: textual literacy, meaning literacy, and practical literacy. The study provides participants with opportunities to understand Qur’anic verses contextually and relate them to daily life, while also building an inclusive and egalitarian learning community. The contributions of Kajian Kalam include broadening access to Qur’anic interpretation for participants with diverse backgrounds, implementing participatory learning models, and developing grounded and practical Qur’anic literacy. This research demonstrates that community-based Qur’anic studies can be an effective means to improve understanding and practice of the Qur’an, filling a gap in previous studies that focused primarily on formal institutions. The findings are expected to inform the development of more participatory and practical Qur’anic study models in society.

The post-truth phenomenon has posed significant challenges to education, particularly Islamic education, in shaping a young generation that is both critical and religious. Generation Alpha, born and raised in a digital ecosystem, faces an overwhelming flow of information, disinformation, and opinion manipulation that often blurs the line between fact and falsehood. This study aims to analyze how Islamic education can respond to the post-truth crisis by fostering a critical-religious character among Generation Alpha. This research employs a qualitative library-based method, utilizing content analysis that integrates classical Islamic sources on epistemology such as al-haqq and tabayyun with contemporary findings on digital literacy and the psychosocial development of Generation Alpha. The findings indicate that Islamic education should focus on strengthening Islamic digital literacy, promoting dialogical learning that cultivates critical thinking, and integrating strong spiritual values. Curriculum transformation, the role of teachers as epistemic role models, and the support of families and communities are essential in creating an educational ecosystem capable of countering post-truth influences. Thus, Islamic education serves as both a moral and intellectual safeguard, protecting Generation Alpha from the crisis of truth while preparing them to be critical, adaptive, and religious Muslims in the digital age.

This study aims to determine the improvement and category of improvement in students' understanding of the concept of buffer solutions by applying the Search, Solve, Create, and Share learning model. The form of this study is an experimental research with a Randomized Control Group Pretest-Posttest design. The population of this study is all students of class XI MIPA SMAN 7 Pekanbaru for the 2024/2025 school year. The research sample was students in class XI MIPA 1 as an experimental class and students in class XI MIPA 2 as a control class. The experimental class was given the treatment of the application of the SSCS learning model, while the control class was given learning without the SSCS model. The results of the data hypothesis test analysis technique used the right-hand t-test. Based on the analysis of research data, it was obtained that the tcount of 2.07 was greater than the ttable of 1.67 (dk = 67, α = 0.05) with the category of increasing students' understanding of concepts of 0.74 in the high category. The results of the study show that the Search, Solve, Create, and Share (SSCS) learning model can improve students' understanding of the concept of buffer solutions in class XI MIPA SMAN 7 Pekanbaru.

This study aims to determine the differences in problem-solving and critical thinking skills between students taught using the Reciprocal Teaching and Problem-Based Learning models in class X of SMK Ki Hajar Dewantara Kotapinang for the 2021-2022 academic year. This is a quantitative study using a quasi-experimental design. The population consists of all class X students at SMK Ki Hajar Dewantara Kotapinang in the 2021-2022 academic year, totaling 111 students. The sample used was class X AKUNTANSI 1 and X AKUNTANSI 2, each consisting of 20 students, chosen as experimental classes using Cluster Random Sampling. Data were collected from pre-tests and post-tests with problem-solving and critical thinking skill test items, then analyzed descriptively and followed by Two-Way ANOVA. The findings indicate: 1) There is no difference in problem-solving ability between students taught using the Reciprocal Teaching model and the Problem-Based Learning model in class X of SMK Ki Hajar Dewantara Kotapinang, with F_observed = 0.320 < F_table(α= 0.05) = 3.978; 2) There is a difference in critical thinking skills between students taught using the Reciprocal Teaching model and the Problem-Based Learning model in class X of SMK Ki Hajar Dewantara Kotapinang, with F_observed = 5.128 > F_table(α= 0.05) = 3.978; 3) There is a difference in both problem-solving and critical thinking skills between students taught using the Reciprocal Teaching model and the Problem-Based Learning model in class X of SMK Ki Hajar Dewantara Kotapinang, with F_observed = 0.026 > F_table(α= 0.05) = 3.936; 4) There is no interaction between the Reciprocal Teaching and Problem-Based Learning models in class X of SMK Ki Hajar Dewantara Kotapinang, with F_observed = 0.459 < F_table(α= 0.05) = 3.936.

This study aims to describe the management of the Certified Independent Study Program (SIB) in the fields of Data Analytics and Software Engineering organized by PT Revolusi Citra Edukasi. Using a qualitative approach, data were collected through participatory observation, in-depth interviews, daily activity logbooks, and documentation. Data analysis followed an interactive model consisting of data collection, data reduction, data presentation, and verification. The results reveal that the management of the SIB program is implemented through four key aspects: planning, organizing, actuating, and controlling. The planning stage includes the development of an adaptive modular curriculum, the formulation of short-term and long-term objectives, and the active involvement of industry practitioners. This stage reflects the principles of transparency, accountability, and responsibility. The organizing aspect is realized through a well-defined yet flexible organizational structure, supported by fair task distribution and clear role assignments, which embody independence, fairness, and transparency. In the actuating stage, program implementation is carried out using project-based learning methods, mentoring sessions, and active coaching. These activities are designed to ensure equitable access to guidance, transparent communication, and shared responsibility between instructors and participants. The controlling aspect involves regular digital evaluations, weekly feedback mechanisms, and collaborative assessments with industry partners, ensuring continuous improvement and adherence to program goals. Overall, the management of the SIB program at PT Revolusi Citra Edukasi demonstrates a high level of professionalism and alignment with the principles of Good Corporate Governance (GCG). The integration of adaptive planning, transparent organization, participatory implementation, and accountable evaluation processes ensures that the program not only meets its educational objectives but also fosters industry readiness among participants. These findings highlight the importance of structured yet flexible management practices in enhancing the effectiveness of independent study programs within the context of higher education and industry collaboration.

This study investigates the implementation of the Problem-Based Learning (PBL) model integrated with animated video media to enhance student motivation, creativity, and learning outcomes in economics at MA Salafiyah. Employing a classroom action research approach with a pretest-posttest design, the research involved 35 grade XI students. Data were collected through observation sheets, motivation and creativity questionnaires, and learning outcome tests. The Shapiro-Wilk test was used to assess data normality, while the Wilcoxon Signed Rank Test evaluated the significance of differences between pretest and posttest scores. The findings reveal that the application of PBL with animated video media significantly improves student motivation, creativity, and learning outcomes. Students demonstrated increased engagement, generated more creative ideas, and showed deeper understanding of economic concepts. Motivation was reflected in higher posttest scores and active participation, while creativity was evident in the ability to propose innovative solutions and think critically. Learning outcomes improved substantially, with average scores rising from 46.142 (pretest) to 83.571 (posttest). The integration of animated video media in PBL created a dynamic and interactive learning environment that facilitated comprehension, stimulated interest, and encouraged practical application of knowledge. This study concludes that PBL supported by animated video media is an effective pedagogical strategy for improving educational quality in economics learning.

Community Service Learning (CSL) is a tangible manifestation of the implementation of the Tri Dharma of Higher Education, which aims to apply knowledge within the community, particularly in addressing economic challenges in rural areas. This study focuses on the effectiveness of the UIN SU student KKN programme in Sugihen Village, Juhar Subdistrict, Karo Regency, which carries the theme of economic empowerment of the community. The research method used a qualitative approach with participatory observation and practical demonstration techniques, directly involving the Sugihen Village community. The results showed that this programme significantly improved the participants’ knowledge and technical skills, transforming their roles from passive consumers to active producers. This training not only helped reduce household expenses but also opened up new business opportunities that had the potential to increase family income. Therefore, this KKN programme can serve as an effective strategic model for creating stable and independent community-based economic growth.

This study aims to enhance the understanding of fifth-grade students at SDN 060786 in the subject of Natural and Social Sciences (IPAS), specifically the topic "Economic Conditions in My Region," through the use of diorama media. The research uses the Classroom Action Research (CAR) method with the spiral model by Kemmis and McTaggart, which includes the stages of planning, action, observation, and reflection. This study was conducted in two cycles, with data collected through learning outcome tests, observations of the learning process, and interviews with the teacher to gather feedback on the use of diorama media. The results of the study show a significant improvement in both conceptual understanding and learning outcomes of the students after the implementation of diorama media. The students also demonstrated increased engagement in the learning process, becoming more active and motivated to participate in the activities. Moreover, the use of diorama media helped students understand abstract concepts more easily than through text or verbal explanations alone. These findings emphasize that the teacher’s creativity in selecting and utilizing appropriate learning media plays a crucial role in creating an interactive, meaningful, and enjoyable learning environment, ultimately improving the quality of student learning outcomes.

The rapid development of information technology has created significant opportunities for secondary schools to improve the quality of learning through the use of digital-based applications. This study aims to design and develop a web-based tutoring application for students of Junior High School (SMP) Negeri 1 Tana Righu by applying Object Oriented Technology (OOT) as the software development approach. OOT was chosen for its ability to simplify the system design process through structured modeling using the concepts of classes, objects, attributes, and relationships between objects. The developed application provides various features, including the presentation of learning materials, interactive practice questions, learning outcome evaluations, and student progress reports accessible in real time by both teachers and students. The research method consisted of needs analysis, system design using UML diagrams, implementation, and application testing. The testing results indicate that the tutoring application is effective in improving the learning process, assisting teachers in monitoring and evaluating student progress, and providing students with a more engaging and interactive learning experience. Therefore, this application is expected to serve as an innovative solution to support tutoring activities in secondary schools and contribute positively to enhancing the quality of education in the digital era.

This study aims to develop an interactive mobile application-based learning media to introduce Devanagari Sanskrit script to Indonesian teenagers. The background of this research is the lack of communicative, contextual, and engaging learning media for the digital generation in learning traditional scripts. The development method uses the ADDIE model modified with a visual communication design approach and integration of local Balinese cultural values. The results show that this media successfully combines strong visual elements, interactive voice narratives, and Balinese cultural iconography in one mobile-friendly platform. Validation from design and cultural experts shows a very high level of feasibility, supported by positive responses from student users at the Dvipantara Samskrtam Foundation. This research makes a real contribution to the preservation of traditional scripts through a digital educational approach that is adaptive to the learning needs of today's teenagers. In addition, this research also opens opportunities for the development of similar learning media for other traditional scripts, thereby increasing awareness and understanding of Indonesia's rich culture among the younger generation. By integrating technology in learning, it is hoped that the preservation of Indonesian culture can go hand in hand with the progress of the times.

Tomato crop yields face significant threats from plant diseases, with existing deep learning solutions often computationally prohibitive for resource-constrained agricultural settings; to address this gap, we propose Efficient Disease Attention Network (EDANet), a novel lightweight architecture combining depthwise separable convolutions with hybrid attention mechanisms for efficient Tomato disease recognition. Our approach integrates channel and spatial attention within hierarchical blocks to prioritize symptomatic regions while utilizing depthwise decomposition to reduce parameters to only 104,043 (multiple times smaller than MobileNet and EfficientNet). Evaluated on ten tomato disease classes from PlantVillage, EDANet achieves 97.32% accuracy and exceptional (~1.00) micro-AUC, with perfect recognition of Mosaic virus (100% F1-score) and robust performance on challenging cases like Early blight (93.2% F1) and Target Spot (93.6% F1). The architecture processes 128×128 RGB images in ~23ms on standard CPUs, enabling real-time field diagnostics without GPU dependencies. This work bridges laboratory AI and practical farm deployment by optimizing the accuracy-efficiency tradeoff, providing farmers with an accessible tool for early disease intervention in resource-limited environments.

This study focuses on how the use of Student Worksheets (LKPD) can support the Islamic Religious Education (PAI) learning process at MIS Al-Hidayah. Using a qualitative approach, researchers explored the experiences of teachers and students through interviews, observations, and documentation. The results indicate that LKPD equipped with visual media can create a more engaging learning environment, motivate students, and facilitate their understanding of the material. Teachers design LKPD with pictures and sequential steps, enabling students to be more active and able to learn independently or in groups. Despite obstacles, such as limited time for development and incomplete school facilities, teacher creativity and collaboration with colleagues proved key to success. These findings confirm that LKPD can be an effective learning tool, not only for improving cognitive understanding but also for instilling Islamic values ​​in students. This study also has implications for the development of PAI learning strategies in madrasah-based elementary schools. Thus, the innovative use of LKPD can become a sustainable learning model to improve the quality of Islamic education in the future.

Islamic Religious Education (PAI) plays a crucial role in fostering good morals in students, enabling them to develop Islamic character and face the challenges of the times with strong spiritual values. However, the implementation of PAI teaching in the field often still prioritizes traditional lecture methods, which lead to less student participation, boredom, and less than satisfactory learning outcomes. This small study aims to explore the PAI learning models and strategies implemented by teachers at the Al-Hidayah Foundation, the challenges they face, and their impact on students. This study used a qualitative approach with a case study method through in-depth interviews with PAI teachers. The results revealed that teachers have begun to integrate lecture methods with more innovative learning strategies such as contextual, cooperative, and technology-based, although their implementation has not always been consistent. The main challenges faced include limited infrastructure, a lack of professional training for teachers, and low learning motivation among some students. The visible impact is increased student engagement in the learning process when innovative strategies are implemented, although their effectiveness still needs to be strengthened with support from the institution and parents. Therefore, the Islamic Religious Education teachers at the Al-Hidayah Foundation not only function as teachers, but also as motivators and facilitators in the learning process to ensure that the goals of Islamic education can be achieved properly.

The aim of this research is to determine the influence of the Games Based Learning Model on the Learning Activeness of Class The research method used is a quantitative method with a descriptive inferential type. The population was 182 students of Class Data was collected using a closed questionnaire with 14 items for variable Y and 18 items for variable 2025 is shown through: 1) Test analysis requirements: a) positive relationship test obtained rxy = 0,308 > rtabel(α=0,05; IK=95%; n=49) = 0,281.  b) a significant relationship test is obtained from the value thitung = 2,222 > ttabel = 2,021. 2) influence test: a) regression equation test, obtained the regression equation Ŷ  = 42,221  (α) + 0,365 (X).  b) regression coefficient of determination test (r2) = 9,5%. 3hypothesis testing using Fhitung  > Ftabel=(α=0,05,dk pembilang n-1=48, dk penyebut=n-2=49-2=47) yaitu 4,938 > 1,620.Thus H0 is stating there is no influence is rejected and Ha which states there is an influence is accepted.