Lala Septem Riza
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lala Septem Riza has a total of 193 co-authors. Here are the top co-authors by number of shared publications:
- Khyrina Airin Fariza Abu Samah
College of Computing, Informatics and Media, Universiti Teknologi MARA (UiTM) Melaka Branch, Melaka, Malaysia
16 shared publications - Judhistira Aria Utama
Universitas Pendidikan Indonesia
8 shared publications Khyrina Airin Fariza Abu Samah
Universiti Teknologi Mara Cawangan Melaka Kampus Jasin
6 shared publications- Raseeda Hamzah
Universiti Teknologi MARA
6 shared publications - Ida Kaniawati
Universitas Pendidikan Indonesia, Indonesia
4 shared publications Kuntjoro Adji Sidarto
Institut Teknologi Bandung
4 shared publications
Latest Publications
- Open Access
- 1 August 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (4) , 3660-3671
Multi-stage hybrid YOLO-driven and MobileNetV2-CNN variants for robust fish freshness classification
This study presents a multi-stage hybrid representation learning framework for robust fish freshness classification to address the critical challenge of reliable quality assessment in unpreserved food supply chains. The proposed pipeline operates in two stages: stage-1 employs you only look once (YOLO)v8n as feature-gated detector to validate inputs and eliminate non-fish images, while stage-2 leverages transfer-learned MobileNetV2 variants enhanced with convolutional neural network (CNN) layers, fine-tuning, adaptive learning rate schedulers, and expanded fully connected layers for hierarchical classification into three freshness classes i.e., highly fresh, fresh, and not fresh. The framework has been trained and evaluated on two curated datasets comprising 4,500 fish and non-fish images and 11,111 freshness-labeled including augmented dataset to increase diversity. The experimental results showed significant improvements. The best performance model transfer learning (TL)-MobileNetV2 + CNN + fine-tuning achieved 98.07% training accuracy and 67.72% validation accuracy on 80:20 split, and training accuracy of 97.57%, validation accuracy of 97.21% through 10-fold cross-validation. The comparative benchmarking confirmed that dual-stage design outperformed baseline MobileNetV2 and YOLOv5s models across precision, recall, and F1-score. The findings highlighted significant value of integrating detection-driven validation with transfer-learning classification, and propose new benchmark for intelligent freshness monitoring. For future work, this study aims to explore attention-based models, data integration, and species diversity.
- 1 August 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (4) , 3660-3671
Open AccessMulti-stage hybrid YOLO-driven and MobileNetV2-CNN variants for robust fish freshness classification
This study presents a multi-stage hybrid representation learning framework for robust fish freshness classification to address the critical challenge of reliable quality assessment in unpreserved food supply chains. The proposed pipeline operates in two stages: stage-1 employs you only look once (YOLO)v8n as feature-gated detector to validate inputs and eliminate non-fish images, while stage-2 leverages transfer-learned MobileNetV2 variants enhanced with convolutional neural network (CNN) layers, fine-tuning, adaptive learning rate schedulers, and expanded fully connected layers for hierarchical classification into three freshness classes i.e., highly fresh, fresh, and not fresh. The framework has been trained and evaluated on two curated datasets comprising 4,500 fish and non-fish images and 11,111 freshness-labeled including augmented dataset to increase diversity. The experimental results showed significant improvements. The best performance model transfer learning (TL)-MobileNetV2 + CNN + fine-tuning achieved 98.07% training accuracy and 67.72% validation accuracy on 80:20 split, and training accuracy of 97.57%, validation accuracy of 97.21% through 10-fold cross-validation. The comparative benchmarking confirmed that dual-stage design outperformed baseline MobileNetV2 and YOLOv5s models across precision, recall, and F1-score. The findings highlighted significant value of integrating detection-driven validation with transfer-learning classification, and propose new benchmark for intelligent freshness monitoring. For future work, this study aims to explore attention-based models, data integration, and species diversity.
- Open Access
- 14 July 2026
- Published by Elsevier in SSRN Electronic Journal
Spatiotemporal Causality Between Coronal Precursors and Sunspot Formation: A Self‐Supervised Deep Learning Analysis of Multispectral SDO Imagery — Implications for Resilient Infrastructure (SDG 9)
Solar activity, manifested through sunspot formation, drives space‐weather processes that can disrupt satellite systems, navigation, and global communications. Predicting sunspot emergence remains challenging because of complex magnetohydrodynamic dynamics and the scarcity of annotated solar datasets. Here we present a hybrid, self‐supervised deep‐learning framework to investigate spatiotemporal correlations between coronal precursors and subsequent photospheric sunspot formation using multispectral observations from the Solar Dynamics Observatory (AIA and HMI) spanning solar cycles 24 and 25 (2013–2024). We first employ a SimCLR‐based self‐supervised encoder to learn invariant physical representations, then transfer these features to a YOLOv5 detector for robust precursor localization. Kinematic validation with the Snodgrass differential rotation model confirms accurate solar tracking and strong adherence to Spörer’s Law (r = 0.996). Statistical analysis of 1,262 precursor events identifies Active Regions as the dominant coronal precursor (88.0%), substantially exceeding the contribution of coronal holes. Stationary Granger causality tests reveal a significant directional relationship between active‐region evolution and sunspot emergence with an optimal three‐day lag, consistent with the timescale of magnetic flux emergence toward the photosphere. These results demonstrate that self‐supervised deep learning can uncover physically meaningful spatiotemporal patterns in multispectral solar imagery and provide a quantitative early‐warning window that may improve space‐weather forecasting. By improving predictive lead time and reliability, this approach has the potential to strengthen the resilience and innovation of critical telecommunications, power‐grid, and satellite infrastructures, thereby contributing to SDG 9: Industry, Innovation and Infrastructure.
- 14 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSpatiotemporal Causality Between Coronal Precursors and Sunspot Formation: A Self‐Supervised Deep Learning Analysis of Multispectral SDO Imagery — Implications for Resilient Infrastructure (SDG 9)
Solar activity, manifested through sunspot formation, drives space‐weather processes that can disrupt satellite systems, navigation, and global communications. Predicting sunspot emergence remains challenging because of complex magnetohydrodynamic dynamics and the scarcity of annotated solar datasets. Here we present a hybrid, self‐supervised deep‐learning framework to investigate spatiotemporal correlations between coronal precursors and subsequent photospheric sunspot formation using multispectral observations from the Solar Dynamics Observatory (AIA and HMI) spanning solar cycles 24 and 25 (2013–2024). We first employ a SimCLR‐based self‐supervised encoder to learn invariant physical representations, then transfer these features to a YOLOv5 detector for robust precursor localization. Kinematic validation with the Snodgrass differential rotation model confirms accurate solar tracking and strong adherence to Spörer’s Law (r = 0.996). Statistical analysis of 1,262 precursor events identifies Active Regions as the dominant coronal precursor (88.0%), substantially exceeding the contribution of coronal holes. Stationary Granger causality tests reveal a significant directional relationship between active‐region evolution and sunspot emergence with an optimal three‐day lag, consistent with the timescale of magnetic flux emergence toward the photosphere. These results demonstrate that self‐supervised deep learning can uncover physically meaningful spatiotemporal patterns in multispectral solar imagery and provide a quantitative early‐warning window that may improve space‐weather forecasting. By improving predictive lead time and reliability, this approach has the potential to strengthen the resilience and innovation of critical telecommunications, power‐grid, and satellite infrastructures, thereby contributing to SDG 9: Industry, Innovation and Infrastructure.
- 22 May 2026
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 54 (7) , 3063-3078
Analyzing Spatial Urban Features Correlating with Night-Time Light Emission
- 22 May 2026
- Published by Springer Nature in Journal of the Indian Society of Remote Sensing
- Vol. 54 (7) , 3063-3078
Analyzing Spatial Urban Features Correlating with Night-Time Light Emission
- Open Access
- 28 April 2026
- Published by Omnia Publisher SL in Journal of Technology and Science Education
- Vol. 16 (2) , 470-485
Improving students cognitive learning outcomes in computer systems learning through unity-based virtual reality media
This study aims to examine the effect of using Unity-based Virtual Reality (VR) media integrated with the Problem-Based Learning (PBL) model on improving students' cognitive learning outcomes in computer systems learning. This study used a quantitative approach with a one-group pretest-posttest design. Assessment was conducted through structured tests before and after treatment to measure students' cognitive performance. The results of the normality test showed that the posttest data were not normally distributed, so a Wilcoxon Signed Ranks test was conducted. The test results showed a significant difference between the pretest and posttest (Z = -4.611; p < 0.001). In addition, the average N-Gain value of 0.59 (moderate category) indicated a positive increase in learning outcomes. The use of Unity-based VR media provided an immersive and contextual learning experience, thus helping students better understand abstract concepts and increasing motivation and learning engagement. This technology integration also encouraged the development of critical thinking skills and learning independence. Although some technical obstacles were encountered, such as discomfort when using the VR device, these obstacles could be overcome through collaborative learning strategies. These findings confirm that the combination of VR media and the PBL model is an effective approach to improving the quality of learning computer systems material.
- 28 April 2026
- Published by Omnia Publisher SL in Journal of Technology and Science Education
- Vol. 16 (2) , 470-485
Open AccessImproving students cognitive learning outcomes in computer systems learning through unity-based virtual reality media
This study aims to examine the effect of using Unity-based Virtual Reality (VR) media integrated with the Problem-Based Learning (PBL) model on improving students' cognitive learning outcomes in computer systems learning. This study used a quantitative approach with a one-group pretest-posttest design. Assessment was conducted through structured tests before and after treatment to measure students' cognitive performance. The results of the normality test showed that the posttest data were not normally distributed, so a Wilcoxon Signed Ranks test was conducted. The test results showed a significant difference between the pretest and posttest (Z = -4.611; p < 0.001). In addition, the average N-Gain value of 0.59 (moderate category) indicated a positive increase in learning outcomes. The use of Unity-based VR media provided an immersive and contextual learning experience, thus helping students better understand abstract concepts and increasing motivation and learning engagement. This technology integration also encouraged the development of critical thinking skills and learning independence. Although some technical obstacles were encountered, such as discomfort when using the VR device, these obstacles could be overcome through collaborative learning strategies. These findings confirm that the combination of VR media and the PBL model is an effective approach to improving the quality of learning computer systems material.
- Open Access
- 1 April 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (2) , 1337-1346
Comparative analysis of ensemble learning algorithms in enhanced confidence-based assessments
This paper provides a comparative analysis of ensemble learning (EL)algorithms to enhance the confidence-based assessment (CBA) in evaluating student performance. Traditional CBA often suffers from misclassification caused by overconfidence and underconfidence, limiting its accuracy and fairness. To address these challenges, an enhanced CBA-EL model integrating bagging and boosting ensemble algorithms is proposed. Five bagging algorithms, which are random forest (RF), decision tree (DT)support vector machine (SVM), K-nearest neighbors (KNN), Naïve Bayes(NB), and four boosting algorithms, which are adaptive boosting(AdaBoost), eXtreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost), were evaluated using a dataset of 276 responses collected from Pre- and Post-Quiz CBA in a discrete structures course. Algorithm performance was evaluated using accuracy, correlation, weighted mean precision (WMP), and weighted mean recall (WMR). RF achieved 73.19% accuracy, 0.725 correlation, 0.751 WMP, and 0.766 WMR, while CatBoost outperformed all with 86.23% accuracy and the highest correlation, WMP, and WMR values, with 0.842, 0.843, and 0.862, respectively. The findings indicate that integrating EL into CBA improves prediction accuracy and supports bias-aware student evaluation. This research advances reliable assessment practices and informs the development of adaptive learning systems.
- 1 April 2026
- Published by Institute of Advanced Engineering and Science in Bulletin of Electrical Engineering and Informatics
- Vol. 15 (2) , 1337-1346
Open AccessComparative analysis of ensemble learning algorithms in enhanced confidence-based assessments
This paper provides a comparative analysis of ensemble learning (EL)algorithms to enhance the confidence-based assessment (CBA) in evaluating student performance. Traditional CBA often suffers from misclassification caused by overconfidence and underconfidence, limiting its accuracy and fairness. To address these challenges, an enhanced CBA-EL model integrating bagging and boosting ensemble algorithms is proposed. Five bagging algorithms, which are random forest (RF), decision tree (DT)support vector machine (SVM), K-nearest neighbors (KNN), Naïve Bayes(NB), and four boosting algorithms, which are adaptive boosting(AdaBoost), eXtreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost), were evaluated using a dataset of 276 responses collected from Pre- and Post-Quiz CBA in a discrete structures course. Algorithm performance was evaluated using accuracy, correlation, weighted mean precision (WMP), and weighted mean recall (WMR). RF achieved 73.19% accuracy, 0.725 correlation, 0.751 WMP, and 0.766 WMR, while CatBoost outperformed all with 86.23% accuracy and the highest correlation, WMP, and WMR values, with 0.842, 0.843, and 0.862, respectively. The findings indicate that integrating EL into CBA improves prediction accuracy and supports bias-aware student evaluation. This research advances reliable assessment practices and informs the development of adaptive learning systems.
- Open Access
- 28 January 2026
- Published by Universitas Sains dan Teknologi Komputer in Jurnal Ilmiah Sistem Informasi
- Vol. 5 (2) , 58-67
Implementasi Power Bi (Business Intelligence) Dalam Pengolahan Dan Visualisasi Data Penelitian Pada Institusi Xyz
Pengelolaan data penelitian pada Institusi XYZ menghasilkan data dalam jumlah besar dan bersifat historis, sehingga diperlukan sistem yang mampu mengolah dan menyajikan data secara efektif dan terintegrasi. Penelitian ini bertujuan untuk mengimplementasikan Business Intelligence(BI) menggunakan Power BI dalam pengolahan dan visualisasi data penelitian guna mendukung transparansi informasi, proses monitoring, serta pengambilan keputusan yang berbasis data. Metode penelitian meliputi analisis kebutuhan, perancangan model data, proses Extraction, Transformation, and Loading (ETL), serta pengembangan dashboard interaktif menggunakan Power BI tanpa mengubah struktur basis data inti. Hasil penelitian menunjukkan bahwa penerapan Power BI mampu mengintegrasikan data penelitian, pendanaan, luaran, dan data peneliti ke dalam visualisasi yang informatif dan mudah dipahami. Penelitian ini menghasilkan empat dashboard utama, yaitu dashboard proposal penelitian, dashboard pendanaan penelitian, dashboard luaran penelitian, dan dashboard data peneliti, yang dapat membantu pihak institusi dalam memantau dan mengevaluasi kinerja penelitian secara lebih efektif.
- 28 January 2026
- Published by Universitas Sains dan Teknologi Komputer in Jurnal Ilmiah Sistem Informasi
- Vol. 5 (2) , 58-67
Open AccessImplementasi Power Bi (Business Intelligence) Dalam Pengolahan Dan Visualisasi Data Penelitian Pada Institusi Xyz
Pengelolaan data penelitian pada Institusi XYZ menghasilkan data dalam jumlah besar dan bersifat historis, sehingga diperlukan sistem yang mampu mengolah dan menyajikan data secara efektif dan terintegrasi. Penelitian ini bertujuan untuk mengimplementasikan Business Intelligence(BI) menggunakan Power BI dalam pengolahan dan visualisasi data penelitian guna mendukung transparansi informasi, proses monitoring, serta pengambilan keputusan yang berbasis data. Metode penelitian meliputi analisis kebutuhan, perancangan model data, proses Extraction, Transformation, and Loading (ETL), serta pengembangan dashboard interaktif menggunakan Power BI tanpa mengubah struktur basis data inti. Hasil penelitian menunjukkan bahwa penerapan Power BI mampu mengintegrasikan data penelitian, pendanaan, luaran, dan data peneliti ke dalam visualisasi yang informatif dan mudah dipahami. Penelitian ini menghasilkan empat dashboard utama, yaitu dashboard proposal penelitian, dashboard pendanaan penelitian, dashboard luaran penelitian, dan dashboard data peneliti, yang dapat membantu pihak institusi dalam memantau dan mengevaluasi kinerja penelitian secara lebih efektif.
- Open Access
- 16 December 2025
- Published by LKP Karya Prima in Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI)
- Vol. 4 (3) , 1895-1902
Pengembangan Chatbot Informasi Kesehatan Ibu dan Anak Jawa Barat Berbasis Hybrid RAG dan TextToSQL
Tingginya Angka Kematian Ibu dan prevalensi stunting di Jawa Barat menghambat pencapaian SDGs. Aksesibilitas informasi menjadi kendala utama karena data tersebar dalam format narasi dokumen Profil Kesehatan dan Buku KIA. Penelitian ini mengembangkan chatbot hibrida berbasis Retrieval-Augmented Generation (RAG) dan Text-to-SQL menggunakan Large Language Model Google Gemini. Sistem mengintegrasikan mekanisme chunking hierarkis, router cerdas, memori percakapan, dan visualisasi data otomatis untuk menyajikan informasi faktual serta statistik secara presisi. Evaluasi sistem menunjukkan kinerja tinggi: Text-to-SQL mencapai akurasi eksekusi 93,33% dan akurasi Router 85%. Pada modul RAG, pengujian 60 pertanyaan menghasilkan skor Faithfulness 0,990, Context Recall 0,883, dan Answer Relevancy 0,950. Sistem mencapai skor sempurna 1,000 untuk penanganan pertanyaan di luar konteks, membuktikan keamanan dari halusinasi. Pengujian pengguna (UAT) mencatat tingkat keberhasilan 80%, di mana fitur grafik dinilai signifikan dalam membantu pemahaman data. Penelitian menyimpulkan bahwa pendekatan hibrida efektif meningkatkan aksesibilitas wawasan kesehatan bagi masyarakat dan pemangku kebijakan, meskipun ekstraksi tabel kompleks memerlukan optimalisasi lanjut.
- 16 December 2025
- Published by LKP Karya Prima in Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI)
- Vol. 4 (3) , 1895-1902
Open AccessPengembangan Chatbot Informasi Kesehatan Ibu dan Anak Jawa Barat Berbasis Hybrid RAG dan TextToSQL
Tingginya Angka Kematian Ibu dan prevalensi stunting di Jawa Barat menghambat pencapaian SDGs. Aksesibilitas informasi menjadi kendala utama karena data tersebar dalam format narasi dokumen Profil Kesehatan dan Buku KIA. Penelitian ini mengembangkan chatbot hibrida berbasis Retrieval-Augmented Generation (RAG) dan Text-to-SQL menggunakan Large Language Model Google Gemini. Sistem mengintegrasikan mekanisme chunking hierarkis, router cerdas, memori percakapan, dan visualisasi data otomatis untuk menyajikan informasi faktual serta statistik secara presisi. Evaluasi sistem menunjukkan kinerja tinggi: Text-to-SQL mencapai akurasi eksekusi 93,33% dan akurasi Router 85%. Pada modul RAG, pengujian 60 pertanyaan menghasilkan skor Faithfulness 0,990, Context Recall 0,883, dan Answer Relevancy 0,950. Sistem mencapai skor sempurna 1,000 untuk penanganan pertanyaan di luar konteks, membuktikan keamanan dari halusinasi. Pengujian pengguna (UAT) mencatat tingkat keberhasilan 80%, di mana fitur grafik dinilai signifikan dalam membantu pemahaman data. Penelitian menyimpulkan bahwa pendekatan hibrida efektif meningkatkan aksesibilitas wawasan kesehatan bagi masyarakat dan pemangku kebijakan, meskipun ekstraksi tabel kompleks memerlukan optimalisasi lanjut.
- Open Access
- 3 December 2025
- Published by CV Media Inti Teknologi in JENTIK : Jurnal Pendidikan Teknologi Informasi dan Komunikasi
- Vol. 4 (2) , 101-110
School Feasibility Analysis and Grade Improvement Strategies Using the Random Forest Algorithm
Background of Study: Educational disparities across Indonesian provinces persist, particularly in infrastructure, teacher quality, and dropout rates, necessitating data-driven analysis for equitable improvements.Aims: This study investigates school feasibility and proposes strategies to enhance provincial education performance using the Random Forest algorithm.Methods: Aggregated provincial education data covering student numbers, dropout rates, teacher qualifications, and classroom conditions were transformed into derivative indicators. A binary classification (Feasible/Not Feasible) based on national dropout median was applied. The model was developed using R with six systematic steps, including training and evaluation of a Random Forest model (ntree = 100, mtry = 3) using accuracy, sensitivity, and specificity.Result: The model accurately classified school feasibility. Key predictors included teacher quality, student-teacher ratios, and classroom conditions. Several provinces were identified as “Not Feasible.”Conclusion: Machine learning proves effective for education policy support. The study offers targeted recommendations such as improving infrastructure, enhancing teacher training, and reducing dropouts to promote equitable education in Indonesia.
- 3 December 2025
- Published by CV Media Inti Teknologi in JENTIK : Jurnal Pendidikan Teknologi Informasi dan Komunikasi
- Vol. 4 (2) , 101-110
Open AccessSchool Feasibility Analysis and Grade Improvement Strategies Using the Random Forest Algorithm
Background of Study: Educational disparities across Indonesian provinces persist, particularly in infrastructure, teacher quality, and dropout rates, necessitating data-driven analysis for equitable improvements.Aims: This study investigates school feasibility and proposes strategies to enhance provincial education performance using the Random Forest algorithm.Methods: Aggregated provincial education data covering student numbers, dropout rates, teacher qualifications, and classroom conditions were transformed into derivative indicators. A binary classification (Feasible/Not Feasible) based on national dropout median was applied. The model was developed using R with six systematic steps, including training and evaluation of a Random Forest model (ntree = 100, mtry = 3) using accuracy, sensitivity, and specificity.Result: The model accurately classified school feasibility. Key predictors included teacher quality, student-teacher ratios, and classroom conditions. Several provinces were identified as “Not Feasible.”Conclusion: Machine learning proves effective for education policy support. The study offers targeted recommendations such as improving infrastructure, enhancing teacher training, and reducing dropouts to promote equitable education in Indonesia.
- Open Access
- 3 October 2025
- Published by Universitas PGRI Semarang in Jendela Olahraga
- Vol. 10 (4) , 404-420
Analisis Bibliometrik Implementasi Kecerdasan Buatan dalam Riset Kepelatihan Olahraga di Indonesia
Olahraga punya pengaruh besar dalam kehidupan masyarakat Indonesia. Namun, implementasi dari kecerdasan buatan dalam kepelatihan olahraga belum mendapat banyak perhatian oleh peneliti. Penelitian ditujukan untuk menganalisis perkembangan riset pemanfaatan kecerdasan buatan (Artificial Intelligence/AI) dalam bidang kepelatihan olahraga melalui pendekatan bibliometrik. Data diperoleh dari berbagai publikasi ilmiah dengan fokus pada jumlah publikasi, penulis dan institusi produktif, artikel yang paling banyak disitasi, serta struktur hubungan kata kunci dalam jaringan co-occurrence. Hasil analisis menunjukkan bahwa topik ini memiliki kecenderungan multidisipliner, dengan kontribusi terbesar berasal dari institusi seperti Universitas Negeri Surabaya, ITS, dan Universitas Negeri Jakarta. Kata kunci seperti sports, machine learning, artificial intelligence, dan robotics menjadi pusat dalam jaringan keterkaitan konsep. Artikel dengan tema review dan pemanfaatan wearable devices serta algoritma klasifikasi mendominasi jumlah sitasi. Temuan ini mengungkap bahwa penelitian masih cenderung berfokus pada aspek teknis dan fisik, dengan sedikit eksplorasi pada dimensi sosial, psikologis, dan etis dari penggunaan AI dalam olahraga. Penelitian ini memberikan gambaran mengenai gambaran keilmuan dan mengidentifikasi potensi arah pengembangan riset selanjutnya dalam mendukung kepelatihan olahraga modern.
- 3 October 2025
- Published by Universitas PGRI Semarang in Jendela Olahraga
- Vol. 10 (4) , 404-420
Open AccessAnalisis Bibliometrik Implementasi Kecerdasan Buatan dalam Riset Kepelatihan Olahraga di Indonesia
Olahraga punya pengaruh besar dalam kehidupan masyarakat Indonesia. Namun, implementasi dari kecerdasan buatan dalam kepelatihan olahraga belum mendapat banyak perhatian oleh peneliti. Penelitian ditujukan untuk menganalisis perkembangan riset pemanfaatan kecerdasan buatan (Artificial Intelligence/AI) dalam bidang kepelatihan olahraga melalui pendekatan bibliometrik. Data diperoleh dari berbagai publikasi ilmiah dengan fokus pada jumlah publikasi, penulis dan institusi produktif, artikel yang paling banyak disitasi, serta struktur hubungan kata kunci dalam jaringan co-occurrence. Hasil analisis menunjukkan bahwa topik ini memiliki kecenderungan multidisipliner, dengan kontribusi terbesar berasal dari institusi seperti Universitas Negeri Surabaya, ITS, dan Universitas Negeri Jakarta. Kata kunci seperti sports, machine learning, artificial intelligence, dan robotics menjadi pusat dalam jaringan keterkaitan konsep. Artikel dengan tema review dan pemanfaatan wearable devices serta algoritma klasifikasi mendominasi jumlah sitasi. Temuan ini mengungkap bahwa penelitian masih cenderung berfokus pada aspek teknis dan fisik, dengan sedikit eksplorasi pada dimensi sosial, psikologis, dan etis dari penggunaan AI dalam olahraga. Penelitian ini memberikan gambaran mengenai gambaran keilmuan dan mengidentifikasi potensi arah pengembangan riset selanjutnya dalam mendukung kepelatihan olahraga modern.
- Open Access
- 25 July 2025
- Published by Universitas Muhammadiyah Surabaya in MUST: Journal of Mathematics Education, Science and Technology
- Vol. 10 (1) , 1-12
Analysis of User Acceptance of Object-Oriented Programming Learning Multimedia Based on QR Code in Vocational Education Using the Technology Acceptance Model (TAM) Approach
The research objective is to analyze the Technology Acceptance Model (TAM) in measuring QR Code-based object-oriented programming learning multimedia in supporting vocational school students' learning on problem-based object-oriented programming (PBO) material. The TAM model variables used consist of Perceived Usefulness (PU), Perceived Ease of User (PEU), and User Acceptance of IT (UA-IT). The research respondents consisted of 35 students of SMK Negeri 1 Cimahi. The research stages consisted of familiarizing respondents with the use of multimedia, distributing TAM questionnaires, and testing the TAM model using SmartPLS software. The research results show that the average value of the user response questionnaire for QR Code-based PBO learning multimedia is 84.95% in the "Very Good" category. Based on the analysis of the relationship between TAM variables using PLS, it is known that the perceived ease of user variable has a positive influence on the acceptance of QR Code-based PBO learning multimedia, the perceived usage variable has a positive influence on the acceptance of QR Code-based PBO learning multimedia, and the variable perceived ease of use and perceived use. together they have a positive influence on the acceptance of QR Code-based PBO learning multimedia. This research is expected to provide an explanation regarding the use of TAM analysis in learning multimedia
- 25 July 2025
- Published by Universitas Muhammadiyah Surabaya in MUST: Journal of Mathematics Education, Science and Technology
- Vol. 10 (1) , 1-12
Open AccessAnalysis of User Acceptance of Object-Oriented Programming Learning Multimedia Based on QR Code in Vocational Education Using the Technology Acceptance Model (TAM) Approach
The research objective is to analyze the Technology Acceptance Model (TAM) in measuring QR Code-based object-oriented programming learning multimedia in supporting vocational school students' learning on problem-based object-oriented programming (PBO) material. The TAM model variables used consist of Perceived Usefulness (PU), Perceived Ease of User (PEU), and User Acceptance of IT (UA-IT). The research respondents consisted of 35 students of SMK Negeri 1 Cimahi. The research stages consisted of familiarizing respondents with the use of multimedia, distributing TAM questionnaires, and testing the TAM model using SmartPLS software. The research results show that the average value of the user response questionnaire for QR Code-based PBO learning multimedia is 84.95% in the "Very Good" category. Based on the analysis of the relationship between TAM variables using PLS, it is known that the perceived ease of user variable has a positive influence on the acceptance of QR Code-based PBO learning multimedia, the perceived usage variable has a positive influence on the acceptance of QR Code-based PBO learning multimedia, and the variable perceived ease of use and perceived use. together they have a positive influence on the acceptance of QR Code-based PBO learning multimedia. This research is expected to provide an explanation regarding the use of TAM analysis in learning multimedia