Abstract:This study aims to analyze the implementation of deep learning in improving the descriptive text writing skills of grade VI students in Group 1, Bangkala District, Jeneponto Regency. Deep learning is seen as relevant to…
overcome students' low writing ability which is characterized by a lack of detail, weak text structure, and lack of ability to choose diction. This study uses a qualitative approach with the type of Class Action Research (PTK) of the Kemmis and McTaggart model which is carried out in one cycle consisting of planning, action, observation, and reflection stages. Data was collected through observation, interviews, documentation, as well as pretest and posttest. The results of the study showed a significant increase in description writing skills after the application of Deep Learning. The average pretest score of 58.40 with 16% completeness increased to 83.20 in the posttest with 88% completeness. An increase in N-gain of 0.62 indicates a moderate–high increase category. In addition to improved grades, students showed positive changes in learning behavior, characterized by increased participation, analytical skills, and quality of reflection on their writing. This study concludes that deep learning is effective in improving descriptive text writing skills while fostering students' critical thinking and metacognitive skills. This model is feasible to be applied as an alternative to Indonesian learning strategies in elementary schools.
Abstract:This study explores how incorporating artificial intelligence improves institutional resilience and overcomes the rigidity of conventional, data-based methods to alter financial risk management. To find patterns in AI applications,…
applications, resilience theory, and integration pathways, a qualitative systematic literature review was carried out utilizing theme synthesis in accordance with PRISMA peer-reviewed protocols. Findings show that AI techniques, machine learning for tail-risk detection, deep learning for high-frequency forecasting, and explainable AI for transparent decisions, yield up to 28% reductions in forecasting errors and halve recovery times during crises. The hybrid CNN Transformer architectures and transformer-based NLP models significantly enhance predictive accuracy and forward-looking insights. The study suggests financial institutions adopt integrated AI frameworks, invest in data quality and human–AI collaboration, and implement principle-based governance to balance innovation with fairness and stability. Limitations include reliance on published literature and limited representation of emerging AI models, warranting future longitudinal and context-specific empirical research.
Abstract:This study aims to describe the implementation of the deep learning approach in Indonesian language learning and its impact on the development of critical and reflective thinking skills of high school students in several…
al schools in Makassar City. The deep learning approach is seen as an innovative learning strategy that emphasizes high-level thinking processes, active engagement, and deep reflection on teaching materials. The research method used is descriptive qualitative with data collection techniques through observation of learning activities, interviews with teachers and students, and analysis of learning outcome documents. The results of the study show that the application of the deep learning approach contributes positively to improving the quality of learning interactions and students' metacognitive awareness. Students show high ability to identify problems, analyze arguments, draw logical conclusions, and reflect on the learning process. Deep learning-based learning also strengthens collaborative interaction patterns in the classroom and encourages students' intellectual independence. Thus, the deep learning approach is relevant to be applied in Indonesian language learning in high school to foster critical, reflective, and literacy skills in accordance with the demands of 21st century education.
Abstract:This study examines the ethical and pedagogical implications of deep learning integration in fourth-grade classrooms at SDN 100801 Pasar Sempurna, Indonesia. Through classroom observations, semi-structured interviews with…
h teachers, and document analysis, the research found that deep learning applications significantly improved student engagement and individualized learning outcomes. However, ethical concerns emerged regarding data privacy, unequal access to digital tools, and limited teacher preparedness. Teachers expressed uncertainty in balancing technological autonomy with moral and pedagogical control. The study concludes that while deep learning supports more adaptive and inclusive learning environments, its ethical implementation remains constrained by insufficient institutional policies and digital literacy. Strengthening teacher competence and establishing transparent ethical frameworks are crucial for ensuring responsible AI integration in primary education. These findings provide practical insights into balancing innovation and ethics in early educational contexts.
Abstract:The rapid advancement of artificial intelligence (AI) offers new opportunities to enhance teaching and learning in early education. This study applies deep learning approaches to support early cognitive development among…
primary students in an Indonesian Islamic school. A hybrid Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) model was designed to analyse students’ cognitive patterns, attention, and engagement. Using a mixed-methods design, the research involved 60 students aged 8–10 at MIS Terpadu Alhijrah Bintuju. The model processed multimodal classroom data to generate adaptive feedback and personalized learning pathways. Results showed significant improvements in attention (+18%), memory recall (+22%), and problem-solving (+25%) after eight weeks of AI-assisted learning. Qualitative findings revealed higher motivation, engagement, and self-regulation. The study demonstrates that culturally aligned AI systems can effectively enhance early cognitive development and promote learner autonomy in Islamic primary education.
Abstract:The training program “Developing a Growth Mindset Among Elementary School Teachers: A Training Guide for Enhancing Deep Learning” was organized by the Department of Education of Mandailing Natal Regency to strengthen teachers’…
teachers’ pedagogical competence and foster a student-centered learning culture. This initiative was motivated by the 2022 PISA results, which revealed that more than 99% of Indonesian students could only solve problems at lower levels (Lower Order Thinking Skills), while less than 1% reached higher levels (Higher Order Thinking Skills). One of the underlying causes is the prevalence of a fixed mindset among teachers—the belief that intelligence is innate and difficult to change. This training aimed to cultivate a growth mindset based on Carol S. Dweck’s (2006) theory, which emphasizes that abilities can be developed through effort and learning strategies. The method employed was a reflective andragogical workshop involving material presentations, microteaching simulations, and collaborative reflections. The results indicated a significant improvement in teachers’ understanding of the growth mindset concept and its implementation in deep learning. Teachers began providing process praise, applying The Power of Yet strategy, and creating emotionally safe and collaborative classroom environments. Furthermore, the establishment of the Growth-Oriented Teacher Community of Mandailing Natal (KGB-Madina) emerged as a sustainable platform for sharing best teaching practices and fostering continuous professional growth.
Abstract:Learning in the 21st century requires teachers to act not only as conveyors of information but also as designers of creative learning that is relevant to students' needs. The application of a deep learning approach is believed…
lieved to improve critical thinking skills, in-depth conceptual understanding, and collaborative skills, which are crucial in facing the challenges of the independent curriculum. In this context, the role of teachers in the West Angkola District Teacher Working Group (KKG) is crucial to examine, particularly in designing creative learning oriented toward developing higher-order thinking skills. This study aims to analyzea the role of teachers in designing creative learning based on deep learning and explore the strategies used to integrate deep learning principles into learning planning and practice. The method used is descriptive qualitative, with data collection through observation, in-depth interviews, and documentation studies involving teachers who are members of the West Angkola District KKG.The results indicate that teachers play a strategic role in designing creative learning through the use of interactive media, developing problem-based activities, and implementing collaborative learning models. Teachers also strive to foster students' critical thinking skills through structured discussions, explorations, and reflections. The learning design implemented has been proven to not only increase student motivation but also strengthen teachers' professional competence in managing more meaningful learning. Thus, it can be concluded that the role of teachers in designing creative learning using a deep learning approach significantly contributes to the quality of the learning process in elementary schools. The results of this study are expected to serve as a reference in developing creative learning practices based on deep learning in the Teachers' Working Group (KKG) and other teacher professional development forums.
Abstract:Penelitian ini bertujuan untuk menganalisis pengaruh model Problem Based Learning (PBL) berbasis Wayground dengan pendekatan deep learning terhadap keterlibatan murid dalam pembelajaran Biologi di SMA Negeri 11 Kota Jambi.…
i. Keterlibatan murid yang rendah menjadi permasalahan utama dalam proses pembelajaran, sehingga diperlukan inovasi model pembelajaran yang dapat meningkatkan keterlibatan secara komprehensif mencakup dimensi behavioral, emotional, cognitive, dan agentic engagement. Penelitian menggunakan metode Pre-Experimental dengan desain One Group Pretest-Posttest. Sampel penelitian adalah 36 murid kelas XI F1 yang dipilih secara random sampling. Instrumen yang digunakan berupa angket keterlibatan murid dan lembar observasi. Data dianalisis menggunakan uji Sign Test dan uji Effect Size. Hasil penelitian menunjukkan adanya peningkatan keterlibatan murid pada keempat dimensi setelah perlakuan. Uji Sign Test menghasilkan nilai signifikansi 0,012 (<0,05), sehingga H₀ ditolak. Effect Size diperoleh sebesar 0,417 yang termasuk kategori sedang. Hasil observasi juga mendukung temuan angket dengan skor rata-rata 3,00 (kategori Baik) pada semua dimensi. Disimpulkan bahwa model PBL berbasis Wayground dengan pendekatan deep learning berpengaruh positif dalam kategori sedang terhadap peningkatan keterlibatan murid dalam pembelajaran Biologi. Penelitian ini diharapkan dapat menjadi referensi bagi guru dalam mengembangkan pembelajaran yang lebih aktif, interaktif, dan bermakna.
Abstract:Abstract: Existing IoT anomaly detection studies have achieved high classification performance, but most focus on accuracy and F1-score without explicitly controlling the false positive rate (FPR). In addition, many approaches…
oaches rely on a single detection perspective, limiting their operational reliability. To address this gap, this study proposes a hybrid anomaly detection framework integrating Long Short-Term Memory (LSTM), Shannon entropy, and autoencoder reconstruction error. Shannon entropy is incorporated as an additional feature, while LSTM and the autoencoder capture temporal and reconstruction characteristics. The resulting hybrid representation is processed by a constraint-based threshold selection mechanism that enforces FPR . Experiments on the TON-IoT and Edge-IIoTset datasets achieved average F1-scores of 0.9250 and 0.9934, while maintaining average FPR values of 0.0091 and 0.0714, respectively. Analysis of entropy distributions showed consistent differences between normal and anomalous traffic across both datasets, indicating that Shannon entropy provides discriminative information for anomaly detection. These results demonstrate strong detection performance with controlled false alarms, while ablation studies confirm the significant contribution of Shannon entropy to overall model performance.
Keywords: false positive rate; hybrid deep learning; Internet of Things; network anomaly detection; Shannon entropy
Abstrak: Penelitian deteksi anomali Internet of Things (IoT) telah menunjukkan performa klasifikasi yang tinggi, namun sebagian besar masih berfokus pada accuracy dan F1-score tanpa mengendalikan false positive rate (FPR) secara eksplisit. Selain itu, banyak pendekatan hanya memanfaatkan satu perspektif deteksi sehingga reliabilitas operasionalnya masih terbatas. Untuk mengatasi kesenjangan tersebut, penelitian ini mengusulkan kerangka deteksi anomali hybrid yang mengintegrasikan Long Short-Term Memory (LSTM), Shannon entropy, dan autoencoder reconstruction error. Shannon entropy digunakan sebagai fitur tambahan, sedangkan LSTM dan autoencoder menangkap karakteristik temporal dan deviasi rekonstruksi. Representasi hybrid yang dihasilkan kemudian diproses melalui mekanisme constraint-based threshold selection dengan batas FPR . Hasil pengujian pada dataset TON-IoT dan Edge-IIoTset menghasilkan F1-score rata-rata sebesar 0,9250 dan 0,9934, dengan FPR rata-rata sebesar 0,0091 dan 0,0714. Perbedaan nilai entropy yang konsisten antara trafik normal dan anomali pada kedua dataset menunjukkan bahwa Shannon entropy menyediakan informasi diskriminatif untuk deteksi anomali. Hasil tersebut menunjukkan performa deteksi yang kuat dengan false alarm yang terkendali, sementara studi ablasi mengonfirmasi kontribusi signifikan Shannon entropy terhadap performa model.
Kata kunci: deteksi anomali jaringan; false positive rate; hybrid deep learning; Internet of Things; Shannon entropy
Abstract:Abstract: Accurate bone age estimation is essential for monitoring pediatric growth, diagnosing endocrine disorders, and supporting clinical decision-making. Although deep learning has improved prediction accuracy, limited…
ed studies have systematically examined how increasing model depth affects performance and reliability. This study evaluates the effectiveness of progressively deeper convolutional neural networks, specifically EfficientNet variants B0 to B5, for bone age estimation from hand radiographs. Experiments were conducted using 12,611 hand X-ray images from the RSNA Pediatric Bone Age Challenge dataset on Kaggle. To ensure fair comparison, all models were trained using a unified and consistent training pipeline. Model performance was evaluated using Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Concordance Correlation Coefficient (CCC), and Pearson correlation coefficient. The results show a consistent improvement in prediction accuracy as model depth increases. Among the evaluated models, EfficientNet-B5 achieved the best performance, with an MAE of 21.5 months, MAPE of 6.23%, CCC of 0.9148, and Pearson’s r of 0.9203. These findings confirm that model scaling plays a critical role in enhancing prediction robustness and clinical reliability. Future work should emphasize external validation across diverse populations and incorporate interpretability techniques, such as Grad-CAM, to improve clinical transparency and trust.
Keywords: bone age prediction; deep learning; model evaluation; clinical validation
Abstrak: Estimasi usia tulang yang akurat sangat penting untuk memantau pertumbuhan anak, mendiagnosis gangguan endokrin, dan mendukung pengambilan keputusan klinis. Meskipun pembelajaran mendalam telah meningkatkan akurasi prediksi, studi yang secara sistematis meneliti bagaimana peningkatan kedalaman model memengaruhi kinerja dan keandalan masih terbatas. Studi ini mengevaluasi efektivitas jaringan saraf konvolusional yang semakin dalam, khususnya varian EfficientNet B0 hingga B5, untuk estimasi usia tulang dari radiografi tangan. Eksperimen dilakukan menggunakan 12.611 gambar sinar-X tangan dari dataset RSNA Pediatric Bone Age Challenge di Kaggle. Untuk memastikan perbandingan yang adil, semua model dilatih menggunakan alur pelatihan yang terpadu dan konsisten. Kinerja model dievaluasi menggunakan Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Concordance Correlation Coefficient (CCC), dan koefisien korelasi Pearson. Hasil menunjukkan peningkatan yang konsisten dalam akurasi prediksi seiring dengan peningkatan kedalaman model. Di antara model yang dievaluasi, EfficientNet-B5 mencapai kinerja terbaik, dengan MAE sebesar 21,5 bulan, MAPE sebesar 6,23%, CCC sebesar 0,9148, dan Pearson’s r sebesar 0,9203. Temuan ini menegaskan bahwa penskalaan model memainkan peran penting dalam meningkatkan optimasi prediksi dan keandalan klinis. Penelitian selanjutnya dapat menekankan validasi eksternal di berbagai populasi dan menggabungkan teknik interpretasi, seperti Grad-CAM, untuk meningkatkan transparansi dan kepercayaan klinis.
Kata kunci: prediksi usia tulang; deep learning; evaluasi model; validasi klinis