IRPI Publisher Journals (Institute of Research and Publication Indonesia)
Not a member yet
1012 research outputs found
Sort by
Digital Awareness Training and Education In SMA Negeri 6 Pekanbaru: Pelatihan dan Edukasi Kesadaran Digital Pada SMA Negeri 6 Pekanbaru
Get PDFThe “Digital Awareness Training and Education Program at SMA Negeri 6 Pekanbaru” aims to increase students' understanding in managing the use of technology wisely to maintain digital well-being. Problems faced by students include excessive use of technology, lack of self-management skills in the digital world, and the negative impact of social media on mental health. This training includes providing material on digital well-being, practice using Digital Wellbeing features, and evaluating the effectiveness of the program. The evaluation results showed a 51% increase in student understanding, especially in recognizing the negative impact of excessive technology use and how to set digital boundaries. The program helped students understand the balance between the digital world and real life and build healthier technology use habits. In the future, it is recommended that this training be conducted periodically with the involvement of parents as well as continuous evaluation to adjust to the ever-changing technological development
Bridging Youth to Global Education: Workshop on IELTS Awareness and Preparation at SMAN Jatinangor: Bridging Youth to Global Education: Workshop on IELTS Awareness and Preparation at SMAN Jatinangor
No full textMany high school students in suburban areas lack awareness of international English proficiency tests like IELTS, limiting their access to global education opportunities. To address this, a one-day interactive workshop was held at SMAN Jatinangor using the Participatory Learning and Action (PLA) approach. The program introduced students to IELTS structure, objectives, and test strategies through engaging, student-centered activities. Pre- and post-surveys assessed the impact, with results showing a significant improvement: the percentage of students in the high awareness category increased from 0% to 70%, while the low category was completely eliminated. This demonstrates the effectiveness of targeted educational interventions in bridging global readiness gaps
Applying A Supervised Model for Diabetes Type 2 Risk Level Classification
Get PDFDiabetes can lead to heart attacks, kidney failure, blindness, and increased risk of death. This research was conducted with the aim of classifying a diabetes risk dataset. In this context, performance comparison was carried out on three supervised learning algorithms: K-Nearest Neighbor, Naive Bayes, and Random Forest, against a dataset containing information on specific indicators related to diabetes risk. Additionally, this study also aimed to evaluate the accuracy comparison of the results produced by these three algorithms. The results of this research show that Random Forest performs very well in detecting diabetes, prediabetes, and non-diabetes, with high precision, recall, and F1-score levels. Meanwhile, although the results are still below Random Forest, both Naive Bayes and K-NN still demonstrate significant performance, especially regarding prediabetes cases. In conclusion, from the comparison results, the Random Forest algorithm shows the highest accuracy level at 99%, followed by K-Nearest Neighbor with an accuracy of 85%, while Naive Bayes has the lowest accuracy rate of 74%. This research indicates that the Random Forest algorithm excels in classifying data compared to the other two algorithms
Lung Disease Risk Prediction Using Machine Learning Algorithms
No full textLung diseases, including lung cancer, are one of the leading causes of death in the world. Early detection is essential to increase patients' chances of recovery and reduce healthcare costs. The utilization of machine learning algorithms can be used to solve this problem. This study evaluates five machine learning algorithms, namely K-Nearest Neighbors (K-NN), Naïve Bayes Classifier (NBC), Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM), for lung disease prediction using a dataset of 30,000 data with 11 attributes from Kaggle. The dataset was processed through data preprocessing and divided into training and test data with a ratio of 70%:30% and 80%:20%. The algorithm performance was evaluated using precision, recall, F1-score, and accuracy metrics. The results show that RF, SVM, and DT algorithms have the highest performance, with accuracy reaching 94.72% at 70%:30% ratio. The DT algorithm, which previously showed low performance in heart disease classification, provided competitive results in lung disease prediction. This research focuses on the importance of proper algorithm selection and data organization to improve the effectiveness of disease prediction. The findings contribute to the development of artificial intelligence technology for medical applications, particularly in supporting early diagnosis of lung diseases
Leveraging Machine Learning for Early Risk Prediction in Cirrhosis Outcome Patients
No full textMillions of individuals worldwide suffer from liver cirrhosis, which is one of the primary causes of mortality. Healthcare professionals may have more opportunities to treat cirrhosis patients effectively if early death prediction is made and it is postulated that death in this cohort would be correlated with laboratory test findings and other relevant diagnoses. In this study five machine learning models, including LR, SVM, XGBoost, AdaBoost and KNN, are implemented and evaluated. The preprocessing steps included feature selection, categorical data encoding, and data balancing using SVMSMOTE. The XGBoost model demonstrated superior performance, achieving 89.55% accuracy, 89.69% precision, 89.55% recall, and an F1-score of 89.59% after balancing. These findings highlight the potential of machine learning models in accurate risk detection in patients with cirrhosis and providing valuable support in clinical decision-making and improving patient treatment
Comparison of Supervised Learning Algorithms for Cancer Prediction
No full textThis study focuses on the application of Machine Learning algorithms for cancer prediction using a classification dataset. Several algorithms were employed, including K-Nearest Neighbor (KNN), Naive Bayes Classifier, Decision Tree, Random Forest, and Support Vector Machine (SVM). The primary goal of this research is to evaluate the performance of each algorithm to identify the best method for achieving high accuracy in cancer classification prediction. The experimental results reveal variations in performance among these algorithms. The evaluation was conducted using metrics such as accuracy, precision, recall, and F1-Score. Based on the analysis, Random Forest and Support Vector Machine demonstrated the best performance with the highest accuracy compared to other algorithms. Meanwhile, the Naive Bayes algorithm tended to exhibit lower performance in predictions. This study emphasizes the importance of selecting the appropriate algorithm in the implementation of Machine Learning for medical applications such as cancer prediction. With these findings, it is hoped that the identified methods can assist in clinical decision-making and improve the accuracy of early cancer diagnosis
Sistem Kendali Kualitas Air pada Tanaman Hidroponik berbasis Internet of Things: Internet of Things-Based Water Quality Control System for Hydroponic Plants
No full textKualitas larutan nutrisi merupakan faktor krusial dalam sistem hidroponik, terutama dalam menjaga kestabilan kadar zat terlarut (Total Dissolved Solids/TDS) sesuai kebutuhan tanaman. Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem kendali otomatis berbasis Internet of Things (IoT) yang mampu mengatur pemberian larutan nutrisi A/B secara presisi. Sistem dikembangkan menggunakan mikrokontroler ESP32-S3, sensor TDS, dan modul relay untuk mengontrol pompa nutrisi. Berdasarkan data eksperimen, dibangun model regresi kuadratik untuk menghitung kebutuhan volume larutan berdasarkan selisih antara nilai aktual dan target ppm. Sistem bekerja otomatis pada interval waktu tertentu dan terintegrasi dengan dashboard web untuk pemantauan real-time. Hasil pengujian menunjukkan bahwa sistem mampu mempertahankan nilai TDS dalam kisaran target (±15 ppm) dengan selisih rata-rata prediksi sebesar 2,17 ppm, dan selisih maksimum 4,1 ppm, yang masih berada dalam batas toleransi sistem hidroponik. Dengan integrasi IoT, pengguna dapat memantau dan mengendalikan kondisi larutan dari jarak jauh secara efisien. Sistem ini berpotensi untuk diterapkan dalam budidaya hidroponik skala rumah tangga maupun industri kecil
Evaluasi Distribusi Guru-Siswa dan Ketersediaan Sekolah untuk Mendukung Pembangunan Pendidikan Menggunakan K-Means Clustering: An Evaluation of Teacher–Student Distribution and School Availability in Supporting Educational Development Using the K-Means Clustering Algorithm
No full textKetimpangan distribusi guru dan ketersediaan Sekolah Menengah Atas (SMA) Negeri di Indonesia menjadi tantangan serius dalam mewujudkan pemerataan pendidikan. Penelitian ini bertujuan untuk menganalisis dan mengevaluasi distribusi jumlah guru, siswa, dan sekolah SMA Negeri dengan menerapkan algoritma K-Means Clustering. Data bersumber dari Badan Pusat Statistik (BPS) tahun 2023–2024 yang mencakup seluruh provinsi di Indonesia. Melalui pendekatan data mining menggunakan Orange, dilakukan proses pra-pemrosesan data, normalisasi, pemodelan klaster, serta visualisasi hasil. Hasil penelitian menunjukkan terbentuknya tiga klaster wilayah: Klaster 1 yang mencakup 20 provinsi dengan distribusi guru dan sekolah yang relatif ideal, Klaster 2 yang terdiri dari 6 provinsi di kawasan timur seperti Papua dan Maluku dengan tantangan tinggi akibat keterbatasan infrastruktur pendidikan, serta Klaster 3 yang berisi 8 provinsi dengan kondisi distribusi sedang. Penelitian ini mengungkap bahwa kebijakan nasional seperti rasio ideal 20:1 dalam pemberian tunjangan profesi guru belum adaptif terhadap kondisi geografis dan demografis lokal. Hasil klasterisasi ini memberikan dasar visual dan analitik yang kuat bagi pemerintah pusat dan daerah dalam merumuskan kebijakan pemerataan pendidikan yang lebih adil dan kontekstual, khususnya di jenjang menengah atas
Analisis Implementasi Artificial Intelligence dalam Dunia Kesehatan Indonesia: Literature Review: Analysis of Artificial Intelligence Implementation in the Indonesian Healthcare Sector: A Literature Review
No full textArtificial Intelligence (AI) diharapkan menjadi kekuatan utama dalam mendukung transformasi digital sektor kesehatan, sesuai visi Kementerian Kesehatan tahun 2023. Namun, implementasi AI di Indonesia masih jauh dari harapan. Meskipun terdapat inisiatif kuat untuk memanfaatkan AI dalam meningkatkan efisiensi dan efektivitas layanan kesehatan, penerapannya masih terbatas dan belum merata. Penelitian ini dilakukan menggunakan metode literature review terhadap 52 artikel ilmiah periode 2021–2024. Dengan pendekatan teori Diffusion of Innovation, penelitian ini mengevaluasi manfaat AI dalam diagnosis, pengambilan keputusan klinis, manajemen data, dan peningkatan akses pelayanan, serta mengidentifikasi model adopsi dan tantangan utama dalam penerapannya. Hasil analisis menunjukkan bahwa tantangan utama dalam implementasi AI di sektor kesehatan Indonesia mencakup belum adanya regulasi spesifik, lemahnya infrastruktur digital, isu etika, dan rendahnya literasi teknologi. Meski demikian, Indonesia memiliki potensi besar dalam pengembangan ekosistem AI yang adaptif dan inklusif. Keberhasilan implementasi sangat bergantung pada kolaborasi lintas sektor, penguatan regulasi, serta peningkatan kompetensi sumber daya manusia dan kapasitas teknologi. Dengan strategi nasional yang terarah dan berkelanjutan, AI berpeluang menjadi pilar transformasi sistem pelayanan kesehatan yang lebih modern, efisien, dan berdaya saing
Prediksi Academic Burnout pada Mahasiswa: Analisis Komparatif Algoritma Support Vector Machine dan Random Forest: Prediction of Academic Burnout in College Students: A Comparative Analysis of Support Vector Machine and Random Forest Algorithms
No full textAcademic burnout telah menjadi masalah signifikan di kalangan mahasiswa, berdampak negatif pada kesehatan mental dan kinerja akademik. Penelitian ini bertujuan untuk melakukan analisis komparatif terhadap kinerja algoritma Support Vector Machine (SVM) dan Random Forest (RF) dalam memprediksi academic burnout pada mahasiswa di salah satu universitas di DKI Jakarta. Metode penelitian kuantitatif ini menggunakan data primer dari kuesioner Burnout Assessment Tool – Student Version (BAT-S) yang mencakup faktor pribadi, akademik, dan psikologis, serta data sekunder akademik mahasiswa. Data mentah kemudian melalui tahap persiapan yang meliputi pembersihan, penanganan outlier dengan teknik capping, standardisasi, dan penyeimbangan kelas menggunakan BorderlineSMOTE untuk mengatasi distribusi data yang tidak seimbang. Hasil pemodelan menunjukkan performa prediktif yang sangat tinggi untuk kedua algoritma setelah optimasi hyperparameter, dengan SVM mencapai akurasi 98,75% dan RF sebesar 97,50% pada data uji. Meskipun RF menunjukkan keunggulan pada metrik berbasis peringkat seperti ROC-AUC, SVM direkomendasikan sebagai model akhir karena memiliki profil risiko kesalahan yang lebih dapat diterima secara klinis, yakni tidak menghasilkan false negative yang berisiko tinggi. Penelitian ini membuktikan bahwa ML dapat menjadi alat efektif untuk deteksi dini risiko burnout, namun penelitian selanjutnya disarankan untuk mengeksplorasi algoritma yang lebih kompleks seperti gradient boosting dan melakukan analisis kepentingan fitur untuk pemahaman yang lebih mendalam