Garuda - Garba Rujukan Digital

Implementasi Computer Vision pada Media Trainer Kode Semaphore Pramuka Berbasis YOLO-Pose Khairy, Mubarakh Hayatna; Hendriyani, Yeka; Hadi, Ahmadul; Saputra, Hadi Kurnia
Jurnal Pendidikan Tambusai Vol. 9 No. 2 (2025): Agustus
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jptam.v9i2.31202

Semaphore merupakan salah satu jenis sandi dalam kegiatan Pramuka yang digunakan sebagai media komunikasi visual jarak jauh. Namun, pembelajaran semaphore masih menghadapi kendala dalam mengenali gerakan dengan cepat dan tepat. Penelitian ini bertujuan untuk merancang dan membangun media trainer gerakan semaphore berbasis YOLO-Pose, sebuah metode deteksi objek yang dikombinasi dengan Human Pose Estimation. Sistem dilatih menggunakan 649 data citra huruf A–Z dan diuji pada epoch 150. Hasil menunjukkan bahwa model mampu mengenali gerakan dengan tingkat akurasi tinggi, precision mencapai 91–94%, recall 89–93%, dan mAP-50 sebesar 95%. Sistem ini berhasil mengklasifikasikan huruf secara real-time dan menunjukkan potensi sebagai media pembelajaran interaktif dalam kegiatan Pramuka.

Penerapan Sistem Pendeteksian Pemalsuan Tanda Tangan Berbasis Optical Character Recognition (OCR) dan Support Vector Machine (SVM) Zafania, Puti; Saputra, Hadi Kurnia; Novaliendry, Dony; Syukhri, Syukhri
Jurnal Pendidikan Tambusai Vol. 9 No. 2 (2025): Agustus
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jptam.v9i2.31307

Penelitian ini bertujuan mengembangkan sistem deteksi pemalsuan tanda tangan basah pada dokumen resmi dengan menggabungkan Optical Character Recognition (OCR) dan Support Vector Machine (SVM). Data terdiri atas 760 sampel tanda tangan asli dan palsu yang diperoleh dari pemindaian dokumen fisik dan pelabelan kategori. Sistem mendeteksi dan mengekstraksi area tanda tangan menggunakan OCR, lalu mengklasifikasikannya dengan SVM berbasis fitur Histogram of Oriented Gradients (HOG). Pengembangan dilakukan menggunakan metode prototyping dan diuji melalui integration testing. Hasil menunjukkan SVM dengan kernel RBF membedakan tanda tangan asli dan palsu dengan akurasi tinggi. Integrasi OCR dan SVM terbukti efektif serta efisien untuk verifikasi tanda tangan pada dokumen resmi.

Implementasi Sistem Rekomendasi Pemilihan Mata Pelajaran Pada Kurikulim Merdeka Menggunakan Metode TOPSIS Farizi, Habib Al; Saputra, Hadi Kurnia; Hendriyani, Yeka; Budayawan, Khairi
Jurnal Pendidikan Tambusai Vol. 9 No. 2 (2025): Agustus
Publisher : LPPM Universitas Pahlawan Tuanku Tambusai, Riau, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jptam.v9i2.31314

Kurikulum Merdeka memberi kebebasan bagi siswa dalam memilih mata pelajaran sesuai minat, bakat, dan tujuan karier. Namun, proses pemilihan sering tidak berbasis data. Penelitian ini mengembangkan sistem rekomendasi berbasis web bernama Mapick yang membantu siswa memilih mata pelajaran secara objektif menggunakan metode TOPSIS. Sistem memproses tiga kriteria: nilai akademik, hasil tes minat bakat (RIASEC), dan prospek karier dari guru, dengan bobot yang dapat diatur dinamis. Hasil implementasi pada dua siswa menunjukkan bahwa sistem mampu memberikan rekomendasi yang sesuai dengan karakteristik individu. Sistem ini juga telah dilengkapi fitur Progressive Web App (PWA) untuk meningkatkan aksesibilitas. Mapick diharapkan dapat mendukung pelaksanaan Kurikulum Merdeka dan membantu siswa mengambil keputusan akademik yang tepat dan terarah.

Determinants of Cybersecurity Behavior among Social Media Users: The Moderating Role of Self-Efficacy in the Relationship between Cybersecurity Knowledge and Social Media Use Intensity Saputra, Hadi Kurnia; Refdinal, Refdinal; Abdullah, Rijal; Mardizal, Jonni; Ambiyar, Ambiyar; Fadhilah, Fadhilah
Voteteknika (Vocational Teknik Elektronika dan Informatika) Vol 13, No 4 (2025): Voteteknika (Vocational Teknik Elektronika dan Informatika)
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/voteteknika.v13i4.137117

Social media has become an integral part of daily life, but its intensive use also increases users’ exposure to various cybersecurity threats, making it important to understand the determinants of cybersecurity behavior. This study examines the effects of cybersecurity knowledge and social media usage intensity on cybersecurity behavior, as well as the role of cybersecurity self-efficacy as both a direct predictor and a moderating variable. A quantitative approach was employed using a survey of 115 university students who actively use social media, and the data were analyzed using Structural Equation Modeling–Partial Least Squares (SEM-PLS). The results indicate that cybersecurity knowledge has a positive and significant effect on cybersecurity behavior (β = 0.309, t = 3.383, p < 0.01), while cybersecurity self-efficacy emerges as the strongest predictor of cybersecurity behavior (β = 0.479, t = 4.725, p < 0.001). In contrast, social media usage intensity does not show a significant effect on cybersecurity behavior (β = 0.003, t = 0.032, p > 0.05). Furthermore, moderation analysis reveals that cybersecurity self-efficacy does not moderate the relationships between cybersecurity knowledge or social media usage intensity and cybersecurity behavior. The structural model explains 58.3% of the variance in cybersecurity behavior (R² = 0.583). These findings suggest that cybersecurity behavior among social media users is more strongly driven by cognitive and psychological factors than by usage intensity alone. Practically, effective cybersecurity interventions should prioritize strengthening users’ cybersecurity knowledge and self-efficacy rather than merely restricting social media use.Keywords— Cybersecurity behavior; Cybersecurity knowledge; Self-efficacy; Social media usage intensity; SEM-PLS

The Effects of Coding Literacy and Computational Thinking on Student Digital Entrepreneurial Intentions: The Mediating Role of Coding Self-Efficacy Saputra, Hadi Kurnia; Ganefri, Ganefri; Yulastri, Asmar; Yuliana, Yuliana
Voteteknika (Vocational Teknik Elektronika dan Informatika) Vol 13, No 4 (2025): Voteteknika (Vocational Teknik Elektronika dan Informatika)
Publisher : Universitas Negeri Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24036/voteteknika.v13i4.137125

Digital transformation has intensified the importance of digital entrepreneurship as a strategic pathway for university students. This study examines the effects of Coding Literacy and computational thinking on student Digital Entrepreneurial intentions, with coding self-efficacy serving as a mediating variable. A quantitative explanatory design was employed using survey data collected from 119 undergraduate students enrolled in an introductory coding course at Universitas Negeri Padang. Data were analyzed using Partial Least Squares–Structural Equation Modeling (PLS-SEM). The results indicate that Coding Literacy significantly influences coding self-efficacy (β = 0.414, p < 0.001) and Digital Entrepreneurial intentions (β = 0.474, p < 0.001). Computational thinking also shows a significant positive effect on coding self-efficacy (β = 0.340, p = 0.002), but does not exert a significant direct effect on Digital Entrepreneurial intentions (β = 0.074, p = 0.395). Furthermore, coding self-efficacy has a strong positive effect on Digital Entrepreneurial intentions (β = 0.313, p < 0.001). Mediation analysis reveals that coding self-efficacy partially mediates the relationship between Coding Literacy and Digital Entrepreneurial intentions (β = 0.130, p = 0.002), while fully mediating the relationship between computational thinking and Digital Entrepreneurial intentions (β = 0.107, p = 0.035). The model explains 49.3% of the variance in coding self-efficacy and 60.7% of the variance in Digital Entrepreneurial intentions. These findings highlight coding self-efficacy as a critical psychological mechanism that transforms computational competencies into Digital Entrepreneurial intentions, offering important implications for the design of coding-oriented entrepreneurship education in higher education.Keywords— Coding Literacy, computational thinking, coding self-efficacy, digital entrepreneurial intention, PLS-SEM

Rancang Bangun Aplikasi Pengelolaan Layanan Lansia Pada Posyandu Berbasis Web Di Puskesmas Dadok Tunggul Hitam Desy Rahmayanti; Khairi Budayawan; Denny Kurniadi; Hadi Kurnia Saputra
Journal of Innovative and Creativity Vol. 5 No. 3 (2025)
Publisher : Fakultas Ilmu Pendidikan Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/joecy.v5i3.4607

Posyandu lansia merupakan kegiatan pelayanan kesehatan masyarakat yang berperan penting dalam pemantauan dan peningkatan kesehatan lanjut usia. Berdasarkan hasil observasi di Puskesmas Dadok Tunggul Hitam, proses pencatatan kegiatan posyandu masih dilakukan secara manual menggunakan buku register dan spreadsheet, sehingga menimbulkan kendala dalam efisiensi, keakuratan data, serta keterlambatan pelaporan. Penelitian ini bertujuan untuk merancang dan membangun aplikasi pengelolaan layanan lansia berbasis web yang dapat membantu proses pencatatan, pengelolaan data, serta pelaporan kegiatan posyandu secara terintegrasi. Metode pengembangan sistem yang digunakan adalah metode Waterfall, dengan tahapan meliputi analisis kebutuhan, perancangan, implementasi, pengujian, dan pemeliharaan. Aplikasi ini dikembangkan menggunakan framework Laravel dengan basis data MySQL dan diimplementasikan pada lingkungan berbasis web agar mudah diakses oleh kader, perawat, serta kepala puskesmas. Hasil pengujian menggunakan metode black-box testing menunjukkan bahwa seluruh fungsi sistem berjalan sesuai dengan kebutuhan pengguna. Aplikasi mampu menampilkan data lansia, hasil pemeriksaan, jadwal kegiatan, serta laporan otomatis dalam bentuk grafik dan tabel. Sistem ini meningkatkan efisiensi kerja, mengurangi kesalahan pencatatan, serta mempercepat proses pelaporan ke pihak puskesmas. Dengan demikian, aplikasi ini berhasil mendukung transformasi digital dalam pelayanan kesehatan masyarakat khususnya pada kegiatan posyandu lansia di Puskesmas Dadok Tunggul Hitam

Evaluasi Program Pendidikan di SMK: Systematic Literature Review Terhadap Logic Model dan Theory-Based Evaluation Yul, Fadlul Amdhi; Saputra, Hadi Kurnia; Yuberta, Andre; Arianto; Simatupang, Wakhinuddin; Anwar, Muhammad
Indo-MathEdu Intellectuals Journal Vol. 7 No. 3 (2026): Indo-MathEdu Intellectuals Journal (In-Press)
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/imeij.v7i3.5532

This study aims to analyze the application of the Logic Model and Theory-Based Evaluation in evaluating educational programs at Vocational High Schools (SMK), as well as to identify the advantages, limitations, and effectiveness of both approaches. The method used is a Systematic Literature Review (SLR) referring to PRISMA guidelines. Literature searches were conducted through scientific databases with a publication range from 2019 to 2026. From the selection process, 15 articles that met the inclusion criteria were obtained and analyzed qualitatively using a narrative synthesis. The research results indicate that the Logic Model approach is effective in mapping program structures systematically through the relationships between inputs, processes, outputs, and outcomes, making it easier to understand program flow and result achievements. Meanwhile, Theory-Based Evaluation is superior in explaining the mechanisms of change and the cause-and-effect relationships underlying program success. Nevertheless, this approach has a higher level of complexity and requires more in-depth data. The conclusion of this research shows that there is no single approach that is entirely superior, so the integration of Logic Model and Theory-Based Evaluation becomes the most effective strategy in producing a comprehensive, systematic, and evidence-based program evaluation. This integrative approach is recommended to improve the quality of educational program evaluations in vocational high schools (SMK).

Evaluasi Program Pendidikan di SMK: Systematic Literature Review Terhadap Logic Model dan Theory-Based Evaluation Fadlul Amdhi Yul; Hadi Kurnia Saputra; Andre Yuberta; Arianto; Wakhinuddin Simatupang; Muhammad Anwar
Indo-MathEdu Intellectuals Journal Vol. 7 No. 3 (2026): Indo-MathEdu Intellectuals Journal
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/imeij.v7i3.5532

This study aims to analyze the application of the Logic Model and Theory-Based Evaluation in evaluating educational programs at Vocational High Schools (SMK), as well as to identify the advantages, limitations, and effectiveness of both approaches. The method used is a Systematic Literature Review (SLR) referring to PRISMA guidelines. Literature searches were conducted through scientific databases with a publication range from 2019 to 2026. From the selection process, 15 articles that met the inclusion criteria were obtained and analyzed qualitatively using a narrative synthesis. The research results indicate that the Logic Model approach is effective in mapping program structures systematically through the relationships between inputs, processes, outputs, and outcomes, making it easier to understand program flow and result achievements. Meanwhile, Theory-Based Evaluation is superior in explaining the mechanisms of change and the cause-and-effect relationships underlying program success. Nevertheless, this approach has a higher level of complexity and requires more in-depth data. The conclusion of this research shows that there is no single approach that is entirely superior, so the integration of Logic Model and Theory-Based Evaluation becomes the most effective strategy in producing a comprehensive, systematic, and evidence-based program evaluation. This integrative approach is recommended to improve the quality of educational program evaluations in vocational high schools (SMK).

Rancang Bangun Sistem Deep Learning untuk Klasifikasi Tingkat Depresi Melalui Analisis Wajah dan Respons Kuesioner Berbasis Website Putra, Reza Yasa; Sriwahyuni, Titi; Saputra, Hadi Kurnia; Budayawan, Khairi
Journal of Authentic Research Vol. 5 No. 2 (2026): May
Publisher : LITPAM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36312/h850k151

Depresi pada mahasiswa menjadi persoalan akademik dan kesehatan publik karena dapat menurunkan konsentrasi, motivasi belajar, capaian akademik, serta meningkatkan risiko isolasi sosial dan ide bunuh diri. Penelitian ini bertujuan merancang dan mengevaluasi sistem skrining awal tingkat depresi berbasis website yang mengintegrasikan kuesioner Patient Health Questionnaire-9 (PHQ-9) dan analisis ekspresi wajah berbasis Convolutional Neural Network (CNN). Metode pengembangan menggunakan model Waterfall yang mencakup komunikasi kebutuhan, perencanaan arsitektur, pemodelan, konstruksi, pengujian, dan deployment. Model visual dilatih menggunakan dataset ekspresi wajah FER-2013 dan CK+ yang diproses menjadi citra grayscale 48x48 piksel, diseimbangkan dengan oversampling, serta diperkuat melalui augmentasi. Sistem menerapkan decision-level fusion dengan bobot 60% untuk skor PHQ-9 dan 40% untuk rasio ekspresi negatif, sedangkan inferensi wajah dijalankan langsung di peramban melalui TensorFlow.js untuk menjaga privasi biometrik. Hasil pengujian menunjukkan model Custom CNN Mini-VGG memperoleh akurasi global 65,28% pada 7.178 citra uji, dengan kinerja terbaik pada kelas Happy dan Surprise. Pengujian fungsional membuktikan autentikasi, validasi webcam, fusi data, ekspor laporan, dan dasbor institusi berjalan valid. Sistem juga terbukti tidak mengirim citra wajah ke server, sehingga prinsip Zero Data Retention terpenuhi. Temuan ini menunjukkan bahwa pendekatan multimodal dapat memperkuat skrining dini depresi, tetapi hasilnya tetap harus diposisikan sebagai triase awal, bukan diagnosis klinis. Depression among university students is an academic and public health concern because it may reduce concentration, learning motivation, academic achievement, and increase the risk of social withdrawal and suicidal ideation. This study aims to design and evaluate a web-based early screening system for depression severity by integrating the Patient Health Questionnaire-9 (PHQ-9) and facial expression analysis using a Convolutional Neural Network (CNN). The system was developed using the Waterfall model, covering requirement communication, architectural planning, modeling, construction, testing, and deployment. The visual model was trained on FER-2013 and CK+ facial expression datasets, standardized into 48x48 grayscale images, balanced using oversampling, and strengthened with data augmentation. The proposed system applies decision-level fusion, assigning 60% weight to PHQ-9 scores and 40% to the negative facial expression ratio, while facial inference is executed locally in the browser through TensorFlow.js to protect biometric privacy. The evaluation shows that the Custom CNN Mini-VGG model achieved 65.28% global accuracy on 7,178 unseen test images, with the strongest performance for Happy and Surprise classes. Functional testing confirmed that authentication, webcam validation, data fusion, report export, and institutional dashboards worked as expected. Network inspection also confirmed that no facial images were transmitted to the server, thereby satisfying the Zero Data Retention principle. These findings indicate that multimodal screening can strengthen early depression triage, although the system should remain a decision-support tool and not a substitute for clinical diagnosis.

Pengembangan Aplikasi Deteksi Ancaman Siber Real-Time Berbasis Analisis Log Menggunakan Machine Learning dengan Notifikasi Peringatan Otomatis Wijaya, Qhodry Andra; Saputra, Hadi Kurnia; Budayawan, Khairi; Wahyuni, Titi Sri
Journal of Authentic Research Vol. 5 No. 2 (2026): May
Publisher : LITPAM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36312/y98nvh32

Penelitian ini mengembangkan aplikasi deteksi ancaman siber real-time berbasis analisis Apache access log dengan dukungan machine learning dan notifikasi otomatis. Permasalahan utama yang diangkat adalah keterlambatan deteksi ketika administrator masih memeriksa log secara manual, padahal pola serangan web seperti SQL Injection, Cross-Site Scripting, Directory Traversal, dan Brute Force dapat muncul sebagai rangkaian request singkat yang memerlukan respons cepat. Sistem dikembangkan menggunakan model prototipe dengan frontend Next.js, backend FastAPI, database PostgreSQL, pipeline analitik Python, serta Telegram Bot sebagai kanal peringatan. Dataset awal berjumlah 56.757 baris dan diproses melalui pembersihan, ekstraksi fitur perilaku dan signature, deteksi anomali Isolation Forest, klasterisasi DBSCAN, penyeimbangan SMOTE, serta klasifikasi Random Forest. Hasil evaluasi menunjukkan bahwa DBSCAN mencapai Silhouette Score 0,4788, sedangkan Random Forest memperoleh akurasi keseluruhan 0,9971 pada 10.874 data uji dengan performa sangat tinggi pada kelas Normal, SQL Injection, XSS, Directory Traversal, dan Brute Force. Pengujian fungsional menghasilkan seluruh skenario valid, sementara pengujian real-time menunjukkan rata-rata latensi 3,357 detik dari serangan masuk sampai notifikasi diterima. Temuan ini menunjukkan bahwa integrasi analisis log, machine learning, dashboard, dan notifikasi dapat meningkatkan visibilitas keamanan serta mendukung peringatan dini pada server web. This study develops a real-time cyber threat detection application based on Apache access log analysis using machine learning and automated alert notification. The main problem addressed is delayed threat detection when administrators still inspect logs manually, whereas web attack patterns such as SQL Injection, Cross-Site Scripting, Directory Traversal, and Brute Force may occur as short sequences of requests requiring immediate response. The system was developed using a prototyping model with a Next.js frontend, FastAPI backend, PostgreSQL database, Python analytical pipeline, and Telegram Bot as the alert channel. The initial dataset contained 56,757 rows and was processed through cleaning, behavioral and signature-based feature extraction, Isolation Forest anomaly detection, DBSCAN clustering, SMOTE balancing, and Random Forest classification. The evaluation indicates that DBSCAN achieved a Silhouette Score of 0.4788, while Random Forest obtained an overall accuracy of 0.9971 on 10,874 test instances with strong performance across Normal, SQL Injection, XSS, Directory Traversal, and Brute Force classes. Functional testing confirmed that all scenarios were valid, and real-time testing showed an average latency of 3.357 seconds from attack arrival to alert reception. These findings demonstrate that the integration of log analysis, machine learning, dashboards, and notification services can improve security visibility and support early warning on web servers.

Title

Found 33 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 33 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 33 Documents
Search