Claim Missing Document
Check
Articles

PENERAPAN MODEL PEMBELAJARAN MATE-21 BERBASIS WEBSITES DI MADRASAH ALIYAH NURUL AMAL KUALA Ghofur, Abdul; Wete Polili, Andi; Taufik, Insan
Martabe : Jurnal Pengabdian Kepada Masyarakat Vol 7, No 5 (2024): Martabe : Jurnal Pengabdian Kepada Masyarakat
Publisher : Universitas Muhammadiyah Tapanuli Selatan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31604/jpm.v7i5.1677-1686

Abstract

Program ini dianggap penting karena tuntutan pendidikan modern yang mensyaratkan digitalisasi pendidikan. Selain itu, dunia kerja abad ke-21 menuntut penguasaan berbagai keterampilan abad ke-21, seperti berpikir kritis, berkolaborasi, berkomunikasi, dan kreativitas. Model pembelajaran Mate-21 menyediakan berbagai aktivitas pembelajaran untuk melatih berbagai keterampilan tersebut. Metode yang digunakan pada program ini adalah pelatihan terstruktur, yang diawali dengan pelatihan penyusunan materi ajar berbasis model pembelajaran Mate-21, pelatihan penggunaan Sistem Manajemen Pembelajaran Mate-21, dan pelatihan menerapkan model pembelajaran berbasis websites. Selanjutnya untuk menjamin kualitas program dilakukan evaluasi program secara komprehensif. Untuk mendukung kegiatan tersebut, dikembangkan learning management system Mate-21 MAS Nurul Amal.  Kegiatan ini memberi dampak yang signifikan terhadap peningkatan kemampuan guru dalam mengajar berbasis digital yang diperkaya dengan kemampuan menyusun materi ajar dan manajemen pembelajaran di kelas sehingga suasana pembelajaran lebih kolaboratif, kritis, komunikatif, kreatif, dan menyenangkan. Hal tersebut tampak dari respon sangat positif yang diberikan guru terhadap kegiatan ini. Oleh sebab itu penerapan model pembelajaran Mate-21 berbasis websites sangat penting untuk diperluas penggunaannya.
Pengembangan Aplikasi Perkuliahan Interaktif dengan Fitur Pemilihan Posisi Duduk Mahasiswa untuk Meningkatkan Interaksi Insan Taufik; Kana Saputra S; Fevi Rahmawati Suwanto
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 7 No. 2 (2025): Desember 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v7i2.9308

Abstract

Penelitian ini mengembangkan sistem manajemen pembelajaran digital dengan fitur pemilihan posisi duduk mahasiswa secara manual berbasis antarmuka visual untuk meningkatkan efektivitas interaksi dosen-mahasiswa dalam lingkungan hybrid. Sistem yang dikembangkan mengintegrasikan tiga peran utama (admin, dosen, dan mahasiswa) dengan fitur unggulan pemantauan posisi duduk mahasiswa melalui grid interaktif. Metode pengembangan menggunakan pendekatan Agile melalui tahapan analisis kebutuhan, perancangan sistem, implementasi, dan pengujian. Hasil penelitian menunjukkan bahwa sistem berhasil dibangun dengan arsitektur multi-role yang mencakup modul manajemen kursus, sesi interaktif, presensi real-time, dan dashboard pemantauan. Pengujian fungsional dengan 44 responden mahasiswa menunjukkan semua modul berjalan dengan baik, sementara kuesioner kepuasan pengguna menghasilkan skor rata-rata 4,6 (dari skala 5). Sistem ini memberikan solusi inovatif untuk menciptakan lingkungan pembelajaran yang lebih personal dan interaktif, khususnya dalam konteks kelas besar perguruan tinggi.
Eye Disease Classification System Based on Fundus Images Using the InceptionV3 Architecture Annisa Aulia; Hermawan Syahputra; Yulita Molliq Rangkuti; Insan Taufik; Kana Saputra S
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 3 (2026): June 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i3.2263

Abstract

This study aims to develop an automated eye disease classification system based on retinal fundus images using the InceptionV3 deep learning architecture. The dataset consists of four classes: cataract, diabetic retinopathy, glaucoma, and normal, collected from public sources and clinical data. The proposed method applies several preprocessing techniques, including background segmentation, data augmentation, data normalization, and an 80:20 data split to improve model performance and generalization. Transfer learning is implemented by utilizing pretrained ImageNet weights and modifying the final layers to suit the classification task. The model is trained using the Adam optimizer with a learning rate of 0.001 and categorical cross-entropy loss function. Evaluation results show that the model achieves an accuracy of 96%, with average precision, recall, and F1-score values of 0.97, 0.96, and 0.97, respectively. The confusion matrix analysis indicates that most predictions are correctly classified, demonstrating strong performance across all classes. Furthermore, the model is successfully integrated into a web-based system that enables users to upload fundus images and obtain classification results automatically. These findings indicate that the proposed system can effectively assist in early detection of eye diseases and support clinical decision-making.
Prediksi Penjualan Produk Makanan dan Minuman Ringan pada PT. Sinar Niaga Sejahtera Menggunakan Metode Holt-Winters Berbasis Website M. Revano Ananda Lubis; Insan Taufik; Said Iskandar Al Idrus; Arnita Arnita; Hermawan Syahputra
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): INCODING OKTOBER
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.1024

Abstract

PT. Sinar Niaga Sejahtera is a food and beverage distribution company that still relies on conventional methods to determine stock levels, often facing inventory management challenges due to fluctuations in market demand. This study aims to predict sales of the 15 best-selling products at the Tebing Tinggi branch using the Holt-Winters method, based on a website that provides historical sales data from January 2021 to December 2024. The research stages include problem identification, data collection, application of the Holt-Winters method, model evaluation using Mean Absolute Percentage Error (MAPE), and implementation of a website-based system. The results of the study on one product, Garuda Atom Original, show optimal parameters of α = 0.1, β = 0, and γ = 0.8 with an MAPE value of 5,703115%, which is classified as very good. The implementation of a website-based sales prediction system makes it easier for administrators to manage product data, record sales data, and obtain prediction results in the form of informative graphs and tables, thereby helping the company reduce the risk of overstocking or understocking and supporting more effective data-driven decision-making.
Implementasi Algoritma K-Nearest Neighbors (KNN) dalam Deteksi Dini Hipertensi berdasarkan Analisis Tekanan Darah Ary Prandika Siregar; Said Iskandar Al Idrus; Zulfahmi Indra; Insan Taufik
INCODING: Journal of Informatics and Computer Science Engineering Vol 5, No 2 (2025): INCODING OKTOBER
Publisher : Mahesa Research Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34007/incoding.v5i2.1018

Abstract

This study aims to develop a web-based hypertension detection system using the K-Nearest Neighbors (KNN) algorithm and to analyze its accuracy in classifying hypertension status. The dataset was obtained from 447 patient medical records at RSKG Rasyida, consisting of eight variables: gender, age, systolic blood pressure, diastolic blood pressure, height, weight, body mass index (BMI), and hypertension status. The preprocessing stage involved three main steps—feature selection (age, systolic and diastolic blood pressure, BMI), data balancing using undersampling, and data normalization through the Min-Max method—resulting in 425 balanced data samples with five hypertension categories. The web application includes modules for login, dashboard, data input, detection results, and detection history, and has been evaluated using black box testing. The best KNN performance was achieved at k = 13 with 92.94% accuracy, 94% precision, 93% recall, and 93% F1-score. These results indicate that the proposed system can accurately classify hypertension and serve as an effective, data-driven screening tool for healthcare professionals.
Face Recognition Motorcycle Rider Registration System for Rider Data Management Kana Saputra S; Insan Taufik; Irham Ramadhani; Putri Sasalia S; Yusfi Syawali; Dede Yusuf; Rezkya Nadilla Putri; Najwa Latifah Hasibuan; Fauzan Hafiz Harahap
Bulletin of Information Technology (BIT) Vol 6 No 3: September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bit.v6i3.2157

Abstract

This research aims to develop a motorcycle rider registration system using facial recognition technology that can improve the efficiency of rider data management. This system is designed to identify and authenticate riders with high accuracy, thereby simplifying the registration and monitoring process. The methods used in this research include collecting rider facial data through cameras, image processing for feature extraction, and implementing a facial recognition algorithm. Testing was conducted in several locations with varying lighting conditions and viewing angles to ensure the system's robustness. The results show that the developed system is capable of achieving facial recognition accuracy of up to 95%. In addition, this system provides an intuitive user interface to facilitate the registration and data management process. With the implementation of this system, it is expected to reduce the time and costs required in managing motorcycle rider data, as well as improve safety and comfort while riding.
Pengembangan Bahan Ajar Drama Berbantuan Media Virtual Reality Mahasiswa Pendidikan Bahasa dan Sastra Indonesia Trisnawati Hutagalung; Lili Tansliova; Abdurrahman Adisaputera; Insan Taufik
Kode : Jurnal Bahasa Vol. 14 No. 4 (2025): Kode: Edisi Desember 2025
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Tujuan penelitian ini adalah untuk mengembangkan bahan ajar berbantuan media Virtual Reality pada mata kuliah Drama di Program Studi Pendidikan Bahasa dan Sastra Indonesia FBS Unimed. Penelitian ini menggunakan metode Research and Development (R&D), penelitian ini dilakukan sampai revisi produk setelah dilakukan validasi. Populasi penelitian ini adalah seluruh mahasiswa semester VI Program Studi Pendidikan Bahasa dan Sastra Indonesia. Sampel dalam penelitian ini adalah mahasiswa reguler E Program Studi Pendidikan Bahasa dan Sastra Indonesia. Hasil penelitian ini memperoleh persentase validasi ahli materi untuk aspek isi dengan kualifikasi sangat baik (85,7%) hasil penelitian ahli materi untuk aspek penyajian berada pada kualifikasi sangat baik (85,5%), hasil validasi ahli materi aspek kebahasaan berada pada kategori kualifikasi sangat baik (85,8%) dan hasil validasi ahli desain berada pada kualifikasi sangat baik (86,6%). Kata Kunci: Bahan Ajar Virtual Reality, Pembelajaran Drama, Pendidikan Bahasa dan Sastra Indonesia.
Classification of Purple Passion Fruit Ripeness Levels Using Convolutional Neural Network (CNN) Mochammad Gani Alfa Alkhoiri Siregar; Said Iskandar Al Idrus; Hermawan Syahputra; Insan Taufik; Kana Saputra S
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 5 No. 2 (2026): February 2026
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v5i2.1787

Abstract

Passiflora edulis Sims (purple passion fruit) is a fruit that offers numerous health benefits and possesses high economic value. However, the manual assessment of ripeness by traders tends to be subjective and inconsistent, leading to post-harvest losses of up to 50%. This study developed a classification model for determining the ripeness level of purple passion fruit using a Convolutional Neural Network (CNN) and implemented it in a web-based application. The CNN model was designed to classify four ripeness stages (unripe, half-ripe, ripe, and rotten) with the addition of a non-passion-fruit class to enhance the system’s robustness. The dataset consisted of 2,000 images divided into five classes: four ripeness levels of purple passion fruit (unripe, half-ripe, ripe, and rotten) and one non-passion-fruit class as a comparator. All images were in JPG and PNG formats. The CNN architecture comprised four convolutional layers with 16, 32, 64, and 128 filters, respectively. Evaluation of various data-splitting ratios (80:20, 70:30, 60:40) and learning rates (0.001, 0.0001, 0.01) showed that the optimal configuration was achieved at a ratio of 80:20 with a learning rate of 0.001, resulting in a training accuracy of 96.72% and a testing accuracy of 95.76%, with a loss value of 0.1811. Validation using 5-Fold Cross Validation produced an average accuracy of 95.40%. The model was integrated into a web application developed using Flask and JavaScript, deployed on the PythonAnywhere cloud platform, enabling users to upload images and automatically obtain ripeness predictions to assist traders in sorting fruits more quickly and accurately.
Implementation of K-Means for Mapping Cleanliness Levels in Pancur Batu District Raisya Putri; AS Mansur; Hamidah Nasution; Insan Taufik; Adidtya Perdana
Bitnet: Jurnal Pendidikan Teknologi Informasi Vol. 11 No. 3 (2026): Bitnet: Jurnal Pendidikan Teknologi Informasi
Publisher : Institute for Research and Community Services Universitas Muhammadiyah Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33084/bitnet.v11i3.13677

Abstract

This study aims to classify areas in Pancur Batu District based on environmental cleanliness levels using the K-Means Clustering method, analyze the characteristics of each cluster based on cleanliness parameters, and develop a web-based mapping system to visualize the clustering results spatially. The study utilized 578 image data analyzed using five parameters, namely visible waste density, drainage condition, percentage of clean roads, percentage of households with trash bins, and waste collection frequency. The results showed that the areas in Pancur Batu District were successfully grouped into three clusters: Cluster 0 (Clean) consisting of 6 villages, Cluster 1 (Dirty) consisting of 12 villages, and Cluster 2 (Very Clean) consisting of 7 villages. The clustering results were then visualized through a web-based mapping system to facilitate users in identifying the distribution of cleanliness levels across the study area. Expert validation conducted by a geography specialist obtained a total score of 42 with an average score of 4.2, which falls into the good category. Therefore, the implementation of the K-Means Clustering method was able to effectively classify areas based on environmental cleanliness levels and provide useful information to support environmental cleanliness management and decision-making processes in Pancur Batu District.
Penerapan Teknologi Mekanisasi Pakan Mandiri Guna Menekan Biaya Produksi Peternak Bebek Petelur di Sidodadi Batang Kuis Deli Serdang Yuni Warty; Insan Taufik; Dewi Wulandari; Muhammad Aswin Rangkuti; Tuti Hardianti; Silvia Dona Sari; Yanthy Leonita Perdana Simanjuntak
Bima Abdi: Jurnal Pengabdian Masyarakat Vol. 6 No. 3 (2026): Bima Abdi: Jurnal Pengabdian Masyarakat
Publisher : Yayasan Pendidikan Bima Berilmu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53299/ba-jpm.v6i3.5273

Abstract

Usaha peternakan bebek petelur di Desa Sidodadi, Kecamatan Batang Kuis, Kabupaten Deli Serdang menghadapi tingginya biaya pakan, ketergantungan pada pakan pabrikan, serta banyaknya pakan serbuk yang tercecer. Kegiatan pengabdian ini bertujuan menerapkan teknologi mekanisasi pakan mandiri untuk mengubah pakan serbuk menjadi pelet, meningkatkan efisiensi konsumsi, dan menekan biaya produksi. Pelaksanaan kegiatan meliputi sosialisasi, pengadaan dan instalasi mesin, pelatihan formulasi pakan, uji coba produksi, pendampingan, monitoring, dan evaluasi. Mitra memelihara sekitar 8.000 ekor bebek dengan kebutuhan awal 960 kg pakan per hari. Sebelum penerapan teknologi, biaya pakan mencapai Rp4.816.000 per hari dan masih menggunakan 80 kg pakan pabrikan. Setelah mesin digunakan, bahan pakan lokal dapat dicampur merata dan dibentuk menjadi pelet. Biaya pakan menurun menjadi Rp4.200.000 per hari, atau berkurang Rp616.000. Pakan pelet juga lebih seragam, tidak mudah tercecer, dan lebih optimal dikonsumsi ternak. Teknologi ini meningkatkan kemandirian peternak sekaligus mendukung keberlanjutan usaha melalui produksi pakan yang lebih efisien dan ekonomis. Rekomendasi untuk kegiatan pengabdian selanjutnya meliputi optimalisasi kapasitas mesin untuk komersialisasi pakan pelet ke peternak luar, serta hilirisasi produk pascapanen telur (seperti telur asin aneka rasa) untuk meningkatkan nilai tambah ekonomi kelompok.
Co-Authors Abdul Ghofur Abdul Ghofur Abdurrahman Adisaputera Adidtya Perdana, Adidtya Ahmad Landong Alfattah Atalarais Amran Sitohang Andriyani S, Rahayu Annisa Aulia Antonius Purba Arjon Samuel Sitio Arnita Arnita Arnita Arnita Ary Prandika Siregar AS Mansur Chairunisah Chairunisah, Chairunisah Dede Yusuf Dewi Wulandari Dinda Farahdilla Dharma Dinda Kartika Fachrezzy Muhammad Farhan Ramadhan, Haikal Fauzan Hafiz Harahap Fevi Rahmawati Suwanto Fitra, Awaludin Fristy Riandari Hamidah Nasution Hasugian , Paska Marto Hermawan Syahputra Ihsan Zulfahmi Immanuel Batistuta Tarigan Irham Ramadhani Isda Pramuniati Izwita Dewi Kana Saputra S Kuraini, Atifa Nuzulul Lili Tansliova Lubis, Afiq Alghazali M Iqbal Anata Pane M. Revano Ananda Lubis MANSUR AS Mhd Hidayat Mhd Hidayat Mochammad Gani Alfa Alkhoiri Siregar Mohammed Hafizh Al-Areef Muhammad Noer Fadlan Muthmainnah, Inna Najwa Latifah Hasibuan Nasution, Hamidah . Niska, Debi Yandra Nurliani Manurung Pane, Yeremia Yosefan Parapak, R Putri Angela Pinem, Josua Purba, Boy Hendrawan Putri Sasalia S Putri, Rezkya Nadilla Rafif Nauval Tuah Siregar Raisya Putri Raiyan Fairozi Rangkuti, Muhammad Aswin Rezkya Nadilla Putri Said . Iskandar Samosir, Wahyu Ardiantito Saragih, Vinny Ramayani Silvia Dona Sari Simamora, Elmanani Sinaga, Marlina Setia Siregar, Angginy Akhirunnisa Sri Mulyana SUSIANA Syifa Cendikia, Yolanda Tarigan, Yosua Yosephine Tengku Ratna Soraya TONNI LIMBONG Trisnawati Hutagalung Tuti Hardianti Wahabi Hasibuan, Rahman Warjaya, Angga Wete Polili, Andi Wete Polili, Andi Yanthy Leonita Perdana Simanjuntak Yulita Molliq Rangkuti Yulita Molliq Rangkuti Yuni Warty Yusfi Syawali Zulfahmi Indra, Zulfahmi