Article Per Year (5 Year)
p-Index From 2021 - 2026
2.707
P-Index
This Author published in this journals
All Journal JURNAL PENDIDIKAN TAMBUSAI TELEKONTRAN: Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan JURNAL REKAYASA INFORMASI SWADHARMA (JRIS) KOMMAS: Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Masyarakat Information Technology (JPM ITech) Jurnal Abdimas Maduma LOGIC : Jurnal Ilmu Komputer dan Pendidikan OKTAL : Jurnal Ilmu Komputer dan Sains BULLET : Jurnal Multidisiplin Ilmu AMMA : Jurnal Pengabdian Masyarakat APPA : Jurnal Pengabdian Kepada Masyarakat Riau Jurnal Teknik Informatika
Yuda Samudra
Universitas Pamulang
Humanities Astronomy Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Medicine & Pharmacology Nursing Social Sciences Other

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 18 Documents
Search

 1   2 
SISTEM DETEKSI DAN KLASIFIKASI BUNGA MELATI BERBASIS CONVOLUTIONAL NEURAL NETWORK (CNN) UNTUK MENDETEKSI DAN MENGKLASIFIKASI BUNGA PADA ANALISIS CITRA DIGITAL Hizkia Bayu Wijaya; Yuda Samudra
OKTAL : Jurnal Ilmu Komputer dan Sains Vol 4 No 03 (2025): OKTAL : Jurnal Ilmu Komputer Dan Sains
Publisher : CV. Multi Kreasi Media

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

Abstract

Image processing has become an increasingly important technology in various fields, including botany, particularly to support the automatic identification of plants. One of the main challenges in identifying jasmine flowers lies in the manual process, which is time-consuming and heavily reliant on individual expertise. To address these limitations, this research aims to design a detection and classification system for jasmine flowers using Convolutional Neural Network (CNN), capable of identifying four jasmine flower types: Melati Putih, Melati Jepang, Melati Gambir, and Melati Kuning. The system employs a modified CNN architecture, ResNet50v2, incorporating a 50% dropout layer, Adam optimizer with a learning rate of 0.001, and data augmentation techniques to enhance model performance. The dataset used consists of 350 images for training and 88 images for validation. Additionally, the system is designed as a web-based application to provide real time detection features and classification history. Evaluation metrics include accuracy, precision, recall, f1 score, MSE, RMSE, and MAPE. Results indicate that the developed system achieves an accuracy of 97%, MSE 0,33, RMSE 0,18, dan MAPE 1,8%.. These findings demonstrate that the system can effectively detect and classify jasmine flowers with high accuracy, enabling fast and precise identification. Future research is recommended to expand the dataset to improve the model's generalization across broader variations and explore other model architectures for performance comparison. This system is expected to provide significant contributions to education, agriculture, and plant conservation, especially in facilitating the automatic identification of jasmine flowers.
Klasterisasi Data Pendidikan Gender di Sriharjo dengan K-Means Fizram, Muhammad; Samudra, Yuda; Alfian, Zurnan
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.v9i2.30303

Abstract

Penelitian ini bertujuan untuk menganalisis distribusi tingkat pendidikan berdasarkan gender di wilayah Sriharjo menggunakan metode data mining. Data bersumber dari buku Fertility and Family Planning in Sriharjo karya Singarimbun & Manning (1974), yang memuat jumlah penduduk laki-laki dan perempuan berdasarkan kategori pendidikan. Lima kategori tingkat pendidikan dianalisis menggunakan algoritma K-Means untuk mengelompokkan data menjadi dua klaster. Hasil menunjukkan bahwa kategori “Tidak Sekolah” membentuk klaster tersendiri karena jumlah responden tertinggi (terutama perempuan). Kategori lainnya tergabung dalam klaster kedua. Penelitian ini menunjukkan adanya ketimpangan gender dalam akses pendidikan dasar serta efektivitas K-Means dalam mengungkap pola sosial.
Penelitian Klafikasi Tipe Organisasi Fadilah, Muhammad Farhan; Samudra, Yuda; Alfian, Zurnan
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.v9i2.30613

Abstract

Struktur organisasi merupakan elemen penting dalam manajemen bisnis modern buku Pengantar bisnis karya Ismail Solihin membagi struktur organisasi ke dalam dua tipe utama mekanistik dan organic artikel ini bertujuan untuk mengkaji karakteristik kelebihan kekurangan serta relevansi masing-masing tipe organisasi dalam konteks dinamika bisnis saat ini Penelitian ini bersifat kualitatif deskriptif dengan pendekatan literatur hasil kajian menunjukkan bahwa tidak ada satu struktur ideal untuk semua kondisi pemilihan struktur organisasi harus disesuaikan dengan lingkungan bisnis teknologi dan strategi Perusahaan
ANALISIS KOMPARATIF METODE DATA MINING MULTISEKTOR PADA DATASET COVID-19, SAHAM BEI, DAN PERUSAHAAN GLOBAL Fajriansyah, Satria Nur; Pramadhan, Harsya Rafif; Safa, Alaudin; Nurfajriansyah, Dandy; Wijaya, Muhammad Subaktiar; Samudra, Yuda
JRIS : Jurnal Rekayasa Informasi Swadharma Vol 5, No 2 (2025): JURNAL JRIS EDISI JULI 2025
Publisher : Institut Teknologi dan Bisnis (ITB) Swadharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56486/jris.vol5no2.903

Abstract

The rapid advancement of information technology has significantly driven the adoption of data mining techniques across various sectors, primarily to uncover hidden patterns and support data-driven decision-making processes. This study aims to analyse and compare the effectiveness of several data mining methods—namely K-Means Clustering, Decision tree, Principal component analysis (PCA), and Bootstrapping—in processing datasets from three distinct domains: public health (COVID-19), finance (Indonesia Stock Exchange), and global business (multinational corporations). The datasets utilised include COVID-19 data sourced from Kaggle, stock data listed on the Indonesia Stock Exchange, and corporate data comprising industry classifications and revenue attributes of global companies. The methodology adopted in this research encompasses several critical phases: data preprocessing to ensure consistency and reliability; implementation of classification and clustering algorithms; and model evaluation through accuracy metrics and visual analytics. Findings indicate that the K-Means algorithm performs effectively in clustering both COVID-19 spread regions and stock data based on numerical features. The Decision tree method demonstrates strong predictive capabilities in classifying risk categories within both COVID-19 datasets and corporate profiles. PCA proves to be valuable in reducing data dimensionality while retaining essential information. Furthermore, Bootstrapping is employed to enhance the generalizability of the models, particularly in scenarios involving limited data samples. The study concludes that integrating multiple data mining approaches can yield comprehensive insights across sectors, although the level of effectiveness varies depending on the inherent characteristics of each dataset. Such a multidisciplinary and combined approach provides a robust framework for data-driven analysis and strategic decision support in diverse fields.Kemajuan pesat dalam teknologi informasi telah memperluas pemanfaatan teknik data mining di berbagai bidang, khususnya dalam mengidentifikasi pola tersembunyi dan menunjang proses pengambilan keputusan berbasis data. Penelitian ini secara khusus mengkaji dan membandingkan efektivitas empat pendekatan data mining yakni K-Means Clustering, Decision tree, Principal component analysis (PCA), dan Bootstrapping, dalam mengolah data yang berasal dari tiga sektor strategis: sektor kesehatan (terkait COVID-19), sektor keuangan (pasar saham BEI), dan sektor bisnis global (perusahaan multinasional). Dataset yang digunakan bersumber dari berbagai platform terpercaya, termasuk data COVID-19 dari Kaggle, data saham perusahaan yang terdaftar di Bursa Efek Indonesia, serta informasi perusahaan multinasional yang mencakup variabel industri dan pendapatan tahunan. Rangkaian metodologi penelitian diawali dengan proses prapengolahan data (data preprocessing) untuk memastikan kualitas dan konsistensi data, dilanjutkan dengan penerapan algoritma klasifikasi dan pengelompokan (clustering), serta evaluasi performa model menggunakan metrik akurasi dan representasi visual. Dari hasil analisis yang dilakukan, ditemukan bahwa algoritma K-Means menunjukkan performa yang baik dalam mengelompokkan wilayah berdasarkan tingkat penyebaran COVID-19 serta dalam mengklasifikasikan saham berdasarkan indikator numerik. Sementara itu, metode Decision tree terbukti efektif dalam memprediksi kategori risiko, baik dalam konteks data kesehatan maupun data korporasi multinasional. PCA turut berkontribusi signifikan dalam mereduksi dimensi data tanpa kehilangan informasi utama yang relevan. Selain itu, teknik Bootstrapping diaplikasikan untuk meningkatkan kemampuan generalisasi model, terutama saat berhadapan dengan keterbatasan jumlah data. Secara keseluruhan, temuan penelitian ini menegaskan bahwa pendekatan kombinatif dalam data mining dapat menghasilkan wawasan mendalam yang lintas sektoral, dengan efektivitas yang bergantung pada karakteristik dan struktur data yang dianalisis. Pendekatan integratif semacam ini berpotensi memperkaya pemahaman dan mendukung pengambilan keputusan strategis di berbagai domain
Rancang Bangun Alat Otomatis Pengganti dan Pengontrol Air dengan Deteksi Tingkat Kekeruhan dan PH Pada Akuarium Ikan Cupang Sitio, Sartika Lina Mulani; Nardiono; Samudra, Yuda
Telekontran : Jurnal Ilmiah Telekomunikasi, Kendali dan Elektronika Terapan Vol. 13 No. 2 (2025): TELEKONTRAN vol 13 no 2 Oktober 2025
Publisher : Program Studi Teknik Elektro, Fakultas Teknik dan Ilmu Komputer, Universitas Komputer Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/telekontran.v13i2.16690

Abstract

Water quality that is not optimally maintained can have a negative impact on the health of ornamental fish, especially Bluerim betta fish that require an aquarium environment with a certain level of acidity and turbidity of the water. The problems that are often faced by ornamental fish hobbyists are delays in changing water and difficulties in monitoring water conditions manually. This study aims to design and build an automatic water replacement and control system in betta fish aquariums with the ability to detect turbidity levels and water pH in real-time. The system uses a pH-SEN0161 sensor to measure acidity, a turbidity-SEN0189 sensor to detect turbidity in NTU units, and an SRF05 ultrasonic sensor to measure water level. The software was developed using the Arduino IDE and implemented on the Arduino ATMega2560 microcontroller as well as the NodeMCU ESP8266 for data processing and automatic control. The test was carried out for 30 days with an ideal pH standard between 6–7 and a turbidity value below 400 NTU. The test results show that the system can work optimally in replacing and controlling the water conditions of the Bluerim betta fish aquarium, thus supporting the quality of life of the fish effectively and efficiently.
Pemanfaatan Artificial Inteligence Dalam Pembuatan Video Pembelajaran di SMA Alia Islamic School Lely Panca Andriyanto; Nanang; Yuda Samudra
JURNAL ABDIMAS MADUMA Vol. 4 No. 2 (2025): Juli 2025
Publisher : English Lecturers and Teachers Association (ELTA)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52622/jam.v4i2.476

Abstract

Di era digital saat ini, pemanfaatan teknologi, khususnya Artificial Intelligence (AI), menjadi penting untuk menciptakan media pembelajaran yang efektif dan menarik. Namun, di SMA Alia Islamic School, pemanfaatan AI masih terbatas karena guru cenderung menggunakan metode konvensional dan kurang memahami teknologi digital. Kegiatan pengabdian masyarakat ini bertujuan meningkatkan kompetensi profesional guru melalui pelatihan penggunaan AI dalam pembuatan video pembelajaran. Program mencakup pengenalan konsep dasar AI dalam pendidikan, pelatihan penggunaan platform Pictory AI, serta strategi integrasi teknologi dalam pembelajaran. Metode pelatihan meliputi ceramah, diskusi interaktif, dan praktik langsung untuk memberikan pengalaman menyeluruh. Selain meningkatkan keterampilan teknis, kegiatan ini juga mendorong motivasi guru agar lebih terbuka terhadap inovasi digital. Diharapkan, pelatihan ini dapat menghasilkan peningkatan kemampuan guru dalam membuat video pembelajaran berbasis AI yang menarik dan relevan, sekaligus membangun semangat untuk mengembangkan metode pembelajaran yang inovatif. Pemanfaatan AI diharapkan mampu meningkatkan kualitas pembelajaran di SMA Alia Islamic School dan memberikan dampak positif terhadap motivasi serta pemahaman siswa dalam menerima materi ajar Kata Kunci : Artificial Intelligence; video pembelajaran: Aplikasi Pictory AI: pelatihan guru
Rancang Bangun Sistem Aplikasi Ujian Akhir Sekolah Berbasis Jaringan Client Server Menggunakan Topologi Bus Samudra, Yuda
Riau Jurnal Teknik Informatika Vol. 4 No. 2 (2025): Juli 2025
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v4i2.3415

Abstract

The implementation of the final school exam at SMK Al Amanah has so far been carried out manually using paper, which causes various problems such as wasting time, risk of losing documents, and difficulties in the process of correction and recapitulation of grades. These problems encourage the need for the application of information technology in supporting learning evaluation activities. This research aims to design and build a client-server network-based school exam system with an efficient and affordable bus topology. This system was developed to increase the effectiveness of the exam and minimize errors in the assessment process. The methods used in this study include the stages of system design, software development using the PHP programming language and MySQL database, and the implementation of local networks using a simple and cost-effective bus topology. The system consists of a single main server that manages questions and exam result data, as well as several client computers that are used by students to work on questions simultaneously. The test results show that the system can run well in a local network environment with a bus topology, where students can access the questions and take the exam simultaneously without any significant obstacles. In addition, the time of correction and recap of values becomes faster and more accurate. With this system, the exam process at SMK Al Amanah becomes more efficient, safe, and organized.
Predicting Student Academic Performance Using Learning Activity Data: A Comparative Study of Random Forest and Decision Tree Models Hidayat, Rahmat; Herwis Gultom; Samudra, Yuda
Riau Jurnal Teknik Informatika Vol. 4 No. 3 (2025): November 2025
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v4i3.4032

Abstract

This study compares the effectiveness of the Random Forest and Decision Tree algorithms in predicting students' academic performance based on learning activities. The data used included reading scores, writing scores, math scores, and demographic variables such as gender, race/ethnicity, parental level of education, lunch, and test preparation course. The research was carried out through the stages of data cleaning, training and test data sharing, model training, and evaluation using confusion matrix and accuracy, precision, recall, and F1-score metrics. The results show that Random Forest performs best with 97% accuracy, surpassing Decision Tree which has 94% accuracy. The feature importance analysis  revealed that cognitive ability—especially in the reading score, writing score, and math score features—had the greatest influence on prediction results. These findings confirm that the Random Forest model is more reliable and effective as a prediction tool in the academic decision support system to detect the potential for decline in student achievement early.
Co-Authors Amin Hidayat Amin Hidayat Fadilah, Muhammad Farhan Fajar Wahyu, Meidy Fajriansyah, Satria Nur Fizram, Muhammad Herwis Gultom Hizkia Bayu Wijaya Lely Panca Andriyanto Lely Panca Andriyanto Meidy Fajar Wahyu Nanang Nanang Nanang nanang nanang Nardiono Nurfajriansyah, Dandy Oke Hariansyah Panca Andriyanto, Lely Pramadhan, Harsya Rafif Putra Prima Suhendri, Ade Rahmat Hidayat Safa, Alaudin Sartika Lina Mulani Suryaningrat Wijaya, Muhammad Subaktiar Wiwin Winarti Zurnan Alfian