Article Per Year (5 Year)
p-Index From 2020 - 2025
2.832
P-Index
This Author published in this journals
All Journal JOURNAL OF APPLIED INFORMATICS AND COMPUTING INTECOMS: Journal of Information Technology and Computer Science Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Jurnal Informatika Global Jurnal Ekonomi Manajemen Sistem Informasi Jurnal Darma Agung Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) JAPI: Jurnal Akses Pengabdian Indonesia Knowbase : International Journal of Knowledge in Database Ranah Research : Journal of Multidisciplinary Research and Development International Journal of Multidisciplinary Approach Research and Science Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics
Adi Purnama
Universitas Widyatama, Bandung, Indonesia
Agriculture, Biological Sciences & Forestry Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Health Professions Immunology & microbiology Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Nursing Public Health Social Sciences Transportation Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 19 Documents
Search

 1   2 
IoT-Based UPS Device Electricity Usage Monitoring System with MQTT Protocol Adit Oktopryadin; Adi Purnama
Journal of Applied Informatics and Computing Vol. 9 No. 4 (2025): August 2025
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v9i4.9530

Abstract

The continuity of network device operations heavily relies on stable power supply, especially in digital environments that demand uninterrupted connectivity. One commonly used solution to ensure power continuity is the Uninterruptible Power Supply (UPS). However, traditional UPS systems often lack real-time monitoring mechanisms, leaving users uninformed during the transition from main electricity to UPS power. To address this challenge, this study proposes the design of a UPS power consumption monitoring system based on the Internet of Things (IoT) using the Message Queuing Telemetry Transport (MQTT) communication protocol. The system integrates a PZEM-004T power sensor and ESP32 microcontroller to read electrical parameters such as voltage, current, and power in real-time, and displays the data through a digital dashboard built with Node-RED. The implementation results show that the system can automatically detect changes in power source status and record electrical parameters with an average error rate below 1%, both during normal grid operation and when switching to UPS power. This system is expected to serve as a practical and efficient solution for minimizing network downtime caused by power disruptions.
Implementasi Metode Balanced Scorecard dalam Pengembangan Sistem Monitoring Pencapaian Key Performance Indicator di Astra Honda Authorized Service Station (AHASS) 01403 Kautsar, Almila Aulia; Purnama, Adi
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 10, No 2 (2025): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v10i2.913

Abstract

This study develops a web-based monitoring system to evaluate the achievement of Key Performance Indicators (KPIs) for mechanics at Astra Honda Authorized Service Station 01403. The main objective is to provide an objective, measurable, and transparent performance assessment method. The system is designed using the Balanced Scorecard (BSC) framework with four perspectives: financial, customer, internal business process, and learning and growth. Indicator prioritization is carried out using the Urgency, Seriousness, and Growth (USG) method, ensuring each KPI aligns with the company’s strategic needs. The application was developed using the Waterfall model. The results show that the application can calculate KPI achievement scores, automatically recap performance data, and present visual dashboards that assist management in evaluating performance. The use of this system has proven to reduce manual input errors and accelerate data-driven decision-making. This system provides benefits in the form of more systematic and objective performance monitoring, and supports continuous improvement at AHASS 01403.
Image Segmentation for Sweet Potato Leaf Disease Detection using U-Net Syukriyah, Yenie; Purnama, Adi
International Journal of Multidisciplinary Approach Research and Science Том 3 № 03 (2025): International Journal of Multidisciplinary Approach Research and Science
Publisher : PT. Riset Press International

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59653/ijmars.v3i03.1848

Abstract

The detection and management of sweet potato leaf diseases play a vital role in ensuring sustainable crop yields and reducing agricultural losses. This study proposes an automated segmentation approach using the U-Net convolutional neural network to detect disease regions on sweet potato leaves. The dataset, consisting of leaf images and corresponding masks, underwent a structured preprocessing pipeline including resizing, normalization, and reshaping. The U-Net architecture, comprising an encoder-decoder structure with skip connections, was trained on 70% of the dataset and evaluated using accuracy, Intersection over Union (IoU), and Dice coefficient. Experimental results show that the model achieved an accuracy of 94.6%, IoU of 0.88, and a Dice coefficient of 0.92, indicating strong segmentation performance. Visual comparison between predictions and ground truth masks further confirms the model’s effectiveness in isolating disease regions. This research demonstrates the potential of U-Net as a reliable deep learning framework for plant disease detection and contributes to the development of intelligent agricultural monitoring systems.
Evaluation of Use of Linear Regression to Predict Profit, Selling Price, and Stock on HSR Wheels Platform Fauzi, Esa; Prasetyo, Bagus Alit; Purnama, Adi; Pangestu, Rizky Bagus
International Journal of Multidisciplinary Approach Research and Science Том 3 № 03 (2025): International Journal of Multidisciplinary Approach Research and Science
Publisher : PT. Riset Press International

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59653/ijmars.v3i03.1967

Abstract

In the ever-evolving digital era, the e-commerce sector faces significant challenges in efficiently managing sales, selling prices, and inventory. This study aims to evaluate the effectiveness of a linear regression model in predicting sales, selling prices, and stock levels on the HSR Wheels e-commerce platform. A quantitative method was used by analyzing daily transaction data to identify the relationship between the time variable and sales, profit, and stock. The results showed that linear regression has limitations in modeling data complexity, with low R² scores and high Mean Absolute Error (MAE) values. These findings indicate the need for more advanced predictive models, such as machine learning algorithms, to improve prediction accuracy. This research is expected to contribute to developing more efficient and relevant sales strategies for e-commerce platforms.
Implementasi Sistem Informasi Zis Berbasis Web Untuk Transparansi Di Masjid Al-Ikhlas Bandung Rahman, Atep Aulia; Purnama, Adi; Indriani; Prasetyo, Bagus Alit; Fauzi, Esa; Kusramdani, Rizky; Candimadam; Tumaruk, Andry Septian Syahputra
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol. 8 No. 4 (2025): Oktober 2025
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v8i4.3923

Abstract

Abstract: This community service activity aims to improve the transparency and efficiency of zakat, infaq, and shadaqah (ZIS) management at Al-Ikhlas Mosque, Bandung Regency, through the implementation of a web-based information system. The main problem faced by the partner was the manual and unstructured recording and reporting process, as well as the low accessibility of information for congregants. The methods used included consultation to identify needs, science and technology substitution to implement modern systems, and technical training for mosque administrators. The results showed that the administrators were able to operate the system independently, with a level of understanding reaching 93.5% with an average evaluation score of 3.74 out of 4. The developed information system supports transaction recording, financial reporting, and transparent ZIS fund distribution. Additionally, the activity produced outputs in the form of a web application, digital training modules, and technical documentation that can be used sustainably. This program contributes significantly to strengthening accountability and congregational engagement in religious social fund management. Keywords: accountability; information system; training; web application; zakat Abstrak: Kegiatan pengabdian ini bertujuan untuk meningkatkan transparansi dan efisiensi pengelolaan zakat, infaq, dan shadaqah (ZIS) di Masjid Al-Ikhlas Kab. Bandung melalui implementasi sistem informasi berbasis website. Masalah utama yang dihadapi mitra adalah proses pencatatan dan pelaporan manual yang tidak terstruktur serta rendahnya akses informasi bagi jamaah. Metode yang digunakan meliputi konsultasi untuk identifikasi kebutuhan, substitusi ipteks untuk penerapan teknologi, serta pelatihan teknis untuk pengurus masjid. Hasil kegiatan menunjukkan bahwa pengurus masjid mampu mengoperasikan sistem secara mandiri dengan tingkat pemahaman mencapai 93.5% dengan skor rata-rata evaluasi sebesar 3.74 dari 4. Sistem informasi yang dikembangkan mendukung pencatatan transaksi, pelaporan keuangan, serta transparansi distribusi dana ZIS. Selain itu, kegiatan ini menghasilkan luaran berupa aplikasi web, modul pelatihan digital, dan dokumentasi teknis yang dapat digunakan secara berkelanjutan. Kegiatan ini memberikan kontribusi nyata dalam memperkuat akuntabilitas dan keterlibatan jamaah dalam pengelolaan dana sosial keagamaan. Kata kunci: akuntabilitas; aplikasi web; pelatihan; sistem informasi; zakat
Optimasi Pengelolaan Zakat, Infaq, Dan Sadaqah (ZIS) Melalui Sistem Informasi Berbasis Single Page Application (SPA) Di DKM Masjid Riyadhul Jannah Ciwastra, Kota Bandung Purnama, Adi; Rahman, Atep Aulia; Fauzi, Esa; Prasetyo, Bagus Alit; Nuryana, Alif; Robani, Husni
JAPI (Jurnal Akses Pengabdian Indonesia) Vol 9, No 1 (2024)
Publisher : Universitas Tribhuwana Tunggadewi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33366/japi.v9i1.5775

Abstract

Pengelolaan kegiatan keagamaan seperti Zakat, Infaq, dan Sadaqah (ZIS) di DKM Masjid Riyadhul Jannah saat ini masih dilakukan secara manual, yang menimbulkan beberapa permasalahan yang signifikan. Tantangan yang dihadapi meliputi kurangnya efektivitas dalam pengawasan keuangan dan penanganan infaq, kurangnya efisiensi dalam proses administratif terkait zakat dan sadaqoh, serta risiko tinggi terkait kehilangan data yang memiliki nilai penting. Dalam era perkembangan teknologi digital yang pesat, situs web telah menjadi sarana yang relevan untuk menyimpan, mengelola, dan menyajikan data dengan akurat dan efisien. Pendekatan khusus menggunakan Single Page Application (SPA) semakin menambah keunggulan dalam menyediakan pengalaman pengguna yang lebih interaktif dan responsif. Dengan demikian, pengembangan dan implementasi SPA berbasis website menjadi solusi yang sangat diperlukan untuk mengatasi tantangan tersebut. Melalui langkah ini, diharapkan DKM Masjid Riyadhul Jannah dapat meningkatkan transparansi dan akuntabilitas keuangan, mengurangi risiko yang mungkin terjadi, serta memberikan pelayanan yang lebih efektif kepada jamaah dan masyarakat umum. Dengan adopsi teknologi informasi yang tepat, DKM Masjid Riyadhul Jannah dapat memperoleh manfaat signifikan dalam pengelolaan ZIS, menjadikannya lebih efisien dan adaptif terhadap tuntutan zaman serta memperkuat peran sosial dan spiritualnya dalam masyarakat.
Modelling Time Series Data for Stock Prices Prediction Using Bidirectional Long Short-Term Memory Syukriyah, Yenie; Purnama, Adi
Knowbase : International Journal of Knowledge in Database Vol. 4 No. 2 (2024): December 2024
Publisher : Universitas Islam Negeri Sjech M. Djamil Djambek Bukittinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30983/knowbase.v4i2.8759

Abstract

The dynamic nature of stock markets, characterized by intricate patterns and sudden fluctuations, poses significant challenges to accurate price prediction. Traditional analytical methods are often unable to capture this complexity. This requires the use of advanced techniques capable of modelling non-linear dependencies. This study aims to build a model using recurrent neural network and predict the Indonesian stock prices. PT Gudang Garam Tbk.'s (GGRM.JK) stock was selected due to its significant role in the Indonesian stock market and its contribution to national revenue through excise tax. The method used in this research involves training the BiLSTM (Bidirectional Long Short-Term Memory) model using historical stock price data with training and test data ratios of 90:10, 80:20 and 70:30 to determine the optimal configuration. The evaluation results showed that the 90:10 data ratio gave the best performance with a MAPE of 1.51%, MAE of 343.55 IDR and RMSE of 522.30 IDR. These results indicate that the BiLSTM model has high accuracy and minimal prediction errors. Further analysis showed that the model performed optimally with a batch size of 32 and higher epochs, such as 200 and 250, providing greater stability and prediction accuracy. These results demonstrate the potential of the BiLSTM model as an effective predictive tool to support strategic investment decisions, particularly for high volatility stocks. Future research is recommended to test this model on other stock data and to consider external factors to improve its generalizability.
Deteksi Penyakit Pada Daun Tanaman Ubi Jalar Menggunakan Metode Convolutional Neural Network Suhendar, Sidik; Purnama, Adi; Fauzi, Esa
Jurnal Ilmiah Informatika Global Vol. 14 No. 3
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jiig.v14i3.3478

Abstract

Sweet potatoes are the world's third most important root crop and the fourth most popular staple food in developing countries, including Indonesia. Some diseases commonly found in sweet potato leaves are early blight (identified by leaves containing batataezim) and late blight (characterized by leaves that have chlorosis). These two diseases have different symptoms and require different treatments, but a slow identification process can lead to additional costs for plant care. This research will classify image data of sweet potato diseases using the Convolutional Neural Network (CNN) method. CNN is a derivative of the Multilayer Perceptron (MLP) designed to process image data with high network depth and is often used for classification tasks. The research uses a total of 750 images divided into 3 classes: images of healthy leaves, images of leaves with chlorosis, and images of leaves containing batataezim. Each leaf class will be labeled with 250 image data, and the labeled data will be further divided into training and testing sets. From these sets, prediction data will be obtained from the testing process during the CNN model training. The training accuracy resulted in a value of 98.17%, while the testing accuracy reached 98.67%. Additionally, the resulting loss values are remarkably low, at 0.04% for training and 0.03% for testing. The research findings will provide insights into the CNN method's ability to detect diseases in sweet potato plants, potentially impacting agricultural supervision, plant disease identification, and enabling more precise decisions regarding plant care actions.
The LEACH Protocol to Improve Energy Efficiency of Wireless Sensor Networks in Smart Agriculture Purnama, Adi; Aulia Rahman, Atep; Fauzi, Esa
Jurnal Ilmiah Informatika Global Vol. 15 No. 1: April 2024
Publisher : UNIVERSITAS INDO GLOBAL MANDIRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36982/jiig.v15i1.3805

Abstract

Smart agriculture is the application of technology to improve efficiency, productivity, and sustainability in agricultural practices. However, smart agriculture systems face major challenges related to connectivity and energy management. To address connectivity issues, the Wireless Sensor Network (WSN) architecture is utilized, consisting of sensor nodes to collect and transmit sensor data wirelessly. Despite the implementation of WSN, there are still issues related to high power consumption in smart agriculture systems. This can lead to reduced battery life for each sensor node in the WSN architecture. Therefore, increasing energy efficiency is crucial to optimizing the performance of smart agriculture systems. This study proposes the use of the LEACH (Low-Energy Adaptive Clustering Hierarchy) protocol in smart agriculture to manage clusters within the WSN and reduce energy consumption in each sensor node. Experimental methods were conducted by building the WSN using the nRF24L01 as the sensor data transmitter and Arduino / Node MCU as the microcontroller. The use of the LEACH protocol aims to address energy issues. Additionally, data from each sensor is collected using the Message Queuing Telemetry Transport (MQTT) protocol to facilitate monitoring of sensor data transmission and battery power information. Test results show that the integration of the LEACH protocol into the WSN can be carried out at each stage, from Discovery-State to Steady-State, to Setup-State. These steps are aimed at significantly reducing energy consumption in sensor nodes by 13% over a 12-hour testing period. Furthermore, it can extend battery life and improve the overall system efficiency.
Co-Authors Adit Oktopryadin Alif Nuryana Atep Aulia Rahman Bagus Alit Prasetyo Benny Yustim Calvin Matulessy Candimadam Esa Fauzi Herlistiono, Iwa Ovyawan Husni Robani Huynh, Phuoc-Hai Indriani Kautsar, Almila Aulia Kusramdani, Rizky Luhur Bayuaji, Luhur Nuryana, Alif Pangestu, Rizky Bagus Robani, Husni Sriyani Violina Suharno, Mochammad Syahrindra Akbar Suhendar, Sidik Tumaruk, Andry Septian Syahputra Viddi Mardiansyah Widyanto, Adi Yan Puspitarani Yenie Syukriyah