Claim Missing Document
Check
Articles

Found 15 Documents
Search

Klasifikasi Mata Katarak dan Mata Normal Menggunakan Algoritma Dasar Convolutional Neural Network (CNN) Swengky, Better; Wathan, M Hizbul; Irawan, Indra; Aulia, Rosaura
Jurnal Pengembangan Sistem Informasi dan Informatika Vol. 6 No. 3 (2025): Jurnal Pengembangan Sistem Informasi dan Informatika
Publisher : Training & Research Institute - Jeramba Ilmu Sukses

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47747/jpsii.v6i3.2758

Abstract

Eye diseases encompass a wide range of conditions, from mild visual impairments to complete blindness, with cataracts being one of the leading causes. Despite advances in medical imaging, automated classification of cataract versus normal eye images remains a challenging task. This study proposes a classification method using a Convolutional Neural Network (CNN) to distinguish between cataract-affected eyes and normal eyes accurately. The approach involves collecting and preprocessing a labeled dataset, extracting features such as color and vein patterns (including average RGB values), and training the CNN model with optimized parameters. Experimental results demonstrate that the proposed model achieves a high classification accuracy of 95.1%. These findings indicate that CNN-based image classification is a promising tool for supporting automated cataract detection and early diagnosis
InfusCare: Smart Infusion Monitoring System with Real-Time Notifications via ESP32 and Blynk Wathan, M Hizbul; Irawan, Indra; Swengky, Better; Cahyadi, Irsan
Jurnal Pengembangan Sistem Informasi dan Informatika Vol. 6 No. 3 (2025): Jurnal Pengembangan Sistem Informasi dan Informatika
Publisher : Training & Research Institute - Jeramba Ilmu Sukses

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47747/jpsii.v6i3.2759

Abstract

Manual infusion monitoring in medical settings can lead to errors and delays in care steps that can put patients at risk. Internet of Things (IoT) technology provides a solution that enhances the accuracy and efficiency of real-time infusion monitoring. This study develops an IoT-based infusion monitoring system with the HX711 module and ESP32 microcontroller, using a connected load cell sensor as a monitoring interface through the Blynk application. This system can accurately measure the volume of infusion fluid and provide automatic notifications when the fluid volume approaches the minimum limit. Tests were conducted with infusion fluid simulation, load cell sensor calibration, and system calibration integration testing. The test results indicate that the system can display data on fluid weight in real time with an accuracy level of 98.5%, and when the fluid volume reaches 1 second in average response time, you can send notifications at the right time. Therefore, this system is expected to be implemented in various medical facilities as a solution for patient safety and the effectiveness of infusion care, as well as for automatic and reliable infusion monitoring.
Tomato Ripeness Identification Using Recurrent Neural Network Algorithm Hamdani, Dede; Wathan, M.Hizbul
International Journal of Informatics Engineering and Computing Vol. 1 No. 2 (2024): International Journal of Informatics Engineering and Computing
Publisher : ASTEEC

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70687/ijimatic.v1.i2.43

Abstract

Tomatoes undergo distinct ripeness stages, typically categorized into ripe, semi-ripe, and unripe phases. Traditional methods for assessing ripeness often face challenges in accuracy due to difficulties in comparing variables and subjective interpretations. This study proposes an innovative approach to classify tomato ripeness using a dataset of 200 tomato images and employs a Recurrent Neural Network (RNN) for precise classification. The experimental results demonstrate that the RNN-based model achieves a 95.0% accuracy rate in identifying ripeness stages, significantly outperforming conventional methods. This high level of accuracy highlights the model's potential to minimize errors and provide reliable assessments of tomato maturity. The proposed method offers a robust and efficient solution for agricultural applications, enabling improved quality control and harvest timing. Future research could explore the integration of additional data sources or advanced machine learning techniques to further enhance the model's performance and applicability across diverse agricultural contexts.
EFEKTIVITAS PENERAPAN SISTEM ABSENSI GURU BERBASIS GEOLOKASI MENGGUNAKAN METODE FEATURE DRIVEN DEVELOPMENT (FDD) DI SMP NEGERI 2 RIAU SILIP deswita, deswita; Irwan; Wathan, M Hizbul
KHARISMA Tech Vol 20 No 2 (2025): KHARISMATech Journal
Publisher : STMIK KHARISMA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55645/kharismatech.v20i2.645

Abstract

The supervision of teacher attendance plays a crucial role in ensuring the smooth implementation of the learning process. However, the manual attendance system used at SMP Negeri 2 Riau Silip often leads to recording errors, time inefficiency, and data manipulation. This study aims to implement and evaluate the effectiveness of a teacher attendance system based on geolocation using the Feature Driven Development (FDD) method. The system was developed with the Flutter framework for the mobile application and Laravel for the backend, integrated through an API and supported by a MySQL database. The main features include GPS-based attendance validation, photo-based activity verification, attendance history, and real-time monitoring by administrators. The development process followed five stages of FDD, ensuring a structured and feature-oriented approach. System testing using black box testing and User Acceptance Testing (UAT) resulted in an average feasibility score of 89.73%, categorized as highly feasible. The results indicate that the implementation of the geolocation-based attendance system effectively improves efficiency, accuracy, and transparency in managing teacher attendance at SMP Negeri 2 Riau Silip.
Design and Development of a QR Code-Based Ordering System and Mobile Cashier Application at Rumah Seduh Coffee Shop Fadhilah, Indirokan; Rindri, Yang Agita; Wathan, M. Hizbul
KHARISMA Tech Vol 20 No 2 (2025): KHARISMATech Journal
Publisher : STMIK KHARISMA Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55645/kharismatech.v20i2.636

Abstract

This research was carried out with the aim of designing and developing a QR Code–based ordering system integrated with a mobile cashier application at Warung Kopi Rumah Seduh. The previously manual process created several issues, including long queues, delayed service, and frequent transaction recording errors that disrupted operational efficiency. To address these challenges, a digital system was introduced that allows customers to place orders independently by scanning a QR Code, with the orders being automatically recorded in the cashier system. The mobile cashier application supports real-time order processing, transaction management, and structured sales data storage. The system was developed using a prototyping approach, beginning with requirements analysis through field observations and user interviews. The implementation results demonstrate that this solution improves service efficiency, accelerates the ordering process, reduces input errors, and enhances the organization of sales data. Ultimately, this study is expected to provide practical contributions for MSMEs in adapting to the challenges of service digitalization.