Article Per Year (5 Year)
p-Index From 2021 - 2026
2.727
P-Index
This Author published in this journals
All Journal Jurnal Buana Informatika Journal of Telematics and Informatics Sistemasi: Jurnal Sistem Informasi Indonesian Journal of Information System JURTEKSI JOURNAL OF SCIENCE AND SOCIAL RESEARCH J-Com (Journal of Computer) JoDENS: Journal of Digital Ecosystem for Natural Sustainability Al'Adzkiya International of Computer Science and Information Technology Journal Journal of Information Technology
Raymond Erz Saragih
Universitas Universal
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Social Sciences

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
Integrating Design Thinking and CBT for Mobile Telemedicine Depression Recovery Therapy for Adolescents and Women Steffi Adam; Raymond Erz Saragih; Azizah Nur Arifah Awali
SISTEMASI Vol 15, No 3 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i3.5776

Abstract

Depression among adolescents and women has become a significant mental health issue, yet access to effective therapy remains limited due to factors such as geographical barriers and a lack of professional support. This research aims to integrate Design Thinking and Cognitive Behavioral Therapy (CBT) to develop a mobile telemedicine application, Moelih, for supporting the recovery of depression. The study employs a systematic Design Thinking approach, including Empathy, Define, Ideate, Prototype, and Test stages. The black-box testing method was employed to evaluate the app’s functionalities, ensuring that its features—such as mood tracking, journaling (both free and guided CBT), and teleconsulting with professional companions—are intuitive and effective from the user’s perspective. The results demonstrate that the Moelih app successfully meets the needs of its target audience by providing an accessible, flexible, and user-centered digital therapy tool. However, the testing phase revealed areas for improvement, such as enhancing user engagement and optimizing app responsiveness. This research highlights the potential of combining user-centered design and CBT to create effective digital interventions for mental health recovery, contributing to the growing field of telemedicine for mental health.
Mango and Banana Ripeness Detection based on Lightweight YOLOv8 Raymond Erz Saragih; Akhmad Rezki Purnajaya; Ilwan Syafrinal; Yonky Pernando; Yodi
Jurnal Buana Informatika Vol. 15 No. 2 (2024): Jurnal Buana Informatika, Volume 15, Nomor 02, Oktober 2024
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v15i2.8895

Abstract

Fruits like bananas and mangoes are harvested after reaching a specific ripeness stage. Traditionally, farmers rely on manual inspection to determine ripeness, a process that can be tedious, time-consuming, expensive, and subjective. This work proposes an automatic bananas and mangoes ripeness detector utilizing computer vision technology. The detected bananas and mangoes fall into two classes: ripe and unripe. The state-of-the-art YOLOv8 architecture serves as the core of the detector. Three YOLOv8 variants, YOLOv8n, YOLOv8s, and YOLOv8m, were investigated for their performance. Results show that YOLOv8s achieved the highest overall performance, 0.9991 recall, and a mean Average Precision (mAP) of 0.8897. While YOLOv8m achieved the highest precision of 0.9995, YOLOv8n is the most miniature model, making it suitable for deployment on devices with limited resources.
Monitoring Expiration and Beyond-Use Dates of Non-Compounded Drugs Through Rule-Based and Machine Learning Approaches Marfuah Marfuah; Masparudin Masparudin; Raymond Erz Saragih
Al'adzkiya International of Computer Science and Information Technology (AIoCSIT) Journal Vol 7, No 1 (2026)
Publisher : Al'Adzkiya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55311/aiocsit.v7i1.392

Abstract

Public knowledge regarding the time limit for drug usage is still limited, despite existing educational efforts. Many people rely solely on the Expiration Date (ED) stated on the primary packaging, which indicates the post-production shelf life. However, once the packaging is opened, the usage limit no longer refers to the ED, but instead to the Beyond Use Date (BUD), which depends on the drug type, time, form, aroma, and color. The application of a Rule-Based Expert System, through a series of IF-THEN rules and machine learning. Three methods were used: decision tree (DT), Gaussian Naive Bayes (GBN), and K-Nearest Neighbor (KNN). The results showed that the decision tree method (95%), the GBN method (94%), and the KNN method (81%) can assist in monitoring drug use limits, minimizing losses, and enhancing user awareness and compliance to prevent medication errors.
Monitoring A Nutrient Film Technique (NFT) Hydroponic System For Nutrient Delivery To Bokchoy Plants Jaswin; Muhammad Khaerul Naim Mursalim; Raymond Erz Saragih
Journal of Digital Ecosystem for Natural Sustainability Vol 6 No 1 (2026): Juli 2026
Publisher : Fakultas Komputer - Universitas Universal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63643/jodens.v6i1.375

Abstract

A small-scale Nutrient Film Technique (NFT) hydroponic system requires continuous monitoring because it strongly depends on nutrient solution flow, water availability, and the stability of operational parameters. Manual monitoring is often less effective because system disturbances may be detected too late by users. This study aims to design, implement, and test an Internet of Things (IoT)-based NFT hydroponic monitoring and automatic nutrient dosing system prototype capable of displaying data, storing monitoring history, providing warnings during abnormal conditions, and automatically dosing nutrient solution based on sensor readings. The method used is prototyping. The prototype integrates an NFT hydroponic system, IoT devices, Firebase, a web dashboard, Telegram notifications, an automatic nutrient dosing system, and supporting actuators. Test results show that the system is able to read and transmit monitoring data, display information on the dashboard, store historical data, and classify system conditions into normal, warning, and critical statuses based on predetermined thresholds. The system also successfully provides warnings through the dashboard, Telegram, and a local alarm when abnormal conditions are detected. The automatic nutrient dosing system, implemented using two G328 peristaltic pumps controlled via PID-based logic in response to TDS sensor readings, was successfully integrated and functioned as intended.
ArachnoSAR_A Quadruped Spider Robot Prototype with Haar Cascade-Based Face Detection to Support Search and Rescue Operations James Lim; Eril Sanjaya; Fernando; Augustian Gautama; Tino Winata Sumarno; Canniago Verrian; Andi Saputra; Agus Suwandi; Raymond Erz Saragih
Journal of Digital Ecosystem for Natural Sustainability Vol 6 No 1 (2026): Juli 2026
Publisher : Fakultas Komputer - Universitas Universal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63643/jodens.v6i1.386

Abstract

Search and rescue (SAR) operations often require access to areas that are hazardous or unreachable for human rescuers. This study developed ArachnoSAR, a low-cost four-legged (quadruped) spider robot prototype that integrates legged locomotion, camera-based human detection, and automatic notification. The robot is driven by eight SG90 servo motors controlled by an ESP32, while a Raspberry Pi processes the camera stream using a Haar Cascade classifier and sends detection photographs to a Telegram bot, accompanied by a buzzer alert. Preliminary indoor testing showed that the system detected frontal faces at distances of up to 300 cm at 12 to 17 frames per second, while locomotion tests recorded speeds of 0.55 cm/s on ceramic and 1.36 cm/s on asphalt surfaces, with an estimated operating time of about 51 minutes. Identified limitations include the requirement for frontal face orientation, sensitivity to low lighting, motion blur, and dependence on internet connectivity for notification. These results indicate that the prototype is feasible as a proof of concept, while highlighting the need for image stabilization, deep learning based detection, and offline communication for real SAR deployment.
Performance Analysis of YOLO11 for Welding Defect Detection Under Low-Light Conditions Yonky Pernando; Raymond Erz Saragih; Masparudin Masparudin; Agus Suwandi; Ihsan Verdian; Fazlul Rahman; Ilwan Syafrinal
Al'adzkiya International of Computer Science and Information Technology (AIoCSIT) Journal Vol 7, No 1 (2026)
Publisher : Al'Adzkiya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55311/aiocsit.v7i1.370

Abstract

This study aims to analyze the impact of image enhancement techniques on welding defect detection performance using a deep learning-based YOLO11L model. The dataset consists of 1392 welding images categorized into four classes: Good, Crack, Porosity, and Bad, with a significant class imbalance. Five image enhancement methods were evaluated, namely Zero-DCE, RETINEX, CLAHE, Supervision, and Gamma Correction, and compared against a no-enhancement baseline. Image quality was assessed using SSIM, and PSNR, while detection performance was evaluated using Precision, Recall, F1-Score, and mAP50. The results show that Gamma Correction achieves the best image quality improvement, with an average SSIM of 0.569, and a PSNR of 18.862 dB. However, contrasting results are observed at the detection stage, where 0.7772 and 0.6969, respectively, for the Gamma Correction-based model while for the baseline model without enhancement outperforms the enhanced model, achieving a mAP50 of 0.7098 and an F1-Score of 0.6965. This finding reveals a paradox where improved visual image quality does not necessarily lead to better object detection performance. This study highlights the importance of end-to-end evaluation in computer vision systems, particularly in industrial inspection applications, and demonstrates that original images, which are closer to the pretrained data distribution, may yield better detection results than heavily enhanced images.
Co-Authors Abdullah Abdullah Adam, Steffi Agus Suwandi Agus Suwandi Akhmad Rezki Purnajaya Andi Saputra Anton, Oey Anuari, Nong Augustian Gautama Azizah Nur Arifah Awali Budi Yanto Canniago Verrian Cecillia, Febby David Chow Eril Sanjaya Fazlul Rahman Fernando Ferry Govert Anwar Hendry . Husin, Husna Sarirah Ihsan Verdian Ilwan Syafrinal Ilwan Syafrinal Ilwan Syafrinal James Lim Jaswin Kaharuddin Kaleb Yefune Sun Kurniawan, Ade lustini Marfuah, Marfuah Masparudin Masparudin Masparudin, Masparudin MUHAMMAD KHAERUL NAIM MURSALIM Muhammad Naufal, Muhammad oktavia, sanni Pernando, Yonky Purnajaya, Akhmad Rezki Quynh Huong To Satyawira, Ryan Suwandi, Agus Tino Winata Sumarno Tony Lau Verdian, Ihsan Victor Winda Andrini Wulandari Yodi Yodi Yuni Roza Yuni Roza