cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ni Made Satvika Iswari
Contact Email
satvika@umn.ac.id
Phone
-
Journal Mail Official
ultimacomputing@umn.ac.id
Editorial Address
-
Location
Kota tangerang,
Banten
INDONESIA
Jurnal ULTIMA Computing
Published by Universitas Multimedia Nusantara
ISSN : 23553286     EISSN : 25494007     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Engineering
urnal ULTIMA Computing merupakan Jurnal Program Studi Sistem Komputer Universitas Multimedia Nusantara yang menyajikan artikel-artikel penelitian ilmiah dalam bidang Sistem Komputer serta isu-isu teoritis dan praktis yang terkini, mencakup komputasi, organisasi dan arsitektur komputer, programming, embedded system, sistem operasi, jaringan dan internet, integrasi sistem, serta topik lainnya di bidang Sistem Komputer. Jurnal ULTIMA Computing terbit secara berkala dua kali dalam setahun(Juni dan Desember) dan dikelola oleh Program Studi Sistem Komputer Universitas Multimedia Nusantara bekerjasama dengan UMN Press.
Arjuna Subject : -
Articles 163 Documents
 13   14   15   16   17 
Unlocking Wellness: Pionering IoT Wearable Sensor with The Smart Ring for Body Fatigue Monitoring Hadi Putri, Dewi Indriati; Irawan, Elysa Nensy; Venica, Liptia; Pratama, Hafiyyan Putra
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4172

Abstract

In this study, we present the development and implementation of a low-cost IoT wearable device, the Smart Ring, designed to monitor body fatigue levels. Fatigue, often resulting from energy-draining physical activities, can lead to serious health conditions such as heart attacks, strokes, and asthma. Current devices like smartwatches offer limited functionality in preventing fatigue by merely providing vital sign information. Our Smart Ring aims to bridge this gap by integrating advanced sensors (MAX30100 for heart rate, SpO2, and body temperature) and utilizing fuzzy logic for real-time fatigue level classification. The Smart Ring is paired with an Android application that not only tracks the user's physiological data but also issues alerts and notifications when fatigue thresholds are reached, ensuring timely intervention. The device is designed to be economical and accessible, promoting widespread adoption for better health monitoring in the Society 5.0 era. Preliminary testing with users has demonstrated the effectiveness of the Smart Ring in accurately detecting and categorizing fatigue levels during various activities, supporting its potential as a valuable tool in personal health management. Index Terms— Low-cost, IoT, wearable sensor, body fatigue, the smart ring
Six-axis Force–Torque Analysis of a Flexible-Tube Wrist for Misaligned Ports in Robotic EV Charging Rifansyah, Raihan Yusuf; Setya Budi, Agus Heri; Saputra, Hendri Maja
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4344

Abstract

This paper presents a systematic 6-axis force-torque characterization of a flexible-tube wrist for robotic electric vehicle (EV) charging under various angular misalignments. Robotic plug insertion often relies on simplified models that fail to capture the complex contact dynamics of compliant mechanisms, limiting system robustness. To address this, we developed an experimental platform based on a cartesian robot with a roll–pitch–yaw wrist to measure full force–torque profiles during quasi-static insertions with controlled misalignments ranging from −8° to +8° in pitch and yaw. The results reveal a highly non-linear and asymmetric response, quantitatively demonstrated by a contact onset that shifts from a maximum depth of 45.8 mm at 0° to as early as 31.8 mm at +8° yaw, and peak axial forces reaching -18 N in pitch and -24 N in yaw. This asymmetry has practical implication, where a -5-degree pitch resulted in insertion failure while an equivalent +5-degree was successful. From this dataset, unique and repeatable force signatures were identified for each condition, providing a foundational basis for hybrid control strategies with force sensing to handle the final delicate insertion
IoT-Based Fire Detection System Using a Flame Detector and Arduino Uno R4 WiFi Dewi, Ratih; Fadhliansyah, Ivan; Ma'rufi, Riado; Lubis, Dwiki Ar-Raiyyan
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4347

Abstract

According to data from the DORS POLRI application, there were 935 fire incidents recorded from January to October 7, 2024. Based on these data, a fire detection security system with early warning capabilities is needed to mitigate fire risks and prevent casualties. The system designed in this study is IoT-based, which sends notifications via Telegram when a fire is detected.The results of this research show that by reducing the sensor sensitivity to 33%, the sensor still performs well in detecting fire — it can detect a flame at a distance of 35 cm and detect light from an incandescent bulb at approximately 95 cm. However, the sensor cannot detect paraffin flames at distances of 10–50 cm because the paraffin flame’s wavelength lies outside the detectable range of the sensor.Thus, this system has proven effective in detecting fire and providing real-time automatic notifications via Telegram, allowing users to respond quickly when potential fire hazards occur.
Convolutional Neural Network Roasted Coffee Bean Classification Based on Color Hanes, Natanael; Wulandari, Meirista; Setyaningsih, Endah
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4351

Abstract

Coffee quality is significantly influenced by the roasting level, which is commonly determined by the color of the beans. Traditional classification methods rely on manual sorting and human judgment, making the process labor-intensive, subjective, and prone to error. To address these limitations, this project proposes a deep learning-based coffee bean classification system using Convolutional Neural Networks (CNNs). CNNs, known for their strong performance in image recognition, can analyze visual features like color, texture, and shape to automatically classify coffee beans based on roast level. The system is evaluated using metrics such as accuracy, precision, recall, and F1 score. Among the tested input sizes, the CNN model performs best at 64×64 pixels, achieving a peak accuracy of 99% with minimal misclassifications. This result highlights the model’s effectiveness in delivering high classification performance while maintaining computational efficiency, even with low-resolution images.
Implementation of Trajectory Tracking on Mobile Robot Differential Drive Imam Taufiqurrahman; Sujarwanto, Eko; Andri Ulus Rahayu; Mira Riski Aldiani; Sayyid Qhutub Abdul Hakim
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4413

Abstract

Abstract—This study discusses the implementation of trajectory tracking on a differential drive mobile robot using the odometry method. The system was designed by utilizing rotary encoders to estimate the robot’s position and a proportional controller to regulate movement toward the target point. Experiments were carried out on multi-point trajectories, namely three-way and four-way paths, under two different surface conditions: flat and textured fields. The results showed that the robot was able to follow the predetermined path with a relatively high level of accuracy, especially on flat surfaces. However, on textured paths, the accuracy decreased due to wheel slip and disturbances in encoder readings. The comparison between both conditions emphasizes that surface characteristics have a significant influence on the performance of odometry-based trajectory tracking. Keyword — Mobile robot, differential drive, odometry, trajectory tracking, proportional control
Development of a Dimming and Color Automation System Based on a Microcontroller-Based Dynamic Lighting Scheme Salehuddin, Muhammad; Bagus Adli Pangestu; Cindy Cornelia; Danial Irfachsyad
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4462

Abstract

Office buildings in urban areas are most likely situated and clustered close to one another, which can impede the penetration of natural sunlight. In contrast, artificial lighting maintains constant intensity and color throughout the day. This paper proposes a strategy to address these limitations by incorporating dynamic lighting systems that automatically adjust the light intensity and color. At this development stage, an IoT-based microcontroller device is deployed. The data collected will be processed and displayed on a web page, providing a monitoring tool for light intensity in the work area. This system's dimming and color adjustment features will be tailored to dynamic lighting characteristics. By conducting laboratory-scale trials using the system design that has been made, it is estimated that 1 lamp can save 17% of electric power compared to if the lamp is lit at maximum conditions continuously.
Predictive Control of Speed, Steering, and Braking For an Autonomous Car on Uphill and Downhill Road Aditya, Ryan; Santoso, Ari
ULTIMA Computing Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v17i2.4474

Abstract

Countries around the world have roads that go through mountains and hills. These roads can have features such as winding and change of elevation. When passing through such roads, the car’s dynamics are influenced by the unknown elevations and curvatures, which can threaten stability if not properly controlled. The purpose of this research is to control the cars longitudinal speed through acceleration, braking through regenerative braking and maintain lateral control through steering inputs. The proposed control system consists of a high-level predictive controller which predicts the car’s dynamics under varying road condition and a low-level Fuzzy-PID controller for the actuators, which is motor driver and electric power steering. Additionally, the energy recovery from the regenerative braking system is monitored to evaluate its impact on battery state of charge, especially when the car is slowing down or going through downhill roads. The control system proposed aims to maintain speed and steering stability under varying road conditions and improve energy efficiency.
Controlling and Monitoring Milk Pasteurization using Fuzzy Logic integrated with the Internet of Things (IoT) Lisa Yihaa Roodhiyah; Nashrullah Afif Zuhma
ULTIMA Computing Vol 18 No 1 (2026): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v18i1.4547

Abstract

Precise temperature control in nonlinear thermal processes with fluctuating conditions remains a challenge for traditional control methods. This research presents a Mamdani-type fuzzy logic control system integrated with an IoT architecture for milk pasteurization using the Low-Temperature Long-Time (LTLT) method, which is widely used in Indonesia for small-scale dairy production. The controller takes milk temperature and volume as linguistic inputs and outputs a continuous PWM signal to regulate heater power. Unlike traditional on–off systems or model-based PID controllers, this fuzzy logic approach does not rely on an explicit mathematical model and remains effective across different milk volumes without retuning. Experiments with 3 L, 5 L, and 8 L of milk show that the controller keeps temperatures close to the 64°C target, with averages of 64.11°C, 64.07°C, and 64.03°C, respectively. Max overshoot is limited to 1.56%, 0.29%, and 0.19%, while high-temperature stability is demonstrated by standard deviations of 0.26, 0.08, and 0.12, indicating robustness. Furthermore, it functions at a lower average PWM duty cycle compared to on–off control, leading to smoother operation and improved efficiency. This system can handle nonlinear thermal processes with varying loads and is supported by real-time IoT connectivity monitoring.
Early Detection of Non-Melanoma Skin Lesions: A ResNet50 and SVM-Based Deep Learning Approach Ray Louie D’Angelito; Josephine Larissa Rachmadiana; Muhammad Nur Rohman; Timothy Wirjantoro Harjanto; I Nyoman Julian Sanjaya; Yuri Pamungkas
ULTIMA Computing Vol 18 No 1 (2026): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v18i1.4634

Abstract

This study presents a computer-aided detection method for these skin conditions by employing deep learning techniques, specifically a ResNet50-based Convolutional Neural Network (CNN), alongside a Support Vector Machine (SVM) classifier. The aim is to improve diagnostic accuracy and accessibility through image data processing and feature extraction. The main contribution of this research is the application of deep learning for automated classification of non-melanoma skin lesions, with the goal of enhancing early detection. The models were trained and evaluated using the International Skin Imaging Collaboration (ISIC) dataset, with two test scenarios to assess their performance. In Test 4, the CNN demonstrated superior results, achieving F1-scores of 44.70% for actinic keratosis, 85.25% for dermatofibroma, 78.76% for nevus, and a perfect 100.00% for vascular lesion. In comparison, the SVM model achieved lower F1-scores: 21.88% for actinic keratosis, 27.91% for dermatofibroma, 62.46% for nevus, and 70.58% for vascular lesion. The results highlight the effectiveness of deep learning, particularly CNNs, in automated dermatological diagnosis. These findings lay the groundwork for future web and mobile applications that could support early skin cancer detection and clinical decision-making.
Feature Selection Benchmarks for Breast Cancer Diagnosis: A Comparative Machine Learning Study R. Rossa Alfi Nur; Nashir Abbas Husaini; Moch. Arjunnaja; Az-Zahra Batrisyia Juniarto; Yuri Pamungkas
ULTIMA Computing Vol 18 No 1 (2026): Ultima Computing: Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v18i1.4636

Abstract

Breast cancer remains one of the most common causes of death among women, making early and precise detection essential. Yet conventional diagnosis can be limited by specialist shortages, cost, and slow workflows. We therefore assess machine-learning classification with feature selection to streamline diagnosis. Our contribution is a comparative benchmark of feature-selection strategies and classifiers on the WDBC dataset. We evaluated five models (SVM, neural-networks, decision tree, bagged-tree, and boosted-tree). Chi2, mRMR, and ReliefF selected 5, 10, 15, and 30 features, and performance was measured across multiple train–test splits using accuracy, precision, recall, specificity, and F1-score. SVM was overall the top performer and stable across splits. The best SVM setting reached 97.81% accuracy, with strong precision and F1-score, indicating reliable benign–malignant separation. Neural-networks usually ranked second but were more sensitive to the split. Bagged trees generally improved on a single decision tree, while boosted trees showed mixed gains depending on the subset. ReliefF and mRMR often matched or exceeded Chi2 with smaller subsets, showing that careful feature reduction can retain accuracy while lowering dimensionality. In conclusion, combining effective feature selection with an appropriate classifier improves breast cancer classification, and SVM with a compact feature set is a practical choice.

Page 16 of 17 | Total Record : 163

 13   14   15   16   17 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol 18 No 1 (2026): Ultima Computing: Jurnal Sistem Komputer Vol 17 No 2 (2025): Ultima Computing: Jurnal Sistem Komputer Vol 17 No 1 (2025): Ultima Computing: Jurnal Sistem Komputer Vol 16 No 2 (2024): Ultima Computing : Jurnal Sistem Komputer Vol 16 No 1 (2024): Ultima Computing : Jurnal Sistem Komputer Vol 15 No 2 (2023): Ultima Computing : Jurnal Sistem Komputer Vol 15 No 1 (2023): Ultima Computing : Jurnal Sistem Komputer Vol 14 No 2 (2022): Ultima Computing : Jurnal Sistem Komputer Vol 14 No 1 (2022): Ultima Computing : Jurnal Sistem Komputer Vol 13 No 2 (2021): Ultima Computing : Jurnal Sistem Komputer Vol 13 No 1 (2021): Ultima Computing : Jurnal Sistem Komputer Vol 12 No 2 (2020): Ultima Computing : Jurnal Sistem Komputer Vol 12 No 1 (2020): Ultima Computing : Jurnal Sistem Komputer Vol 11 No 2 (2019): Ultima Computing : Jurnal Sistem Komputer Vol 11 No 1 (2019): Ultima Computing : Jurnal Sistem Komputer Vol 10 No 2 (2018): Ultima Computing : Jurnal Sistem Komputer Vol 10 No 1 (2018): Ultima Computing : Jurnal Sistem Komputer Vol 9 No 2 (2017): Ultima Computing : Jurnal Sistem Komputer Vol 9 No 1 (2017): Ultima Computing : Jurnal Sistem Komputer Vol 7 No 2 (2015): Ultima Computing : Jurnal Sistem Komputer Vol 7 No 1 (2015): Ultima Computing : Jurnal Sistem Komputer Vol 6 No 1 (2014): Ultima Computing : Jurnal Sistem Komputer Vol 5 No 1 (2013): Ultima Computing : Jurnal Sistem Komputer More Issue