cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Fristi Riandari
Contact Email
hengkitamando26@gmail.com
Phone
+6281381251442
Journal Mail Official
hengkitamando26@gmail.com
Editorial Address
Romeby Lestari Housing Complex Blok C Number C14, North Sumatra, Indonesia
Location
Unknown,
Unknown
INDONESIA
Jurnal Mandiri IT
Published by Institute of Computer Science
ISSN : 23018984     EISSN : 28091884     DOI : https://doi.org/10.35335/mandiri
Core Subject : Science, Education,
Computer Science & IT Library & Information Science Mathematics
The Jurnal Mandiri IT is intended as a publication media to publish articles reporting the results of Computer Science and related research.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 35 Documents
 1   2   3   4 
Search results for , issue "Vol. 14 No. 1 (2025): July: Computer Science and Field." : 35 Documents clear
Comparative performance of LSTM and DNN in sentiment analysis Tampubolon, Jandri; Kusrini, Kusrini
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v13i4.403

Abstract

Understanding public sentiment toward online transportation services through social media analysis has gained increasing importance. This study provides a comparison between the effectiveness of Deep Neural Network (DNN), and Long Short-Term Memory (LSTM) models in analyzing user sentiment toward online transportation services in Indonesia using Twitter data. The dataset consists of 10,000 tweets related to Gojek, Grab, Maxim, and InDrive, collected from January to December 2023. Data preprocessing includes noise removal, case folding, tokenization, and stemming. Sentiment labeling was conducted using IndoBERTweet and manually validated. Using K-Fold Cross-Validation, both DNN and LSTM models were trained, and assessed using performance metrics such as accuration, precision, recall, and F1-score, training time, and Mean Absolute Error (MAE). The LSTM model demonstrated superior performances with accuration of 82,15%, precision of 82,21%, recall of 82,15%, specificity of 90,74%, F1-score of 82,10%, and MAE of 23,15%, compared to the DNN model which achieved an accuracy of 81,22%, precision of 81,20%, recall of 81,22%, specificity of 90,18%, F1-score of 81,12%, and MAE of 24,46%. However, DNN outperformed LSTM in training time efficiency (50,435 seconds vs. 148,765 seconds). LSTM shows significant advantages in understanding context and word relationships in sentiment analysis, while DNN offers better computational efficiency. The findings of this study can be utilized by online transportation services providers to improve service quality based on user feedback from social media.
Artificial intelligence-based hand gesture recognition for sign language interpretation Rais, M. Fazil; AlFatrah, M. Ilham; Noorta, Chadafa Zulti; Rimbawa, H.A Danang; Atturoybi, Abdurrosyid
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.395

Abstract

This paper presents an artificial intelligence-based system for real-time hand gesture recognition to support sign language interpretation for the deaf and hard-of-hearing community. The proposed system integrates computer vision techniques with deep learning models to accurately identify static hand gestures representing alphabetic signs. The MediaPipe framework is employed to detect and track hand landmarks from live video input, which are then processed and classified using a Convolutional Neural Network (CNN) model. The model is trained on a publicly available BISINDO (Bahasa Isyarat Indonesia) gesture dataset retrieved from Kaggle, comprising 312 images across 26 hand gestures captured under multiple background conditions. Preprocessing includes resizing, grayscale conversion, data augmentation, and landmark extraction with specific innovations in preprocessing techniques, such as the use of advanced data augmentation methods and landmark normalization, which significantly enhance gesture identification accuracy and model robustness. Experimental results show that the system achieves an average classification accuracy of 88.03% and maintains stable performance in real-time applications. Despite these promising results, the system exhibits limitations, including challenges with dynamic gesture recognition, background interference, and limited handling of complex hand movements, all of which can be explored in future research to improve the system’s accuracy and generalization. These findings highlight the system’s potential as an inclusive communication tool to bridge language barriers between deaf individuals and non-signers. This research contributes to the development of accessible assistive technologies by demonstrating a non-intrusive, vision-based approach to sign language interpretation. Future development may involve dynamic gesture translation, sentence-level recognition, and deployment on mobile platforms.
Determination of desalination system pricing in Penjaringan Utara subdistrict, North Jakarta using HOMER simulation Rimbawa, H. A. Danang; Nurrahman, Muhammad Irsyaad; Saragih, Gabriel Winandika
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.399

Abstract

The coastal area of Muara Angke in North Jakarta grapples with significant challenges regarding access to clean water, compounded by limited energy availability. In 2024, a desalination project utilizing reverse osmosis (RO) technology was launched to address this issue, with a capacity to produce 320 liters of clean water per hour. A key feature of this initiative is its reliance on solar energy, which offers a sustainable solution to the region’s energy constraints. However, to ensure the project's long-term viability, it is essential to conduct an economic evaluation, particularly focusing on the cost of producing the desalinated water. This cost is intricately linked to the energy required to power the reverse osmosis (RO) system. Specifically, the Cost of Energy (CoE) plays a crucial role in determining the price of the desalinated water. To assess the economic feasibility of the solar-powered desalination system, HOMER simulation software was used to model the performance of the solar power system, considering factors such as solar energy potential, system capacity, and the financial costs of the solar infrastructure, including the solar panels, inverters, and battery storage. The simulation results reveal an annual energy production of 58,900 kWh and a CoE of Rp 575.55 per kWh, which directly influences the cost of water production, resulting in a price of Rp 17.27 per liter for the desalinated water. This study highlights the essential role of renewable energy sources in ensuring the sustainability of desalination systems and emphasizes the importance of accurate cost analysis to make such systems economically viable in coastal communities like Muara Angke. By integrating RO technology with solar energy, this initiative offers a promising approach to addressing water scarcity while reducing reliance on non-renewable energy sources, ultimately providing a long-term solution to clean water access.
Optimization of quicksort algorithm for real-time data processing in IoT systems with random pivot division and tail recursion Laia, Firdaus; Wau, Ferdinand Tharorogo; Manurung, Jonson
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.401

Abstract

Real-time data processing in Internet of Things (IoT) systems requires efficient sorting algorithms to handle large and ever-increasing volumes of data. The QuickSort algorithm is often used due to its speed and efficiency, but on large pre-sorted datasets, this algorithm can experience performance degradation due to poor pivot selection and the use of regular recursion. This study aims to optimize the QuickSort algorithm through random pivot selection and the application of tail recursion to improve sorting efficiency on IoT datasets. Experiments were conducted by comparing the standard QuickSort version and the optimized version, using synthetic and real-time IoT datasets from temperature and humidity sensors. Performance evaluation was based on execution time and memory usage metrics. The results show that QuickSort with random pivot and tail recursion can reduce execution time by up to 27% and memory usage by up to 18% compared to the standard QuickSort implementation. These findings indicate that the proposed algorithm is more efficient for IoT applications that require real-time data processing, and has the potential to be applied in distributed data systems and parallel processing for large-scale scenarios.
Evaluation of free nutritious food program distribution in Tanah Sareal sub-district with ANOVA Simarmata, Dicky Daniel; Hidayati , Ajeng; Saragih, Hondor
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.402

Abstract

This study aims to evaluate The Makan Bergizi Gratis (MBG) or Free Nutritious Meal Program in Tanah Sareal Sub-district in the first quarter of 2025 by using one-way ANOVA test. The results of the analysis show that the F-statistic values for January, February, and March are 0.00044 which are all smaller than the F-critical value of 3.490, so the null hypothesis (H₀) stating that there is no significant difference in the distribution of food portions is accepted. The sample size of this study consisted of 5 schools, with data collected over a three-month period (January, February, and March). The calculated p-value for the F-statistic was 0.9996, indicating that the observed difference in meal distribution was not statistically significant. These findings suggest that the distribution of nutritious food portions in Kecamatan Tanah Sareal was relatively stable during the first quarter of 2025, with small fluctuations, but no significant variations. Although the program shows stability in distribution, further improvements in logistical aspects and coordination of distribution are recommended to ensure more equitable and timely distribution. Periodic evaluation of the program is needed to assess its efficiency and ensure that all areas in need are well served.
Hybrid clustering and supervised learning model for digital MSME segmentation Marcelina, Dona; Terttiaavini, Terttiaavini
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.404

Abstract

Digitalization became a key factor in enhancing the competitiveness of Micro, Small, and Medium Enterprises (MSMEs). However, its implementation still faced several challenges, including low levels of technology adoption and inaccurate data segmentation. This study aimed to develop a hybrid approach by combining clustering techniques and supervised learning to conduct segmentation and prediction of MSMEs based on their level of digitalization. Four clustering algorithms were tested: K-Means, Agglomerative, Gaussian Mixture Model, and HDBSCAN. The evaluation results showed that HDBSCAN outperformed the other algorithms, achieving the highest Silhouette Score (0.3501), the lowest Davies-Bouldin Index (0.9557), and the highest Calinski-Harabasz Index (132.38). The segmentation process generated three distinct clusters: Cluster 0 (Traditional – low digitalization, small revenue), Cluster 1 (Semi-Digital – moderate technology adoption, medium revenue), and Cluster 2 (Fully Digital – high technology adoption, large revenue). These cluster results were then used as labels to train six classification algorithms. Among them, XGBoost and Neural Network delivered the best performance, reaching a prediction accuracy of 98.63%. The main contribution of this study was the development of an analytical framework for data-driven segmentation and prediction of MSMEs, providing more precise, targeted, and adaptive support for national digitalization strategies.
Classification eligibility recipient BPJS in ward sendang sari using the naive bayes method Prayoga, Dio; Kurniawan, Rakhmat
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.405

Abstract

Study This done for classify eligibility BPJS recipients in the sub-district Sendang Sari with use Naive Bayes method, which is relevant in support transparency and efficiency distribution benefit guarantee social at the level sub-district. Problems main in study This is Still its use manual system in the classification process, which causes the decision-making process decision become slow, subjective and vulnerable error. Research methods involving collection of 1000 citizen data Ward Sendang Sari which consists of from attributes like type gender, employment status, ownership house, income, and amount liability. Data then through preprocessing stage, including conversion variable categorical use LabelEncoder and determination of eligibility labels based on threshold income and amount liability. Next, the data is divided into training data and test data with 80:20 ratio. Classification model built use Gaussian Naive Bayes algorithm and evaluated use confusion matrix metrics which include accuracy, precision, and recall. Evaluation results show that the model achieves accuracy of 0.97 or 97%, precision of 0.95 or 95%, and recall of 0.90 or 90%, and F1-Score of 0.93 or 93 % which to signify that this model Enough effective For classify eligibility BPJS recipients. Research This conclude that The Naive Bayes method is capable of give accurate and consistent classification, which can increase efficiency administration ward as well as speed up distribution benefit to entitled community.
Machine learning-based approach for evaluating physical fitness through motion detection Rais, M. Fazil; Chadafa Zulti Noorta; M. Ilham AlFatrah; H.A Danang Rimbawa; Fatmawati, Uvi Desi
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.406

Abstract

Physical fitness assessment is crucial for evaluating an individual's physical performance and endurance. However, traditional methods often rely on manual observation, which can lead to subjectivity and inconsistent results. This study proposes a machine learning-based approach for physical fitness evaluation through motion detection using pose estimation and exercise classification models. A quantitative method was employed to train and evaluate models for four exercise types: push-ups, sit-ups, pull-ups, and chinning. Each model was trained separately and assessed using accuracy, precision, recall, and F1-score metrics, achieving accuracies of 97.50% for push-ups, 97.67% for sit-ups, 97.00% for pull-ups, and 98.50% for chinning. The maximum error margin compared to manual counting was 2.48%. System-generated outputs were validated against manual observations using standard evaluation matrices. These findings indicate that machine learning can offer a reliable, consistent, and automated solution for physical fitness assessment, with the potential to enhance training programs, support remote fitness monitoring, and reduce human error in performance evaluation.
Portable oceanic solutions for enhanced IoT-based desalination and salt extraction (POSEIDON) Randi Agustio; Onky Prilianda Putra; Dananjaya Ariateja; Refino Maulana Hansbullah Subarkah; H. A Danang Rimbawa
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

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

Abstract

The clean water crisis remains a significant challenge in many remote areas, particularly on small islands in Indonesia where freshwater resources are limited. Desalination technology offers a promising solution; however, conventional methods often face obstacles such as high energy consumption, costly operations, and limited real-time water quality monitoring. This study aims to design and evaluate a distillation-based desalination device integrated with Internet of Things (IoT) technology, called POSEIDON. The system utilizes solar energy and heating elements to support the distillation process and is equipped with pH, TDS, ultrasonic, and water level sensors connected to the Blynk application for real-time monitoring and alert notifications. Testing was conducted over 10 hours under both daytime and nighttime conditions. Results show that the distilled water had pH values ranging from 7.01 to 7.51 and PPM values from 798 to 588.38. One-way ANOVA indicated no statistically significant variation (p > 0.05), demonstrating consistent system performance. The average volume of fresh water produced was 0.403 liters from 0.7 liters of seawater, with an average salt yield of 23.1 grams. POSEIDON exhibits good energy efficiency and portability, and it can operate at night. Nevertheless, improvements are needed in production capacity and water quality. Overall, POSEIDON presents a viable and sustainable solution to meet clean water needs in remote, water-scarce regions.
Alphabet SIBI sign language recognition using YOLOv11 for real-time gesture detection Putri, Salsabilla Azahra; Murinto, Murinto; Sunardi, Sunardi
Jurnal Mandiri IT Vol. 14 No. 1 (2025): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v14i1.408

Abstract

Modern gesture recognition systems for sign language face challenges in balancing computational efficiency and detection accuracy in complex and dynamic environments. To address this, this study proposes a SIBI alphabet recognition framework based on YOLOv11, optimized for real-time applications. The model architecture integrates a modified, efficient YOLOv11 backbone to enable accurate hand gesture feature extraction with minimal latency. A custom SIBI dataset comprising alphabet signs and essential vocabulary is used to train the model, supported by data augmentation techniques that enhance robustness against variations in position, lighting, and background. Experimental results demonstrate that the model achieves a high detection accuracy with an mAP50 of 97%, while significantly reducing computational complexity. These findings present a meaningful scientific contribution by showcasing how a lightweight yet highly accurate deep learning model can be effectively applied to sign language recognition, particularly for SIBI in the Indonesian context. From a practical standpoint, this framework offers a real-time gesture detection solution that is suitable for deployment on resource-constrained devices, making it accessible for mobile or embedded systems. The system can replace or complement traditional communication aids, especially in inclusive education, public services, and healthcare. Furthermore, the proposed method can be adapted for gesture-based interaction in other domains such as athletic training, physical education, and app-based fitness programs where accurate and real-time motion recognition is essential.

Page 1 of 4 | Total Record : 35

 1   2   3   4 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol. 14 No. 2 (2025): October: Computer Science and Field Vol. 14 No. 2 (2025): Computer Science and Field Vol. 14 No. 1 (2025): July: Computer Science and Field. Vol. 13 No. 4 (2025): April: Computer Science and Field. Vol. 13 No. 3 (2025): January: Computer Science and Field. Vol. 13 No. 2 (2024): CALL FOR PAPER !!! Scope Computer Science Vol. 13 No. 1 (2024): July: Computer Science and Field Vol. 12 No. 4 (2024): April: Computer Science and Field. Vol. 12 No. 3 (2024): January: Computer Science and Field. Vol. 12 No. 2 (2023): October: Computer Science and Field. Vol. 12 No. 1 (2023): July: Computer Science and Field. Vol. 11 No. 4 (2023): April : Computer Science and Field. Vol. 11 No. 3 (2023): January: Computer Science and Field. Vol. 11 No. 2 (2022): October: Computer Science and Field. Vol. 11 No. 1 (2022): July: Computer Science and Field. Vol. 10 No. 2 (2022): January: Computer Science and Field. Vol. 10 No. 1 (2021): July: Computer Science and Field. Vol. 9 No. 2 (2021): January: Computer Science and Field. Vol. 9 No. 1 (2020): July: Computer Science and related. Vol. 8 No. 2 (2020): January: Coputer Science and related. More Issue