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 187 Documents
 15   16   17   18   19 
Design and construction of telegram bot-based data breach preprocessing application for cyber threat intelligence in institution x Gandhara, Seto; Satria, Tegar Pandu; 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.v14i1.413

Abstract

Data breaches pose a significant threat in today's digital landscape, especially for organizations handling sensitive information, such as government institutions. These incidents can result in serious consequences, including risks to national security, loss of public trust, and financial harm. Institution X, an Indonesian organization dedicated to cyber threat prevention, faces challenges due to the high volume of unstructured and "dirty" leaked data, often shared via hidden platforms like the dark web and Telegram. To address this issue, a Telegram bot-based application was designed and developed using the Rapid Application Development (RAD) method. The application automates data collection, cleaning, and preprocessing, with features such as keyword-based search and CSV file conversion. It was built using Python and deployed through the Replit cloud platform, utilizing the Telebot library to interact with Telegram APIs. Internal testing covered six usage scenarios, including keyword processing, multi-file handling, and unauthorized access control, with all scenarios producing successful outcomes. The application significantly improves the CSIRT team's effectiveness and efficiency in responding to cyber threats. The results confirm the system’s readiness for operational deployment and its potential contribution to enhancing cyber threat intelligence for Institution X and other government agencies.
Hybrid CRITIC–VIKOR method for objective-based component selection in ICT infrastructure planning for university laboratory systems Pratiwi, Merina; Syarief, Amiroel Oemara
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.v14i1.415

Abstract

Selecting appropriate hardware materials is a critical aspect in planning computer laboratory infrastructure at higher education institutions, aiming to support effective technology-based learning. This study aims to evaluate and identify the optimal hardware material alternatives by applying an integrated CRITIC–VIKOR approach to multi-criteria decision making (MCDM). The CRITIC method is employed to determine objective weights for each criterion based on standard deviation and inter-criteria correlation, while the VIKOR method is used to rank the alternatives through a compromise solution approach. Nine hardware material alternatives including types of casings, cooling systems, and cables were assessed against five key criteria: cost, durability, energy efficiency, compatibility, and availability. The analysis results show that Energy Efficiency had the highest objective weight (0,260563785), followed by Durability (0,234238828) and Availability (0,211419693). Based on the compromise index (Q), the best alternatives in each category were Steel Casing (Q = 0,059737547), Liquid Cooler (Q = 0,350101862), and Braided Cable (Q = 0.0000). These findings demonstrate that the integrated CRITIC–VIKOR method effectively produces objective and balanced evaluations. This model may serve as a strategic decision-making tool for higher education institutions in the procurement of computer laboratory hardware based on data-driven considerations.
Fetal heart chamber segmentation on fetal echocardiography image using deep learning Sutarno, Sutarno; Rachmatullah, Muhammad Naufal; Abdurahman; Isnanto, Rahmat Fadli
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.v14i1.416

Abstract

Advances in medical imaging and utilization have encouraged the development of more sophisticated image analysis technologies. In this context, image segmentation acts as a fundamental preprocessing step, but fetal echocardiography (FE) image segmentation still faces challenges in terms of accuracy and efficiency. The dataset for developing the FE image segmentation model was obtained from the examination results of patients at Muhammad Husein Hospital (RSMH) in Palembang who had normal conditions, atrial septal defect (ASD), ventricular septal defect (VSD), and atrioventricular septal defect (AVSD), totaling 650 FE images, which have been verified by experts. Compared to previous studies, this study focuses on creating a DL-based segmentation model for FE images using an open-source framework and the Python MIScnn library, which is specifically designed for medical imaging. This differs from previous DL frameworks that are more general, such as TensorFlow or PyTorch, which do not emphasize specialization for medical imaging. Furthermore, in an effort to improve model accuracy and efficiency, various configurations were tested, including variations in batch size and loss functions. the Model performance evaluation was conducted comprehensively using various important metrics in addition to pixel accuracy and IoU, such as F1 score, average accuracy, precision, recall, and False Positive Rate (FPR). This method is expected to provide a more in-depth picture of model performance compared to previous studies that may have only considered a few metrics. The best results were achieved using the U-Net architecture with a batch size of 32 and the binary cross-entropy loss function. This U-Net model demonstrated excellent overall performance, achieving a pixel accuracy of 0.996, an IoU of 0.995, a mean accuracy of 0.965, an FPR of 0.004, a precision of 0.929, a recall of 0.933, and an F1-score of 0.941. These findings highlight the significant potential of deep learning methods in improving the accuracy and efficiency of fetal echocardiography image analysis.
Application of fuzzy time series method to determine medical equipment inventory Iskandar, Rozai; Furqan, Mhd.
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.v14i1.417

Abstract

This study applied the Fuzzy Time Series (FTS) method to forecast monthly stock requirements for medical equipment at PT. Karya Metropolis. The FTS process including interval determination, fuzzification, fuzzy rule formation, and defuzzification successfully identified historical patterns in sales data and produced predictions closely aligned with actual values. Forecast results indicated the next month’s needs for several items, such as 154.5 units of gauze rolls, 129 units of leukocrepe, 26.5 units of hypafix, 25 liters of 95% alcohol, 487.5 oxygen nebulizer masks, 109.5 units of Vaseline swabs, and 61 Maxter gloves. Forecast accuracy was assessed using Mean Absolute Percentage Error (MAPE), where most items showed low error rates, including gauze rolls (6.16%), Vaseline swabs (7.21%), and Maxter gloves (9.28%). However, the oxygen nebulizer mask showed a higher MAPE value of 47.28%, indicating a need for method refinement or integration with other approaches for that item. Overall, the FTS method proved effective in supporting accurate, efficient, and measurable stock planning decisions for medical supplies.
K-Means clustering analysis of public satisfaction with 50% electricity tariff reduction Harahap, Muhammad Fitrah Affandi; Hasugian, Abdul Halim
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.v14i1.418

Abstract

At the beginning of 2025, the Indonesian government implemented a policy to reduce electricity tariffs by 50% for household customers with power capacities of up to 2,200 VA. This policy aims to boost public purchasing power and stimulate economic growth, particularly among lower-middle-income groups. However, public responses to the policy have been varied and widely expressed on social media, especially on platform X (formerly known as Twitter). This study aims to evaluate public satisfaction with the electricity tariff reduction policy through sentiment analysis on social media X using the K-Means Clustering method. Data were collected through a crawling process using specific relevant keywords, followed by preprocessing steps such as cleansing, case folding, tokenizing, stemming, and conversion into numerical form using TF-IDF. The clustering results show that Cluster 1 dominates with 662 tweets (68.74%), predominantly reflecting positive sentiment, indicating that the majority of the public responded favorably to the 50% electricity tariff reduction policy. Cluster 2 consists of 165 tweets (17.13%) expressing negative sentiment, suggesting that some members of the public voiced concerns or dissatisfaction with the policy. Meanwhile, Cluster 0 includes 136 tweets (14.12%) containing neutral sentiment, representing moderate responses without a strong stance. These findings indicate that, overall, the policy received a generally positive reception from the public, although there are still critical and neutral perspectives.
Decision support for trucking vendor selection at PT. Ricakusuma Lestari Abadi Based on the SAW method Indriyanti, Zahra Kiky Dwi; Sumanto, Sumanto
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.v14i1.420

Abstract

PT. Ricakusuma Lestari Abadi is a company engaged in freight forwarding services, distributing goods both domestically and internationally. In the shipping process, the company heavily relies on third-party trucking services. However, the selection process for trucking vendors has so far been conducted manually, without standardized evaluation criteria, which risks leading to subjective and inefficient decisions. Therefore, this study aims to develop a decision support system to select the best trucking vendor using the Simple Additive Weighting (SAW) method. The SAW method is used because it provides objective evaluation results based on the weighting of five main criteria: service quality (40%), cost (25%), vehicle condition (15%), vendor location (10%), and fleet availability (10%) (Alamsyah et al., 2021; Gunawan et al., 2023; Wibowo & Azizah, 2022). This research adopts a quantitative approach through observation, interviews, and literature study. The collected data were used to calculate the scores of seven trucking vendor alternatives. The results show that Johan Putra Perkasa scored the highest with a value of 0.80 and is recommended as the best vendor. Kumala ranked second with a score of 0.75, followed by Global Sukses Transportama with a score of 0.72. The developed system was implemented as a web-based application using PHP and MySQL to facilitate a more efficient, faster, and standardized vendor selection process (Lim & Silalahi, 2023).
Integration of gas and dust detection sensors with human detection and LORA communication on drones for smart campus surveillance patrols at UNHAN RI Adama, Audirialy Naufal; Nurjaman, Ahmad Idlof; Faariz H, Naufal; Ariateja, Dananjaya; Sunarta, Sunarta
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.v14i1.421

Abstract

To improve the effectiveness of environmental monitoring and security activities in open areas or the UNHAN RI Smart Campus, this study provides solutions and recommendations, namely the integration of gas and dust detection sensors with a human detection system based on drones and LoRa as the communication protocol. Drones equipped with gas sensors such as the MQ-135 and dust particle sensors like the Nova PM SDS011 can monitor air quality in real-time. Additionally, a camera-based human detection system combined with an Artificial Intelligence algorithm such as YOLOv8, along with LoRa SX1278 as the communication protocol, can detect the presence of humans or intruders in the patrol area. The integration of these two systems can facilitate campus security personnel in using drones for automatic patrols, monitoring and assessing air pollution levels, and identifying individual movements in the monitored area simultaneously. Test results indicate that the combination of sensors and data processing systems based on the ESP8266 microcontroller on the drone device, along with communication protocols using LoRa SX1278, can provide sufficiently accurate visual and numerical information to support rapid response decisions in emergency situations such as theft, fires, and illegal activities within the UNHAN RI smart campus zone. This research can serve as an initial step toward developing an autonomous multi-sensor drone system based on Artificial Intelligence for integrated surveillance patrol tasks in the future.
Comparison of random forest and SVM methods in sentiment analysis about electric cars in Indonesia Pratistha, Indra; Iskandar, Adi Panca Saputra; Lanang, Eugenius Gene Rangga; Dewi, Ni Wayan Jeri Kusuma
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.v14i1.424

Abstract

This study examined public sentiment toward electric vehicles (EVs) in Indonesia, where the adoption of EVs reached 28,188 registered units in 2023. The research analyzed user-generated content from the social media platform X (formerly known as Twitter), collecting 1,507 tweets that underwent preprocessing, including text normalization and sentiment labeling. Two machine learning models, Random Forest and Support Vector Machine (SVM), were implemented to classify the tweets into positive and negative sentiments. Each model was evaluated under three experimental scenarios with varying training dataset sizes. The results indicated that the SVM model achieved the best performance in the third scenario, with an accuracy of 81.3%, precision of 88%, and recall of 91%. In comparison, Random Forest achieved its highest results in the same scenario, with an accuracy of 77%, precision of 91%, and recall of 81%. These findings demonstrated that SVM outperformed Random Forest in terms of overall balance between accuracy and recall, making it the more effective model for sentiment classification in this context.
Implementation of a deep neural network model to predict critical joint loads based on SAP2000 structural data Ridwan, Ridwan; Setyawan, Ryan Ari; Fitriastuti, Fatsyahrina
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.v14i1.425

Abstract

This study propose~s a De~e~p Ne~ural Ne~twork (DNN) frame~work to pre~dict joint re~action force~ ratios in structural analysis using datase~ts obtaine~d from SAP2000 simulations. The~ datase~ts cove~r various load case~s and ge~ome~trical parame~te~rs, e~nsuring the~ mode~l is e~xpose~d to dive~rse~ structural sce~narios. The~ DNN archite~cture~ comprise~s multiple~ fully conne~cte~d laye~rs, e~mploying Re~LU activation functions, dropout re~gularization, and batch normalization for stable~ training. Mode~l pe~rformance~ was e~valuate~d using Me~an Square~d E~rror (MSE~), Me~an Absolute~ E~rror (MAE~), R² score~, and pre~diction accuracy within a 5% e~rror margin critical for civil e~ngine~e~ring applications. The~ re~sults de~monstrate~ e~xce~lle~nt pre~dictive~ capabilitie~s, achie~ving accuracy le~ve~ls e~xce~e~ding 98% across all datase~ts. Notably, the~ third datase~t yie~lde~d the~ lowe~st accuracy at 98.97% and an R² score~ of 0.9915, with slightly e~le~vate~d e~rror me~trics (MSE~ of 5.11, RMSE~ of 2.26, and MAE~ of 1.51). De~spite~ the~se~ challe~nge~s, the~ DNN mode~l consiste~ntly de~live~rs robust pre~dictions, showcasing its pote~ntial for practical structural he~alth monitoring and de~sign optimization. Future~ work should conside~r incorporating more~ dive~rse~ and e~xpe~rime~ntal data to e~nhance~ mode~l robustne~ss furthe~r.
Attention-based convolutional neural networks for interpretable classification of maritime equipment fabrianto, luky; Prihandayani, Tiwuk Wahyuli; Rasenda, Rasenda; Faizah, Novianti Madhona
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.v14i1.426

Abstract

This study introduces a Convolutional Neural Network with an Attention Mechanism (CNN+AM), utilizing the Squeeze-and-Excitation (SE) block, to classify critical ship components: generators, engines, and oil-water separators (OWS). The SE block enhances the model's ability to focus on discriminative features, thereby improving classification performance. To overcome the limitation of the original dataset, which contained only 199 images, extensive data augmentation techniques were applied, expanding the dataset to 2,648 images. The augmented dataset was divided into training (70%), validation (15%), and testing (15%) sets to ensure reliable evaluation. Experimental results show that the CNN-AM achieved an accuracy of 72.39%, surpassing the baseline CNN model with 68.16%. These findings confirm that the attention mechanism significantly improves generalization and the ability to differentiate visually similar classes. Furthermore, the integration of interpretability tools, such as Gradient-weighted Class Activation Mapping (Grad-CAM), provides visual explanations of model predictions, increasing trust and reliability for safety-critical maritime applications. The proposed approach demonstrates strong potential for real-time ship component monitoring, offering meaningful contributions to predictive maintenance and operational safety within the maritime industry.

Page 17 of 19 | Total Record : 187

 15   16   17   18   19 

Filter by Year

2020 2025


Reset
Filter By Issues
All Issue 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