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 240 Documents
 20   21   22   23   24 
Web-based project material inventory information system at PT XYZ using the waterfall method Cut Zahra Malahayatinur; Antika Zahrotul Kamalia; Candra Naya
Jurnal Mandiri IT Vol. 15 No. 1 (2026): 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.v15i1.550

Abstract

PT XYZ is an enterprise operating in the building contractor sector with a high intensity of material movement. Currently, the warehouse inventory management procedure in the company still relies on conventional methods using a manual physical Logbook. This mechanism triggers various operational obstacles, such as a high risk of handwriting errors (human error), stock discrepancies between physical availability and written balances, and a slow cascade of report recapitulation for management. This study aims to design and develop a Web-Based Project Material Inventory System to digitalize the entire workflow of stock management. The system development method implemented is the Waterfall model, which encompasses requirement analysis, design, implementation, testing, deployment, and maintenance. This computerized application is built using the PHP programming language with the Laravel framework, a MySQL database, and supported by a Tailwind CSS-based interface. System functionality testing was conducted through the Black Box Testing method to ensure all operational modules run according to the system requirements. The final result of this research is a centralized information system capable of managing master data (items, vendors, units, projects), processing incoming and outgoing item transactions with automatic stock calculation, and presenting inventory mutation reports in real-time. The implementation of this system has been proven to reduce warehouse administrative burdens, eliminate the risk of physical damage to paper documentation, and accelerate managerial decision-making processes at PT XYZ.
Sentiment analysis of public opinion on the non-cash food assistance (BPNT) program on platform x using naive bayes Nurul Asma As-shidiq; Donny Maulana; M. Zubair Abdurrohman
Jurnal Mandiri IT Vol. 15 No. 1 (2026): 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.v15i1.551

Abstract

The Non-Cash Food Assistance (BPNT) program is one of the Indonesian government's social assistance policies that frequently receives public attention and discussion on social media. This study aims to analyze public sentiment toward the implementation of the BPNT program based on comments posted on Platform X. The dataset consisted of 1,758 Indonesian-language comments collected through web crawling between October 2025 and January 2026. The collected data were processed through several preprocessing stages, including case folding, cleaning, tokenization, normalization, stopword removal, and stemming. Furthermore, TF-IDF was applied to transform textual data into numerical features, and sentiment classification was performed using the Multinomial Naive Bayes algorithm. The dataset was divided into training and testing data using an 80:20 ratio. The results showed that neutral sentiment dominated public discussions with 51.48%, followed by positive sentiment with 33.90% and negative sentiment with 14.62%. Performance evaluation using a Confusion Matrix achieved an accuracy of 79.545%. These findings indicate that the Naive Bayes approach can effectively classify public sentiment regarding the BPNT program and provide useful insights for evaluating social assistance policies.
Attention-enhanced hybrid deep learning for skin cancer diagnosis with hierarchical feature fusion Ahmad Sanmorino; Rendra Gustriansyah; Shinta Puspasari
Jurnal Mandiri IT Vol. 15 No. 1 (2026): 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.v15i1.552

Abstract

Skin cancer is one of the most prevalent cancers worldwide, making early and accurate diagnosis essential for improving patient outcomes and reducing mortality. However, automated skin lesion classification remains challenging due to high inter-class similarity, class imbalance, and variations in lesion appearance. This study proposes an attention-enhanced hybrid deep learning for skin cancer diagnosis with hierarchical feature fusion. The proposed framework integrates channel and spatial attention with hierarchical feature fusion to enhance discriminative feature learning and improve classification robustness. Experiments were conducted on the PAD-UFES-20 dataset using image preprocessing and data augmentation. The proposed model achieved approximately 98% training accuracy, 95% validation accuracy, and a validation loss below 0.5, outperforming DRMv2Net, DenseNet201, ResNet101, and MobileNetV2 while demonstrating faster convergence and stronger generalization. These findings demonstrate the potential of hybrid attention and hierarchical feature fusion to improve the reliability and robustness of artificial intelligence-based diagnostic systems in dermatology, supporting more effective clinical decision-making and early skin cancer screening.
Sentiment analysis of public opinion toward government regulations concerning the implementation of tabungan perumahan rakyat (Tapera) using the convolutional neural network (CNN) model on social media X M. Iqbal Noviansyah; Kusrini Kusrini
Jurnal Mandiri IT Vol. 15 No. 2 (2026): Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v15i2.559

Abstract

Sentiment analysis is one of the applications of Natural Language Processing (NLP) for identifying public opinion on social media. Although previous studies on Tapera sentiment analysis have applied conventional machine learning and transformer-based approaches, limited attention has been given to integrating automatic lexicon-based sentiment labeling with semantic word representation and deep learning classification within a unified framework. This study proposes an approach that integrates the Indonesian Sentiment Lexicon (InSet), Word2Vec, and Convolutional Neural Network (CNN) to classify public sentiment toward the Tabungan Perumahan Rakyat (Tapera) policy on social media X. A total of 1,291 tweets were processed through the preprocessing stage and automatically labeled using InSet. Word2Vec was employed to construct semantic word representations that were used as the initial weights of the CNN embedding layer. The proposed model was evaluated using four hold-out data split scenarios and compared with BiLSTM and Random Forest. The experimental results showed that the 80:20 configuration achieved the best performance with an accuracy of 74.52%, outperforming BiLSTM (71.43%) and Random Forest (69.88%). The novelty of this study lies in integrating automatic sentiment labeling using the Indonesian Sentiment Lexicon (InSet), semantic representation through Word2Vec, and CNN-based classification within a unified framework, together with an empirical evaluation of different train-test split ratios for Tapera policy sentiment analysis. These findings demonstrate that the proposed approach provides competitive sentiment classification performance while reducing dependence on manual sentiment annotation.
Development of a multi-parameter based agricultural land condition monitoring system Fristi Riandari; M. Hilmi Syuhada; Naufal Nabil; Zaky Farhan Sitorus; ‎Moreno Aulya Septyawan; Rafli Al Ghifari Nasution
Jurnal Mandiri IT Vol. 15 No. 1 (2026): July: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

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

Abstract

Regular soil monitoring is essential to support agricultural land management and maintain crop productivity. Conventional methods generally require separate analyses to obtain information on several soil parameters, necessitating a system capable of integrating soil condition measurements and interpretation in a more practical manner. This research aims to develop Farm Thrive, a multi-parameter soil monitoring system based on expert knowledge rules. The system processes pH, humidity, temperature, nitrogen (N), phosphorus (P), potassium (K), electrical conductivity (EC), and rainfall as additional parameters. Measurement values ​​are validated and compared against target ranges based on the selected crop. Each parameter is classified as low, optimal, or high and scored based on its proximity to the target range. Parameter scores are then aggregated using a weighted average to generate a soil condition score and categorized as Ready for Planting, Needs Improvement, or Not Ready for Planting. Implementation results demonstrate that the system is capable of integrating multi-parameter measurements, classifying soil conditions, identifying parameters requiring attention, and providing improvement recommendations based on the rules used. The system also stores measurement history to support monitoring changes in soil conditions over time. Farm Thrive can be a tool for monitoring and initial interpretation of agricultural soil conditions.
Development of A Web-Based Study Program Accreditation Monitoring Information System for The Information Systems and Technology Study Program at Universitas Muhammadiyah Kotabumi Intan Addies Adila; M Abu Jihad Plaza R
Jurnal Mandiri IT Vol. 15 No. 2 (2026): Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v15i2.571

Abstract

Study program accreditation requires structured management of documents, progress monitoring, task allocation, validation, deadline control, and report preparation. At the Information Systems and Technology Study Program, Universitas Muhammadiyah Kotabumi, the previous accreditation monitoring process faced several challenges, including scattered document storage, difficulties in monitoring the progress of each criterion, and unintegrated document coordination and retrieval. This study aims to develop a web-based study program accreditation monitoring information system capable of integrating document management and monitoring processes within a centralized system. System development was carried out through the stages of requirements identification, data collection, prototype design, design evaluation and refinement, implementation, and system testing. The system was implemented using Laravel, PHP, Bootstrap, and MySQL, with UML used for system design. The developed features include a monitoring dashboard, document management, progress monitoring for each accreditation criterion, timeline management, reminders and notifications, document verification, document search, audit trail, document versioning and revision, and reporting. Testing was conducted using the Black Box Testing method on the main system functions, including the monitoring dashboard, accreditation progress monitoring, document search, document verification, and report generation. The test results show that all tested functions produced outputs consistent with the predefined test scenarios and were declared successful. The developed system provides a more centralized accreditation monitoring workflow, enabling document information, progress, verification status, and reports to be managed within a single web-based application environment
Real-Time Counting Web Application for DPD IMM Lampung Elections Using Laravel Muhammad Abdurasyid Dzakirah; Adi Wibowo
Jurnal Mandiri IT Vol. 15 No. 2 (2026): Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

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

Abstract

Muhammadiyah Student Association (IMM) Lampung at the Regional Deliberation forum is still conducted conventionally using paper ballots, making printing, casting, and counting relatively time-consuming and prone to recording errors, while live result information is not available to participants. This study aims to design and build a Laravel 12-based Real-Time Counting web application equipped with Laravel Reverb/WebSocket to support the election of the Chairperson and Field Coordinator of DPD IMM Lampung. The system was developed using the waterfall method, modeled with Unified Modeling Language (UML), and supported by a MySQL database. The implementation integrates voter-right validation using membership card numbers and tokens, digital ballot casting, anti-double-vote enforcement through a database unique constraint, real-time result broadcasting through the VoteCasted event, and a re-voting mechanism for tied results. Black Box Testing and User Acceptance Testing (UAT) were defined as evaluation procedures for assessing functional suitability and user acceptance. The article presents the testing scenarios and UAT indicators used in the evaluation. The implemented system provides the functional basis for replacing the manual ballot workflow and presenting election results more quickly and transparently The evaluation included 14 Black Box Testing scenarios and UAT with 20 respondents (15 voters/participants and 5 committee/administrator users). The UAT obtained a total score of 706 out of 800, equivalent to 88.25%, categorized as Very Good. The Black Box table documents the 14 functional scenarios and expected outputs; quantitative pass/fail execution totals were not separately recorded in the source testing table
Development of a multi-objective preference analysis (MOPA)-based multicriteria model for assessing the resilience of tourism destinations to flood risk Fristi Riandari; Hikmah Adwin Adam
Jurnal Mandiri IT Vol. 15 No. 1 (2026): 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.v15i1.575

Abstract

Floods can disrupt the accessibility, facilities, and sustainability of tourism destination activities. This study aims to develop a preliminary model to assess the resilience of tourism destinations to flood risk using a Multi-Objective Preference Analysis (MOPA) approach based on secondary data and openly available digital information. The case study was conducted at the Siombak Lake Tourism Park, Medan City, with five alternative observation periods from 2020-2024. The five indicators used include flood risk, rainfall, area exposure, accessibility, and availability of tourism facilities. Factual data was used when available, while indicators that did not have numerical data were supplemented using proxy scores based on expert judgment. Data were processed through the preparation of a decision matrix, classification of cost and benefit indicators, normalization, weighting, and aggregation of MOPA preference values. Sensitivity testing was conducted by changing the indicator weights by ±5% and ±10%. The results showed that alternative A4-2023 obtained the highest preference value of 0.7595, while A5-2024 obtained the lowest value of 0.4000. All sensitivity scenarios produced the same ranking order as the baseline, achieving 100% ranking stability. This research produces a simple, transparent, and replicable initial assessment framework. Future research can develop the model by integrating real-time or near-real-time meteorological, spatial, disaster, and sensor data
Development of UI/UX and design thinking integration model for optimizing oisrum's MSME digital platform Fristi Riandari; Gabriel Ardi Hutagalung; Hikmah Adwin Adam
Jurnal Mandiri IT Vol. 15 No. 2 (2026): Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v15i2.573

Abstract

Usability is a critical factor in digital commerce platforms because it influences users’ ability to find product information and complete transactions efficiently. This study evaluates the usability of Oisrum, an MSME digital commerce platform, and identifies priorities for interface improvement based on actual user-testing results. The evaluation involved 10 participants performing six predefined tasks covering product discovery, access to product information, product selection, cart interaction, checkout, and access to platform information. The results showed an overall task completion rate of 93.33%, with 56 successful task executions out of 60, and a System Usability Scale (SUS) score of 83.0. Task-level analysis identified access to product information (T2), with a completion rate of 90%, and checkout completion (T5), with a completion rate of 80% and an average completion time of 148 seconds, as areas requiring further attention. These findings demonstrate that overall usability scores should be interpreted alongside task-level performance to identify specific interaction problems. A weighted objective-function approach may complement this evaluation by supporting the prioritization of interface improvement alternatives based on measurable usability indicators. However, the effectiveness of specific improvements must be established through documented implementation and follow-up user testing. This study provides an empirical basis for identifying usability issues and prioritizing further improvements to the Oisrum digital commerce platform.
Indonesian handwritten word segmentation using a neural word detector Zulkarnaen Hatala
Jurnal Mandiri IT Vol. 15 No. 2 (2026): Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v15i2.574

Abstract

Word segmentation is an essential preprocessing step in offline handwritten text recognition because accurate word localization directly affects subsequent recognition performance. This study presents an Indonesian handwritten word segmentation approach using a neural word detector designed to localize individual words in handwritten student assignment documents. The dataset consists of real handwritten student assignments, with word-level ground truth annotations manually created using LabelMe in the form of rectangular bounding boxes. A pretrained neural word detector was trained for five epochs and evaluated using an Intersection over Union (IoU) threshold of 0.50. Predicted word bounding boxes were matched with ground-truth boxes using the Hungarian assignment algorithm, with the matching cost defined from the IoU between corresponding boxes. Evaluation was conducted on 120 paired files containing 9,267 ground-truth word boxes and 9,308 evaluated predicted boxes. The detector achieved a precision of 92.35%, recall of 92.76%, and F1-score of 92.55%, while the mean IoU of matched bounding boxes reached 86.27%. These results indicate that the neural word detector can effectively localize handwritten Indonesian words with high detection consistency and spatial overlap. The study demonstrates the feasibility of neural word detection as a practical approach for word-level segmentation of real Indonesian handwritten documents. The resulting segmentation can provide localized word regions for subsequent handwritten word recognition and document analysis applications.

Page 24 of 24 | Total Record : 240

 20   21   22   23   24 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 2 (2026): Computer Science and Field. Vol. 15 No. 1 (2026): July: Computer Science and Field. Vol. 14 No. 4 (2026): April: Computer Science and Field. Vol. 14 No. 3 (2026): Jan: Computer Science and Field Vol. 14 No. 2 (2025): Computer Science and Field Vol. 14 No. 2 (2025): October: 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