International Journal Software Engineering and Computer Science (IJSECS)
IJSECS is committed to bridge the theory and practice of information technology and computer science. From innovative ideas to specific algorithms and full system implementations, IJSECS publishes original, peer-reviewed, and high quality articles in the areas of information technology and computer science. IJSECS is a well-indexed scholarly journal and is indispensable reading and references for people working at the cutting edge of information technology and computer science applications..
Articles
10 Documents
Search results for
, issue
"Vol. 5 No. 3 (2025): DECEMBER 2025"
:
10 Documents
clear
<![CDATA[Classification Optimization of Aedes albopictus and Culex quinquefasciatus Mosquito Larvae Using Vision Transformer Method ]]>
<![CDATA[Al Faruq, Abdullah]]>;
<![CDATA[Mulyana, Dadang Iskandar]]>;
<![CDATA[Adrianto, Sopan]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5120
<![CDATA[Mosquito-transmitted diseases like Dengue Hemorrhagic Fever and Filariasis pose serious health threats throughout tropical regions, particularly in Indonesia. Quick and accurate identification of mosquito larvae plays a crucial role in disease prevention, especially for Aedes albopictus and Culex quinquefasciatus species that act as main disease carriers. Manual identification methods using microscopes or visual guides often struggle with time constraints, accuracy issues, and dependence on trained specialists. Our research focuses on improving the classification of Aedes albopictus and Culex quinquefasciatus mosquito larvae using Vision Transformer (ViT) technology, a deep learning method that has shown strong results in image recognition tasks. We applied the Vision Transformer model to classify mosquito larvae from microscopic field images. The study also tested how different factors impact model performance, such as image clarity, lighting conditions, and image resolution. Our findings show that using Vision Transformer in classification systems produced excellent results, achieving 98.00% accuracy in recall, precision, and F1-score measurements. The research reveals that Vision Transformer methods deliver better accuracy than traditional approaches like Convolutional Neural Networks and can be adapted into working systems for technology and healthcare sectors.]]>
<![CDATA[Design of BPJS Patient Referral Information System Based on Python Tkinter at Mulia Medika Clinic ]]>
<![CDATA[Dewi, Piyyawati]]>;
<![CDATA[Yunengsih, Yuyun]]>;
<![CDATA[Abdussalaam, Falaah]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5168
<![CDATA[Digital transformation is still an ongoing process in health service delivery to improve operational performance and service quality. However, BPJS Kesehatan patient referrals are still trapped in administrative bottlenecks. At Mulia Medika Clinic, staff used to handle BPJS patient referrals manually, so that records were prone to errors and delays in obtaining information. We designed, implemented, and tested a desktop-based BPJS referral information system using Python and Tkinter for clinic operations. The development process followed the Waterfall methodology, which consisted of requirements analysis, system architecture design using Context Diagrams, Data Flow Diagrams, Entity-Relationship Diagrams as well as Flowcharts followed by implementation and black-box testing validation. The system will manage patient records, referral processing as well as user administration. Automated features include generating referral letters and producing reports. Testing has proven that this system is accurate and efficient—the manual workload has reduced, data traceability has improved, and continuity in the referral service has been maintained. Results prove operational readiness for clinic deployment to enhance administrative efficiency and precision of the referral data. Currently, it runs standalone without real-time database synchronization; hence workflow integration cannot be achieved. Future versions should have direct connections with both clinic management and BPJS databases to allow seamless data exchange without manual synchronization]]>
<![CDATA[Development of a Web-Based Educational Information System Using the RAD Method: A Case Study at Persahabatan Hospital ]]>
<![CDATA[Setiawan, Reza]]>;
<![CDATA[Arinal, Veri]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5249
<![CDATA[RSUP Persahabatan operates as a teaching hospital supporting clinical education for medical professionals through Specialist Medical Education Programs (PPDS) and medical internships (Coass). The current registration infrastructure exhibits significant operational deficiencies, including recurring data entry errors, compromised information integrity, and dependence on manual reporting via Microsoft Excel. These limitations create administrative bottlenecks and reduce process reliability. To address these challenges, we developed a web-based student registration platform employing the Rapid Application Development (RAD) methodology. RAD facilitates accelerated development cycles through iterative prototyping and continuous stakeholder engagement. The platform incorporates automated document validation mechanisms and WhatsApp notification systems triggered upon registration approval. Implementation involved four RAD phases: planning, user design, construction, and cutover. Black-box testing and user acceptance testing validated functional integrity across all modules. Testing results demonstrated zero errors in registration workflows, document uploads, and verification processes. The platform achieved a maximum response time of 2.8 seconds per transaction while supporting concurrent user access. Results indicate measurable improvements in administrative efficiency, data accuracy, and processing speed compared to the previous manual system.]]>
<![CDATA[Decision Tree-Based Potential Athletics Athlete Selection System for PASI DKI Jakarta ]]>
<![CDATA[Sugiyono, Sugiyono]]>;
<![CDATA[Arpinda, Arpinda]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5242
<![CDATA[Selection of athletes in competitive sports is mostly based on subjective judgments; therefore, it results in inconsistency. This research presents a classification model that will help to measure the potential of athletes using the Decision Tree algorithm by utilizing real competition data from PASI DKI Jakarta. The dataset used consists of 450 records of athletes with attributes such as race category, time records, and ranking information. The analysis was performed based on the CRISP-DM framework which comprises six stages: business understanding, data exploration, preparation, modeling, evaluation, and deployment. Development and testing of the model were carried out in RapidMiner software using a 10-fold cross-validation technique. It achieved an accuracy of classification equal to 92.22% with a standard deviation of ±5.37%. The performance metrics show precision rates at 96.88% for High, 78.95% for Medium, and 94.87% for Low classes; while recall values are 100%, 88.24%, and 88.10%, respectively. The decision tree model generated specifies ranking as the root node meaning that this attribute has the highest influence on class separation among other attributes in this dataset. There are three classification rules produced by this model: ranking ≤3.500 is classified into high potential; between 3.500-6.500 belongs to medium potential; otherwise greater than 6.500 will be classified into low potential which can be applied practically as a decision support system enabling coaches to perform objective systematic data-driven processes in selecting athletes]]>
<![CDATA[Implementation of Haar Cascade and K-Nearest Neighbors (KNN) Face Recognition for Optimizing Warehouse Access Control Security ]]>
<![CDATA[Mulyana, Dadang Iskandar]]>;
<![CDATA[Ramadhan, Muhammad Adri]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5244
<![CDATA[Warehouse facility access control security represents a critical factor in maintaining operational integrity and preventing criminal activities. This research addresses the elevated security threat risks associated with physical surveillance systems that continue to rely on manual methods with suboptimal performance. The study develops an automated security system based on face recognition technology, implementing Haar Cascade and K-Nearest Neighbors Classifier methods to identify and verify warehouse user identities with precision and automation. The research object focuses on facial recognition systems for warehouse access control. The methodology applies Haar Cascade algorithms for facial detection and K-Nearest Neighbors Classifier for classifying detected faces against existing datasets. Implementation utilizes external webcams, computer hardware, and Python-based programming software. Results demonstrate that the developed system achieves facial recognition accuracy exceeding 90%, delivering superior security performance compared to manual systems. The research concludes that face recognition technology effectively enhances efficiency and security in warehouse access management. The study recommends implementing such systems in large-scale warehouse facilities to optimize security management protocols]]>
<![CDATA[Monitoring Information System to Ensure Completion of Medical Procedure Informed Consent Forms at Hospital X ]]>
<![CDATA[Yuspita, Shinta]]>;
<![CDATA[Yunengsih, Yuyun]]>;
<![CDATA[Abdussalaam, Falaah]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5263
<![CDATA[Medical action consent forms are known to be legal documents in the delivery of healthcare services. However, when they are not well completed, it affects the quality of services and the accountability of an institution. Recurring problems in documentation processes include incomplete data entry, late submissions, and substandard recording; all these increase risks for medical errors and administrative complications. A web-based information system was developed to address these systematic deficiencies using Rapid Application Development (RAD) methodology. Field observations and structured interviews with healthcare personnel were used as research tools in the design of this system. The development process continued through four iterative phases: requirements planning, user-centered design, system construction, and deployment evaluation. This platform comprises automated validation protocols that prevent incomplete submissions from being accepted into the database until all required fields have been completed by the user; real-time alert mechanisms for missing data fields within a submission; and streamlined interfaces optimized for clinical workflows. Functional testing shows statistically significant improvements in documentation efficiency and completion rates among medical staff documented by the system compared to those not documented by it. The system permits real-time documentation of procedures with lower error margins compared to existing methods plus shorter processing times than existing methods. This study found that RAD-based solutions present feasible approaches toward improving accuracy and speed in medical consent documentation while simultaneously achieving legal compliance and patient safety goals within hospitals. The platform uses technology-driven quality assurance mechanisms to solve longstanding challenges in documentation]]>
<![CDATA[Implementation of a Chatbot Using the Waterfall Method to Improve Helpdesk Service Efficiency at IT Consulting Companies ]]>
<![CDATA[Lestari, Sri]]>;
<![CDATA[Aprillia, Eka Putri]]>;
<![CDATA[Aula, Raisah Fajri]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5207
<![CDATA[PT XYZ is a company engaged in information and communication technology services, supporting customers' digital transformation. The effectiveness of helpdesk services plays a crucial role in maintaining operations and fostering customer relationships. However, the issue reporting process is still handled manually through platforms such as WhatsApp and email, causing several problems, including inefficient ticket management, delays in ticket number assignment, and limited historical data. This study developed a chatbot based on Microsoft Copilot Studio to automate ticket creation, supported by Power Apps to address the lack of two-way communication features, aiming to support Customer Relationship Management (CRM) efforts. The system was developed using Waterfall methodology. The results showed significant improvements in service efficiency: the previous average initial response time of 2 days, 19 hours, and 13 minutes was eliminated due to automatic ticket number assignment; the average issue resolution time decreased from 5 days, 6 hours, and 20 minutes to 42 minutes; and ticket history search time improved from 14 minutes to 2 seconds. The chatbot successfully accelerated the reporting process, enhanced data recording, and reduced the workload of the helpdesk team. This solution significantly improved helpdesk efficiency and strengthened customer engagement.]]>
<![CDATA[Mobile Application Development for Waste Management System with K-Means Clustering of Waste Collection Points in Jonggol and Sukamakmur Sub-Districts, Bogor Regency ]]>
<![CDATA[Aziz, Naufal]]>;
<![CDATA[Mulyana, Dadang Iskandar]]>;
<![CDATA[Kastum, Kastum]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5250
<![CDATA[The disparity in the distribution of Temporary Disposal Sites (TPS) within Jonggol and Sukamakmur Districts of Bogor Regency results in inefficiencies in waste collection services, increases travel times, and creates an unequal operational burden on collection fleets. There is no mobile-based digital platform for residents to report TPS conditions in real-time, which further delays responses to waste management. The lack of interactive digital map visualization makes it hard for local sanitation managers to make informed decisions about space. A mobile waste management information system was created using Flutter and Firebase, with the K-Means algorithm used to cluster TPS locations based on their spatial coordinates. The clustering results are presented as an interactive digital map that is integrated with the Google Maps API; this application allows residents to input TPS condition reports, upload visual evidence, and receive notifications about the status in real-time. This project is an extension of our previous web-based work done during the practical internship (KKP) phase but has a larger scope due to a more advanced spatial approach integrated into mobile devices. The system will optimize the distribution efficiency of waste collection services while assisting spatial decision-making processes as well as motivating active participation from residents in maintaining their environment particularly within Jonggol and Sukamakmur Districts under Bogor Regency’s smart city program initiatives.]]>
<![CDATA[Image Quality Improvement for Sign Language Gestures Through Gaussian Filter and Contrast Stretching Techniques ]]>
<![CDATA[Mulyana, Dadang Iskandar]]>;
<![CDATA[Abyan, Muhammad Abdul Aziz]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5254
<![CDATA[Deaf people use sign language as their primary means of communication. Images of sign language gestures are usually low quality because visual impairments like noise and low contrast prevent an automatic recognition system from working well. This research tries to enhance the quality of images with sign language gestures using two preprocessing methods, namely Gaussian Filter and Contrast Stretching. The first one eliminates noise while keeping important details in the image, and the second increases pixel intensity distribution to make hand gestures more apparent and outlined. An experiment was done on a dataset that includes 54,049 static hand gesture images taken from videos that contain certain sign languages divided into 28 classes for hijaiyah letters. A quantitative evaluation indicated substantial enhancements in processed image quality. The preprocessing method resulted in an average PSNR of 20.13 dB, SSIM equal to 0.8875, and MSE equal to 976.39 for all samples tested confirming that this combination method improves sharpness, structural integrity, and contrast when compared with original unprocessed images significantly. This study recommends using Gaussian Filter along with Contrast Stretching as a practical option for improving the quality of sign language images which can eventually help automated recognition systems that need clear visual input to correctly classify gestures.]]>
<![CDATA[A Comparative Analysis of Support Vector Machine and Artificial Neural Network Methods for Predicting Vocational High School Student Graduation ]]>
<![CDATA[Sahrudin, Didin]]>;
<![CDATA[Aziz, Ferhat]]>;
<![CDATA[Basir, Choirul]]>
<![CDATA[ International Journal Software Engineering and Computer Science (IJSECS) Vol. 5 No. 3 (2025): DECEMBER 2025 ]]>
Publisher : <![CDATA[Lembaga Komunitas Informasi Teknologi Aceh (KITA) ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.35870/ijsecs.v5i3.5742
<![CDATA[Identifying which students may struggle in examinations early on is a critical challenge in vocational schools. This study aims to create and compare two machine learning models to predict the graduation status of Vocational High School (SMK) students majoring in Software and Game Development (PPLG). This prediction is based on their Competency Skills Test (UKK) scores. We used data from 310 students and tested two methods: Support Vector Machine (SVM) and Artificial Neural Network (ANN). The results are very clear: the SVM model performed exceptionally well, achieving an accuracy of 99%. SVM was able to recognize both 'Competent' and 'Not Yet Competent' students in a balanced manner. Conversely, the ANN model's performance was poor, with an accuracy of only 66%. This occurred because the ANN failed to learn and simply guessed that all students would pass. This research concludes that SVM is a highly effective method to be used as an early warning system. With this system, schools can more quickly assist students who are at risk of failing. SVM achieved 99% accuracy with perfect precision for the Competent class and full recall for the Not Yet Competent class. ROC-AUC and PR-AUC indicated excellent separability and strong minority-class detection. ANN achieved only 66% accuracy, predicting all samples as Competent. Learning curves revealed stagnation and failure to learn minority class patterns. Additional baseline models (Logistic Regression, Random Forest) were tested, with SVM outperforming all others consistently. Statistical significance testing using McNemar's test confirmed that SVM provides significantly better classification performance than ANN (p < 0.01).]]>
