Claim Missing Document
Check
Articles

Found 23 Documents
Search

Implementation of a Face Recognition API for an Automated Web-based Attendance System using Extreme Programming Rizky Wandri; Mutia Fadhillah; Dwi Fiqri Qurniawan; Eka Deddy Saputra
SISTEMASI Vol 15, No 6 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i6.6388

Abstract

Manual attendance recording is still vulnerable to data manipulation, entry delays, and high reliance on manual input. This research focuses on the implementation and integration of the Facial Recognition REST API into a web-based attendance information system to automate attendance recording. The novelty of this research lies in the integration of REST API-based facial recognition services with a three-layer architecture consisting of a camera device, a Raspberry Pi 5-based edge server, and a Laravel-based application server, developed using the Extreme Programming (XP) method, resulting in a modular, responsive, and easily scalable attendance system compared to previous approaches. The system was developed in four sprints over one month with an average speed of 15.5 story points per sprint, based on twelve user stories defined in the planning stage. In the facial recognition module, the identification process utilizes a combination of Haar Cascade for facial position detection, FaceNet for facial embedding formation, and Cosine Similarity for similarity measurement against a reference database consisting of 18 students with 6 reference photos per student. System testing was conducted using three class videos with a resolution of 1920×1080 pixels with an average duration of 5 minutes and 28 seconds. Evaluation of the accuracy of the facial recognition model was part of a collaborative study reviewed separately; this paper focuses on the system's integration performance and functionality. Functional testing using black box methods across 20 scenarios demonstrated that all modules—authentication, master data management, facial registration, facial recognition-based attendance, reporting, and error handling—performed according to specifications, with a consistent system response time of 2–4 seconds. The results demonstrate that the system reduces reliance on manual input, improves record-keeping efficiency, and provides real-time attendance data, and is ready for further development for broader adoption in educational settings.
Design of the 'Abdimas' Marketplace System: A Digital Platform for PKM Collaboration (Version 0.0) M Rizki Fadhilah; Rizky Wandri; Mutia Fadhilla; Dwi Fiqri Gunawan; Ause Labellapansa; Hendra Gunawan
SISTEMASI Vol 15, No 1 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i1.5545

Abstract

Community Service (Pengabdian kepada Masyarakat or PkM) is one of the three core responsibilities (Tridharma) of higher education in Indonesia, alongside education and research. However, many lecturers especially those new to academia face difficulties in identifying suitable community partners. This study addresses that issue through the design of a digital platform called “Abdimas”, intended to function as a marketplace system for matching lecturers with PkM partners. Applying the Design Thinking methodology, focusing on the conceptual and architectural design of the “Abdimas” platform, this study implemented a user-centered design approach. Data from interviews with lecturers, partners, and university administrators were analyzed using thematic analysis to identify core requirements. Based on these findings, the system was designed to support lecturer registration, partner discovery, and need-based matching. Senior lecturers are also supported in exploring new, underserved areas, while partners can publicly express their needs to attract suitable academic collaborators. University administrators can monitor the distribution of PkM activities over time to ensure equity and effectiveness. Unlike existing administrative platforms that often function as one-way reporting tools, the “Abdimas” marketplace introduces a bidirectional matching mechanism that allows partners to actively broadcast their specific community needs, bridging the information gap for lecturers. The system design includes use case diagrams, UI/UX prototypes, an Entity Relationship Diagram (ERD), and blackbox test scenarios to validate functionality. Although still in the design phase (Version 0.0), “Abdimas” has the potential to scale beyond academic users by supporting Corporate Social Responsibility (CSR) initiatives and facilitating student-level community services. This research contributes a structured and scalable system design to improve collaboration and outreach in community service programs within higher education.
Sentiment Analysis of #Saverafah Hashtag on TikTok Using Naive Bayes and Decision Tree Methods Nisa Pirsingki; Rizky Wandri
Jurnal Informatika Vol. 12 No. 1 (2025): April
Publisher : Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/informatika.v12i1.12256

Abstract

Social media facilitates user communication, both in positive, negative and neutral aspects. Tiktok is a popular platform that allows users to stay up to date on the latest news, including the major conflict between Palestine and Israel. In this war, many Palestinian civilians, including children and the elderly, became victims, and are currently trying to flee to Rafah to seek protection. The objective of this study is to evaluate public sentiment regarding the news of Palestinian refugees en route to Rafah. To achieve this purpose, we will examine 2982 comments on TikTok relating to the hashtag #SaveRafah, which will be the data to be trained. Prior to classification, the data will undergo a preprocessing process and TF-IDF weighting. The two classification methods will be compared to ascertain the most accurate approach. Because the data at the labeling stage has a larger percentage of positive data 90.7%, this study will employ the technique SMOTE to address class imbalance in the data set. The results showed that the Naive Bayes Multinomial method with the application of SMOTE produced an accuracy of 85.43%, a precision of 86.22%, a recall of 85.43%, and an f1-score of 85.53%. Meanwhile, the Decision Tree C4.5 method with the application of SMOTE produced an accuracy of 94.23%, a precision of 94.58%, a recall of 94.23%, and an f1-score of 94.22%. Based on the evaluation results, the best method for sentiment analysis of the hashtag #SaveRafah is Decision Tree C4.5.