Claim Missing Document
Check
Articles

Found 19 Documents
Search

Web-based Information System for Ornamental Fish Business in Surabaya Cendra Devayana Putra; Muhammad Sonhaji Akbar; Muhamad Aris Burhanudin; Bartolomeus Priya Perkasa Utama Widada; Rizqiyatul Khoiriyah; Pandu Dwi Luhur Pambudi‬‬‬‬‬‬
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.v15i6.6358

Abstract

Digital transformation has emerged as a strategic imperative for small and medium enterprises (SMEs) in emerging economies, yet the ornamental fish retail sector in Indonesia remains predominantly offline, constrained by limited digital infrastructure and high customer knowledge barriers. No prior identified study has implemented artificial intelligence (AI)-assisted consultation within a domain-specific ornamental fish e-commerce platform, and comprehensive security implementation combined with multi-layer testing has been largely absent in comparable SME web systems. This study presents the design, implementation, and evaluation of a web-based information system for Toko Oasis, an ornamental fish and aquascape SME in Surabaya, Indonesia, developed within a Design Science Research (DSR) paradigm following a structured Software Development Life Cycle (SDLC). The system integrates a configurable large language model (LLM) consultation module—supporting OpenAI GPT-4 and Google Gemini—that delivers domain-specific advisory on ornamental fish species selection, aquarium parameters, and aquascape design through natural language interaction. System development produced twelve Unified Modeling Language (UML) artifacts and was evaluated through a tri-layer testing protocol operationalized against the ISO/IEC 25010:2011 software quality model. Functional testing achieved a 100% pass rate across 24 use cases. Performance testing recorded a mean response time of 4.2 seconds under 25 concurrent users, within the defined threshold of 5 seconds. Usability evaluation yielded a mean System Usability Scale (SUS) score of 80.0, classified as Good. Security validation confirmed full compliance across HTTPS/SSL-TLS transport and AES-256 at-rest encryption domains. Comparative analysis against prior literature and analogous commercial platforms confirms that this system constitutes the first identified deployment of AI-assisted consultation in ornamental fish retail, contributing a replicable digitalization architecture for niche-market SMEs in developing economies.
EVALUATING PARTICIPANTS’ UNDERSTANDING OF TEXT-TO-DESIGN FOR LOCAL-BASED WISDOM: EVALUASI PEMAHAMAN PESERTA PADA APLIKASI TEXT-TO-DESIGN BERBASIS KEARIFAN LOKAL Cendra Devayana Putra; Daniel Evan Rusli; I Kadek Dwi Nuryana; Rahadian Bisma
Darmabakti Cendekia: Journal of Community Service and Engagements Vol. 8 No. 1 (2026): JUNE 2026
Publisher : Faculty of Vocational Studies, Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/dc.V8.I1.2026.44-49

Abstract

Background: This study presents an evaluation of the dissemination of the Text-to-Design (TTD) application for developing design materials based on local wisdom. Objective: With increased accessibility to AI-supported technology, educators can apply TTD tools to produce learning materials that are consistent, flexible, and culturally contextual. Method: Using survey data and participant feedback, the study analyzes levels of understanding, clarity of presentation, the usefulness of practical sessions, and development recommendations. Results: The findings indicate a high level of understanding (88.9%), strong engagement through hands-on activities, and interest in integrating local content into digital listening materials. Conclusion: These results align with recent research on digital literacy and culturally relevant learning.
Edukasi Interaktif Tuberculosis dan Keamanan Foto Rontgen untuk Percepatan Program TOSS-TB di Puskesmas Kowel, Kab. Pamekasan Berliana Devianti Putri; Winda Kusumawardani; Tesa Eranti Putri; Riris Medawati; Endah Sekar Palupi; Cendra Devayana Putra; Aisyah Widayani; Alif Majid Firdaus; Andyka Salom
Jurnal Abdimas Kesehatan (JAK) Vol. 8 No. 1 (2026): Januari
Publisher : Universitas Baiturrahim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36565/jak.v8i1.1046

Abstract

Tuberculosis (TB) can affect people of all ages, from young to old. It also impacts the quality of life of human resources and can become an obstacle to national development. TB can be prevented by optimizing the TOSS-TB (Find, Treat, and Cure) program initiated by the Ministry of Health of the Republic of Indonesia to achieve the TB-Free 2030 target. Based on the 2023 East Java Provincial Health Profile Report, the case detection and treatment success TB rate in Pamekasan is still low, at 80,2%, which is below the national target of 90%. This activity employs an interactive educational approach to raise awareness about TB and the safety of X-ray examinations through digital gamification, then promotes public understanding of TB screenings and recommendations for visiting community health centers. This information and interactive games were designed in two languages, namely Indonesian and Madurese. The community service activity began with the creation of the application that provides information and interactive games. Socialization and hands-on application were conducted in September 2025. Sixty-five participants, including community health center heads, TB program managers, health cadres, TB patients, and community members living near TB patients, participated in this activity. Results of the Wilcoxon signed-rank test (α=0.05) showed a significant increase in participants' knowledge regarding TB (p=0.000) and knowledge regarding X-ray safety (p=0.000). Participants also experienced improved skills in operating the application as an educational tool for health cadres in the Kowel Community Health Center, Pamekasan. This activity supports the Sustainable Development Goals, specifically SDGs No. 3 (Good Health and Well-being) and SDGs No. 4 (Quality Education).
Implementasi Modul ESP32 Sebagai Pengendali Kipas Angin Otomatis Berbasis Jaringan WiFi Nadia Alfi Ni’amah; Husna Lathifunisa Arif; Aryawangi Rahmawanto; Edwyn Wahyu Prasetya; Riza Akhsani Setyo Prayoga; Cendra Devayana Putra
Jurnal Ilmu Komputer dan Multimedia Vol. 3 No. 1 (2026): ILKOMEDIA Edisi Juni 2026
Publisher : Akademi Komunitas Negeri Putra Sang Fajar Blitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46510/ilkomedia.v3i1.90

Abstract

Kipas angin konvensional masih menjadi perangkat yang banyak digunakan masyarakat, terutama di wilayah tropis seperti Indonesia. Di sisi lain kipas angin konvensional masih bergantung pada kontrol manual, kipas sering dibiarkan menyala terus-menerus tanpa memperhatikan kebutuhan pengguna, sehingga penggunaan energi menjadi kurang efisien dan kenyamanan tidak selalu terjamin. Penelitian ini bertujuan untuk merancang dan mengimplementasikan SmartFan, yaitu sistem pengendali kipas angin berbasis Internet of Things (IoT) menggunakan ESP32, MQTT, dan Flutter mobile application. Sistem ini dikembangkan untuk memberikan kendali kipas yang lebih presisi, responsif, dan mudah digunakan dibandingkan metode konvensional maupun aplikasi pihak ketiga seperti MQTT Dash. Aplikasi Flutter memungkinkan pengguna mengatur kecepatan kipas secara bertahap (0–100%), melakukan kontrol daya, serta memantau status koneksi perangkat secara real-time. Pada sisi perangkat keras, ESP32 dilengkapi dengan WiFi Manager sehingga dapat dikonfigurasi pada berbagai jaringan tanpa proses pemrograman ulang, serta menghasilkan sinyal PWM yang stabil untuk mengatur putaran motor melalui driver L298N. Pemisahan sumber daya antara ESP32 dan motor melalui powerbank dan adaptor 12V terbukti meningkatkan stabilitas sistem dengan mencegah brownout yang biasanya terjadi akibat lonjakan arus motor. Hasil pengujian menunjukkan bahwa komunikasi MQTT berjalan stabil, respons kendali cepat, dan integrasi antara perangkat keras serta aplikasi berfungsi sesuai tujuan. Secara keseluruhan, SmartFan berhasil dikembangkan sebagai sistem IoT yang efektif, fleksibel, dan mudah digunakan. Penelitian ini juga membuka peluang pengembangan lanjutan melalui penambahan sensor lingkungan, otomatisasi berbasis kondisi dengan kendali jarak jauh berbasis mobile, serta integrasi keamanan MQTT Secure dan platform smart home.
Analisis Perbandingan Kualitas Jawaban Pada Qa Berbasis Rag : Kombinasi Zero-Shot Instruction Prompting Dan Self-Verification Nevitya Elmaira Nurjannah; Cendra Devayana Putra
Jurnal Ilmu Ekonomi, Pendidikan dan Teknik Vol. 3 No. 5 (2026): IDENTIK - September
Publisher : CV. SINAR HOWUHOWU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70134/identik.v3i5.1962

Abstract

Retrieval-Augmented Generation (RAG) reduces hallucinations by grounding language model (LM) responses in the context of retrieved results, but does not automatically guarantee evidence-based (faithful) responses. This study examines the effect of combining zero-shot instruction prompting and self-verification on the faithfulness of responses to answerable questions, across four RAG pipeline configurations: (1) RAG, (2) RAG + prompting, (3) RAG + self-verification, and (4) RAG + prompting + self-verification, which were tested on three scales of the Qwen3 language model (0.6B, 4B, 8B) using the SQuAD v2.0 dataset. A total of 100 queries were selected via stratified random sampling from the validation split to avoid topic bias. Faithfulness was measured at the claim level using an NLI model (DeBERTa-v3-large). The results show that basic RAG (configuration 1) achieved the highest average faithfulness score, while configurations 2–4 (with prompting and/or self-verification) showed relatively similar and lower scores. In SLM, adding self-verification lowered faithfulness the most, while in LLM the score remained relatively stable across configurations. A retrieval-quality control analysis indicated that this decline was linked to the generator's capacity rather than retrieval quality. These findings suggest that the combination of prompting and self-verification does not automatically improve the quality of evidence-based answers, and its benefits depend on the adequacy of the language model's capacity.  
Perbandingan Kinerja Lstm, Random Forest, Dan Xgboost Dalam Memprediksi Harga Penutupan Indeks Harga Saham Gabungan (Ihsg) Berbasis Data Historis Mohammad Faiz Rakhman; Cendra Devayana Putra
Jurnal Ilmu Ekonomi, Pendidikan dan Teknik Vol. 3 No. 5 (2026): IDENTIK - September
Publisher : CV. SINAR HOWUHOWU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70134/identik.v3i5.1979

Abstract

This study compares the performance of three machine learning algorithms, Long Short-Term Memory (LSTM), Random Forest, and Extreme Gradient Boosting (XGBoost), in predicting the next-day closing price of Indonesia's Composite Stock Price Index (IHSG) as a baseline before further feature engineering is applied in a broader ongoing study. Daily historical price data (Open, High, Low, Close, Volume) covering January 2015 to early 2026 were collected from Yahoo Finance. Two feature representations were compared: the raw 5-dimensional OHLCV attributes, and a 64-dimensional temporal representation extracted from the same OHLCV data using a Bidirectional LSTM (Bi-LSTM) encoder. Each representation was evaluated using LSTM, Random Forest, and XGBoost, with performance measured by Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) on a chronological 80:20 train-test split. The results show that the raw OHLCV representation combined with LSTM achieved the best performance (RMSE = 196.11, MAE = 164.14, MAPE = 2.18%), outperforming Random Forest and XGBoost on the same representation (MAPE 3.78% and 3.80%). Encoding the OHLCV data into a 64-dimensional Bi-LSTM representation without any external signal reduced accuracy across all three algorithms, most notably for LSTM (MAPE rising to 7.13%), indicating that unsupervised temporal encoding discards useful absolute price information when no additional predictive feature is introduced. These findings establish a validated baseline configuration and evaluation pipeline for IHSG closing-price prediction, intended as the foundation for a subsequent study that integrates external textual features into the same experimental framework.  
INOVASI PEMBELAJARAN INTERAKTIF DI ERA DIGITAL: VIDEOSCRIBE JADI SOLUSI DI SDN SEMOLOWARU IV Nuryana, I Kadek Dwi; Cinthya, Monica; Yustanti, Wiyli; Devayana Putra, Cendra
ABIDUMASY Vol 7 No 2 (2026): ABIDUMASY : JURNAL PENGABDIAN KEPADA MASYARAKAT
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33752/abidumasy.v7i2.12099

Abstract

The development of multimedia technology provides opportunities for teachers to deliver learning materials in a more engaging and interactive manner. However, its utilization in elementary schools remains limited, including at SDN Semolowaru IV Surabaya, which affects the quality of instructional material delivery. This community service activity aimed to enhance teachers’ competencies in developing multimedia-based learning media through training on the use of VideoScribe as a whiteboard animation tool. The program was implemented through a series of activities consisting of socialization, demonstrations, hands-on video production practice, mentoring, and evaluation. A total of 20 teachers participated in the training and were provided with a training module as a guide for further implementation. The results indicated that 87.5% of participants considered the training highly beneficial and easy to apply in classroom learning, while most participants found the materials and training methods easy to understand. The activity successfully improved teachers’ skills in producing multimedia-based learning videos and encouraged the adoption of digital learning media. These findings demonstrate that VideoScribe can serve as an effective alternative instructional medium that supports the development of more engaging learning materials and contributes to improving the quality of education in the digital era.
Development and Functional Testing of an AI-Based Virtual Personal Assistance Guide for Detecting Psychological Disorders among University Students Wahono, Satriyo Imam Arifin; Putra, Cendra Devayana; Wiyono, Agus; Nuryana, I Kadek Dwi
Decode: Jurnal Pendidikan Teknologi Informasi Vol. 6 No. 3: NOVEMBER 2026
Publisher : Program Studi Pendidikan Teknologi Infromasi UMK

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51454/decode.v6i3.1853

Abstract

Student mental health has become an important concern, as academic, financial, social, and emotional pressures may be associated with symptoms of depression, anxiety, and stress. This study aims to develop and evaluate a Virtual Personal Assistance Guide (VPAG) based on Artificial Intelligence as a supporting tool for initial screening and self-reflection among students at Universitas Negeri Surabaya. The study employed a Research and Development approach using the ADDIE model, comprising Analysis, Design, Development, Implementation, and Evaluation. The system provides 11 features, including DASS-21, voice input, indicative interpretation, action recommendations, professional referrals, and progress charts. The evaluation involved Black Box Testing, validation by two experts, and assessments from 68 students across seven study programs. Functional testing demonstrated that all 11 features operated according to the predefined test scenarios. Expert validation yielded a mean score of 4.50 out of 5, while student evaluations achieved a mean score of 4.27 out of 5 based on the evaluation questionnaire. Expert feedback emphasized the need for empathetic language, non-diagnostic explanations of results, and clearer professional referral mechanisms. These findings indicate that VPAG has potential as a supporting tool for initial screening, mental health education, and student self-reflection. However, the evaluation does not establish clinical effectiveness or the accuracy of AI-generated interpretations; therefore, VPAG cannot replace professional diagnosis or mental health services.
INTERNASIONALISASI PROGRAM STUDI SISTEM INFORMASI MELALUI BENCHMARKING KURIKULUM, PEER LECTURE, DAN KOLABORASI RISET Cendra Devayana Putra; Ghea Sekar Palupi; Erik Rahman
Masyarakat: Jurnal Pengabdian Vol. 3 No. 3 (2026)
Publisher : Yayasan Pendidikan Dan Pengembangan Harapan Ananda

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58740/m-jp.v3i3.891

Abstract

Kerja sama Program Studi S1 Sistem Informasi Universitas Negeri Surabaya (UNESA) dan Universiti Teknologi MARA (UiTM), Malaysia, telah dilandasi nota kesepahaman, tetapi belum memiliki pemetaan kurikulum tingkat mata kuliah, aturan konversi antara satuan kredit semester (SKS) dan kredit Malaysian Qualifications Framework (MQF), penyelarasan kalender akademik, maupun agenda riset bersama, sementara mahasiswa mitra jarang memanfaatkan database ilmiah. Kegiatan pengabdian kepada masyarakat (PkM) ini bertujuan memetakan keselarasan kurikulum sebagai dasar pengakuan kredit, merintis peer lecture dua arah, dan membangun kolaborasi riset. Sasaran kegiatan adalah 33 dosen dan mahasiswa UiTM Rembau dan Shah Alam. Kegiatan menerapkan Asset-Based Community Development (ABCD) dalam tiga tahap: analisis dokumen kurikulum dan kalender akademik; pelaksanaan research presentation, pemaparan benchmarking, peer lecture, dan lokakarya literasi database; serta evaluasi melalui kuesioner pre–post, tugas penelusuran database, dan analisis dokumen luaran. Benchmarking menunjukkan 14 dari 15 area pengetahuan selaras dengan program Information Systems Engineering (CDCS266), sedangkan pemetaan dengan program Information Systems Management (SI262) menghasilkan 25 pasangan mata kuliah, 11 di antaranya pada paritas semester yang sama. Konversi berbasis jam belajar (1 SKS = 45 jam; 1 kredit UiTM = 40 jam) memungkinkan transfer kredit tanpa mengubah kurikulum, dan lecture exchange memperoleh skor kesiapan 15/15. Kepuasan peserta mencapai 4,37/5, skor pemahaman naik 40,6% (p < 0,001), 80% peserta mampu menelusur database ilmiah secara mandiri, dan tiga topik riset bersama disepakati. Kegiatan ini memberikan dasar operasional bagi pertukaran dosen dan mahasiswa serta peta jalan kolaborasi berkelanjutan, dari kuliah tamu daring hingga double degree 2+2, yang dapat direplikasi pada kemitraan sejenis.