Article Per Year (5 Year)
p-Index From 2021 - 2026
3.46
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Kursor Khizanah al-Hikmah : Jurnal Ilmu Perpustakaan, Informasi, dan Kearsipan Jurnal Penelitian Pendidikan IPA (JPPIPA) JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI JURNAL TEKNOLOGI DAN OPEN SOURCE Jurnal Teknologi Sistem Informasi dan Aplikasi JSI (Jurnal sistem Informasi) Universitas Suryadarma Journal of Information System,Graphics, Hospitality and Technology Jurnal Ilmu Komputer dan Desain Komunikasi Visual ScientiCO : Computer Science and Informatics Journal bit-Tech JATI (Jurnal Mahasiswa Teknik Informatika) JTIK (Jurnal Teknik Informatika Kaputama) Jurnal Ilmiah Manajemen, Bisnis dan Kewirausahaan Jurnal Teknik Informatika Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI) Seminar Nasional Ilmu Terapan Jurnal Multidisiplin Sahombu Computing Insight: Journal of Computer Science
Prasasti Karunia Farista Ananto
Universitas Islam Negeri Sunan Ampel Surabaya
Agriculture, Biological Sciences & Forestry Arts Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mechanical Engineering Physics Other

Published : 26 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : bit-tech

 1 
UI/UX Development of a Boarding House Reservation Application: A Design Thinking Approach in Surabaya Azizatul Fara Dibah; Abdul Rezha Efrat Najaf; Prasasti Karunia Farista Ananto
bit-Tech Vol. 8 No. 2 (2025): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i2.3320

Abstract

Fragmented, inconsistent, and frequently outdated information about boarding-house availability, facilities, and pricing remains a persistent usability problem in existing digital platforms. Current UI/UX and reservation-system research has not sufficiently addressed these issues within the specific context of urban rental ecosystems, creating gap in designing solutions that respond to the needs of both tenants and property owners. This study addresses that gap by developing and evaluating a user-centered interface for a boarding-house reservation application using the five-stage Design Thinking framework: empathize, define, ideate, prototype, and test. Insights were gathered from 30 participants representing owners, tenants, and administrators in Surabaya, forming the basis for personas, information architecture, user flows, and low- to high-fidelity prototypes designed in Figma. Usability and interface quality were examined through task-based testing, the System Usability Scale (SUS), and Nielsen’s heuristic evaluation to integrate both user perception and normative usability standards. Initial testing produced SUS scores of 74.5 (owners), 76.5 (tenants), and 66 (administrators), indicating acceptable but improvable usability and several interface issues. Iterative refinement led to marked enhancements, with second-round SUS scores of 90, 87, and 89, accompanied by high learnability (96–97%), strong memorability (95–96%), and low error rates (0.0306–0.0800). A minor efficiency decrease was attributed to unstable network conditions rather than design flaws. Overall, the findings demonstrate that structured, iterative UI/UX development supported by heuristic auditing effectively resolves core information and interaction challenges in boarding-house reservation systems. The final prototype demonstrates high usability and provides a replicable design rationale for future implementation and scaling.
Performance Analysis of Reasoning Models in RAG-Based Question Answering System for University Admission Services Setiawan, Muhammad Surya Adhi; Pratama, Arista; Ananto, Prasasti Karunia Farista
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3707

Abstract

Access to accurate, relevant, and timely information is crucial for prospective university students; however, conventional information services often struggle with high query volumes and the risk of generative hallucinations in automated systems. This study investigates whether reasoning-oriented large language models provide measurable improvements in response quality within a Retrieval-Augmented Generation (RAG) architecture for university admission services. The study hypothesizes that internal chain-of-thought reasoning improves factual grounding compared with non-reasoning models under identical retrieval conditions. A vector-based institutional knowledge base was constructed from 30 official admission sources using VoyageAI embeddings and evaluated on a multilingual dataset of 353 real-world inquiries in Indonesian, English, and Javanese dialects. To isolate the effect of reasoning capabilities, retrieval outputs and prompt configurations were controlled across all models. Performance was evaluated using the RAGAS framework across six models categorized as reasoning (DeepSeek-R1, Gemini-2.5-Flash, o4-mini) and non-reasoning (DeepSeek-V3, Gemini-2.0-Flash, GPT-4o-mini). The results show that reasoning models achieved a higher average RAGAS score (0.7772) than non-reasoning models (0.7289), representing a 6.63% improvement, with the largest gain observed in factual correctness (+15.95%). Additional multilingual benchmarking confirmed that reasoning models maintain more stable performance across languages. Gemini-2.5-Flash achieved the highest composite score (0.8207) while maintaining favorable cost efficiency. These findings indicate that reasoning-enabled models significantly improve factual reliability in domain-specific RAG systems, although overall system performance remains strongly dependent on retrieval quality.
Co-Authors A., Faris Muslihul Abdul Rezha Efrat Najaf Adisty Yudianto Putri, Dinda Adit Haptono, Anggoro Ahmad Yusuf Aji, Bramasta Kurnia Alvian Jaya, Muhammad Andhika Maheswara, Wahyu Pratama Auralia Wibowo, Zyndi Aurelia Salsabiila Putri Azizatul Fara Dibah Bondan Setya Adi N Cahyo Wibowo, Nur DA, Suryani Damayanti, Arifa Devina Nur Rahmadani S.P Evi Fatimatur Rusydiyah Fitri, Anindo Saka Hatma Suryotrisongko ILHAM Ilham Ilham Iqbal Ramadhani Mukhlis Mahardhika, Muhammad Ilyasa Melinda Citrasena Cahyaningrum Milad, Mohammad Khusnu Moch Yasin, Moch Novia Ramadhani Pratama, Arista Puput Nur Fadilah Putra, M. Naufal Rizqullah Kesih S. Rafika Rahmawati Rafika Rahmawati Rafika Rahmawati Rahmawati, Ulfa Emi Randu Yudhistira Trisna Fauzi, Damar Raulia Riski Rizvina Hadi Imani Satibi, Iswanda Fauzan Sembilu, Nambi Setiawan, Muhammad Surya Adhi Thomas Aquino Berno Doduk Tri Luhur Indayanti Sugata Tri Puspa Rinjeni Ulfa Emi Rahmawati Virdha Rahma Aulia Wafrina, Nadiatu Yusuf Amrozi Zuna, Muhammad