Claim Missing Document
Check
Articles

Fuzzy-Driven Adaptive NPC Behavior in a Meme-Based Platformer Game for Android Mobile: Perilaku NPC Adaptif Berbasis Fuzzy dalam Game Meme Platformer Berbasis Ponsel Android Encep Sayid Amrulloh; Rio Andriyat Krisdiawan; Iwan Lesmana; Lutfi Rohmawati
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.440

Abstract

Game-based applications are increasingly used beyond entertainment to deliver adaptive, engaging user experiences. Yet, many mobile platformer games still rely on static enemy behaviors, leading to repetitive gameplay. This study introduces Pepe the Ponderland Warrior, a 2D platformer for Android that incorporates culturally relevant meme characters and dynamic NPC behavior using fuzzy logic. Developed with the Game Development Life Cycle (GDLC), the game uses the Fuzzy Sugeno inference system to adapt NPC responses based on player distance, health, and damage received. UML modeling guided the system design, while testing included black-box, white-box, and User Acceptance Testing (UAT). The fuzzy-based system enabled real-time, context-aware NPC decisions, creating more varied and challenging gameplay. The game passed functional and logical testing, with UAT from 30 users producing a high feasibility score of 81.2%, reflecting satisfaction in design, gameplay, and difficulty balance. By integrating fuzzy logic with meme-inspired content, this study offers a novel and efficient AI approach for mobile games, highlighting potential for expansion across platforms and with more adaptive inputs.
Real-Time Bayesian Knowledge Tracing for Adaptive Vocabulary Practice in an Adventure Educational Game: Architecture, Verification, and Reproducibility: Real-Time Bayesian Knowledge Tracing untuk Praktik Kosakata Adaptif pada Game Edukasi Bergenre Petualangan: Arsitektur, Verifikasi, dan Reproducibility Ikhsan Khaeruddin; Rio Andriyat Krisdiawan; Nida Amalia Nasikin
NUANSA INFORMATIKA Vol. 20 No. 1 (2026): Nuansa Informatika 20.1 Januari 2026
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v20i1.535

Abstract

Vocabulary learning in primary English classes is often constrained by heterogeneous learner readiness, where fixed game progression can under-serve both struggling and advanced students. This study aims to implement and technically validate a reproducible real-time adaptivity mechanism using Bayesian Knowledge Tracing (BKT) in a Unity-based Android vocabulary game. The research adopts a design-and-verification approach using the Game Development Life Cycle (GDLC), supported by requirements elicitation (classroom observation, teacher interview, and literature review). The adaptive engine applies BKT to update mastery after each quiz response and routes learners using a mastery-threshold policy, while event-level logs are stored locally and exportable for auditability. The main results demonstrate that adaptive mode activation, mastery updates, persistence of adaptive state, and mastery-gated progression function consistently in end-to-end black-box tests. Algorithm-level credibility is strengthened through white-box basis-path verification of the UpdateProbability() routine, ensuring independent execution paths for correct and incorrect responses are covered. This work contributes a deployable Unity/Android architecture for real-time BKT-driven adaptivity, accompanied by verification artifacts and reproducibility recommendations to support technical audit, replication, and subsequent controlled effectiveness studies.
Preprocessing and Feature Engineering of Gameplay Logs for Adaptive Mathematics Learning Dataset Construction Rio Andriyat Krisdiawan; Dede Husen; Heri Herwanto
Bulletin of Intelligent Machines and Algorithms Vol. 1 No. 4 (2026): BIMA May 2026 Issue
Publisher : Maheswari Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.65780/bima.v1i4.23

Abstract

This study reports the preprocessing and feature engineering of gameplay logs collected from a first-grade elementary mathematics educational game prototype. The study aimed to transform raw gameplay activity records into structured analytical datasets that can support early performance description and serve as an initial data preparation stage for future adaptive mathematics learning research. A limited trial was conducted with nine first-grade students who played six sequential game levels covering early numeracy topics, including counting, number ordering, number reading, place value, and mixed review. The gameplay logs captured event-based student interactions, including session identity, level, question, selected answer, correctness status, attempt count, help usage, response time, score, and event type. The data processing workflow included data validation, cleaning, anonymization, data type handling, event filtering, feature engineering, dataset aggregation, and descriptive analysis. The preprocessing stage produced 262 clean gameplay log records consisting of 171 answer events, 28 help events, 54 level completion events, and nine game completion events. Feature engineering generated analytical indicators such as level accuracy, average response time, total help usage, average attempt count, performance category, student state, and initial adaptation action. The final outputs were organized into answer-level, level-level, student-level, and adaptive feature datasets. The anonymized dataset and data dictionary are provided as supplementary materials to support reproducibility and future reuse. The results indicate that raw gameplay logs can be converted into structured datasets for early learning analytics and preliminary adaptive learning data preparation, without making claims about learning effectiveness or final adaptive model performance.
OPTIMALISASI PEMBELAJARAN MATEMATIKA BERBASIS GAMIFIKASI MELALUI PENDAMPINGAN APLIKASI DUOLINGO MATH UNTUK MENINGKATKAN NUMERASI SISWA SEKOLAH DASAR Rio Andriyat Krisdiawan; Nida Amalia Asikin; Dede Husen; Heri Herwanto
Jurnal Abdi Insani Vol 13 No 5 (2026): Jurnal Abdi Insani
Publisher : Universitas Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/abdiinsani.v13i5.3845

Abstract

Rendahnya capaian numerasi siswa sekolah dasar masih menjadi permasalahan utama dalam pembelajaran matematika. Pembelajaran yang didominasi metode konvensional cenderung membuat siswa kurang termotivasi dan sulit memahami konsep numerasi dasar. Di sisi lain, perkembangan teknologi digital membuka peluang pemanfaatan media pembelajaran berbasis aplikasi yang lebih interaktif dan menarik. Namun, pemanfaatan teknologi tersebut di sekolah dasar belum dilakukan secara optimal dan terintegrasi dalam pembelajaran. Kegiatan pengabdian kepada masyarakat ini bertujuan untuk mengoptimalkan pembelajaran matematika melalui pendampingan penggunaan aplikasi Duolingo Math berbasis gamifikasi guna meningkatkan motivasi dan kemampuan numerasi siswa sekolah dasar serta memperkuat peran guru dalam pemanfaatan media pembelajaran digital. Metode kegiatan menggunakan pendekatan edukatif-partisipatif berbasis teknologi yang meliputi analisis kebutuhan, perancangan solusi pembelajaran, implementasi pendampingan langsung di kelas, serta evaluasi berbasis kuesioner. Kegiatan melibatkan siswa kelas III dan IV serta guru kelas di dua sekolah dasar mitra di Kabupaten Kuningan. Evaluasi dilakukan menggunakan kuesioner skala Likert 1–5 untuk mengukur persepsi guru dan siswa. Hasil kegiatan menunjukkan bahwa penggunaan Duolingo Math memperoleh respons sangat positif. Rata-rata skor evaluasi guru berada pada kategori sangat baik (mean > 4,6) pada aspek persepsi manfaat, kemudahan penggunaan, dan kesesuaian kurikulum. Siswa menunjukkan peningkatan motivasi dan keterlibatan belajar yang sangat tinggi dengan skor motivasi rata-rata 4,95 serta persepsi positif terhadap peningkatan pemahaman numerasi dasar. Hambatan teknis relatif rendah dan tidak mengganggu pelaksanaan kegiatan. Kesimpulannya, pendampingan penggunaan Duolingo Math efektif sebagai media pendukung pembelajaran matematika berbasis gamifikasi di sekolah dasar dan berpotensi diterapkan secara berkelanjutan.
Dynamic Scoring for Quran Memorization Assessment in Journey of Ayat Educational Game Using the Fuzzy Tsukamoto Algorithm Aysyah Noor Shobah; Rio Andriyat Krisdiawan; Rio Priantama
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6401

Abstract

Conventional Qur’an memorization assessment in Madrasah Diniyah Takmiliyah (MDT) often relies on direct teacher evaluation and simple correct-or-wrong scoring, which may not fully represent students’ memorization performance. At MDT An-Nidzom, preliminary assessment showed that students experienced difficulties in completing verse fragments of selected short surahs. Objective: This study aimed to develop Journey of Ayat, an Android-based educational game, and implement the Fuzzy Tsukamoto algorithm as a dynamic scoring mechanism for Qur’an memorization assessment. Methods: The study employed a Research and Development approach using the Game Development Life Cycle. The scoring model used three input variables, namely correct answers, completion time, and remaining lives, to generate a final score. The system was evaluated through black-box testing, white-box testing, Fuzzy Tsukamoto calculation validation, User Acceptance Testing, and pretest-posttest analysis involving 40 students and one teacher at MDT An-Nidzom. Results: The developed system provided memorization practice, gameplay interaction, score calculation, and teacher monitoring. The Fuzzy Tsukamoto calculation was consistent with manual calculation, with an error value of 0.00 in the validation scenario. Black-box testing showed that the main features operated as expected, while white-box testing produced a cyclomatic complexity value of 2. The UAT results indicated very feasible ratings of 92.00% from the teacher and 89.06% from students. The mean memorization score increased from 62.75 to 70.00, and the Wilcoxon signed-rank test showed a statistically significant difference in the observed sample (p = 0.0237). Conclusion: Journey of Ayat is feasible as a supporting medium for Qur’an memorization practice and preliminary assessment. However, further studies involving broader samples, control-group comparison, and oral recitation assessment are needed to strengthen evidence of learning effectiveness.
Gamified English Vocabulary Puzzle Game with FSM-Based Emotional Feedback and Fisher–Yates Shuffle Muhammad Fachrul Reihan Fauzian; Rio Andriyat Krisdiawan; Nida Amalia Asikin
Media Jurnal Informatika Vol 18 No 1 (2026): Media Jurnal Informatika
Publisher : Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v18i1.6402

Abstract

English vocabulary learning among elementary school students often faces challenges related to low engagement, repetitive practice activities, and limited interactive feedback in conventional learning media. Educational games with gamification elements can provide a more engaging learning environment, while rule-based character feedback and randomized puzzle arrangements may improve gameplay variation and user interaction. Objective: This study aimed to develop an Android-based English vocabulary puzzle game that integrates gamification elements, an FSM-based emotional feedback mechanism, and the Fisher–Yates Shuffle algorithm for sixth-grade elementary school students. Methods: The game was developed using the Game Development Life Cycle (GDLC) method through initiation, pre-production, production, testing, beta, and release stages. The application was implemented using Unity and C#, with Firebase Realtime Database used for data management. System evaluation was conducted through Black Box Testing, White Box Testing, and User Acceptance Testing involving 35 sixth-grade students of SD Negeri 2 Cikeusal. Results: The developed game successfully implemented gamification elements, including scores, levels, time limits, life indicators, and visual character feedback. The FSM-based mechanism generated predefined emotional responses through thirteen states and seventeen events, while the Fisher–Yates Shuffle algorithm produced varied puzzle arrangements. Black Box Testing confirmed that all main features functioned as expected, and White Box Testing verified the control flow of the FSM and Fisher–Yates Shuffle implementations. User Acceptance Testing produced an overall acceptance score of 94.3%, indicating that the game was well accepted by users. Conclusion: The integration of gamification, FSM-based emotional feedback, and Fisher–Yates Shuffle  indicates its potential to provide an engaging and interactive medium for English vocabulary practice. However, this study evaluated user acceptance and system functionality, not direct vocabulary learning improvement.
Real-Time Character Matching Using Brute Force Algorithm in Typing Game-Based Learning Rio Andriyat Krisdiawan; Rifky Putra Pratama; Nida Amalia Asikin
METIK Jurnal Vol. 10 No. 1 (2026): METIK Jurnal Issue Published
Publisher : LPPM Universitas Mulia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47002/vfc61h04

Abstract

Typing skills are an essential component of digital literacy; however, conventional typing practice methods tend to be less engaging, which negatively affects students’ motivation and typing accuracy. This study aims to design and implement a computer-based typing game–based learning system that applies the Brute Force algorithm as a real-time character matching mechanism. The system was developed using the Game Development Life Cycle (GDLC) method, which consists of the initiation, pre-production, production, testing, and release phases. The Brute Force algorithm is employed to validate the correspondence between user input and the target words displayed in the game by sequentially comparing each character. System evaluation was conducted through functional testing, algorithm performance analysis, and a User Acceptance Test (UAT) involving teachers and students. The results indicate that the Brute Force algorithm achieves high character matching accuracy, deterministic behavior, and fast response time for relatively short word lengths. The time complexity analysis demonstrates a linear pattern O(n), while still satisfying real-time feedback requirements in educational games. Furthermore, the UAT results show a high level of user acceptance, indicating that the system is stable, consistent, and feasible as a game-based typing practice medium. Therefore, the Brute Force algorithm is proven to be suitable for implementation in typing game–based learning, particularly for basic to intermediate learning scenarios.
Implementasi Mekanisme Adaptif Berbasis Q-Learning pada Game Edukasi Matematika Numerasi Awal Krisdiawan, Rio Andriyat; Husen, Dede; Herwanto, Heri
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol. 12 No. 2 (2026): Volume 12 No 2
Publisher : Program Studi Informatika

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

Abstract

Pembelajaran numerasi awal membutuhkan media digital yang tidak hanya interaktif, tetapi juga mampu menyesuaikan tingkat tantangan berdasarkan performa peserta didik. Penelitian ini bertujuan mengimplementasikan mekanisme adaptif berbasis Q-Learning pada game edukasi matematika numerasi awal untuk siswa kelas awal sekolah dasar. Penelitian menggunakan pendekatan implementatif-deskriptif dengan fokus pada integrasi alur permainan, gameplay logging, pemodelan state siswa, pemilihan action adaptif, perhitungan reward, pembaruan Q-value, dan transisi tingkat kesulitan. Game dikembangkan dalam enam level aktivitas yang mencakup materi menghitung objek, mengenali simbol bilangan, mengurutkan bilangan, serta memahami nilai tempat sederhana sampai 20. Pengujian dilakukan di SDN 1 Langseb dengan melibatkan 38 siswa dan 2 guru. Hasil implementasi menunjukkan bahwa sistem mencatat 1.430 baris gameplay log yang terdiri atas 683 event jawaban, 253 event bantuan, 228 event penyelesaian level, 228 event keputusan adaptif, dan 38 event penyelesaian permainan. Jumlah 228 keputusan adaptif sesuai dengan enam level yang diselesaikan oleh 38 siswa, sehingga menunjukkan bahwa mekanisme adaptif berjalan pada setiap akhir level. Distribusi action menghasilkan 71 keputusan Naik, 47 Tetap, dan 110 Turun/Penguatan. Rata-rata Q-value meningkat dari 1,115 menjadi 1,199 dengan rata-rata delta Q sebesar 0,084. Hasil uji penerimaan pengguna menunjukkan persentase UAT sebesar 79,21% pada siswa, 80,00% pada guru, dan 79,25% secara keseluruhan, dengan kategori baik. Hasil penelitian menunjukkan bahwa mekanisme adaptif berbasis Q-Learning dapat diintegrasikan ke dalam game edukasi matematika numerasi awal melalui pencatatan aktivitas, pembentukan state, pemilihan action, reward, pembaruan Q-value, dan pengaturan tingkat kesulitan. Penelitian ini dibatasi pada evaluasi implementasi dan penerimaan pengguna, bukan pada pengujian kausal terhadap peningkatan hasil belajar.