Febri Abdullah

ORCID: 0009-0004-6685-8517
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Artificial Intelligence in Games
  • Natural Language Processing Techniques
  • Video Analysis and Summarization
  • Explainable Artificial Intelligence (XAI)
  • Artificial Intelligence in Healthcare and Education
  • Digital Games and Media
  • Educational Games and Gamification
  • AI in Service Interactions
  • Virtual Reality Applications and Impacts
  • Human Motion and Animation
  • Machine Learning and Data Classification
  • Machine Learning in Healthcare
  • Creativity in Education and Neuroscience
  • Cognitive Abilities and Testing
  • EEG and Brain-Computer Interfaces
  • Gaze Tracking and Assistive Technology
  • Psychosomatic Disorders and Their Treatments
  • Sleep and Wakefulness Research
  • Computer Graphics and Visualization Techniques
  • Advanced Vision and Imaging
  • Media Influence and Health
  • Software Engineering Research
  • Social Robot Interaction and HRI
  • Emotion and Mood Recognition

Ritsumeikan University
2019-2025

This paper presents the first ChatGPT4PCG Competition at 2023 IEEE Conference on Games. The objective of this competition is for participants to create effective prompts ChatGPT–enabling it generate Science Birds levels with high stability and character-like qualities–fully using their creativity as well prompt engineering skills. ChatGPT a conversational agent developed by OpenAI. selected platform because designing an Angry Birds-like level not trivial task due in-game gravity; quality...

10.1109/cog57401.2023.10333206 article EN 2021 IEEE Conference on Games (CoG) 2023-08-21

This study summarizes the first ChatGPT4PCG competition held at 2023 IEEE Conference on Games. The goal of is to explore emergent abilities publicly available LLMs in performing complex tasks related procedural content generation, specifically physics-based level generation for Angry Bird-like games. Participants are tasked with submitting their prompts ChatGPT generate Birds-like game structures that resemble English uppercase characters. A structure a collection stacked objects comprising...

10.1109/tg.2024.3376429 article EN IEEE Transactions on Games 2024-01-01

This paper presents null-shot prompting. Null-shot prompting exploits hallucination in large language models (LLMs) by instructing LLMs to utilize information from the "Examples" section that never exists within provided context perform a task. While reducing is crucial and non-negligible for daily critical uses of LLMs, we propose current landscape which these still hallucinate, it possible, fact, exploit increase performance performing tasks compared standard zero-shot Experiments with...

10.48550/arxiv.2401.08273 preprint EN cc-by arXiv (Cornell University) 2024-01-01

This paper presents a study on biases present in the story endings for story-driven games generated by ChatGPT. The uses various prompts to assess ChatGPT's output. results emphasize consistent inclination towards positive stories Even when explicitly instructed generate neutral endings, ChatGPT exhibited bias outcomes. These raise concerns regarding training data and alignment processes used OpenAI train ChatGPT, as they may reflect societal or preferences of majority data. Addressing these...

10.1109/icce-berlin58801.2023.10375663 article EN 2023-09-03

10.18653/v1/2024.emnlp-main.740 article EN Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing 2024-01-01

This study proposes a method for generating Angry Birds-like game levels featuring domino effect generated based on Rube Goldberg Machine (RGM) mechanisms, which allow them to be completed by one shot of bird. The proposed generates level selecting predefined segments consisting several objects arranged in way that creates among them. To increase the variability levels, procedurally varying structure top certain blocks segment. Our results show RGM generator is comparable two existing...

10.1109/cig.2019.8847996 article EN 2021 IEEE Conference on Games (CoG) 2019-08-01

This paper proposes a method to generate interesting Angry Birds-like game levels featuring the Rube Goldberg machine (RGM) mechanism using Constrained Novelty Search (CNS). An RGM level in Birds emphasizes domino effect, which allows it be completed by only one bird shooting. By evolving feasible population and infeasible CNS, our results show that entropy of block-type frequencies is higher than previous generator two requirements achieve playable - 100% stability perfect-shot rate are...

10.1109/cog47356.2020.9231547 article EN 2021 IEEE Conference on Games (CoG) 2020-08-01

This paper proposes a method for generating Angry Birds-like game levels, and their gameplays, that promote spectator's emotions. Each of such levels features domino effect generated based on Rube Goldberg Machine (RGM) mechanisms, allowing it to be completed by one perfect shot bird. We evaluate the effects emotions comparing two sets gameplay videos; with only shots other imperfact (i.e., gameplays were not successfully shot). conducted an online survey using Positive Negative Affect...

10.1109/icce-asia46551.2019.8941596 article EN 2022 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia) 2019-06-01

This paper presents a game system aimed towards promoting mental health, which implements singing as an input modality to control the bird-shots in Angry-Birds-like game. Based on existing research, can act catalyst that medically reduces stress and thus be used for rehabilitation. Our works by analyzing player adjusting shooting performance based score. focuses how is developed its functions.

10.1109/cog47356.2020.9231716 article EN 2021 IEEE Conference on Games (CoG) 2020-08-01

This study presents the Web-Agile Facial Emotion Recognition and Eye-Tracking System (WAFER-ET), which combines AI-based facial expression recognition eye-tracking models. Eye tracking is implemented using WebGazer.js, a custom lightweight CNN-based model (CLCM). Experimental analysis showed effective performance in system's real-time processing data streaming. The low delay between experimental results platforms memory load were achieved. Moreover, integrating eye WAFER-ET system enables...

10.1109/icce-berlin58801.2023.10375633 article EN 2023-09-03

This paper presents the second ChatGPT4PCG competition at 2024 IEEE Conference on Games. In this edition of competition, we follow first edition, but make several improvements and changes. We introduce a new evaluation metric along with allowing more flexible format for participants' submissions making to pipeline. Continuing from aim foster explore realm prompt engineering (PE) procedural content generation (PCG). While saw success, it was hindered by various limitations; mitigate these...

10.48550/arxiv.2403.02610 preprint EN arXiv (Cornell University) 2024-03-04

This paper presents our work to enhance a state-of-the-art level generator (Sketch-to-Level Generator) that generates levels for an Angry-Birds-like game from drawn sketches. To achieve this task, Cycle-Consistent Adversarial Networks (Cycle-GAN) are used. CycleGAN is trained using two datasets: sketch drawings and typical level-structures. The former taken Google's Quick, Draw! datasets, the latter winning at 2017 2018 AIBIRDS generation competitions. output of used as input Sketch-to-Level...

10.1109/gcce50665.2020.9291893 article EN 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE) 2020-10-13

This paper investigates to which degrees of playing games by using hand motions improve brain memory. Based on previous studies in psychology reporting that exercise could affect function and memory, we develop an interface for motions. It works detecting through image processing, translating them into commands keyboard press, sending such the target game application; it with any existing without need modify source code only requires off-the-self webcam. An experiment is conducted a jumping...

10.1145/3359566.3364689 article EN 2019-10-25

This demo paper presents a smile interface to promote the spectator's emotion. Here, is defined as human-computer interaction system that detects user's smile. A past study suggested watching Science Birds gameplay featuring Rube Goldberg Machine mechanisms with domino effect can clone version of Angry for research purposes. Furthermore, other studies playing has benefit promoting player's However, such from perspective yet be investigated. The presented will used in investigation future.

10.1109/cog51982.2022.9893545 article EN 2021 IEEE Conference on Games (CoG) 2022-08-21

This paper presents the first ChatGPT4PCG Competition at 2023 IEEE Conference on Games. The objective of this competition is for participants to create effective prompts ChatGPT--enabling it generate Science Birds levels with high stability and character-like qualities--fully using their creativity as well prompt engineering skills. ChatGPT a conversational agent developed by OpenAI. selected platform because designing an Angry Birds-like level not trivial task due in-game gravity; quality...

10.48550/arxiv.2303.15662 preprint EN cc-by arXiv (Cornell University) 2023-01-01

This study presents a virtual reality (VR) game with mechanic that enables audience participation. It has been previously shown VR games offer better immersion, as well improved enjoyment for the player. By introducing participation we aim to investigate extent which an becomes emotionally invested while observing and providing support To achieve that, preliminary experiment was conducted measure of player audiences, evaluate social interaction among members. The results show potential in...

10.1109/gem59776.2023.10390005 article EN 2023-11-19
Coming Soon ...