This paper presents a new approach for leveraging ChatGPT in fighting game commentary generation task. Commentary generation often relies on deep learning techniques, which typically demand extensive data to achieve effectiveness. Large language models (LLMs) have become essential due to their remarkable ability to process data efficiently, thanks to their extensive training on vast datasets. Our proposed approach integrates the use of LLMs, specifically the GPT-3.5 model, for generating commentaries through the utilization of various prompts with data from the open-source fighting game, DareFightingICE. Four prompt variants are employed to assess the effectiveness of each prompt components. Objective evaluation using natural language metrics reveals that different prompt components significantly affect the generated commentaries. Additionally, subjective evaluation through a questionnaire reveals that prompts without parameter definitions received the highest preference from human evaluators. These results suggest that LLMs exhibit versatility in generating fighting game commentaries and hold promise for broader applications.
1 January 2007 in International Journal of Computational Intelligence Research
This paper used IBM Watson Assistant to create dialog for a “friendly” chatbot for supporting elderly people who have to live alone. The system invites the elderly to have a continued conversation for the purpose of decreasing problems related to depressions and slowing the progression of dementia. We created dialogues in Japanese for three characters, a benign nurse, a lovely girl, and a kind senior, and seven events. The accuracy was 93.44% in the case of talking with the different words in dialogues having the same meaning. This chatbot can act as a communication function in our previously proposed smart mirror to support the elderly by enabling them to talk with a bot in long-term health-care programs for monitoring the elderly in the future.
This paper describes a conceptual framework for smart home that supports elderly people. We describe and compare the principles and general techniques used in automatic human fall detection via a surveillance indoor camera, which are implemented in smart home applications. The comparisons illustrate the benefits and the weak points of each technique. In addition, the challenges and trends are discussed for improving the effective fall detection applications, which is a part in elderly smart care systems in near future.
This paper presents RehabHub, a home-based exergaming system that integrates standardized physical assessment directly into gameplay by using a common webcam and MediaPipe for real-time pose estimation. The system quantifies upper-limb movement quality, specifically abduction, shoulder flexion, and elbow flexion based on FMA-UE guidelines, by applying Dynamic Time Warping (DTW) together with a Z-score-based scoring model that relies on data from non-clinical adult participants. A pilot study, which included movements simulated with a 5-kg resistance band, evaluated three feature-extraction methods. The findings indicate that the single-angle method provides the clearest distinction between normal and abnormal movements, particularly for abduction and elbow flexion. In the case of shoulder flexion, the score separation was less distinct because of movement variability and posture-related angle fluctuations, which suggests that further refinement of feature design is needed. The cloud-based platform supports remote monitoring and gives caregivers access to both performance scores and recorded exercise videos. Overall, the results demonstrate the feasibility of a low-cost webcam-based assessment integrated into exergaming, and they highlight important trends for improving abnormal-movement detection in home rehabilitation systems.
This paper discusses the popularity of live streaming video games and its potential to address psychological challenges, especially during the COVID-19 pandemic. An audience participation game (APG) that involve massive audiences in gameplay, blurring the lines between viewers and players, is introduced. The game highlights the dynamic adjustment of AI character strengths based on audience inputs, specifically cheering and jeering. The study examines factors that influence user experience (UX) and activeness in APG. System evaluation includes comprehensive AI testing, consisting of 500,000 one-minute game rounds, and a user experiment involving 82 participants. UX assessment is conducted using a pairwise preference, four-alternative forced choice (4-AFC), version of the Game User Experience Satisfaction Scale (GUESS). Finally, the paper concludes by offering guidelines and hypotheses for future research in the field of APGs.