Symptom-based automated disease diagnosis involves an iterative process of gathering potential symptoms through natural language interactions with patients. Previous research has made use of Reinforcement Learning (RL) techniques to optimize policy networks for symptom inquiry and disease diagnosis, yielding promising results. However, reinforcement learning methods encounter various challenges such as the risk of getting stuck in suboptimal solutions, limited efficacy in training, and difficulties in designing appropriate reward functions, especially when confronting large decision spaces. To address these challenges, this paper converts policy learning in automated disease diagnosis into generative task-QA by utilizing language models in a fully supervised way. We further introduced beam search decoding and an early stop mechanism to facilitate efficient interactive symptom queries and improve the efficiency of the diagnostic process, respectively. To assess the efficacy of our approach, we conducted extensive experiments on three Chinese real-world medical dialogue datasets: Dxy, MUZHI, and IMCS. Preliminary experimental results demonstrate that our method is comparable to or better than previous RL methods in terms of symptom recall and diagnostic accuracy.
Physics-based cloth simulation is a classic topic in computer graphics, which aims to simulate realistic cloth effects in virtual environments. In recent years, the rapid development of virtual reality has put forward higher requirements for physics-based cloth simulation, and this technology has played an increasingly important role. This paper first introduces the fundamental knowledge of cloth simulation, then summarizes the existing mainstream methods in this field. We give a classification of these works and provide an overview of each one of them. We have also conducted a large number of experiments to compare the performance of several typical algorithms. Towards the end of the article, we identify some existing limitations in this field and provide targeted suggestions for future development.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.