Search

Your search keyword '"Zhu, Yitong"' showing total 151 results
Start Over Author "Zhu, Yitong"
151 results on '"Zhu, Yitong"'

1. A comparative study of sensory encoding models for human navigation in virtual reality

Author

Li, Tangyao, Zhan, Qiyuan, Zhu, Yitong, Hou, Bojing, and Wang, Yuyang

Subjects
Computer Science - Human-Computer Interaction, Quantitative Biology - Neurons and Cognition
Abstract

In virtual reality applications, users often navigate through virtual environments, but the issue of physiological responses, such as cybersickness, fatigue, and cognitive workload, can disrupt or even halt these activities. Despite its impact, the underlying mechanisms of how the sensory system encodes information in VR remain unclear. In this study, we compare three sensory encoding models, Bayesian Efficient Coding, Fitness Maximizing Coding, and the Linear Nonlinear Poisson model, regarding their ability to simulate human navigation behavior in VR. By incorporating the factor of physiological responses into the models, we find that the Bayesian Efficient Coding model generally outperforms the others. Furthermore, the Fitness Maximizing Code framework provides more accurate estimates when the error penalty is small. Our results suggest that the Bayesian Efficient Coding framework offers superior predictions in most scenarios, providing a better understanding of human navigation behavior in VR environments., Comment: 6 pages, 4 figures, submitted to IEEE

Published
2025

2. Real-time Cross-modal Cybersickness Prediction in Virtual Reality

Author

Zhu, Yitong, Li, Tangyao, and Wang, Yuyang

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Human-Computer Interaction
Abstract

Cybersickness remains a significant barrier to the widespread adoption of immersive virtual reality (VR) experiences, as it can greatly disrupt user engagement and comfort. Research has shown that cybersickness can significantly be reflected in head and eye tracking data, along with other physiological data (e.g., TMP, EDA, and BMP). Despite the application of deep learning techniques such as CNNs and LSTMs, these models often struggle to capture the complex interactions between multiple data modalities and lack the capacity for real-time inference, limiting their practical application. Addressing this gap, we propose a lightweight model that leverages a transformer-based encoder with sparse self-attention to process bio-signal features and a PP-TSN network for video feature extraction. These features are then integrated via a cross-modal fusion module, creating a video-aware bio-signal representation that supports cybersickness prediction based on both visual and bio-signal inputs. Our model, trained with a lightweight framework, was validated on a public dataset containing eye and head tracking data, physiological data, and VR video, and demonstrated state-of-the-art performance in cybersickness prediction, achieving a high accuracy of 93.13\% using only VR video inputs. These findings suggest that our approach not only enables effective, real-time cybersickness prediction but also addresses the longstanding issue of modality interaction in VR environments. This advancement provides a foundation for future research on multimodal data integration in VR, potentially leading to more personalized, comfortable and widely accessible VR experiences.

Published
2025

6. DiffusionTalker: Personalization and Acceleration for Speech-Driven 3D Face Diffuser

Author

Chen, Peng, Wei, Xiaobao, Lu, Ming, Zhu, Yitong, Yao, Naiming, Xiao, Xingyu, and Chen, Hui

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Sound, Electrical Engineering and Systems Science - Audio and Speech Processing
Abstract

Speech-driven 3D facial animation has been an attractive task in both academia and industry. Traditional methods mostly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the non-deterministic fact of speech-driven 3D face animation and employ the diffusion model for the task. However, personalizing facial animation and accelerating animation generation are still two major limitations of existing diffusion-based methods. To address the above limitations, we propose DiffusionTalker, a diffusion-based method that utilizes contrastive learning to personalize 3D facial animation and knowledge distillation to accelerate 3D animation generation. Specifically, to enable personalization, we introduce a learnable talking identity to aggregate knowledge in audio sequences. The proposed identity embeddings extract customized facial cues across different people in a contrastive learning manner. During inference, users can obtain personalized facial animation based on input audio, reflecting a specific talking style. With a trained diffusion model with hundreds of steps, we distill it into a lightweight model with 8 steps for acceleration. Extensive experiments are conducted to demonstrate that our method outperforms state-of-the-art methods. The code will be released.

Published
2023

21. Latent Information in the Evolving Energy Structure: The Intersection of Artificial Intelligence Development and Social Progress

Author

Lin, Boqiang and Zhu, Yitong

Subjects
Artificial intelligence -- Forecasts and trends -- Analysis -- Research, Alternative energy sources -- Forecasts and trends -- Research -- Analysis, Energy industry -- Analysis -- Research -- Forecasts and trends, Force and energy -- Forecasts and trends -- Research -- Analysis, Market trend/market analysis, Artificial intelligence, Economics, Business, international
Abstract

Recent studies indicate that Artificial Intelligence (AI) technology, characterized by its integration of information and communication technology attributes, exerts a multifaceted influence on the energy system. The authors employ Difference-in-Differences (DID) and Triple-Difference (DDD) models to investigate the effects of AI. The research initially demonstrates that AI may exhibit dual attributes of constraining energy structure. Specifically, the rapid development of AI tends to increase the proportion of fossil fuel-based electricity generation while optimizing the consumption of renewable energy. Furthermore, the degradation of energy structure stems from the surge in electricity consumption by AI, which the renewable energy consumption capacity is unable to satisfy. Lastly, industrial agglomeration effects and the construction of the digital economy have positive impacts on development of renewable energy; technological innovation aids in mitigating the negative shocks to the energy structure. This study provides a new perspective on the role of AI technology in energy transition., Author(s): Boqiang Lin, School of Management, China Institute for Studies in Energy Policy, Xiamen University, China, Yitong Zhu, School of Management, China Institute for Studies in Energy Policy, Xiamen University, [...]

Published
2024
Full Text
View/download PDF

25. High‐Performance Cooperative DNA Nanodevice Enables Sensitive Circular RNA Imaging and Precise Tumor Growth Suppression.

Author

Zhang, Ye, Chen, Siting, Luo, Shihua, Li, Wenbin, Zhang, Lifeng, Lan, Fei, Zhu, Yitong, Du, Huijun, Li, Ke, Liu, Chunchen, Situ, Bo, Li, Bo, and Yan, Xiaohui

Subjects
DEOXYRIBOZYMES, CIRCULAR DNA, DNA nanotechnology, TUMOR growth, DNA, CIRCULAR RNA
Abstract

The utility of circular RNAs (circRNAs) as emerging biomarkers and regulatory factors in medical diagnostics and therapeutics is hampered by the challenges associated with their sensitive detection and precise modulation. Herein, a high‐performance cooperative DNA nanodevice (HCDN) based on DNA tetrahedron‐confined catalytic DNA assembly reaction (DT‐CDA) that enables both imaging and regulation of circRNAs is developed. Activation of the DT‐CDA is contingent upon the presence of the target circRNA, which, together with a replicative fuel probe, catalyzes the sequential opening of additional DT‐CDAs. This cooperative exponential signal amplification with negligible background interference allows HCDN to effectively detect minute quantities of circRNAs. Employing circSATB2 as a model, the HCDN demonstrates substantial downregulation of Cyclin D1 (CCND1) mRNA and protein levels in cellular and in vivo models, thereby inhibiting tumor growth. The innovative design of HCDN sets the stage for a powerful methodology conducive to enhanced clinical diagnostics and biomolecule manipulation, thereby advancing the capabilities and applications of DNA nanotechnology. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

32. An Ecological Discourse Analysis of Silent Spring from the Perspective of Corpus-based Attitude System: Human Image as an Example

Author

null Zhu Yitong

Subjects
General Medicine
Abstract

The book Silent Spring by Rachel Carson, a famous contemporary American marine biologist, has prompted environmental issues to become the biggest theme of our time and triggered the rise of the modern environmental movement. In this paper, Two corpus tools are used to analyze the attitude resources related to the human characters in Silent Spring from an ecological linguistic perspective of the attitude system. The study finds that the farmers and workers portrayed in the book are both destroyers and victims of ecology, while the scientists and ecologists play the role of protectors and managers of ecology. The article rejects the previous notion of "an thropocentrism" and reveals that the author advocates an ecological view of nature in which "all things are equal and interdependent", with a view to awakening the ecological consciousness of human beings and then taking the initiative to care for nature and protect the earth.

Published
2023
Full Text
View/download PDF

35. An Ecological Discourse Analysis of Silent Spring from the Perspective of Corpus-based Attitude System: Human Image as an Example

Author

Zhu Yitong and Zhu Yitong

Abstract

The book Silent Spring by Rachel Carson, a famous contemporary American marine biologist, has prompted environmental issues to become the biggest theme of our time and triggered the rise of the modern environmental movement. In this paper, Two corpus tools are used to analyze the attitude resources related to the human characters in Silent Spring from an ecological linguistic perspective of the attitude system. The study finds that the farmers and workers portrayed in the book are both destroyers and victims of ecology, while the scientists and ecologists play the role of protectors and managers of ecology. The article rejects the previous notion of "an thropocentrism" and reveals that the author advocates an ecological view of nature in which "all things are equal and interdependent", with a view to awakening the ecological consciousness of human beings and then taking the initiative to care for nature and protect the earth.

Published
2023

40. Trend in incidence and mortality of cancer, a high -risk area in Gansu province: Analysis of the 2010 to 2018 in Gansu Central Cancer Registry

Author

Liu Yuqin, Yuan Haoran, Zhu Yitong, Ding Gaoheng, Guzhanuer Niyazi, and Zhu Gongjian

Abstract

Background: The incidence and mortality of cancer in Gansu Province remain high, especially the digestive system tumors have long been in the top 5, and there is a rising trend. This paper uses the cancer registration data in Gansu Province from 2010 to 2018 to analyze the trend of trend changes, and provides information for the government basis for decision-making.Methods: The registration data of cancer incidence, death and population data reported by 23 cancer registration sites in Gansu Province in 2021 were collected, and the data of 15 registration sites met the quality control standards. The incidence (mortality) rate, age-standardized incidence(mortality) rate, cumulative rate(0~74 years old) were calculated according to gender, areas(urban and rural) and age groups. The age-standardized rate was calculated and adjusted by Chinese standard population in 2000(ASIRC, ASMRC) and world standard(Segi’s) population(ASIRW, ASMRW), respectively. Joinpoint Regression Program was used to estimate the annual percentage change（APC），and average annual percentage change（AAPC） to analyze the temporal trends of annual all cancer incidence and mortality rates.Results: In 2018, the number of new cancer cases in Gansu was 13 592, with an incidence rate of 252.98/105, ASIRC and ASIRW were 189.79/105 and 205.89/105 respectively; there were 7,568 cancer deaths in the province, with a mortality rate of 140.86/105, ASMRC and ASMRW were 103.40/105 and 116.83/105 respectively. The ASIRC and ASMRC in urban areas were lower than those in rural areas. The incidence of cancer in males and females peaked in the 80-84 and 75-79 age groups, respectively, and the mortality rates of cancer in both males and females peaked in the 80-84 age groups. From 2010 to 2018, the ASIRC of cancer in the cancer registration areas of Gansu Province showed a downward trend (AAPC, -1.7%, 95%CI, -4.4%-10%), and the difference was not statistically significant (P>0.05). ASMRC showed a downward trend (AAPC, -3.9%, 95%CI,-10.0%-2.7%), the difference was not statistically significant (P>0.05).Conclusions: Digestive tract cancer, lung cancer and female breast cancer have high morbidity and mortality in Gansu Province, and are the main cancer types for the prevention and control of cancer in Gansu Province. According to the epidemic characteristics of cancer, multi-dimensional joint efforts should be made to promote the prevention of cancer populations in our province and reduce the disease burden of cancer in Gansu Province.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results