Search

Your search keyword '"Sun, Jingyi"' showing total 709 results
Start Over Author "Sun, Jingyi"
709 results on '"Sun, Jingyi"'

1. Blockchain-Enabled IoV: Secure Communication and Trustworthy Decision-Making

Author

Sun, Jingyi, Shi, Qi, Jin, Guodong, Xu, Hao, and Liu, Erwu

Subjects
Computer Science - Cryptography and Security, Computer Science - Distributed, Parallel, and Cluster Computing, Computer Science - Networking and Internet Architecture
Abstract

The Internet of Vehicles (IoV), which enables interactions between vehicles, infrastructure, and the environment, faces challenges in maintaining communication security and reliable automated decisions. This paper introduces a decentralized framework comprising a primary layer for managing inter-vehicle communication and a sub-layer for securing intra-vehicle interactions. By implementing blockchain-based protocols like Blockchain-integrated Secure Authentication (BiSA) and Decentralized Blockchain Name Resolution (DBNR), the framework ensures secure, decentralized identity management and reliable data exchanges, thereby supporting safe and efficient autonomous vehicle operations., Comment: The 2024 7th IEEE Conference on Dependable and Secure Computing

Published
2024

2. A Unified Framework for Input Feature Attribution Analysis

Author

Sun, Jingyi, Atanasova, Pepa, and Augenstein, Isabelle

Subjects
Computer Science - Computation and Language, 68T50, I.2.7
Abstract

Explaining the decision-making process of machine learning models is crucial for ensuring their reliability and fairness. One popular explanation form highlights key input features, such as i) tokens (e.g., Shapley Values and Integrated Gradients), ii) interactions between tokens (e.g., Bivariate Shapley and Attention-based methods), or iii) interactions between spans of the input (e.g., Louvain Span Interactions). However, these explanation types have only been studied in isolation, making it difficult to judge their respective applicability. To bridge this gap, we propose a unified framework that facilitates a direct comparison between highlight and interactive explanations comprised of four diagnostic properties. Through extensive analysis across these three types of input feature explanations--each utilizing three different explanation techniques--across two datasets and two models, we reveal that each explanation type excels in terms of different diagnostic properties. In our experiments, highlight explanations are the most faithful to a model's prediction, and interactive explanations provide better utility for learning to simulate a model's predictions. These insights further highlight the need for future research to develop combined methods that enhance all diagnostic properties.

Published
2024

3. BeACONS: A Blockchain-enabled Authentication and Communications Network for Scalable IoV

Author

Shi, Qi, Sun, Jingyi, Fu, Hanwei, Fu, Peizhe, Ma, Jiayuan, Xu, Hao, and Liu, Erwu

Subjects
Computer Science - Distributed, Parallel, and Cluster Computing
Abstract

This paper introduces a novel blockchain-enabled authentication and communications network for scalable Internet of Vehicles, which aims to bolster security and confidentiality, diminish communications latency, and reduce dependence on centralised infrastructures like Certificate Authorities and Public Key Infrastructures by leveraging Blockchain-enabled Domain Name Services and Blockchain-enabled Mutual Authentication. The proposed network is structured into a primary layer, consisting of Road Side Units and edge servers as servers of Blockchain-enabled Domain Name Services for managing inter-vehicle communications identities, and a sub-layer within each vehicle for intra-vehicle communications via the Blockchain-enabled Mutual Authentication Protocol. This design facilitates secure connections across vehicles by coordinating between the layers, significantly improving communications security and efficiency. This study also evaluates Road Side Unit availability against the random distribution of Road Side Units along the route of different vehicles. The proposed model presents a novel pathway towards a decentralised, secure, and efficient Internet of Vehicles ecosystem, contributing to the advancement of autonomous and trustworthy vehicular networks.

Published
2024

7. Stand for Something or Fall for Everything: Predict Misinformation Spread with Stance-Aware Graph Neural Networks

Author

Chen, Zihan, Sun, Jingyi, Liu, Rong, and Mai, Feng

Subjects
Computer Science - Social and Information Networks, Computer Science - Artificial Intelligence, Computer Science - Computers and Society, Computer Science - Machine Learning, H.0, J.4, I.2.7
Abstract

Although pervasive spread of misinformation on social media platforms has become a pressing challenge, existing platform interventions have shown limited success in curbing its dissemination. In this study, we propose a stance-aware graph neural network (stance-aware GNN) that leverages users' stances to proactively predict misinformation spread. As different user stances can form unique echo chambers, we customize four information passing paths in stance-aware GNN, while the trainable attention weights provide explainability by highlighting each structure's importance. Evaluated on a real-world dataset, stance-aware GNN outperforms benchmarks by 32.65% and exceeds advanced GNNs without user stance by over 4.69%. Furthermore, the attention weights indicate that users' opposition stances have a higher impact on their neighbors' behaviors than supportive ones, which function as social correction to halt misinformation propagation. Overall, our study provides an effective predictive model for platforms to combat misinformation, and highlights the impact of user stances in the misinformation propagation., Comment: Accepted by the 2023 International Conference on Information Systems (ICIS 2023)

Published
2023

8. A Little Goes a Long Way: How Gesture Visibility in Video Lectures Impacts Attention and Learning

Author

Cuffari, Elena C, Howard, Lauren H., Belka, Ayako, Reilly, Alonna, Samson, Kyle M, Sun, Jingyi, HUANG, WEI, and Zang, Zeyi

Subjects
Attention, Embodied Cognition, Interactive behavior, Eye tracking, Gesture analysis
Abstract

In classroom interactions that take place over video conferencing platforms, teachers and students continue to gesture, but their bodies are neither physically copresent nor fully visible to each other. Do instructor gestures help learning in this context, as has been found for in-person learning and for video-based learning in lab experiments? We showed professors lecturing spontaneously with unscripted co-speech gestures. In some conditions, we cropped the video so only the top half of the professor's gesture space is available, or removed the video altogether. Results from our between-subjects experiment show that participants paid significantly more visual attention to the partial gesture condition than to stimuli where the gesturing was fully visible, and they scored significantly higher on an immediate comprehension test if they had seen lectures in the partially visible condition. This work raises further questions of how gestures help learning.

Published
2024

33. Vision Transformer Based Multi-class Lesion Detection in IVOCT

Author

Wang, Zixuan, Shao, Yifan, Sun, Jingyi, Huang, Zhili, Wang, Su, Li, Qiyong, Li, Jinsong, Yu, Qian, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Greenspan, Hayit, editor, Madabhushi, Anant, editor, Mousavi, Parvin, editor, Salcudean, Septimiu, editor, Duncan, James, editor, Syeda-Mahmood, Tanveer, editor, and Taylor, Russell, editor

Published
2023
Full Text
View/download PDF

34. Beyond Car Human-Machine Interface (HMI): Mapping Six Intelligent Modes into Future Cockpit Scenarios

Author

Cui, Shuyi, Hou, Donghan, Li, Jiayue, Liu, Yuwei, Wang, Zi, Zheng, Jiayu, Dou, Xueshi, Feng, Zhanyao, Gu, Yuxuan, Li, Minglan, Ni, Songbo, Ran, Ziwei, Ren, Bojuan, Sun, Jingyi, Wang, Shenmin, Xiong, Xinyan, Zhang, Guanzhuo, Li, Wangjun, Jia, Jingpeng, Xin, Xin, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Marcus, Aaron, editor, Rosenzweig, Elizabeth, editor, and Soares, Marcelo M., editor

Published
2023
Full Text
View/download PDF

35. Exploration and Practice of Art Experimental Teaching System in Comprehensive Universities in the Context of 'New Liberal Arts' Construction: A Case Study of the Arts College of Sichuan University

Author

Fan, Xiaoxi, Sun, Yao, Sun, Jingyi, Zhao, Xinyuan, Striełkowski, Wadim, Editor-in-Chief, Black, Jessica M., Series Editor, Butterfield, Stephen A., Series Editor, Chang, Chi-Cheng, Series Editor, Cheng, Jiuqing, Series Editor, Dumanig, Francisco Perlas, Series Editor, Al-Mabuk, Radhi, Series Editor, Scheper-Hughes, Nancy, Series Editor, Urban, Mathias, Series Editor, Webb, Stephen, Series Editor, Zhan, Zehui, editor, Chew, Fong Peng, editor, and Anthony, Marcus T., editor

Published
2023
Full Text
View/download PDF

46. Spatial Distribution of Digital Economy Model in Zhejiang Province, China

Author

Ma Renfeng, Zhu Min'er, Sun Jingyi, and Zhang Xuliang

Subjects
digital economy, spatial pattern, driving mechanism, local characteristics, zhejiang, Geography (General), G1-922
Abstract

Taking Zhejiang province as an example, based on county-level economic and social statistics, we established an index system for main factors driving the development of the digital economy. We used entropy, spatial autocorrelation, a Geographically Weighted Regression (GWR) model, and cluster analysis to explore the spatial differences between the development level and driving factors of the digital economy in Zhejiang. First, we observed spatial differences in the development of the digital economy in Zhejiang, with the level being high in the northeast and low in the southwest. Second, the influence of each driving factor represents strong spatial characteristics, and industrial innovation was the most important factor, with a distribution pattern of high in the east and low in the west. As a secondary driving factor, government input is consistent with the spatial layout of the economic factors. Commercial culture is strong in the south and weak in the north. Third, we observed multiple combinations of characteristics in the spatial differences of the four driving factors to establish the mechanism that drives the development of the digital economy in Zhejiang: the local digital economy/new business type is driven by the coupling of industrial innovation atmosphere and consumer demand, formed by developed market advantages. The three main bodies of consumers, government, and enterprises have formed a virtuous circle, promoting each other through the digitization of traditional industries and emerging digital industries, leading the development in the surrounding counties. Fourth, under the action of the four factors, three types of regional development types and 13 subcategories have generally been formed in Zhejiang: enterprise-consumer-led, business-government-led, government-consumer-led. Certain places, such as Hangzhou and Ningbo, are leading the implementation of the concept of digital development, creating the core of the digital economy in Zhejiang; Jiaxing and Jinhua are relying on transportation hub cities or global wholesale centers to rapidly develop intelligent logistics and transportation. In addition, with the support of the government, the later-developing areas are improving their infrastructure and developing the digital industry represented by ecology and tourism. For this reason, in the process of empowering digital economy development, complete attention should be paid to the development path of ecology, tourism, and other suitable digital industries in underdeveloped areas under the leadership of the government. We observed that enterprises and consumers create emerging digital industries in the leading areas of the digital economy in Zhejiang and then promote the digital transformation and upgrading of industries and governments. However, in the later-developing areas dominated by policy investment, the development of the digital economy is mostly oriented toward meeting the needs of industries and consumers, and the force driving emerging digital industries is weak.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results