Dr. Jun Wei

Production-level Autonomous Driving Systems (ADSs), such as Google Waymo and Baidu Apollo, typically rely on the multi-sensor fusion (MSF) strategy to perceive their surroundings. This strategy increases the perception robustness by combining the respective strengths of the cameras and LiDAR, directly affecting the safety-critical driving decisions of autonomous vehicles (AVs). However, in real-world autonomous driving scenarios, both cameras and LiDAR are prone to various faults that can significantly impact the decision-making and subsequent behaviors of ADSs. It is important to thoroughly test the robustness of MSF during development. Existing testing methods only focus on the identification of corner cases that MSF fails to detect. However, there is still a lack of investigation on how sensor faults affect the system-level behaviors of ADSs. To address this gap, we present FADE, the first testing methodology to comprehensively assess the fault tolerance of MSF perception-based ADSs. We systematically build fault models for both cameras and LiDAR in AVs and inject these faults into MSF-based ADSs to test their behaviors in various testing scenarios. To effectively and efficiently explore the parameter spaces of sensor fault models, we design a feedback-guided differential fuzzer to uncover safety violations of ADSs caused by the injected faults. We evaluate FADE on Baidu Apollo, a representative and practical industrial ADS. The evaluation results demonstrate the practical values of FADE, and disclose some useful findings. We further conduct physical experiments using a Baidu Apollo 6.0 EDU AV to validate these findings in real-world settings.

This book constitutes the refereed proceedings of the 6th International Conference on Design, Operation and Evaluation of Mobile Communications, MOBILE 2025, held as part of the 27th International Conference, HCI International 2025, which was held in Gothenburg, Sweden, during June 22–27, 2025. The total of 1430 papers and 355 posters included in the HCII 2025 proceedings was carefully reviewed and selected from 7972 submissions. The MOBILE 2025 proceedings were organized in the following topical sections- Mobile Usability, Experience and Personalization; Mobile Health, Inclusivity and Well-Being; Mobile Security, Protection and Risk Assessment; and, Mobile Applications for Culture, and Social Engagement.

This book constitutes the refereed proceedings of the 6th International Conference on Design, Operation and Evaluation of Mobile Communications, MOBILE 2025, held as part of the 27th International Conference, HCI International 2025, which was held in Gothenburg, Sweden, during June 22-27, 2025. The total of 1430 papers and 355 posters included in the HCII 2025 proceedings was carefully reviewed and selected from 7972 submissions. The MOBILE 2025 proceedings were organized in the following topical sections- Mobile Usability, Experience and Personalization; Mobile Health, Inclusivity and Well-Being; Mobile Security, Protection and Risk Assessment; and, Mobile Applications for Culture, and Social Engagement.

The study focuses on creating a risk assessment system tailored for mobile banking. It involves devising a dynamic model illustrating how information moves between key entities in mobile banking, alongside a static model outlining five types of information threats from three main sources. These models are then merged to indicate potential threats affecting each information flow. In the data analysis phase, risk factors for mobile banking information security are grouped into high, low, and medium categories. This research aims to aid mobile banking developers and decision-makers in system development.

Purpose - The metaverse enables users to create their own avatars in a shared virtual space, giving rise to a new avatar personality that differs from their real-self personality. The aim of this research is to explore how users' real-self and avatar personalities may affect their behavioral engagement and satisfaction in the metaverse context. Design/methodology/approach - This research applies self-discrepancy theory to investigate how the big five traits of both real-self and avatar personalities influence users' engagement and satisfaction in the metaverse. The present research employed a mixed-methods approach, beginning with a qualitative study to identify prevalent personality cues among users on metaverse social media platforms. Subsequently, a quantitative study was conducted to further validate the findings of the qualitative study. Findings - The results indicated that avatar personality scored higher than the real-self personality in the dimensions of openness, conscientiousness and extraversion, while scored lower in the dimensions of agreeableness and neuroticism. Both real-self and avatar personality traits positively influenced metaverse satisfaction via behavioral engagement in the metaverse. Notably, avatar personality traits had a stronger impact on behavioral engagement compared to real-self personality traits, which further influence metaverse satisfaction. Practical implications - The present study offers practical insights for metaverse developers and managers to enhance user satisfaction by focusing on users' big five traits of both real-self and avatar personality. It suggests implementing personalized tools, organizing personality-based social activities and other initiatives to encourage user's behavioral engagement and ultimately enhance metaverse satisfaction. Originality/value - Unlike existing research that concentrates on a single facet of personality traits, this research employs a mixed-methods approach to conceptualize users' real-self personality and avatar personality, further exploring their impacts on metaverse satisfaction.

Considering the technological and institutional nature, along with the inherent complexity, of the rural digital governance context, a data-driven institutional pressure transmission (D-IPT) mechanism is developed in this study. This mechanism aims to facilitate effective regulation of villagers' behaviours, thereby improving rural digital governance performance. Firstly, we proposed a conceptual model based on complex adaptive systems theory and institutional theory to demonstrate how this mechanism can ensure an improvement of the emergent rural digital governance performance. Subsequently, we translated the conceptual model into a computational representation, thereby constructing a theory-informed simulation model. A behavioural dataset consists of 1,255,206 rural households from 119 villages over a span of 18 months was used to instantiate and validate the simulation model based on a specific scenario. Then, we designed five simulation experiments to investigate interventions aimed at harnessing the D-IPT mechanism more effectively to improve the rural digital governance performance. The results show that interventions targeting interaction efficiency, interaction frequency, and institutional environment configuration significantly affect the role of the D-IPT mechanism in enhancing rural governance performance. Finally, we discussed the theoretical and practical implications of the D-IPT mechanism.
•A D-IPT mechanism is developed to improve rural digital governance performance through effective behavioural regulation.•Based on CAS theory and institutional theory, a conceptual model is built to demonstrate the role of the D-IPT mechanism.•The transmission of coercive, normative and mimetic institutional pressures among rural agents is quantified by ABM method.•Interventions targeting interactions among agents and the environment, are explored to better utilize the D-IPT mechanism.

The rise of automated technologies due to recent advances in Intelligent Transportation systems (ITS) from autonomous delivery services to physical transportation is rapidly developing and public availability is imminent with the active deployment and testing of teleoperation models launching this reality. With the inaugural release of the National Roadway Safety Strategy in 2022, the U.S. National transportation industry initiative aims for a goal of zero roadway fatalities and part of the solution is in designing safer autonomous or self-driving vehicle systems as viable forms of transport [14]. This initiative is prompted by the fact that worldwide vehicle related accidents result in 1.3 million deaths annually [13]. Further, this ambitious commitment to deliver safety and reliability in automotive teleoperations is commendable and will require further intentional efforts to focus on mitigating existing cybersecurity vulnerability and threat concerns. Additionally, the automotive industry supports integration of cybersecurity risk assessment and management through enforcing the joint International Organization for Standardization and Society of Automobile Engineers (ISO/SAE) 21434 standard and governance on road vehicle systems design and development. This ongoing research aims to develop a comprehensive framework to aid in threat mitigation by providing a conceptual information exchange flow model on Connected Autonomous Vehicle (CAV) and utilizing existing knowledge of threats to general information system security. By identifying the information flow, threat analysis and risk assessment risk based on threat vectors may be combined hybrid model approach annotating a ranked list to display classify risk factors into three severity levels: high, medium, low. This is an integral part of an overarching research on the design and development of a set of methodologies supporting the automotive industry toward the prevention of connected automotive cybersecurity vulnerability exploitation and promoting risk mitigation.

Despite a large number of retailers have embraced the voice shopping channels, the factors that determine consumers' voice shopping value co-creation intentions are still unclear. This study explores the impacts of two social cognition dimensions (competence and warmth) on voice shopping value co-creation intention from the perspectives of confidence in consumers themselves and in AI. Based on the social exchange theory and stimulus-organism-response, a research model was developed and empirically examined by data collected from 363 students at a university in China. The results of structural equation modeling (SEM) analysis indicate that perceived competence and perceived warmth positively affect confidence in consumers themselves and in AI and consequently determine voice shopping value co-creation intention. In addition, the impacts of confidence in consumers themselves and in AI on voice shopping value co-creation intention varies. The results of the fuzzy set qualitative comparative analysis (fsQCA) method further validate these findings.

A green manufacturing supply chain can improve ecological environments and resource utilization in enterprises. The objective of this paper is to assess green supply chain (GSC) risks in manufacturing to help enterprises increase value. Specifically, based on theoretical analysis and literature review, the risk assessment model of green SC in manufacturing is put forward through questionnaire survey data and Principal Component Analysis. Furthermore, to improve the effectiveness of the risk assessment model obtained from Principal Component Analysis, principal component analysis-based Fuzzy Mature-Element (FME) method is used to form the risk assessment model for green SC in manufacturing. Finally, the FME model on manufacturing green SC risk assessment is tested through the simulation of BP neural network. Some findings present that the proposed risk evaluation system of manufacturing green SC is appropriate and the FME based comprehensive evaluation method is reasonable.

This book constitutes the refereed proceedings of the 5th International Conference on Design, Operation and Evaluation of Mobile Communications, MOBILE 2024, held as part of the 26th International Conference, HCI International 2024, which was held in Washington, DC, USA, during June 29-July 4, 2024.
Part I: Mobile health and wellbeing; mobile applications, serious games and advanced interfaces;
Part II: Mobile commerce, marketing and retail; mobile security, privacy, and safety; mobile user experience and design.