A5004976807- Mobile Crowdsensing and Crowdsourcing
- Auction Theory and Applications
- Privacy-Preserving Technologies in Data
- Advanced Bandit Algorithms Research
- Human Mobility and Location-Based Analysis
- Bacterial Genetics and Biotechnology
- Advanced Chemical Sensor Technologies
- Plant Virus Research Studies
- Natural Language Processing Techniques
- Privacy, Security, and Data Protection
- Topic Modeling
- Bacteriophages and microbial interactions
- Multimodal Machine Learning Applications
- Blockchain Technology Applications and Security
- Indoor and Outdoor Localization Technologies
- Data Stream Mining Techniques
- Anomaly Detection Techniques and Applications
- Evacuation and Crowd Dynamics
Central South University
2023-2024
Jilin University
2019
Drug-resistant bacteria are a serious threat to global public health. Gram-positive bacterial endolysin preparations have been successfully used fight as novel antimicrobial replacement strategy. However, Gram-negative phage endolysins cannot be applied directly destroy strains due the externally inaccessible peptidoglycan layer of cell wall; this has seriously hampered development endolysin-like antibiotics against bacteria. In study, 3-12 hydrophobic amino acids were successively added...
Mobile crowdsourcing (MCS) is an emerging paradigm that harnesses the collective power of crowd to tackle large-scale tasks. To ensure high-quality worker selection, various combinatorial multiarmed bandit (CMAB)-based schemes have been proposed. However, previous often overlook critical issues. First, post-unknown recruitment (PUWR) problem emerges when quality a remains unknown despite reported data. Second, presence Sybil Requesters neglected, who manipulate ratings deceive workers for...
In pursuit of an immersive virtual experience within the Cyber-Physical Metaverse Systems (CPMS), construction Avatars often requires a significant amount real-world data. Mobile Crowd Sensing (MCS) has emerged as efficient method for collecting data CPMS. While progress been made in protecting privacy workers, little attention given to safeguarding task privacy, potentially exposing intentions applications and posing risks development Metaverse. Additionally, existing protection schemes...
The Energy Internet (EI) aims to build a sustainable energy ecosystem by connecting diverse sources and prosumers. Mobile Crowd Sensing (MCS) enables efficient data collection for monitoring aggregation from distributed devices. Given the complex behavior of workers driven self-interest, recruiting trustworthy, high-quality, inexpensive remains significant challenge in research practice. Previous studies often assume that worker characteristics are known or can be obtained after collection....
Class-incremental Learning (CIL) in Time Series Classification (TSC) aims to incrementally train models using the streaming time series data that arrives continuously. The main problem this scenario is catastrophic forgetting, i.e., training with new samples inevitably leads forgetting of previously learned knowledge. Among existing methods, replay-based methods achieve satisfactory performance but compromise privacy, while exemplar-free protect privacy suffer from low accuracy. However,...
While deep learning has made remarkable progress in recent years, models continue to struggle with catastrophic forgetting when processing continuously incoming data. This issue is particularly critical continual learning, where the balance between retaining prior knowledge and adapting new information-known as stability-plasticity dilemma-remains a significant challenge. In this paper, we propose SegACIL, novel method for semantic segmentation based on linear closed-form solution. Unlike...
The recruitment of trustworthy and high-quality workers is an important research issue for MCS. Previous studies either assume that the qualities are known in advance, or platform knows once it receives their collected data. In reality, to reduce costs thus maximize revenue, many strategic do not perform sensing tasks honestly report fake data platform, which called False attacks. And very hard evaluate authenticity received this paper, incentive mechanism named Semi-supervision based...