A5100457571- Crystallization and Solubility Studies
- X-ray Diffraction in Crystallography
- Privacy-Preserving Technologies in Data
- Cryptography and Data Security
- Blockchain Technology Applications and Security
- Internet Traffic Analysis and Secure E-voting
- Transportation Planning and Optimization
- Advanced Steganography and Watermarking Techniques
- Transportation and Mobility Innovations
- Network Security and Intrusion Detection
- Traffic Prediction and Management Techniques
- Traffic control and management
- Crystallography and molecular interactions
- Vehicular Ad Hoc Networks (VANETs)
- Higher Education and Teaching Methods
- Advanced Battery Technologies Research
- Security in Wireless Sensor Networks
- Energy Efficient Wireless Sensor Networks
- Privacy, Security, and Data Protection
- Smart Parking Systems Research
- IoT and Edge/Fog Computing
- Speech and Audio Processing
- Chaos-based Image/Signal Encryption
- Vehicle emissions and performance
- Sparse and Compressive Sensing Techniques
Hefei University of Technology
2013-2025
University of Jinan
2015-2025
Chongqing Technology and Business University
2020-2025
University of Guelph
2024
Shenzhen University
2024
Chinese Academy of Sciences
2018-2024
Shanxi Electromechanical Design and Research Institute
2024
Taiyuan University of Technology
2020-2024
Beijing University of Civil Engineering and Architecture
2024
South China Normal University
2024
Federated learning enables resource-constrained edge compute devices, such as mobile phones and IoT to learn a shared model for prediction, while keeping the training data local. This decentralized approach train models provides privacy, security, regulatory economic benefits. In this work, we focus on statistical challenge of federated when local is non-IID. We first show that accuracy reduces significantly, by up 55% neural networks trained highly skewed non-IID data, where each client...
Carpooling enables passengers to share a vehicle reduce traveling time, carbon emissions, and traffic congestion. However, the majority of lean find local drivers, but querying remote cloud server leads an unnecessary communication overhead increased response delay. Recently, fog computing is introduced provide data processing with low latency, it also raises new security privacy concerns because users' private information (e.g., identity location) could be disclosed when these are shared...
Energy trading in Industrial Internet of Things (IIoT), a fundamental approach to realize Industry 4.0, plays vital role satisfying energy demands and optimizing system efficiency. Existing research works utilize utility company distribute nodes with the help brokers. Afterwards, they apply blockchain provide transparency, immutability, auditability peer-to-peer (P2P) trading. However, their schemes are constructed on weak security model do not consider cheating attack initiated by sellers....
Wav2vec 2.0 is a recently proposed self-supervised framework for speech representation learning.It follows two-stage training process of pre-training and fine-tuning, performs well in recognition tasks especially ultra-low resource cases.In this work, we attempt to extend the speaker verification language identification.First, use some preliminary experiments indicate that wav2vec can capture information about language.Then demonstrate effectiveness on two respectively.For verification,...
Cruising for a vacant and economical parking spot causes not only time-consuming frustrating driving experiences, but fuel waste air pollution. Public spots in crowded cities are scarce expensive. On the contrary, private usually have low utilization rates, suppliers willing to provide their extra resources due maintenance cost by charging fees. Given this situation, it is imperative call smart system that collects provides (e.g., around home or workplace) ease public concerns. However, when...
Fog computing has enabled the extension of cloud functions to network edge by assisting and users in terms communication, computation, storage with a widely spread deployment devices or fog nodes, as they become more powerful capacities functionalities. Smart grid is becoming next-generation power will automate reliable electricity distribution for millions customers. However, data transmitted smart communications reached terabyte level mishandling meter readings may lead customers' privacy...
Traffic monitoring system empowers cloud server and drivers to collect real-time driving information acquire traffic conditions. However, are more interested in local traffic, sending reports a faraway wastes lot of bandwidth incurs long response delay. Recently, fog computing is introduced provide location-sensitive latency-aware data management vehicular crowdsensing, but it new privacy concerns since drivers' could be disclosed. Although these messages encrypted before transmission,...
Amomum villosum, also known as Fructus Amomi, has been used to treat digestive diseases such abdominal pain, vomiting, and dysentery. Volatile terpenoids are the active metabolites in essential oil of Amomi. Nevertheless, downstream genes responsible for activating biosynthesis A. villosum still remain unclear. Here, we report use an integrative volatile terpenoid profiling transcriptomics analysis mining corresponding involved biosynthesis. Ten terpene synthase (TPS) were discovered, two...
Traffic speed forecasting plays an increasingly essential role in successful intelligent transportation systems. However, this still remains a challenging task when the accuracy requirement is demanding. To improve prediction and achieve timely performance, capture of intrinsically spatio-temporal dependencies creation parallel model architecture are required. Accordingly, we propose novel end-to-end deep learning framework named Graph Attention Temporal Convolutional Network (GATCN). The...
Wireless sensor network (WSN) nodes owing to their openness, are susceptible several threats, one of which is dishonest recommendation attacks providing false trust values that favor the attacker. In this letter, a malicious node detection strategy proposed based on fuzzy model and artificial bee colony algorithm (ABC) (FTM-ABC). The (FTM) introduced calculate indirect trust, ABC applied optimize for detecting attacks. Besides, fitness function includes recommended deviation interaction...
E-commerce platforms incorporate reputation systems that allow customers to rate suppliers following financial transactions. Existing cannot defend the centralized server against arbitrarily tampering with supplier’s reputation. Furthermore, they do not offer access across platforms. Rates are faced privacy leakages because rating activities correlated (e.g., identity and rating). Meanwhile, raters could be malicious initiate multiple attacks abnormal attacks. Determining how address these...
Federated learning (FL), as a distributed machine paradigm, enables multiple users to train models locally using individual data and then update global model in privacy-preserving aggregated manner. However, FL, the parameters are at risk of privacy breach. Furthermore, aggregation server may forge results. To address these problems, this paper, we propose SVCA, secure verifiable chained for federated (PPFL) scheme. Specifically, first group construct structure, employ secret sharing prevent...
Face and voice are two of the most popular traits used for authentication tasks in daily life, as they can be easily captured using low-cost visual audio sensors on smartphones, laptops, tablets, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc</i> . Many bimodal biometric schemes based these have been presented to provide higher accuracy than unimodal systems. However, inflexibility due requirement submitting simultaneously, lack template...
A growing number of utility companies are starting to use cellular wireless networks transmit data in the smart grid. Consequently, millions users' daily energy consumption sent by meters. However, broadcast transfer manner communication makes it naturally vulnerable cyber attacks. Since meter readings can easily be leaked, patterns could inferred. Hence, privacy at home is under serious threat. This article begins introducing existing work on stealing from networks. Then three types big...