A5100654633- Artificial Immune Systems Applications
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Anomaly Detection Techniques and Applications
- T-cell and B-cell Immunology
- Influenza Virus Research Studies
- Advanced Graph Neural Networks
- Metaheuristic Optimization Algorithms Research
- Immune Cell Function and Interaction
- Smart Grid Security and Resilience
- Adversarial Robustness in Machine Learning
- Topic Modeling
- Mathematical and Theoretical Epidemiology and Ecology Models
- Traffic Prediction and Management Techniques
- Advanced Decision-Making Techniques
- Advanced Computational Techniques and Applications
- Industrial Technology and Control Systems
- Evolutionary Algorithms and Applications
- Complex Network Analysis Techniques
- Traffic control and management
- Natural Language Processing Techniques
- Photochromic and Fluorescence Chemistry
- Advanced Sensor and Control Systems
- Internet Traffic Analysis and Secure E-voting
- Time Series Analysis and Forecasting
Sichuan University
2016-2025
Hangzhou Seventh Peoples Hospital
2023-2024
Zhejiang University
2023-2024
West China Hospital of Sichuan University
2023-2024
The Affiliated Yongchuan Hospital of Chongqing Medical University
2018-2024
Chongqing Medical University
2018-2024
China Automotive Technology and Research Center
2022-2024
Shanghai Jiao Tong University
2021-2023
Army Medical University
2023
Guangdong Ocean University
2023
The rapid convergence of legacy industrial infrastructures with intelligent networking and computing technologies (e.g., 5G, software-defined networking, artificial intelligence), have dramatically increased the attack surface cyber-physical systems (CPSs). However, withstanding cyber threats to such large-scale, complex, heterogeneous CPSs has been extremely challenging, due insufficiency high-quality examples. In this article, we propose a novel federated deep learning scheme, named...
Android malware and its variants are a major challenge for mobile platforms. However, there two main problems in the existing detection methods: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</i> ) The method lacks evolution ability malware, which leads to low rate of model variants. xmlns:xlink="http://www.w3.org/1999/xlink">b</i> Traditional methods require centralized data training, however, aggregation training samples is limited due...
The paper investigates the use of acoustic based features for music information retrieval. Two specific problems are studied: similarity search (searching sound files similar to a given file) and emotion detection (detection in sounds). Daubechies wavelet coefficient histograms (Li, T. et al., SIGIR'03, p.282-9, 2003), which consist moments coefficients calculated by applying Db8 filter, combined with timbral extracted using MARSYAS system G. Tzanctakis P. Cook (see IEEE Trans. on Speech...
To perform static breath-hold fluorine 19 ((19)F) three-dimensional (3D) ultrashort echo time (UTE) magnetic resonance (MR) imaging of the lungs in healthy volunteers by using a mixture 79% perfluoropropane (PFP) and 21% O2.This study protocol was approved local research ethics board Health Canada. All provided written informed consent. Ten underwent MR at 3.0 T. Fluorine 3D UTE images were acquired during 15-second breath hold according to one two breathing protocols: A, 1-L inhalation PFP...
Biometric image hashing techniques have been widely studied and seen progressive advancements. However, only a handful of available solutions provide two-factor cancelability while simultaneously satisfying the tradeoff among all criteria template protection mechanisms. In this paper, we propose novel scheme for generating secure robust hash from fingerprint using Fourier-Mellin transform fractal coding. First, due to its invariance property, is incorporated into domain minutiae blocks...
This paper presents a stochastic model for the optimal risk-based generation maintenance outage scheduling based on hourly price-based unit commitment in company (GENCO). Such schedules will be submitted by GENCOs to ISO approval before implementation. The objective of GENCO is consider financial risks when its midterm outages. also coordinates proposed with short-term maximizing payoffs. mixed integer linear program which random prices energy, ancillary services, and fuel are modeled as...
The evolving unknown cyberattacks, compounded by the widespread emerging technologies (say 5G, Internet of Things, etc.), have rapidly expanded cyber threat landscape. However, most existing intrusion detection systems (IDSs) are effective in detecting only known because cyberattack samples usually available for IDS training. Identifying therefore, remains a big challenging issue. To meet this gap, paper, motivated artificial immunity (AIm) and differential evolution (DE), we propose...
Islam in the history and modernization of Maldives demonstrates an intrinsic tension, serving both as foundational cornerstone national identity source social conflict political division. On one hand, narrative being a “100% Muslim nation” has shaped highly unified identity, achieving legalization institutionalization within power structure becoming critical pillar state legitimacy integration. other politicization homogenization religion have weakened inclusivity, exacerbating religious...
New privacy implications are induced to individuals and families because of the time-series data classification problem in Internet Things such as appliance classifications smart grid. To prevent adversary from inferring household used grid, a singular spectrum analysis (SSA) has been applied local differential (SSA-LDP). First, Fourier noise added via geometric sum which proved achieve Laplace distribution. Furthermore, we have that sanitized through SSA-LDP is ε -deferentially private for...
The integration of phasor measurement units (PMUs) and data concentrators (PDCs) in smart grids may be exploited by attackers to initiate new sophisticated false injection (FDI) attacks. Existing FDI attack mitigation approaches are generally less effective against attacks, such as collusive (CFDI) attacks launched compromised PDCs (and PMUs) we demonstrate this paper. Thus, propose a secure resilience-enhanced scheme (SeCDM) detect mitigate cyber threats grids. Specifically, design...
A novel negative selection algorithm (NSA), which is referred to as ANSA, presented. In many actual anomaly detection systems, the training data are just partially composed of normal elements, and self/nonself space often varies over time. Therefore, system has build profile based on a part self elements adjust itself adapt those variables. However, previous NSAs need large number system, lack adaptability. order overcome these limitations, proposed approach uses technique radius evolve...