A5100712764- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Neural Networks and Applications
- Probabilistic and Robust Engineering Design
- Model Reduction and Neural Networks
- Reliability and Maintenance Optimization
- Neural Networks and Reservoir Computing
- Physical Unclonable Functions (PUFs) and Hardware Security
- Risk and Safety Analysis
- Advanced Malware Detection Techniques
- Software Reliability and Analysis Research
- Distributed Control Multi-Agent Systems
- Caching and Content Delivery
- IoT and Edge/Fog Computing
- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Stock Market Forecasting Methods
- Meteorological Phenomena and Simulations
- Time Series Analysis and Forecasting
- Energy, Environment, Economic Growth
- Regional Development and Environment
- Optimization and Search Problems
- Adaptive Control of Nonlinear Systems
- Hydrological Forecasting Using AI
- Advanced Multi-Objective Optimization Algorithms
Emory University
2025
Wenzhou Medical University
2025
First Affiliated Hospital of Wenzhou Medical University
2025
West Ukrainian National University
2023-2024
PLA Academy of Military Science
2024
Chinese People's Liberation Army
2019-2024
Beijing Fengtai Hospital
2024
Harbin Finance University
2024
Heilongjiang University
2023-2024
Harbin University
2024
Abstract In the past decade, deep learning has dramatically changed traditional hand-craft feature manner with strong capability, promoting tremendous improvement of conventional tasks. However, neural networks (DNNs) have been demonstrated to be vulnerable adversarial examples crafted by small noise, which is imperceptible human observers but can make DNNs misbehave. Existing attacks divided into digital and physical attacks. The former designed pursue attack performance in lab environments...
As the largest industry that absorbs labor from different levels of employment and provides remuneration, service has faced severe challenges wave artificial intelligence replacement. This study examines whether promotes shared prosperity among enterprises based on microdata listed companies in Chinese 2008 to 2022. The main research results indicate application significantly reduces enterprises' income share. mechanisms action include structure effect squeezing out low-educated frontline...
A reliability-based optimization method under both aleatory and epistemic uncertainties is studied. The mixed are analyzed by combined probability evidence theory. If the uncertainty analysis directly embedded in to quantify uncertain features of each search point, it would be computationally prohibitive. To address this problem, a sequential proposed decompose problem into separate deterministic subproblems, which solved sequentially alternately until convergence achieved. research focus...
Background IgA nephropathy (IgAN) presents a challenging spectrum of outcomes, often complicated by intrarenal arterial/arteriolar lesions (IALs) in affected individuals. Despite their clinical relevance, existing criteria for classifying and assessing the severity these remain undefined. This study aimed to establish semi-quantitative assessment grading IALs evaluate prognostic significance patients with IgAN.
Objective The aims of the study were to characterize clinical manifestations and outcomes patients with antibody-negative severe autoimmune encephalitis (AE). Methods This retrospective, monocentric recruited from Neurology Department Henan Provincial People’s Hospital between April 2017 December 2023. All underwent neural antibody testing in both blood cerebrospinal fluid (CSF) met diagnostic criteria for autoantibody-negative but probable AE, available 1-year follow-up data. Results In...
Abstract In cone beam computed tomography(CBCT)-guided adaptive radiotherapy, rapid and precise segmentation of organs-at-risk(OARs)is essential for accurate dose verification online replanning. The quality CBCT images obtained with current onboard imagers clinical imaging protocols, however, is often compromised by artifacts such as scatter motion, particularly thoracic CBCTs. These not only degrade image contrast but also obscure anatomical boundaries, making on significantly more...
Detection of flow fields constitutes a critical role in the advancement and innovation hypersonic aircraft. Under conditions, aircraft aerodynamics manifest multitude complex phenomena, including intense turbulence fluctuations, transitions within boundary layer, interactions between shock waves layers, as well effects high-temperature gas. Thus, surveillance is imperative not only for flight safety but also progression technologies. Given practical limitations that restrict sensors...
Reliability-based robust design optimization of modern small satellites has recently been receiving much attention. The role multidisciplinary considering system uncertainty is increasingly being recognized in improving satellite performance, safety, and reliability. However, high-dimensional hampers the efficiency accuracy reliability-based optimization. In this study, a novel methodology suitable for established verified. in-loop quantification employing active subspace identification...
Edge-cloud computing has attracted increasing attention recently due to its efficiency on providing services for not only delay-sensitive applications but also resource-intensive requests, by combining low-latency edge resources and abundant cloud resources. A carefully designed strategy of service caching task offloading helps improve the user satisfaction resource efficiency. Thus, in this article, we focus joint problem edge-cloud environments, cooperation between First, formulated into a...
Features extracted from the wavelet transform coefficient matrix are widely used in design of machine learning models to classify event-related potential (ERP) and electroencephalography (EEG) signals a wide range brain activity research clinical studies. This novel study is aimed at dramatically improving performance such wavelet-based classifiers by exploiting information offered cone influence (COI) continuous (CWT). The COI boundary that superimposed on scalogram delineate coefficients...
The past decade has seen a rise in the availability of modern information and communication technologies (ICTs) for developing smart societies communities. However, divide, characterized by inequalities ICT infrastructures, software access, individual capabilities, remains significant barrier rural Limited empirical studies exist that explore what how infrastructures can be developed to bridge divide. paper aimed address broadband access context infrastructural dimensions divide (i.e.,...
Despite the success of input transformation-based attacks on boosting adversarial transferability, performance is unsatisfying due to ignorance discrepancy across models. In this paper, we propose a simple but effective feature augmentation attack (FAUG) method, which improves transferability without introducing extra computation costs. Specifically, inject random noise into intermediate features model enlarge diversity gradient, thereby mitigating risk overfitting specific and notably...
A novel resampling strategy is introduced to improve the forecasting and classification accuracies of events in imbalanced time series (ITS) containing a mix low probability extreme observations high normal observations.The lag-based mitigates imbalance problem by modelling an ITS as composition observations, combining input predictor variables associated forecast output into moving blocks, categorizing blocks event (EE) or (NE) selectively blocks.Combining enables simultaneously joint...