A5051204480- Air Quality Monitoring and Forecasting
- Air Quality and Health Impacts
- Atmospheric chemistry and aerosols
- Bone Metabolism and Diseases
- Bone health and osteoporosis research
- Bone health and treatments
- Face and Expression Recognition
- Cryptographic Implementations and Security
- Image and Video Stabilization
- Thyroid Disorders and Treatments
- Software System Performance and Reliability
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Anomaly Detection Techniques and Applications
- Bacillus and Francisella bacterial research
- Wind and Air Flow Studies
- Advanced Algorithms and Applications
- Blind Source Separation Techniques
- Physical Unclonable Functions (PUFs) and Hardware Security
- Air Traffic Management and Optimization
- Security and Verification in Computing
Delft University of Technology
2021-2024
Hunan University of Science and Technology
2023
Shandong University
2019-2021
Shandong Provincial Hospital
2019-2021
Wuhan University of Technology
2014
Abstract. With the explosive growth of atmospheric data, machine learning models have achieved great success in air pollution forecasting because their higher computational efficiency than traditional chemical transport models. However, previous studies, new prediction algorithms only been tested at stations or a small region; large-scale quality model remains lacking to date. Huge dimensionality also means that redundant input data may lead increased complexity and therefore over-fitting...
Abstract Background As the incidence of secretory osteoporosis has increased, bone loss, and their relationships with thyroid-stimulating hormone (TSH) have received increased attention. In this study, role TSH in metabolism its possible underlying mechanisms were investigated. Methods We analyzed serum levels free triiodothyronine (FT3), thyroxine (FT4), mineral density (BMD) 114 men normal thyroid function. addition, osteoblasts from rat calvarial samples treated different doses for...
Ground-level ozone is a critical atmospheric pollutant, and high concentrations of can damage human health, affect plant growth cause ecological harm. Traditional chemical transport models popular machine learning have difficulty in predicting concentrations, especially times with concentrations. We proposes clustering-based spatial transfer Multilayer Perceptron (SPTL-MLP) to predict concentration at the target observation station for next three days. use k-means clustering algorithm find...
Visibility forecast is a meteorological problems which has direct impact to daily lives. For instance, timely prediction of low visibility situations very important for the safe operation in airports and highways. In this paper, we investigate use Long Short-Term Memory(LSTM) model predict visibility. By adjusting loss function network structure, optimize original LSTM make it more suitable practical applications, superior previous models short-term prediction. addition, there ”time delay...
As the incidence of osteoporosis (OP) and hypercholesterolaemia in men has increased, male OP drawn more attention from clinicians worldwide. The present study sought to investigate effects cholesterol on bone. Between July 2015 October 2015, 216 (aged ≥18 years) were recruited for this cross‑sectional study. To test our clinical hypothesis, we designed two animal models: Exogenous induced by a high‑cholesterol diet (HCD) endogenous apolipoprotein E (ApoE) knockout. Finally, direct...
Log anomaly detection is an important paradigm for system troubleshooting. Existing log based on Long Short-Term Memory (LSTM) networks time-consuming to handle long sequences. Transformer model introduced promote efficiency. However, most existing Transformer-based methods convert unstructured messages into structured templates by parsing, which introduces parsing errors. They only extract simple semantic feature, ignores other features, and are generally supervised, relying the amount of...
Accurately forecasting ozone levels that exceed specific thresholds is pivotal for mitigating adverse effects on both the environment and public health. However, predicting such exceedances remains challenging due to infrequent occurrence of high-concentration data. This research, leveraging data from 57 German monitoring stations 1999 2018, introduces an Enhanced Extreme Instance Augmentation Random Forest (EEIA-RF) approach significantly improves prediction days when maximum daily 8-hour...
The rapid advancement of deep learning has significantly heightened the threats posed by Side-Channel Attacks (SCAs) to information security, transforming their effectiveness a degree several orders magnitude superior conventional signal processing techniques. However, majority existing Deep-Learning (DLSCAs) primarily focus on classification accuracy trained model at attack stage, often assuming that adversaries have unlimited computational and time resources during profiling stage. This...
Abstract Background As the incidence of secretory osteoporosis increases, bone loss and their relationships with thyroid-stimulating hormone (TSH) have received increased attention. In this study, role TSH in metabolism underlying possible mechanisms were investigated. Methods We analyzed serum triiodothyronine (FT3), tetraiodothyronine (FT4), mineral density (BMD) levels 114 men normal thyroid function. addition, osteoblasts from rat calvarial samples treated different doses for times at...
In this paper, Gabor filtering and linear local tangent space alignment algorithm its improved are used on face recognition. The wavelet transform can detect the image information in different directions scales, according to selective direction frequency characteristics. LLTSA reduces dimension of sample while other algorithms extract secondary feature. Experiment analyze average recognition rate with variation dimension. experiment results show effectiveness method, increasing accuracy.