- Acute Ischemic Stroke Management
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Blood Pressure and Hypertension Studies
- Cerebrovascular and Carotid Artery Diseases
- Advanced Neural Network Applications
- Advanced Image Fusion Techniques
- Parallel Computing and Optimization Techniques
- Image and Signal Denoising Methods
- Neurological Disorders and Treatments
- Image Retrieval and Classification Techniques
- Remote Sensing and LiDAR Applications
- Interconnection Networks and Systems
- Video Surveillance and Tracking Methods
- Advanced Image and Video Retrieval Techniques
- Embedded Systems Design Techniques
- Lipoproteins and Cardiovascular Health
- Stroke Rehabilitation and Recovery
- Industrial Vision Systems and Defect Detection
- Adipokines, Inflammation, and Metabolic Diseases
- Diabetes, Cardiovascular Risks, and Lipoproteins
- Algorithms and Data Compression
- Software Engineering Research
- Heart Rate Variability and Autonomic Control
- Colorectal Cancer Screening and Detection
Harbin University of Science and Technology
2016-2025
Soochow University
2016-2025
Tongji University
2021-2025
Zhejiang University
2024-2025
Heilongjiang University of Science and Technology
2025
Yangpu Hospital of Tongji University
2025
Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)
2022-2024
Weifang University of Science and Technology
2018-2024
State Key Laboratory of Remote Sensing Science
2024
Heilongjiang Provincial Metrology and Testing Institute
2024
Intrusion detection system (IDS) plays an important role in network security by discovering and preventing malicious activities. Due to the complex time-varying environment, intrusion samples are submerged into a large number of normal samples, which leads insufficient for model training results with high false rate. According problem data imbalance, we propose algorithm combined hybrid sampling deep hierarchical network. Firstly, use one-side selection (OSS) reduce noise majority category,...
To examine the association between serum matrix metalloproteinases-9 (MMP-9) levels and prognosis of acute ischemic stroke.We measured MMP-9 in 3,186 participants (2,008 men 1,178 women) from China Antihypertensive Trial Acute Ischemic Stroke (CATIS). Study outcome data on death, major disability (modified Rankin Scale score ≥3), vascular disease were collected at 3 months after stroke onset.During follow-up, 767 (24.6%) experienced or died. Serum was significantly associated with an...
Objective Polycystic ovary syndrome (PCOS) is a frequent reproductive and metabolic disorder associated with insulin resistance (IR). Berberine (BBR) an isoquinoline derivative alkaloid extracted from Chinese medicinal herbs that has been used as sensitizer. BBR may have potential therapeutic value for PCOS. The aim of this study was to evaluate the effects in comparison metformin (MET) on features women Design methods Eighty-nine subjects PCOS IR were randomized into one three treatment...
Deep learning-based methods, especially deep convolutional neural network (CNN), have proven their powerfulness in hyperspectral image (HSI) classification. On the other hand, ensemble learning is a useful method for classification task. In this letter, order to further improve accuracy, combination of CNN and random forest (RF) proposed HSI The well-designed used as individual classifier extract discriminant features RF randomly selects extracted training samples formulate multiple system....
Accumulating evidence suggests a role of semaphorins in vascular homeostasis. Here, we investigate the Sema7A (semaphorin 7A) atherosclerosis and its underlying mechanism.Using genetically engineered Sema7A-/-ApoE-/- mice, showed that deletion attenuates atherosclerotic plaque formation primarily aorta ApoE-/- mice on high-fat diet. A higher level atheroprone lesser curvature correlation with disturbed flow. This notion is supported by elevated expression human umbilical venous endothelial...
Choline metabolism was suggested to play pathophysiological roles in nervous system and atherosclerosis development. However, little is known about the impacts of choline pathway nutrients metabolites on poststroke cognitive impairment. We aimed prospectively investigate relationships between circulating choline, betaine, trimethylamine N-oxide with impairment among acute ischemic stroke patients.We derived data from CATIS (China Antihypertensive Trial Acute Ischemic Stroke). Plasma...
Silicone polyurethanes have gained widespread application in the biomedical field due to their excellent biocompatibility. This study comprehensively investigates four silicone polyurethane materials suitable for polymer heart valves, each exhibiting distinct chemical compositions and structural characteristics, leading significant differences, particularly mechanical performance Surface analysis reveals an elevated surface silicon element content all compared bulk, indicating a migration of...
The modulation recognition of digital signals under non-cooperative conditions is one the important research contents here. With rapid development artificial intelligence technology, deep learning theory also increasingly being applied to field recognition. In this paper, a novel signal algorithm proposed, which has combined InceptionResNetV2 network with transfer adaptation, called InceptionResnetV2-TA. Firstly, received preprocessed and generated constellation diagram. Then, diagram used...
Background Epidemiological studies have reported discrepant findings on the relationship between education level and outcomes after stroke. We aimed to prospectively investigate mortality, recurrent stroke, cardiovascular events in Chinese patients with ischemic Methods Results included 3861 participants from China Antihypertensive Trial Acute Ischemic Stroke. Education was categorized as illiteracy, primary school, middle college. Study were all-cause stroke-specific within 2 years A...
To compared the effect of early antihypertensive treatment started within 24-48 h stroke onset versus delaying until day eight on reducing dependency or death.Multicentre, randomised, open label trial.106 hospitals in China between 13 June 2018 and 10 July 2022.4810 patients (≥40 years) were enrolled with acute ischaemic symptom elevated systolic blood pressure 140 mm Hg <220 Hg.Patients randomly assigned to receive immediately after randomisation (aimed at by 10%-20% first 24 a mean <140/90...
Traditional end-to-end (E2E) training of deep networks necessitates storing intermediate activations for back-propagation, resulting in a large memory footprint on GPUs and restricted model parallelization. As an alternative, greedy local learning partitions the network into gradient-isolated modules trains supervisely based preliminary losses, thereby providing asynchronous parallel methods that substantially reduce cost. However, empirical experiments reveal as number segmentations module...
BACKGROUND: We performed a prespecified subgroup analysis of the CATIS-2 trial (China Antihypertensive Trial in Acute Ischemic Stroke II) to compare effect early versus delayed antihypertensive treatment on death and disability patients with without medical history hypertension. METHODS: is multicenter randomized clinical conducted 106 hospitals China. The 4810 acute ischemic stroke within 24 48 hours symptom onset elevated systolic blood pressure between 140 <220 mm Hg receive...
Polyamines have been suggested to play pivotal roles in ischemic stroke and neurodegenerative disorders, but the associations of plasma polyamines with poststroke cognitive impairment (PSCI) remain unclear. We aimed prospectively investigate putrescine, spermidine, spermine PSCI among patients a multicenter cohort study. measured polyamine levels at baseline 619 from preplanned ancillary study CATIS (China Antihypertensive Trial Acute Ischemic Stroke). used Mini-Mental State Examination...
Spiking Neural Networks (SNNs) are emerging as a brain-inspired alternative to traditional Artificial (ANNs), prized for their potential energy efficiency on neuromorphic hardware. Despite this, SNNs often suffer from accuracy degradation compared ANNs and face deployment challenges due fixed inference timesteps, which require retraining adjustments, limiting operational flexibility. To address these issues, our work considers the spatio-temporal property inherent in SNNs, proposes novel...
Pose estimation (PE) is a cutting-edge technology in computer vision, essential for AI-driven sport analysis, advancing technological applications, enhancing security, and improving the quality of life. Deep learning has markedly advanced accuracy efficiency field while propelling algorithmic frameworks model architectures to greater complexity, yet rendering their underlying interrelations increasingly opaque. This review examines deep learning-based PE techniques, classifying them from two...
Objective— Serum Dkk-1 (dickkopf-1) level has been shown to be elevated in patients with ischemic stroke, but its impact on clinical outcomes of stroke remains unclear. The aim this study is investigate the association between serum and prognosis stroke. Approach Results— We measured levels 3178 from CATIS (China Antihypertensive Trial Acute Ischemic Stroke). primary outcome was a combination all-cause mortality major disability (modified Rankin scale score, ≥3) at 1 year after Secondary...
Background and Purpose- Previous experimental studies suggested that serum netrin-1 was associated with the progression of ischemic stroke. Knowledge about among stroke patients may provide new ideas for prognostic assessment The aim this study to investigate association between prognosis Methods- Serum levels at baseline were measured 3346 from CATIS (China Antihypertensive Trial in Acute Ischemic Stroke), all followed up 3 months after onset. primary outcome a combination death major...