A5101888130- Underwater Vehicles and Communication Systems
- Underwater Acoustics Research
- Target Tracking and Data Fusion in Sensor Networks
- Maritime Navigation and Safety
- GNSS positioning and interference
- Indoor and Outdoor Localization Technologies
- Intracranial Aneurysms: Treatment and Complications
- Traumatic Brain Injury and Neurovascular Disturbances
- Genetic and Kidney Cyst Diseases
- Image Enhancement Techniques
- Genetic Mapping and Diversity in Plants and Animals
- Soil Moisture and Remote Sensing
- Seismic Imaging and Inversion Techniques
- Fetal and Pediatric Neurological Disorders
- Cerebrovascular and Carotid Artery Diseases
- Advanced SAR Imaging Techniques
- Robotic Path Planning Algorithms
- Advanced Image Fusion Techniques
- Blind Source Separation Techniques
- Inertial Sensor and Navigation
- Genetic Syndromes and Imprinting
- Protist diversity and phylogeny
- Bioinformatics and Genomic Networks
- Genetic Associations and Epidemiology
- Hedgehog Signaling Pathway Studies
Shandong University
2021-2024
Panzhihua University
2022
Beihang University
2021
Timely and accurate prediction of delayed cerebral ischemia is critical for improving the prognosis patients with aneurysmal subarachnoid hemorrhage. Machine learning (ML) algorithms are increasingly regarded as having a higher power than conventional logistic regression (LR). This study aims to construct LR ML models compare their on (DCI) after hemorrhage (aSAH).This was multicenter, retrospective, observational cohort that enrolled from five hospitals in China. A total 404 aSAH were...
Abstract Underwater acoustic Long-Baseline System (LBL) is an important technique for submarine positioning and navigation. However, the high cost of seafloor equipment complex construction a network restrict distribution LBL within small area, making underwater vehicle difficult long-distance high-precision acoustic-based or inertial-based We therefore propose LBL-based Inertial Measurement Unit (IMU) calibration algorithm. When can receive signal from beacon, IMU precisely calibrated to...
Backgrounds As a most widely used machine learning method, tree-based algorithms have not been applied to predict delayed cerebral ischemia (DCI) in elderly patients with aneurysmal subarachnoid hemorrhage (aSAH). Hence, this study aims develop the conventional regression and models determine which model has better prediction performance for DCI development hospitalized after aSAH. Methods This was multicenter, retrospective, observational cohort analyzing aSAH aged 60 years older. We...
Precipitable water vapor (PWV) is an important parameter reflecting atmospheric vapor, which plays role in the global hydrological cycle. At present, brightness temperatures (Tbs) at frequencies of 18 and 23 GHz from Advanced Microwave Scanning Radiometer 2 (AMSR2) are commonly applied PWV data retrieval. Two tools usually employed to perform retrieval: physical models neural networks. In this article, we creatively deduced a more universal equation verified consistency between theoretical...
Underwater acoustic navigation technology is an important approach to achieving high precision ocean navigation. One of the critical issues correct systematic errors, which are related time delays and time-varying sound speed errors. In this study, we propose augmented underwater with error model based on seafloor datum network. The proposed algorithm first selects data sets piece-wise modeling by extracting main periodic term errors Fourier transform. Before that, wavelet transform used for...
Underwater sound speed is one of the most significant factors that affects high-accuracy underwater acoustic positioning and navigation. Due to its complex temporal variation, forecasting field (SSF) becomes a challenging task. Taking advantage machine learning methods, we propose new method for SSF based on least square support vector (LSSVM) multi-parameter model, aiming enhance accuracy with hourly resolution. We first use matching extension standardize profile data train LSSVM parameters...
In underwater acoustic round-trip positioning, the incident angle calculation in constant gradient ray tracing significantly hinders efficiency of positioning calculation. To address this issue, we proposed an ultra-fast method for determining based on positioning. Specifically, employs k-mean++ clustering algorithm to streamline sound velocity profile. Additionally, a function formula is constructed, and its partial derivative with respect Snell's derived. Finally, Newton's applied...
Underwater long baseline system is widely used for underwater vehicle navigation. However, the traditional method exhibits a significant increase in navigation error when acoustic observation data quality poor. To resolve this issue, we propose an round-trip algorithm that incorporates depth constraint and Rauch-Tung-Striebel (RTS) smoothing. Specifically, derives detailed function model Additionally, position dilution of precision (PDOP) to search optimal information. This information then...
在深海定位中，声线传播距离长、声速剖面层数多，采用常梯度声线跟踪虽然提高了定位精度，但明显降低了定位的计算效率。针对这一问题，本文引入优化聚类算法，提出了一种基于K-Means++的声速剖面精简方法。该方法将原始声速剖面的梯度分为正负2个部分，采用K-Means++对每部分进行初始聚类，再对聚类后的每一簇进行不同类别数的K-Means++聚类，将相邻相同类的层合并后得到精简声速剖面。采用精简声速剖面进行水下定位，并与原始声速剖面定位效果对比。实验结果表明：本文方法在确保原始声速剖面空间结构和水下定位精度的前提下，显著提高了定位计算效率，且在不同深度的定位精度与原始声速剖面定位精度保持一致。