A5008917503- Cooperative Communication and Network Coding
- Cardiovascular Health and Disease Prevention
- Machine Fault Diagnosis Techniques
- Advanced Wireless Communication Techniques
- Stock Market Forecasting Methods
- Advanced MIMO Systems Optimization
- Complex Systems and Time Series Analysis
- Fluid Dynamics and Vibration Analysis
- Time Series Analysis and Forecasting
- Technology and Data Analysis
- Data Stream Mining Techniques
- Lattice Boltzmann Simulation Studies
- Ultrasound Imaging and Elastography
- Energy Load and Power Forecasting
- Vibration and Dynamic Analysis
- Advanced Statistical Modeling Techniques
- Statistical Methods and Inference
- Phonocardiography and Auscultation Techniques
- Anomaly Detection Techniques and Applications
Tianjin University
2024
Wuhan University of Technology
2023-2024
Yunnan University
2013-2014
Telus (Canada)
2013-2014
<title>Abstract</title> Genetic variants across the genome contribute to architecture of complex traits, which are highly polygenic in nature. Understanding this complexity and improving genomic prediction requires accurate inference distribution genetic effects. We introduce SumHEM, a summary-level heteroscedastic effects model that leverages summary statistics from genome-wide association studies (GWAS) estimate SNP efficiently. SumHEM outperformed state-of-the-art methods, including...
In stock prediction problems, deep ensemble models are better adapted to dynamically changing market environments compared single time-series networks. However, the existing often underutilize real-time feedback for effective supervision, and base pre-trained fixed in their optimization, which makes them lack adaptability evolving environments. To address this issue, we propose a deep-reinforcement-learning-based dynamic model (DRL-DEM). Firstly, employ reinforcement learning optimize...
In recent years, time series forecasting has been widely used in various fields, especially financial markets. Stock trend become one of the most common and complex challenges faced by investors researchers. However, much current research relies primarily on single-granularity stock data for forecasting, with relatively few studies multi-granularity fewer spatial correlation data. This inherent limitation restricts comprehensive extraction valuable information. To address this challenge, we...
The fluidelastic instability (FEI) in heat exchanger tubes has been of widespread concern due to its tendency cause damage the tubes. Generally, FEI transverse direction tube occurs earlier than streamwise direction, and intrinsic frequency as well way distribution have a great influence. mechanisms involved inducing need be further investigated. We set up an air-water two-phase flow water tunnel test system adopt normal triangular arrangement plate with pitch-to-diameter ratio 1.41 conduct...
Summary Multiple‐input multiple‐output (MIMO) transmission techniques constitute an important technology in modern wireless communication. Hence, performance analysis methods for such systems are of considerable interest. This paper considers first the average pairwise error probability uncoded MIMO employing maximum likelihood detection over a composite Rayleigh‐Lognormal fading channel with spatial correlation. It provides general results, applicable also to wider class shadowing models,...
Abstract This work considers a simple bit level combining technique, aided by robust reliability information, for uplink collaborating multiple‐input multiple‐output (MIMO) base‐stations (also known as macrodiversity MIMO), operating over composite Rayleigh‐lognormal fading channels. Bit weights based on modification of the logarithmic likelihood ratio, combined with instantaneous symbol signal‐to‐noise ratio are derived different local MIMO detection schemes. information is used at fusion...
Based on the ensemble empirical mode decomposition (EEMD) time-frequency analysis for avoiding mixing, an algorithm to delicately separate Doppler blood flow and vessel wall beat signals is proposed in this paper. Firstly, proper amplitude of added noise number average cancellation are estimated, then mixed ultrasound signal decomposed into IMFs by using EEMD method. Finally, around division between separated soft-threshold denoising Experiments both computer simulated with WBSR 20dB, 40dB...