A5102759645- Direction-of-Arrival Estimation Techniques
- Speech and Audio Processing
- Sparse and Compressive Sensing Techniques
- Indoor and Outdoor Localization Technologies
- Blind Source Separation Techniques
- Antenna Design and Optimization
- Advanced Neural Network Applications
- Advanced SAR Imaging Techniques
- Image and Signal Denoising Methods
- Wireless Signal Modulation Classification
- Structural Health Monitoring Techniques
- Vehicle License Plate Recognition
- Target Tracking and Data Fusion in Sensor Networks
- Anomaly Detection Techniques and Applications
- Microwave Imaging and Scattering Analysis
- Handwritten Text Recognition Techniques
- Brain Tumor Detection and Classification
- Infrared Target Detection Methodologies
- Advanced Sensor and Control Systems
- Aviation Industry Analysis and Trends
- Microwave Engineering and Waveguides
- Air Traffic Management and Optimization
- Domain Adaptation and Few-Shot Learning
- UAV Applications and Optimization
- Hand Gesture Recognition Systems
China University of Mining and Technology
2024-2025
Shanxi University
2025
Civil Aviation Flight University of China
2020-2024
Peking University
2024
Peking University Cancer Hospital
2024
University of Electronic Science and Technology of China
2011-2023
Hohai University
2021-2023
Waseda University
2021
PLA Army Service Academy
2019
Wannan Medical College
2019
This work addresses the direction-of-arrival (DOA) estimation issue with multiple noncoherent subarrays. We use a maximum likelihood approach to derive weighted MUSIC (w-MUSIC) algorithm for such arrays, which obtains overall spatial spectrum via combining of Theoretical analysis and numerical examples demonstrate that w-MUSIC has better performance compared previously introduced
Aiming at the problem that it is difficult to adjust parameters of controller in circulating fluidized bed (CFB) boiler combustion system due its multivariable and strong coupling, an improved linear active disturbance rejection (ILADRC) parameter tuning strategy based on Lévy flight double chaotic sparrow search algorithm (LF-DCSSA) proposed. The LF-DCSSA used tune ILADRC coupled control CFB built by Simulink, so effect can reach best state. step response simulation perturbation are carried...
Direction-of-arrival (DoA) estimation is one of the most promising technologies in array signal processing. Existing data-driven methods for DoA are usually implemented by classification networks, which suffer from insufficient utilization about features sources and require spectral peak-search stage. In this letter, we reframe as a target detection problem propose novel approach on basis you only look once v3 (YOLOv3) framework, namely YOLO-DoA. DoAs with confidence scores directly...
With the continuous promotion of smart substations, staff fall detection has become a key issue in automatic substations. The injuries and safety hazards caused by falls among substation personnel are numerous. If timely response can be made event fall, reduced. In order to address issues low accuracy poor real-time performance detecting human complex scenarios, this paper proposes an improved algorithm based on YOLOX. A customized feature extraction module is introduced YOLOX fusion network...
This article describes a system being developed to process bank checks. To interpret the various items of information contained in image check, many modules are required. These begin with implementation image-processing techniques isolate and identify each category handwritten information. The relevant recognizers then used read numeric legal amounts, as well date on check. must be able digits (in isolated or connected form), cursive words, mixture numerals last which is necessary for...
Purpose:The medical-pharmaceutical separation (MPS) reform is a healthcare that focuses on reducing the proportion of drug expenditure.This study aims to analyze impact MPS hospitalization expenditure and its structure in tertiary public hospitals.Methods: Using propensity score matching multi-period difference-in-difference methods structure, difference-in-difference-in-difference model was established heterogeneity whether hospital diagnosis-related-group (DRG) payment hospital.Of 22...
Source number determination is important for some communication applications. Existing source enumeration methods are sensitive to the of snapshots, signal-to-noise ratio and sources. In letter, we propose a multi-path features fusion network (MFFNet) enhance accuracy. The inherent multi-scale scheme Feature Pyramid Networks (FPN) path augmentation Path Aggregation Network (PANet) exploited, which fuses spatial feature array temporal snapshots. proposed method can extract sufficient...
Background: Mining knowledge from microarray data is one of the popular research topics in biomedical informatics. Gene selection a significant trend mining, since accuracy tumor identification heavily relies on genes biologically relevant to identified problems. Objective: In order select small subset informative numerous for identification, various computational intelligence methods were presented. However, due high dimensions, sample size, and inherent noise available, many confront...
In this paper, we present new results on using orthogonal matching pursuit (OMP), to solve the sparse approximation problem over redundant dictionaries for complex cases (i.e., measurement vector, dictionary and additive white Gaussian noise (CAWGN)). A sufficient condition that OMP can recover optimal representation of an exactly signal in is proposed both noiseless bound settings. Similar exact recovery (ERC) real cases, extend them case derivate corresponding ERC paper. It leverages...
Pulmonary nodule detection system consists of two steps: candidate and false positive reduction. To dynamically adapt the sizes ratios nodules, Local Density based Iterative Self-Organizing Data Analysis Techniques Algorithm (D-ISODATA) is proposed for automated anchor boxes configuration. For detection, instead fixed anchor, D-ISODATA utilized automatically generate anchors to high variability nodules. initializes clustering center removes noises on principle maximum local density further...
In this paper, an intelligent direction finding (DF) architecture based on hybrid neural network is proposed. Firstly, the array outputs of DF system are multiplied by corresponding ideal manifold and a high-dimensional preprocessed feature vector derived. next, straightly fed into auto-encoder. The auto-encoder then used as input cascaded deep residual in order to extract spatial spectral sources. Finally, direction-of-arrival (DOA) results derived according locations normalised peaks....
This article proposes a new angle difference of directions arrival (ADOA) estimation algorithm. It can estimate the values ADOA incidence signals even under channel incoherence environments. performs an eigenvalue decomposition covariance matrix to obtain signal and noise subspace eigenvectors, then estimates based on orthogonality between eigenvectors steering vectors. Its main advantage is that performance not degenerated by array elements incoherence. In addition, system complexity also...
In wireless sensor networks (WSNs), node localization issue from pairwise Euclidean distance measurements has become a fundamental research topic. this paper, we investigate the of improving noisy positions using accurate connected inter-sensor range measurements. Different previous researchers proposed an efficient algorithm for case fully connected, semidefinite programming (SDP) method is derived to relax nonconvex maximum likelihood estimation (MLE) problem into convex problem. To be...
Abstract Tissue module (TM) is a spatially organized tissue region and executes specialized biological functions, recurring varying at different sites. However, the computational identification of TMs poses challenges due to their convoluted poorly-defined molecular features, patterns. Here, we present hypothesis-free graph Fourier transform model, SpaGFT, represent features using coefficients, leading an accurate representation variable genes proteins characterization TM fast speed. We...
Fault diagnosis plays a crucial role in maintaining the operational integrity of mechanical systems, preventing significant losses due to unexpected failures. As intelligent manufacturing and data-driven approaches evolve, Deep Learning (DL) has emerged as pivotal technique fault research, recognized for its ability autonomously extract complex features. However, practical application current methods is challenged by complexity industrial environments. This paper proposed Temporal Denoise...