A5101695932- Sparse and Compressive Sensing Techniques
- Image and Signal Denoising Methods
- Energy Efficient Wireless Sensor Networks
- Photoacoustic and Ultrasonic Imaging
- Aeolian processes and effects
- Wireless Sensor Networks and IoT
- High voltage insulation and dielectric phenomena
- Energy Load and Power Forecasting
- Soil erosion and sediment transport
- Indoor and Outdoor Localization Technologies
- Smart Grid and Power Systems
- Underwater Vehicles and Communication Systems
- Speech and Audio Processing
- Microwave Imaging and Scattering Analysis
- Distributed Sensor Networks and Detection Algorithms
- Advanced Image Fusion Techniques
- Remote Sensing and LiDAR Applications
- Power Line Inspection Robots
- Water Quality Monitoring Technologies
- Simulation and Modeling Applications
- Face and Expression Recognition
- Geoscience and Mining Technology
- Remote Sensing and Land Use
- IoT-based Smart Home Systems
- Advanced Computational Techniques and Applications
Northeast Petroleum University
2023
Nankai University
2018-2021
Chongqing University
2019
Xinjiang Normal University
2010
As a classic and effective edge detection operator, the Sobel operator has been widely used in image segmentation other processing technologies. This obvious advantages speed of extracting images, but it also disadvantage that effect is not ideal when contains noise. In order to solve this problem, paper proposes an optimized scheme for detection. scheme, weighted nuclear norm minimization (WNNM) denoising algorithm combined with algorithm, excellent performance WNNM noise environment...
In order to reduce the error of short-term power load forecasting and improve its accuracy, A prediction method based on combination random forest (RF), convolution neural network (CNN) support vector machine (SVM) is proposed. First, data preprocessed, RF algorithm introduced optimize input variables, Then feature extracted through CNN, Finally, results are into SVM model, output realize forecasting. this paper, Singapore used for experimental analysis, compared with CNN-SVM model without...
Decreasing the number of data gathered is most highly effective way to decrease power consumption for wireless sensor networks. Compressed Data Gathering, as it known all, a collection method in networks, but cannot achieve sparse sensing all need be sensed and then transmitted practical applications. At same time, has been shown effectiveness total variation low rank constraints restoration. In order enhance accuracy recovery energy cost we propose Multi-Timeslots Collection scheme, which...
This paper designs and implements an image transmission algorithm applied to plant information collection based on the wireless sensor network. It can effectively reduce volume of transmitted data, low-energy, high-availability compression algorithm. mainly has two aspects improvement measures: first is number pixels that transmit images, from interlaced scanning neighbor scanning; second use JPEG [1], changing value quantization table in [2]. After compression, data greatly reduced;...
The most effective way to reduce the energy consumption of energy-limited wireless sensor networks is amount data collected. However, this will increase difficulty recovery. At same time, collection and recovery algorithms based on matrix completion are optimized by decomposition. Therefore, mathematical model corresponding optimization algorithm be more complicated take a lot running time. In order deal with above problems, we propose method low rank short-term stability in paper. low-rank...
Compressed Sensing (CS) is intended to recover a high-dimensional but sparse vector by small number of linear sampling. Seeking an appropriate domain great importance achieve high enough degree sparsity. In this paper, we propose new scheme for image using multiscale strategy and structural group representation, which efficiently characterizes the sparsity multi-scale self-similarity natural images in adaptive domain. Then, constraint are exploited simultaneously under unified framework. A...
The ultrahigh frequency (UHF) method is a reliable monitoring for the insulation condition of power equipment, but existing UHF equipment are mostly immovable, which can only monitor one equipment. In this paper, Partial Discharge (PD), based on robot and antenna array, proposed. Signal processing circuit designed. patrol algorithm designed to realize function transformer substation monitoring. It improve using efficiency PD reduce cost This paper starts with positioning makes lot...