A5101926080- Advanced Algorithms and Applications
- Indoor and Outdoor Localization Technologies
- Radar Systems and Signal Processing
- RFID technology advancements
- Vehicle Routing Optimization Methods
- Underwater Vehicles and Communication Systems
- Advanced Computational Techniques and Applications
- Metaheuristic Optimization Algorithms Research
- Advanced Decision-Making Techniques
- Wireless Signal Modulation Classification
- Image and Video Stabilization
- Advanced Sensor and Control Systems
- Optimization and Packing Problems
- Simulation and Modeling Applications
- Advanced Measurement and Detection Methods
- Microwave Imaging and Scattering Analysis
- Energy Load and Power Forecasting
- Machine Learning in Healthcare
- Topic Modeling
- Spider Taxonomy and Behavior Studies
- CCD and CMOS Imaging Sensors
- Molten salt chemistry and electrochemical processes
- Military Defense Systems Analysis
- QR Code Applications and Technologies
- Power Systems Fault Detection
Shandong University of Science and Technology
2022
Qingdao University
2021
Central South University
2021
Shandong University
2016-2020
Boston University
2020
Shenyang Aluminum & Magnesium Engineering & Research Institute (China)
2019
Dalian Naval Academy
2016
National Space Science Center
2013
Hangzhou Normal University
2011
Tiangong University
2010
Accurate, automated extraction of clinical stroke information from unstructured text has several important applications. ICD-9/10 codes can misclassify ischemic events and do not distinguish acuity or location. Expeditious, accurate data could provide considerable improvement in identifying large datasets, triaging critical reports, quality efforts. In this study, we developed report a comprehensive framework studying the performance simple complex stroke-specific Natural Language Processing...
Timely calls for help can really make a difference elders who suffer from falls, particularly in private locations. Considering privacy protection and convenience the users, this paper, we approach problem by using impulse–radio ultra-wideband (IR-UWB) monostatic radar propose learning model that combines convolutional layers long short term memory (ConvLSTM) to extract robust spatiotemporal features fall detection. The performance of proposed scheme was evaluated terms accuracy,...
Facial expression extraction is the essential step of facial recognition. The paper presents a system that uses 28 feature key-points in images detection and Gabor wavelet filter provided with 5 frequencies, 8 orientations. In according to actual demand, It can extract low quality image target, have good robust for automatic Experimental results show performance proposed method achieved excellent average recognition rates, when it applied system.
Passive indoor localization has gained much attention recently. Numerous applications including storage management and somatosensory systems would benefit from accurate passive localization. As a potential technology for the internet of things, radio frequency identification (RFID) many advantages localization, such as low cost, parallel processing, complexity. In this paper, system, named Lobain, was proposed based on interference ultrahigh RFID tags. Using commercial off-the-shelf reader,...
Crude oil is an important fuel resource for all countries. Accurate predictions of prices have economic and social values. However, the price crude highly nonlinear under influence many factors, so it very difficult to predict accurately. Shanghai futures were officially listed in March 2018. It great significance accurately guiding China’s domestic production practice. Forecasting even more because lack data due short listing time. In order solve this problem, paper proposes using Long...
Automatic modulation classification (AMC) is the premise for signal detection and demodulation applications, especially in non-cooperative communication scenarios. It has been a popular topic decades gained significant progress with development of deep learning methods. To further improve accuracy, hierarchical multifeature fusion (HMF) based on multidimensional convolutional neural network (CNN)-long short-term memory (LSTM) proposed this paper. First, CNN module (MD-CNN) feature...
To achieve device-free indoor localization without the active participation of users, this paper presents WallSense, a system based on off-the-shelf Radio RFID (Radio-Frequency Identification) equipment. The deploys two orthogonal tag arrays in adjoining walls and uses RSSI phase information measured by readers to localize target. By differentiating backscattered signal between adjacent pairs, WallSense is able eliminate most undesirable factors extract directly related location applying...
Deep belief network (DBN) is a powerful tool for extracting high level features of sequential data. This paper proposes DBN based automatic modulation recognition method RFID signals in ultra-low signal-to-noise ratio (SNR) conditions. First, we perform FFT with simulated data to get its spectrum. The spectrum and amplitude the original signal are then used as train DBN. After training, deployed process modulated low SNR. Experiments were conducted calculate performance proposed ASK, single...
This paper proposes a passive UHF RFID indoor localization system for both tag and tag-free target based on interference. We take number of tags as landmarks interpolate virtual using nature-neighbour interpolation. monitor the interference by measuring phase difference reference tags. Two situations are considered: ground in free-space. When or is deployed, it likes stone thrown water. The difficulty find projection point target. use peak area trough to get nearest points situation least...
Automatic modulation classification plays a significant role in numerous military and civilian applications. Deep learning methods have attracted increasing attention achieved remarkable success recent years. However, few can generalize well across changes varying channel conditions signal parameters. In this paper, based on an analysis of the challenging domain shift problem, we proposed method that simultaneously achieve good accuracy well-annotated source data unlabeled signals with...
Providing uninterrupted, reliable and high-quality power supply to consumers have been very challenging for utilities around the world. The spend a considerable amount maintenance, inspection, testing monitoring of infrastructure achieve above. overhead lines are main carriers delivery electricity consumers. These prone risk fires faults caused by vegetation encroachment touches on corridor, resulting in damage conductors, blackouts catastrophic events such as wildfires or bushfires....
Radio frequency identification (RFID) provides a simple and effective solution to the passive indoor localization. The conventional wisdom about RFID localization is using reference tags. It performs well in tag or single target However, multiple scenario, based suffers from some limitations, including array aperture, mutual coupling of tags, coherent superimposition signals. These problems are harmless ignored localization, but degrade performance severely scenario. Therefore, this paper,...
Multifunction radar has been applied broadly because of its great performance. But the multifunction a wide variety signal types. How to recognition is most puzzled aspect whole environment cognition. This paper presents cognition algorithm based on wavelet transform used analyze and estimate modulation types signals in complex electromagnetic environment. And according target moving characteristics electromagnetism scattering theory, micro-Doppler feature model was established revealed...
This paper introduces the remote image monitoring system based on ARM and GPRS. Server of is used embedded Linux as platform which adopted S3C2240 chip processor, stores digital camera images after JPEG compression coding, finally transfers data to centre with static IP or domain name using terminal GPRS through its serial interface, displays decoding.
Due to the lack of criterion on efficiency UHF RFID systems in dense environment, this paper shows a novel test method for EPC C1 G2 readers environment. A new parameter based identification rate that describes performance working environment is demonstrated and generate given. Experiment show capable measuring
In order to locate human targets in highly cluttered indoor environments accurately with impulse radio ultra-wideband (IR-UWB) radar, environmental clutter need be removed first reveal the signal reflected from target. this paper, we approach problem new processing procedures. An efficient adaptive removal algorithm based on variance estimation is proposed estimate dynamic in-door environment. Test results experimental data an environment moving and non-moving verified that method can...
The autonomous technology of unmanned platforms is the most dynamic frontier among fields and, inevitably, trending towards future development. Aiming at dual requirements reliable and real-time decision-making underwater vehicles in complex unfamiliar environments, this article proposes an intelligent method attack behavior based on model fusion. experimental dataset generated through simulation modeling, appropriate amount noise added to simulate observation error a real situation....
Normally, Fuzzy decision can show the faintness of resultant, but can't maker.This paper will introduce concept non-normal fuzzy number and distance, then improve on multiple attribute method.This not only present also belief maker degree group decision.
In this paper, a fault diagnosis system is developed for radar electric equipment hybrid circuit broad based on PXI DAQ and NI computer's virtual instrument. This which uses the tree supported byLabVIEW8.6 database tools. It can quickly locate as possesses functions such data acquisition, signal analysis, intelligent detection, storage, test report generation so on. Owing to its strong generality simple operation, maintenance efficiency has been improved, makes system's rise new level.