A5040959196- Wireless Signal Modulation Classification
- Radar Systems and Signal Processing
- Gaze Tracking and Assistive Technology
- Smart Parking Systems Research
- Blind Source Separation Techniques
- Advanced Memory and Neural Computing
- Mobile and Web Applications
- Impact of Light on Environment and Health
- EEG and Brain-Computer Interfaces
- DNA and Biological Computing
Huaqiao University
2021-2022
Xi’an University of Posts and Telecommunications
2021
Modulation classification is one of the key tasks for communications systems monitoring, management, and control addressing technical issues, including spectrum awareness, adaptive transmissions, interference avoidance. Recently, deep learning (DL)-based modulation has attracted significant attention due to its superiority in feature extraction accuracy. In DL-based classification, major challenge preprocess a received signal represent it proper format before feeding into neural networks....
In this paper, the differences between two motor imagery tasks are captured through microstate parameters (occurrence, duration and coverage, mean spatial correlation (Mspatcorr)) derived from a novel method based on electroencephalogram Teager energy operator. The results show that significance for is different (P < 0.05) with paired t-test. Furthermore, these utilized as features. Support vector machine to classify accuracy of 93.93%, which yielded superior performance compared other methods.
Channel code recognition, which aims to recognize the channel adopted by received signal, plays an important role in fields of non-cooperative communications. Deep learning based recognition methods have been attracting great attention due their superiority from massive signals and extracting signal features automatically. However, these mainly use a single type neural network suffer low accuracy. In this paper, we propose algorithm on two types networks including bi-directional long...
In order to solve the problem of tunnel lighting safety and energy waste, a optimization system based on wireless communication is established. According different light intensity changes traffic flow outside tunnel, related factors affecting illumination in gives dimming command through algorithm optimize illuminance lamps lanterns. The simulation results show that can lanterns, realize intelligent controlled by single lamp tunnels, effectively save energy.
The tasks of identifying which modulation format and channel coding scheme have been utilized by the wireless signal are crucial to intelligent communications, electronic warfare, spectrum management. Currently, most research on these digs into either identification or identification, while joint has not fully investigated. In this paper, we propose two algorithms based deep learning handle simultaneously. first algorithm adopts a successive architecture, in neural networks used tasks,...
Automatic modulation recognition (AMR) is of great importance in various communications applications. Deep Learning (DL) based AMR has been becoming a popular choice as it inhibits the powerful classification capability DL. However, existing DL methods mostly exploit single network and can hardly obtain full understanding received signal. This paper proposes multi-network algorithm with confidence fusion to improve performance. According proposed algorithm, four different deep neural...