#NETWORK RADAR COUNTERMEASURE SYSTEMS HOW TO#

Ka Lok Man is currently a Professor in the School of Advanced Technology at Xi'an Jiaotong-Liverpool University (XJTLU) in Suzhou, China and an Adjunct Professor in the Faculty of Engineering and Science, Swinburne University of Technology Sarawak, Malaysia. Supervisor Profile: Principal Supervisor:

Using engineering-related ideas, the project is optimized for all aspects of project deployment and engineering applications, including consideration and optimization of time and space complexity in different functional scenarios.įor more information about doctoral scholarship and PhD programme at Xi’an Jiaotong-Liverpool University (XJTLU): Please visit.

Transition the task of static target recognition to dynamic target tracking, understand the differences and difficulties, try to use the generative countermeasure network in deep learning to solve the problem of too few samples of radar tracking targets, and study the strengthening of the adaptive The possibility of integrating self-learning methods into neural network sequence models.

Read and try to apply some excellent methods or ideas in ImageNet Large Scale Visual Recognition Challenge to the target task. Design and develop the corresponding neural network sequence model, and adjust the parameters and optimization methods of the model according to the model evaluation results.

According to the target task, first use some traditional machine learning ideas and algorithms to conduct a pre-experiment on the task, play a role of qualitative analysis, and understand its difficulties and the possibility of optimization.

The feature is analyzed, and the feature set is extracted based on the common sense of feature engineering theory in machine learning.

Based on the working principle of the millimeter wave radar system and the signal processing system, research its target characteristic information measurement theory, according to the information carried by the target scattering echo, the target’s electro-ceramic scattering characteristics, motion characteristics, wave characteristics, polarization characteristics, image characteristics, etc.

Grasp the signal processing method based on the millimeter wave radar system, analyze the optimal signal processing method corresponding to the millimeter wave radar under different interference conditions, and apply and improve it in some scenarios.

Based on the millimeter-wave radar system, master its basic working principles (including ranging, speed, angle measurement, etc.), and analyze the key factors that affect millimeter-wave radar imaging.

This project intends to adopt the following research methods: Therefore, applying the ideas and technologies of machine learning and deep learning to radar signal processing can assist the radar to better realize various perception tasks, which has high scientific research significance. Secondly, deep learning can also solve the problem of insufficient training sample size and model optimization under small sample conditions.

#NETWORK RADAR COUNTERMEASURE SYSTEMS HOW TO#

First of all, how to extract effective features from radar signals is a difficult problem, and deep learning weakens this problem, and can mine potential features as much as possible to improve the accuracy of target recognition or indirectly improve the use of radar. Therefore, the combination of related technologies in the field of machine learning and millimeter wave radar can achieve the purpose of technological complementarity. Compared with traditional image processing, radar automatic target classification and recognition technology is more complicated, but with the development of artificial intelligence technology In the application of radar signal processing, the performance of radar target recognition and tracking is constantly improving.

Based on radar sensors and relying on target echoes for signal processing, it can perform tasks such as target recognition, classification, and tracking. It can realize high-precision measurement of the measured target, and has the advantages of mature technology, wide application, and low cost.

Millimeter-wave radar has the characteristics of short wavelength, wide frequency band, narrow beam, and strong anti-interference ability.

Intelligent transportation and intelligent driving represent the current major trends in the development of the transportation industry, while environmental perception is the key core technology of transportation intelligence and is also a hot area of long-term academic research.

Network radar countermeasure systems