Lagrange programming neural network for radar waveform design
Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 12_Chapter in an edited book (Author) › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Title of host publication | Radar Waveform Design Based on Optimization Theory |
| Editors | Guolong Cui, Antonio De Maio, Alfonso Farina, Jian Li |
| Publisher | Institution of Engineering and Technology |
| Chapter | 8 |
| Pages | 221-261 |
| ISBN (Electronic) | 9781785619441 |
| ISBN (Print) | 9781785619434 |
| Publication status | Published - 2020 |
Link(s)
Abstract
In this chapter, Lagrange programming neural network (LPNN) that is a constrained
optimization solver is exploited to design radar probing waveforms under constraints
due to unit-modulus, spectral requirement and/or ambiguity function (AF). In the
LPNN, there are two types of neurons to compute the optimum solution, namely, variable and Lagrangian neurons, which are responsible for finding a minimum point of
the cost function as well as the solution at an equilibrium point and leading the dynamic
trajectory into the feasible region. The local stability conditions of the dynamic neuron model are also analyzed. Simulation results show that the LPNN-based approach
is a competitive alternative for waveform design.
Citation Format(s)
Lagrange programming neural network for radar waveform design. / Liang, Junli; Jing, Yang; So, Hing Cheung; Leung, Chi Sing; Li, Jian; Farina, Alfonso.
Radar Waveform Design Based on Optimization Theory. ed. / Guolong Cui; Antonio De Maio; Alfonso Farina; Jian Li. Institution of Engineering and Technology, 2020. p. 221-261.Research output: Chapters, Conference Papers, Creative and Literary Works (RGC: 12, 32, 41, 45) › 12_Chapter in an edited book (Author) › peer-review
