Signal constellation design in the presence of radar interference and Gaussian noise

Nartasilpa, Narueporn; Tuninetti, Daniela; Devroye, Natasha

doi:10.1109/milcom.2017.8170767

Cited by 2 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neither an analytical expression of the mutual information (or of the symbol error rate) nor an a priori on the geometry of the constellation are needed for the optimization process. This is in contrast with previous works [21], [22], [23], [13]. The constellation geometry and the labeling are optimized jointly.…”

Section: Introductionmentioning

confidence: 83%

“…Thanks to this optimization framework, the constellation shape, the constellation labeling 1 and the soft demapping device are optimized jointly. This in contrast with [13] in which the constellation labeling is not addressed. Indeed, in [13] the symbol error rate (SER) is considered in the optimization problem whereas here the loss function is based on bit probabilities.…”

Section: System Modelmentioning

confidence: 95%

“…This in contrast with [13] in which the constellation labeling is not addressed. Indeed, in [13] the symbol error rate (SER) is considered in the optimization problem whereas here the loss function is based on bit probabilities. This is a key difference that will be discussed in section V-C.…”

Section: System Modelmentioning

confidence: 95%

“…To the best of our knowledge, this problem has not been widely investigated in the past. Very recently, this question was addressed in [13]. The objective function considered for the minimization process is the symbol error rate which is based on the analytical expressions given in [14] for the weak and for the very strong interference regime leading to very interesting results for these two situations.…”

Section: Introductionmentioning

confidence: 99%

“…The objective function considered for the minimization process is the symbol error rate which is based on the analytical expressions given in [14] for the weak and for the very strong interference regime leading to very interesting results for these two situations. The method in [13] cannot be extended to other regimes since closed form expressions are not known in the general case. Instead, it is proposed here to use deep learning and AEs for constellation design.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Deep Learning Constellation Design for the AWGN Channel With Additive Radar Interference

Alberge

2019

IEEE Trans. Commun.

View full text Add to dashboard Cite

Radar and wireless communication coexistence is considered in this paper as a possible solution to face the exploding demand and rising congestion in wireless networks. The transmission medium is modeled as an AWGN channel with additive radar interference. Standard constellations are not optimal in this context and an auto-encoder (AE) is used to design proper constellations and corresponding receiver devices. AE is a powerful tool in neural networks that shares strong similarities with communication systems. This technique is particularly relevant in the lack of an analytical expression of the loss function. In the asymptotic region (high interference regime), the optimal constellation shape is known and the AE always converges towards this optimal solution. In the other regions, the AE is able to yield solutions that outperform the standard configurations. Several demapping alternatives are also considered leading to the conclusion that it is possible to maintain the communication link in the presence of radar interference independently of the interference power. This is a step further compared to previous works in which solutions were limited to low or high interference regimes.

show abstract