Blind Digital Modulation Identification for Time-Selective MIMO Channels

On classifiers for blind feature‐based automatic modulation classification over multiple‐input–multiple‐output channels

“…ANN is typically a mathematical model which aims at defining a function f : A → B, where A is the set of features and B is the set of classes. With their high classification accuracy and generalisation ability, ANN is a widely employed classifier for pattern recognition problems such as FB-AMC [5,8,13]. Such as other supervised learning-based classifiers, ANN requires a training phase before being ready to be used.…”

Denoising Higher-Order Moments for Blind Digital Modulation Identification in Multiple-Antenna Systems

“…As such, most of HOS-based DMI algorithms rely on HOC as features [1], [5], [7], [8]. However, many other HOSbased DMI algorithms attempt to improve the identification performance by including a set of HOM [2]- [4], [6].…”

“…Also, within the framework of this paper, we consider multiple-input-multipleoutput (MIMO) systems as an essential part of state-of-theart wireless systems. Moreover, multi-antenna systems are amply involved in the subject of DMI [2]- [6], [8], [10]- [13]. As far as we know, there is no yet attempt on offsetting noise in HOM in the blind DMI context.…”

Blind modulation classification algorithm based on machine learning for spatially correlated MIMO system

“…In [10], the author adopts a ML approach for blind modulation recognition and considers two different situations with different modulation classifiers: hybrid likelihood ratio and average likelihood ratio tests. In [11], the authors cover blind digital modulation identification's trouble in time‐selective MIMO channels, accepting a definite multi‐artificial‐neural‐network (ANN) classifier. The methods’ major drawbacks are the highly computational complexity.…”