Blind Modulation Recognition Algorithm For Spatially Correlated MIMO Systems Based On Extreme Learning Machines

Multiple Input Multiple Output(MIMO)technology has been put forward for a long time.Since the MIMO technology was actually applied to wireless communication in the 1990 s,this technology has gradually been adopted by many standards in the communication industry by virtue of its outstanding advantages in improving the channel capacity and spectrum utilization of communication systems,and has gradually become the core technology of the next generation of mobile communications.In the actual MIMO transmission channel environment,there is spatial correlation problem between the transmission subchannels due to factors such as propagation environment,antenna array placement,and scatterer distribution around the antenna,resulting in MIMO systems unable to always get potential multi-antenna gain,restricting the capacity and error performance of the communication system.With the wide application of communication technology in people's daily life,the monitoring and identification of signals are very important research topics in military and civilian fields.However,the traditional modulation method identification algorithm has a large limitation in the actual situation due to the dependence on the prior information,which also causes great difficulty in the modulation and recognition of the spatially correlated MIMO communication signal with poor information validity.The research focuses on blind digital modulation pattern recognition in spatially correlated MIMO systems and provides signal recognition algorithms based on Extreme Learning Machines(ELM)and high-order statistical features.The superiority of ELM lies in random selections of hidden nodes and ascertains output weights analytically,which result in lower computational complexity.Theoretically,this algorithm has a tendency to supply excellent generalisation performance at staggering learning rate.At the same time,the research also uses ELM's derivative algorithm-Bidirectional Extreme Learning Machine to solve the defects of ELM algorithm.The simulation results indicate that the ELM could reap a perfectly acceptable recognition performance and thus provides a solid ground structure for tackling MIMO modulation challenges in low signal-to-noise ratio.