Energy-efficient transmit antenna selection with Fast-ABC-Boost

Antenna selection is an appealing energy-efficient solution for multiple-input multiple-output (MIMO) systems. This paper handled the antenna selection problem in MIMO systems as a multi-class classification task, and propounded an antenna selection technique for energy efficiency (EE) maximization based on Fast-Adaptive Base Class-Boost (Fast-ABC-Boost) which boosts the classification performance of many "weak" classifiers, i.e. regression trees, to produce a powerful "committee" to make classification decision. Simulation results prove the superiority of Fast-ABC-Boost over the up-to-date learning method based on Deep Reinforcement Learning (DRL) and the conventional optimization driven Cyclic Binary Particle Swarm Optimization (CBPSO) approach in terms of EE performance with feasible complexity.