Radio modulation classification has always been an important technology in the field of communications.The difficulty of incremental learning in radio modulation classification is that learning new tasks will lead to ...Radio modulation classification has always been an important technology in the field of communications.The difficulty of incremental learning in radio modulation classification is that learning new tasks will lead to catastrophic forgetting of old tasks.In this paper,we propose a sample memory and recall framework for incremental learning of radio modulation classification.For data with different signal-to-noise ratios,we use a partial memory strategy by selecting appropriate samples for memorizing.We compare the performance of our proposed method with three baselines through a large number of simulation experiments.Results show that our method achieves far higher classification accuracy than finetuning method and feature extraction method.Furthermore,it performs closely to joint training method which uses all old data in terms of classification accuracy which validates the effectiveness of our method against catastrophic forgetting.展开更多
A cascade glow discharge in atmospheric helium was excited by a microsecond voltage pulse and a pulse-modulated radio frequency(RF) voltage, in which the discharge ignition dynamics of the RF discharge burst was inves...A cascade glow discharge in atmospheric helium was excited by a microsecond voltage pulse and a pulse-modulated radio frequency(RF) voltage, in which the discharge ignition dynamics of the RF discharge burst was investigated experimentally. The spatio-temporal evolution of the discharge, the ignition time and optical emission intensities of plasma species of the RF discharge burst were investigated under different time intervals between the pulsed voltage and RF voltage in the experiment. The results show that by increasing the time interval between the pulsed discharge and RF discharge burst from 5 μs to 20 μs, the ignition time of the RF discharge burst is increased from 1.6 μs to 2.0 μs, and the discharge spatial profile of RF discharge in the ignition phase changes from a double-hump shape to a bell-shape. The light emission intensity at 706 nm and 777 nm at different time intervals indicates that the RF discharge burst ignition of the depends on the number of residual plasma species generated in the pulsed discharges.展开更多
文摘Radio modulation classification has always been an important technology in the field of communications.The difficulty of incremental learning in radio modulation classification is that learning new tasks will lead to catastrophic forgetting of old tasks.In this paper,we propose a sample memory and recall framework for incremental learning of radio modulation classification.For data with different signal-to-noise ratios,we use a partial memory strategy by selecting appropriate samples for memorizing.We compare the performance of our proposed method with three baselines through a large number of simulation experiments.Results show that our method achieves far higher classification accuracy than finetuning method and feature extraction method.Furthermore,it performs closely to joint training method which uses all old data in terms of classification accuracy which validates the effectiveness of our method against catastrophic forgetting.
基金supported by the National Natural Science Foundation of China (Grant Nos. 11875104 and 12175036)。
文摘A cascade glow discharge in atmospheric helium was excited by a microsecond voltage pulse and a pulse-modulated radio frequency(RF) voltage, in which the discharge ignition dynamics of the RF discharge burst was investigated experimentally. The spatio-temporal evolution of the discharge, the ignition time and optical emission intensities of plasma species of the RF discharge burst were investigated under different time intervals between the pulsed voltage and RF voltage in the experiment. The results show that by increasing the time interval between the pulsed discharge and RF discharge burst from 5 μs to 20 μs, the ignition time of the RF discharge burst is increased from 1.6 μs to 2.0 μs, and the discharge spatial profile of RF discharge in the ignition phase changes from a double-hump shape to a bell-shape. The light emission intensity at 706 nm and 777 nm at different time intervals indicates that the RF discharge burst ignition of the depends on the number of residual plasma species generated in the pulsed discharges.
