针对上肢肌音信号(Mechanomyography,MMG)动作识别准确率不高的问题,提出一种基于粒子群算法(PSO)与长短期记忆网络相结合的混合模型(Particle Swarm Optimization-Long Short Term Memory,PSO-LSTM)的动作识别方法。采用5通道传感器对...针对上肢肌音信号(Mechanomyography,MMG)动作识别准确率不高的问题,提出一种基于粒子群算法(PSO)与长短期记忆网络相结合的混合模型(Particle Swarm Optimization-Long Short Term Memory,PSO-LSTM)的动作识别方法。采用5通道传感器对受试者进行上肢肌音信号采集,使用巴特沃斯滤波(Butterworth Filter)等方法对肌音信号进行预处理,并进行特征提取;构建基于PSO-LSTM的上肢肌音信号识别模型并进行模型训练和测试;最后从不同测度对比了长短期记忆(LSTM)模型、麻雀搜索算法(Sparrow Search Algorithm,SSA)优化的LSTM模型(Sparrow Search Algorithm-Long Short Term Memory, SSA-LSTM)以及PSO-LSTM模型的实验结果。结果表明,PSO-LSTM模型的准确度均高于LSTM、 SSA-LSTM模型,达到96.9%左右,在迭代损失、迭代速度等方面也优于LSTM、SSA-LSTM模型,从而证明了该模型用于上肢肌音信号识别的优越性。展开更多
When a 2-D progressive wave train normally or obliquely approaches a vertical wall and then is normally or obliquely reflected from it, the combination of the approaching and reflected waves may result in a standing w...When a 2-D progressive wave train normally or obliquely approaches a vertical wall and then is normally or obliquely reflected from it, the combination of the approaching and reflected waves may result in a standing wave or a short-crested wave in front of the wall. This paper presents the experimental observations of sand bed configurations under the action of these water waves in front of the wall. The geometry of sand ripples under these water waves in front of the vertical wall is presented as a function of flow parameters, such as the water particle semi-excursion and the mobility number.展开更多
文摘针对上肢肌音信号(Mechanomyography,MMG)动作识别准确率不高的问题,提出一种基于粒子群算法(PSO)与长短期记忆网络相结合的混合模型(Particle Swarm Optimization-Long Short Term Memory,PSO-LSTM)的动作识别方法。采用5通道传感器对受试者进行上肢肌音信号采集,使用巴特沃斯滤波(Butterworth Filter)等方法对肌音信号进行预处理,并进行特征提取;构建基于PSO-LSTM的上肢肌音信号识别模型并进行模型训练和测试;最后从不同测度对比了长短期记忆(LSTM)模型、麻雀搜索算法(Sparrow Search Algorithm,SSA)优化的LSTM模型(Sparrow Search Algorithm-Long Short Term Memory, SSA-LSTM)以及PSO-LSTM模型的实验结果。结果表明,PSO-LSTM模型的准确度均高于LSTM、 SSA-LSTM模型,达到96.9%左右,在迭代损失、迭代速度等方面也优于LSTM、SSA-LSTM模型,从而证明了该模型用于上肢肌音信号识别的优越性。
文摘When a 2-D progressive wave train normally or obliquely approaches a vertical wall and then is normally or obliquely reflected from it, the combination of the approaching and reflected waves may result in a standing wave or a short-crested wave in front of the wall. This paper presents the experimental observations of sand bed configurations under the action of these water waves in front of the wall. The geometry of sand ripples under these water waves in front of the vertical wall is presented as a function of flow parameters, such as the water particle semi-excursion and the mobility number.
