摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑-关于智能系统的最新研究结果已经发表。根据NewsRx记者在厄瓜多尔基多的新闻报道，研究表明，"使用ELECT ROMYography(EMG)信号的手势识别(HGR)是一个具有挑战性的问题，因为不同个体之间的信号具有差异性和无ISE。"这项研究的财政支持者包括国家理工学院。新闻记者从国立理工学院的研究中获得了一句话：“这项研究通过研究引入后处理算法的效果来应对这一挑战，该算法过滤预测序列并去除虚假标签，研究了基于Spectrog RAMS和卷积神经网络(CNN)的HGR模型的性能,并比较了CNN和CNN-lstm的记忆细胞对模型的影响。实验结果表明，后处理算法对CNN模型和CN-LSTM模型的识别率分别提高了41.86%和24.77%，记忆细胞的加入使识别率提高了3.29%，但代价是可学习量的53倍，后处理的CN-LSTM模型的识别率达到90.55%(SD=9.45%)。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on intelligent s ystems have been published. According to news reporting from Quito, Ecuador, by NewsRx journalists, research stated, “Hand Gesture Recognition (HGR) using elect romyography (EMG) signals is a challenging problem due to the variability and no ise in the signals across individuals.” Financial supporters for this research include Escuela Politecnica Nacional. The news journalists obtained a quote from the research from Escuela Politecnica Nacional: “This study addresses this challenge by examining the effect of incor porating a post-processing algorithm, which filters the sequence of predictions and removes spurious labels, on the performance of a HGR model based on spectrog rams and Convolutional Neural Networks (CNN). The study also compares CNN vs CNN -LSTM to assess the influence of the memory cells on the model. The EMG-EPN-612 dataset, which contains measurements of EMG signals for 5 hand gestures from 612 subjects, was used for training and testing. The results showed that the post-p rocessing algorithm increased the recognition accuracy by 41.86% f or the CNN model and 24.77% for the CNN-LSTM model. The inclusion of the memory cells increased accuracy by 3.29%, but at the cost of 53 times more learnables. The CNN-LSTM model with post-processing achieved a me an recognition accuracy of 90.55% (SD=9.45%).”
NETL
NSTL