ID 原文 译文
15245 针对数据特征选择欠佳导致负荷识别准确率不高的问题，提出了一种基于ReliefF-DDC特征选择算法，用于降低特征维数减少复杂度，改善负荷识别效果。 In this paper, a ReliefF-DDC feature selection algorithm was proposed to reduce feature dimension, reduce complexity and improve load recognition.
15246 首先，利用ReliefF算法分析各特征与类别的关系计算特征权重，筛选无关特征； Firstly, ReliefF algorithm was used to analyze the relationship between each feature and category, calculate feature weight, and screen irrelevant features.
15247 其次，利用DDC算法计算特征之间与类别的互信息分析相关性，根据特征子集评价度量删除冗余特征； Secondly, DDC algorithm is used to calculate the mutual information analysis correlation between features and categories, and redundant features are removed according to feature subset evaluation mea-surement.
15248 最后，采用孪生支持向量机(TWSVM)作分类器进行负荷识别。 Finally, twin support vector machine(TWSVM) is used as classifier for load recognition.
15249 实验表明，所提出的算法在提升分类效果的同时减少了运行时间。 Experiments show that the algorithm proposed in this paper improves the classification effect and reduces the running time.
15250 近年来大数据、自然语言处理等技术得到了飞速发展。 In recent years, big data, natural language processing and other technologies have been developed rapidly.
15251 情感分析作为自然语言处理细分领域的前沿技术之一，得到了极大的重视。 As one of the cutting-edge technologies in the field of natural language processing, emotion analysis has received great attention.
15252 然而，低参数量、高精度依然是制约情感分析的关键因素之一。 However, High precision and high performance are still the key factors restricting emotional analysis.
15253 为实现模型参数少、模型分类精度高的情感分析需求，通过改进特征级注意力机制的输入向量，以及前馈神经网络与注意力编码的前后位置关系，得到可复位特征级注意力机制，并基于该机制提出了基于可复位特征级注意力方面级情感分类模型(RFWA)和基于可复位特征级自注意力方面级情感分类模型(RFWSA)，实现了高精度的方面级情感分析效果。 In order to achieve high-precision emotion analysis, based on the feature-level neural network, this paper improves the reset feature level attention mechanism, and proposes an aspect level emotion classification model based on the reset feature level attention(RFWA) and an aspect level emotion classification model based on the reset feature level self-attention(RFWSA). Finally, combined with Bi-LSTM-CRF,high quality aspect level emotion analysis is realized by aspect level phrase extraction in the network.
15254 在公开数据集上的实验结果表明，相比现有的主流情感分析方法，所提出的模型有明显的优势，尤其是在取得相当分类效果的情况下，模型的参数量仅为最新AOA网络的1/4。 The experimental results show that compared with the existing mainstream emotion analysis model, the model proposed in this paper has obvious advantages. Especially when the classification ef-fect is quite good, the parameters of the model are only 1/4 of the AOA Network.