1.College of Computer Science and Electronic Engineering, Hunan University, Changsha 410082, China 2.College of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China 3.College of Instrument Science and Opto Electronic Engineering, Beihang University, Beijing 100191, China 4.Shanghai Institution of Satellite Engineering, Shanghai 200240, China
Abstract:Pulsar candidate selection is an important step in the search task of pulsars. The traditional candidate selection is heavily dependent on human inspection. However, the human inspection is a subjective, time consuming, and error-prone process. A modern radio telescopes pulsar survey project can produce totally millions of candidates, so the manual selection becomes extremely difficult and inefficient due to a large number of candidates. Therefore, this study focuses on machine learning developed in recent years. In order to improve the efficiency of pulsar candidate selection, we propose a candidate selection method based on self-normalizing neural networks. This method uses three techniques: self-normalizing neural networks, genetic algorithm and synthetic minority over-sampling technique. The self-normalizing neural networks can improve the identification accuracy by applying deep neural networks to pulsar candidate selection. At the same time, it solves the problem of gradient disappearance and explosion in the training process of deep neural networks by using its self-normalizing property, which greatly accelerates the training process. In addition, in order to eliminate the redundancy of the sample data, we use genetic algorithm to choose sample features of pulsar candidates. The genetic algorithm for feature selection can be summarized into three steps: initializing population, assessing population fitness, and generating new populations. Decoding the individual with the largest fitness value in the last generation population, we can obtain the best subset of features. Due to radio frequency interference or noise, there are a large number of non-pulsar signals in candidates, and only a few real pulsar signals exist there. Aiming at solving the severe class imbalance problem, we use the synthetic minority over-sampling technique to increase the pulsar candidates (minority class) and reduce the imbalance degree of data. By using k-nearest neighbor and linear interpolation to insert a new sample between two minority classes of samples that are close to each other according to certain rules, we can prevent the classifier from becoming biased towards the abundant non-pulsar class (majority class). Experimental results on three pulsar candidate datasets show that the self-normalizing neural network has higher accuracy and faster convergence speed than the traditional artificial neural network in the deep structure, By using the genetic algorithm and synthetic minority over-sampling technique, the selection performance of pulsar candidates can be effectively improved. Keywords:pulsar candidate selection/ self-normalizing neural networks/ feature selection/ class imbalance
全文HTML
--> --> --> -->
2.1.SELU激活函数
SELU激活函数表达式为
$selu\left( x \right) = \left\{ {\begin{array}{*{20}{l}} {\lambda x,\qquad~~~~~~~~~~\, x > 0,} \\ {\lambda(\alpha {{\rm{e}}^x} - \alpha),\quad x \leqslant 0,} \end{array}} \right. $
表5不同学习速率的分类效果 Table5.Classification results with the different learning rates.
34.3.2.不同方法的比较 -->
4.3.2.不同方法的比较
为证明SNN的有效性, 本文对SNN与传统ANN在HTRU 2数据集上进行对比实验, 图3给出了8层神经网络训练过程中的损失函数曲线对比图, 迭代次数为100次. 损失函数是用来衡量模型预测值与真实值的不一致程度, 损失函数越小, 模型鲁棒性就越好. 由图3可知SNN模型比传统ANN具有更低的误差, 且其收敛速度明显大于ANN, 证明了SNN在深层网络中的有效性. 图 3 SNN与ANN损失函数的对比 Figure3. Comparison of the loss function between SNN and ANN.