Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (10): 2959-2963.DOI: 10.11772/j.issn.1001-9081.2020081338

Special Issue: 多媒体计算与计算机仿真

• Multimedia computing and computer simulation • Previous Articles     Next Articles

Reconstruction method for uncertain spatial information based on improved variational auto-encoder

TU Hongyan1, ZHANG Ting1, XIA Pengfei1, DU Yi2   

  1. 1. College of Computer Science and Technology, Shanghai University of Electric Power, Shanghai 200090, China;
    2. College of Engineering, Shanghai Polytechnic University, Shanghai 201209, China
  • Received:2020-09-02 Revised:2020-12-10 Online:2021-10-10 Published:2021-10-27
  • Supported by:
    This work is partially supported by the Surface Program of National Natural Science Foundation of China (41672114), the Youth Program of National Natural Science Foundation of China (41702148).

基于改进型变分自编码器的不确定性空间信息重建方法

屠红艳1, 张挺1, 夏鹏飞1, 杜奕2   

  1. 1. 上海电力大学 计算机科学与技术学院, 上海 200090;
    2. 上海第二工业大学 工学部, 上海 201209
  • 通讯作者: 张挺
  • 作者简介:屠红艳(1996-),女,江苏扬州人,硕士研究生,主要研究方向:深度学习、图像重建;张挺(1979-),男,安徽安庆人,教授,博士,主要研究方向:图像处理、机器学习;夏鹏飞(1997-),男,江苏宿迁人,硕士研究生,主要研究方向:深度学习、信息重建;杜奕(1977-),女,江苏吴江人,副教授,博士,主要研究方向:数据挖掘。
  • 基金资助:
    国家自然科学基金面上项目(41672114);国家自然科学基金青年科学基金资助项目(41702148)。

Abstract: Uncertain spatial information is widely used in many scientific fields. However, the current methods for uncertain spatial information reconstruction need to scan the Training Image (TI) for many times, and then obtain the simulation results through complex probability calculation, which leads to the low efficiency and complex simulation process. To address this issue, a method of Fisher information and Variational Auto-Encoder (VAE) jointly applying to the reconstruction of uncertain spatial information was proposed. Firstly, the structural features of the spatial information were learned through the encoder neural network, and the mean and variance of the spatial information were obtained by training. Then, the random sampling was carried out to reconstruct the intermediate results according to the mean and variance of the sampling results and the spatial information, and the encoder neural network was optimized by combining the optimization function of the network with the Fisher information. Finally, the intermediate results were input into the decoder neural network to decode and reconstruct the spatial information, and the optimization function of the decoder was combined with the Fisher information to optimize the reconstruction results. By comparing the reconstruction results of different methods and the training data on multiple-point connectivity curve, variogram, pore distribution and porosity, it is shown that the reconstruction quality of the proposed method is better than those of other methods. In specific, the average porosity of the reconstruction results of the proposed method is 0.171 5, which is closer to the 0.170 5 porosity of the training data compared to those of other methods. Compared with the traditional method, this method has the average CPU utilization reduced from 90% to 25%, and the average memory consumption reduced by 50%, which indicates that the reconstruction efficiency of this method is higher. Through the comparison of reconstruction quality and reconstruction efficiency, the effectiveness of this method is illustrated.

Key words: spatial information reconstruction, neural network, random sampling, Fisher information, Variational Auto-Encoder (VAE)

摘要: 不确定性空间信息在众多科学领域得到了广泛应用。然而目前用于不确定性空间信息重建的方法需要多次对训练图像(TI)进行扫描,再通过复杂的概率计算获得模拟结果,导致这些方法的效率较低,且模拟过程复杂。针对这一问题,提出了将费雪信息量和变分自编码器(VAE)结合应用于不确定性空间信息的重建。首先,通过编码器神经网络对空间信息的结构特征进行学习,并训练得到空间信息的均值和方差;然后,进行随机采样,根据采样结果和空间信息的均值、方差重建中间结果,并将编码器神经网络的优化函数与费雪信息量相结合来优化网络;最后,将中间结果输入解码器神经网络中,以对空间信息进行解码重建,并将解码器的优化函数与费雪信息量结合对重建结果进行优化。通过比较各方法重建结果与训练数据的多点连通曲线、变差函数、孔隙分布和孔隙度表明,所提方法的重建质量比其他方法的更好。具体来说,该方法重建结果的平均孔隙度为0.171 5,与其他方法重建结果的平均孔隙度更接近训练数据的孔隙度0.170 5。且相较于传统方法,其平均CPU利用率从90%下降到25%,平均内存占用下降了50%,说明该方法的重建效率更高。而通过重建质量和重建效率两个方面的对比,说明了该方法的有效性。

关键词: 空间信息重建, 神经网络, 随机采样, 费雪信息, 变分自编码器

CLC Number: