location:Home > 2019 VOL.2 Aug No.4 > Economic time series big data multi-pattern retrieval method based on machine learning theory

2019 VOL.2 Aug No.4

  • Title: Economic time series big data multi-pattern retrieval method based on machine learning theory
  • Name: Elijah Fabian
  • Company: University of St Andrews
  • Abstract:

    In view of the fact that the traditional retrieval method is affected by the index establishment time, the retrieval effect is poor. An economic time series big data multi-pattern retrieval method based on machine learning theory is proposed. According to the good scalability of big data, the retrieval model is constructed, and the big data is matched by the binary data conversion method. The binary sequence is defined by the relationship between different data, the data feature similarity is calculated, the candidate sequence is reduced, the data without similar features is filtered, and the sub-sequence sets matching the pattern are given according to the similarity size. After adding the threshold, on the basis of slightly reducing the filtering range, the similarity matching calculation amount in the big data retrieval process is greatly reduced, and the fixed interval sampling matching method is combined to determine the big data feature. This realizes economic time series big data multi-mode retrieval based on machine learning theory. The experimental comparison results show that the highest retrieval efficiency of this method can reach 95%, which provides effective help for large-scale retrieval of massive data.

  • Keyword: Machine Learning; Economic Time Series; Big Data; Retrieval;
  • DOI: 10.12250/jpciams2019040130
  • Citation form: Elijah Fabian.Economic time series big data multi-pattern retrieval method based on machine learning theory[J]. Computer Informatization and Mechanical System, 2019, vol. 2, pp. 11-15.
Reference:

[1] Su Tengfei, Liu Quanming, Su Xiuchuan. Crop Remote Sensing Classification Based on Time Series of Multiple Vegetation Index and Machine Learning [J]. Jiangsu Agricultural Science, 2017, 45(16):219-224.

[2] Dong Fang, Liu Yufei, Zhou Yuan. Prediction of Emerging Technologies Based on LDA-SVM Abstracts [J]. Intelligence magazine, 2017, 36(7):40-45.

[3] Zhu Yi, Liu Yuman, Chen Shuguang, et al. Prediction of network purchase behavior based on machine learning fusion algorithm [J]. Statistics and Information Forum, 2017, 25 (12):94-100.

[4] Sun Cunyi, Gong Liutang. Research on Interest Rate Pricing under Big Data Thinking——An Empirical Analysis from the Perspective of Machine Learning [J]. Financial theory and practice, 2017, 18 (7):1-5.

[5] Li Li, Lin Yilun, Cao Dongpu, et al. Parallel Learning: A New Theoretical Framework for Machine Learning [J]. Journal of Automation, 2017, 43(1):1-8.

[6] Jiao Jiafeng, Li Yun, Jiao Jiafeng, et al. A Survey of Typical Machine Learning Platforms under Big Data [J]. Computer Application, 2017, 37(11):3039-3047.

[7] Wu Yongliang, Jia Zhijie, Chen Jianping, et al. Construction and prediction of prospecting model based on big data intelligence [J]. China Mining, 2017, 26(9):79-84.

[8] Xia Jingming, Tang Lingling, Tan Ling, et al. Physiological parameter monitoring system based on K-means and MTLS-SVM algorithm [J]. Telecommunications science, 2017,16 (10):43-49.

[9] Xing Xue, Yu Dexin, Tian Xiujuan, et al. Time series analysis of multi-state traffic flow combined with viewable view [J]. Journal of Physics, 2017, 66(23):51-59.

[10] Mei Yi. Simulation of resource target information extraction in big data environment [J]. Computer Simulation, 2018, 35(03):337-340.


 


Tsuruta Institute of Medical Information Technology
Address:[502,5-47-6], Tsuyama, Tsukuba, Saitama, Japan TEL:008148-28809 fax:008148-28808 Japan,Email:jpciams@hotmail.com,2019-09-16