Medical Data Acquisition Platform Based on Synthetic Intelligence

  • Zhao Gu
  • Yongjun LiuEmail author
  • Mingxin Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11242)


Nowadays, most medical device manufacturers are still using on-device data integrating and transmitting. However the real hospital situation is complex. Medical devices have different interfaces. Some of them are even outdated. This situation makes medical data can’t be automatically exported. Data can only be copied by hospital staff manually. In order to solve this data extraction problem caused by interface incompatibility and device version incompatibility, we implemented this medical data acquisition platform base on synthetic information. It uses OCR (Optical Character Recognition) technology to collect intuitive data directly from the screen interface. This platform also includes an embedded voice recognition module implemented on Raspberry Pi. The voice recognition system is used to solve the time consuming and inconvenience problem caused by manually data recording through transforming the voice signal into texts and instructions. Finally, we upload medical data to the server through the socket for effective data integration. The system hardware structure is simple; cost is under control. It has good stability and can be used in a wide range of applications.


Embedded systems Intelligent medical Character recognition Speech blind separation Speaker recognition 



This work was supported by the Next Generation Internet Technology Innovation Project of CERNTE under grant No. NGII20170709, the Natural Science Foundation of Jiangsu Province under grant No. 15KJB520001.


  1. 1.
    Abadpour, A., Kasaei, S.: A new parametric linear adaptive color space and its implementation. In: Proceedings of Annual Computer Society of Iran Computer Conference (2004)Google Scholar
  2. 2.
    Antani, S., Crandall, D., Kasturi, R.: Robust extraction of text in video. In: Proceedings of IEEE International Conference on Pattern Recognition (2000)Google Scholar
  3. 3.
    Ai, C., Hou, H., Li, Y., Beyah, R.: Authentic delay bounded event detection in heterogeneous wireless sensor networks. Ad Hoc Netw. 7(3), 599–613 (2009)CrossRefGoogle Scholar
  4. 4.
    Gao, W., Zhang, X., Yang, L., Liu, H.: An improved Sobel edge detection. In: 2010 3rd International Conference on Computer Science and Information Technology, Chengdu, pp. 67–71 (2010)Google Scholar
  5. 5.
    Reynolds, D.A.: Speaker identification and verification using Gaussian mixture speaker models. Speech Commun. 17(1), 91–108 (1995)MathSciNetCrossRefGoogle Scholar
  6. 6.
    Tan, R., Liu, J., Li, Z.: Speaker recognition technology and its applications. Inf. Technol. 23–25 (2008)Google Scholar
  7. 7.
    Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. 13(4), 411–430 (2000)CrossRefGoogle Scholar
  8. 8.
    Liang, S., Zhang, Z., Cui, L., Zhong, Q.: Dimensionality reduction method based on PCA and KICA, Syst. Eng. Electron. 2144–2148 (2012)Google Scholar
  9. 9.
    Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech Audio Process. 3(1), 72–83 (1995)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.College of Software EngineeringNortheastern UniversityShenyangChina
  2. 2.College of Computer Science and EngineeringNortheastern UniversityShenyangChina
  3. 3.Department of Computer Science and EngineeringChangshu Institute of TechnologyChangshuChina

Personalised recommendations