Technique for Data-Driven Mining in Physiological Sensor Data by Using Eclat Algorithm

  • Shraddha KalbhorEmail author
  • S. V. Kedar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 755)


In this paper, we discuss the technique developed for mining the rules automatically in time series data which represent the physiological parameters in the clinical situation. Basically, the technique which mined the prototypical pattern for physiological time series data is known as data-driven technique. The patterns which are generated by the data-driven technique are explained in the format of text that seizes the tendency in each physical parameter and its connection with the data. In the following work, the sensor information in the multiparameter intelligent monitoring in intensive care (MIMIC) online database was utilized for appraisal, in which the mined transitory rules that were identified with different clinical conditions are expressed as a printed representation. Moreover, the proof that removed the tenet set for a specific medical condition was particular from different conditions. Moreover, for generating the patterns of rule, the system uses the FP-growth algorithm. But use of FP-growth algorithm may slow down the system. To solve this problem, the proposed system uses Eclat algorithm for generating the patterns of rule. Additionally, in this system, authorization of user is done; data can be shared with the authorized users only. Rule generation and pattern generation are performed at doctor side, and it can be accessed by authorized users and another doctor. If the system can refer the user to another doctor, then the only user can visit other doctors. At the doctor side, rules are encrypted by ECC algorithm. Doctor can prevent the disease, diagnose the disease, and also give suggestions to the patient. It gives better performance than previous algorithms. Evaluation of results shows the time and memory comparison of the proposed system with the existing system.


  1. 1.
    Banaee, H., Loutfi, A.: Data-Driven rule mining and representation of temporal patterns in physiological sensor data. IEEE J. Biomed. Health Inf. 19(5) (2015)Google Scholar
  2. 2.
    Hu, Y., Wan, X.: PPSGen: learning-based presentation slides generation for academic papers. In: IEEE Transactions on Knowledge and Data Engineering, vol. 27, no. 4, Apr 2015Google Scholar
  3. 3.
    Conrad, S., Schluter, T.: About the analysis of time series with temporal association rule mining. IEEE Symp. Comput. Intell. Data Min. pp. 325–332 (2011)Google Scholar
  4. 4.
    Dudek, D.: In: Measures for comparing association rule sets. Artificial Intelligence and Soft Computing, pp. 315–322. Springer, New York, NY, USA (2010)Google Scholar
  5. 5.
    Conrad, S., Schluter, T.: About the analysis of time series with temporal association rule mining. IEEE Symp. Comput. Intell. Data Min. 325–332 (2011)Google Scholar
  6. 6.
    Marlin, B.M., Kale, D.C., Khemani, R.G., Wetzel, R.C.: Unsupervised pattern discovery in electronic health care data using probabilistic clustering models. In: Proceedings of 2nd ACM SIGHIT, pp. 389–398 (2012)Google Scholar
  7. 7.
    Loutfi, A., Banaee, H., Ahmed, M.U.: A framework for automatic text generation of trends in physiological time series data. IEEE Int. Conf. Syst. Man Cybern. 3876–3881 (2013)Google Scholar
  8. 8.
    Zolhavarieh, S., Aghabozorgi, S., Wah, Y.: The a review of subsequence time series clustering. Sci. World J. 2014, Article ID 312–521 (2014)Google Scholar
  9. 9.
    Umarani, V., Punithavalli, M.: Sampling based association rules mining-a recent overview. (IJCSE) Int. J. Comput. Sci. Eng. 02(02), 314–318 (2010)Google Scholar
  10. 10.
    Wahyuningsih, Y., Muflikhah, L.: Fuzzy rule generation for diagnosis of coronary heart disease risk using subtractive clustering mMthod. Softw. Eng. Appl. 6, 372–378 (2013). 25Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of Computer EngineeringRajarshi Shahu College of Engineering, Savitribai Phule Pune UniversityPuneIndia

Personalised recommendations