مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Persian Verion

Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

video

Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

sound

Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Persian Version

Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

View:

1,368
Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Download:

0
Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Cites:

Information Journal Paper

Title

COMPARISON OF ACCURACY OF MACHINE LEARNING ALGORITHMS ON MISSING VALUES ESTIMATION OF DNA MICROARRAY DATASETS

Pages

  612-622

Abstract

 Presence of missing values in MICROARRAY data decreases accuracy of drawing regulatory gene networks and may cause mistake in clustering and specialized classification of genes and further analysis. Therefore, missing values estimation is one of the most important steps in preprocessing of MICROARRAY data. Function of estimation algorithms is varied in different datasets and different missing percentage. Select a proper algorithm, in order to achieve the most accurate results in calculation of missing values, is a critical point. In this study, three MICROARRAY datasets were used. Dimensions of expression matrix was determined, and data normalization was carried out, then, different missing percentages were applied on under studied datasets.11 MACHINE LEARNING ALGORITHMS were used to estimate the missing values, and their accuracy were compaied based on the output. Based on the archeived results, accuracy of each algorithms depends on used datasets, missing percentage, and missing distribution. Also, the number of experimental samples in datasets can affect the accuracy of missing values estimation algorithms. The results revealed a descending trend in accuracy over increasing the percentage of missing data. However, Least Square Adaptive and Local Least Square algorithms showed more accuracy through increasing of missing percentage rather than others.

Cites

  • No record.
  • References

  • No record.
  • Cite

    APA: Copy

    MOSHIRY, M., GHADERI ZEFREHEI, M., & GHANE GOLMOHAMMADI, F.. (2015). COMPARISON OF ACCURACY OF MACHINE LEARNING ALGORITHMS ON MISSING VALUES ESTIMATION OF DNA MICROARRAY DATASETS. JOURNAL OF MOLECULAR AND CELLULAR RESEARCH (IRANIAN JOURNAL OF BIOLOGY), 28(4), 612-622. SID. https://sid.ir/paper/248572/en

    Vancouver: Copy

    MOSHIRY M., GHADERI ZEFREHEI M., GHANE GOLMOHAMMADI F.. COMPARISON OF ACCURACY OF MACHINE LEARNING ALGORITHMS ON MISSING VALUES ESTIMATION OF DNA MICROARRAY DATASETS. JOURNAL OF MOLECULAR AND CELLULAR RESEARCH (IRANIAN JOURNAL OF BIOLOGY)[Internet]. 2015;28(4):612-622. Available from: https://sid.ir/paper/248572/en

    IEEE: Copy

    M. MOSHIRY, M. GHADERI ZEFREHEI, and F. GHANE GOLMOHAMMADI, “COMPARISON OF ACCURACY OF MACHINE LEARNING ALGORITHMS ON MISSING VALUES ESTIMATION OF DNA MICROARRAY DATASETS,” JOURNAL OF MOLECULAR AND CELLULAR RESEARCH (IRANIAN JOURNAL OF BIOLOGY), vol. 28, no. 4, pp. 612–622, 2015, [Online]. Available: https://sid.ir/paper/248572/en

    Related Journal Papers

    Related Seminar Papers

  • No record.
  • Related Plans

  • No record.
  • Recommended Workshops






    Move to top