Archives

  • 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • 2021-03
  • br The fourth parameter taken

    2020-08-18


    The fourth parameter taken for classifying lung cancer diagno-sis is F1-score. F1-score is a single measure of performance test for the positive class. It is defined both precision and recall of the test. Precision is the number of correct positive results divided by the number of all positive results returned by the classifier and recall is the number of correct positive results divided by the number of all relevant samples. The F1-score is calculated as follows:
    Precision × Recall
    Precision + Recall
    From Eq. (17), the classification time ‘F 1 − score’ is measured using average mean of precision and recall value. Higher the F1-score, early the lung cancer diagnosis is said to be. The sam-ple calculation for F1-score using the five methods is given as follows:
    Sample calculations: 
    Fig. 6 illustrates the measure of F1-score to classify the patient data with higher accuracy. In order to conduct the experiments, 1000 to 10,000 patient data is considered. The performance anal-ysis of F1-score using proposed method is compared with existing NSCLC, BSVM, NPPC, and MV-CNN . When considering 1000 num-ber of patient data for the performance analysis, the proposed method provides the F1-score of 92% whereas the existing NSCLC, BSVM, NPPC and MV-CNN produced 88%, 85%, 81%, and 76%, respectively. From the discussion, it 80306-38-3 is clear that the F1-score using proposed method is higher as compared to other existing methods. While increasing the number of patient data, the value of F1-score is increased in all methods. Comparatively, F1-score using proposed method is high than the [1–3] and [17] methods.
    Fig. 7. Performance measure of space complexity.
    This is due the application of weighted optimized neural network with maximum likelihood boosting which classifies the patient data with higher accuracy. Therefore, F1-score is improved using proposed WONN-MLB approach by 7%, 11%, 19%, and 26% as com-pared to NSCLC by Wu et al. [1], BSVM by Zięba et al. [2], NPPC by Ghorai et al. [3], and MV-CNN by Liu et al. [17], respectively.
    4.5. Scenario 5: Space complexity
    Space complexity is defined as an amount of storage space required to store the patient data in big healthcare data analytics. It is measured in terms of megabyte (MB). The mathematical formula for space complexity is measured as follows,
    SC = n ∗ space (storing the one patient data) (18) In (18), ‘SC’ denotes a space complexity and ‘n’ denotes the number of the patient data. The sample calculation for space complexity using the five methods is given as follows:
    Sample calculations:
    • Proposed WONN-MLB: With ‘1000’ patient data considered for experimentation and space for storing one patient data is 0.01 MB, the space complexity is calculated as follows:
    • NSCLC: With ‘1000’ patient data considered for experimenta-tion and space for storing one patient data is 0.012 MB, the space complexity is calculated as follows:
    • BSVM: With ‘1000’ patient data considered for experimenta-tion and space for storing one patient data is 0.015 MB, the space complexity is calculated as follows:
    • NPPC: With ‘1000’ patient data considered for experimenta-tion and space for storing one patient data is 0.018 MB, the space complexity is calculated as follows:
    • MV-CNN: With ‘1000’ patient data considered for experi-mentation and space for storing one patient data is 0.021 MB, the space complexity is calculated as follows:
    Fig. 7 shows the measure of space complexity to store the patient data with minimum space. To conduct the experiments, 1000 to 10,000 patient data is considered. From Fig. 7, the perfor-mance analysis of space complexity using WONN-MLB approach is compared with existing NSCLC, BSVM, NPPC, and MV-CNN. While considering 1000 number of patient data for analyzing the performance, the proposed WONN-MLB approach provides the 10 MB of space complexity whereas the existing NSCLC, BSVM, NPPC and MV-CNN offers 12 MB, 15 MB, 18 MB, and 21 MB, respectively. From the above discussion, space complexity using proposed WONN-MLB approach is lower as compared to other existing [1–3] and [17] methods. This is because of the appli-cation of boosted weighted optimized neural network ensemble classification algorithm in proposed WONN-MLB approach. This algorithm classifies the patient data with higher accuracy and eccrine glands is further stored for diagnosing the cancer diseases. Therefore, space complexity is reduced using proposed WONN-MLB approach by 13%, 24%, 31%, and 36% as compared to NSCLC by Wu et al. [1], BSVM by Zięba et al. [2], NPPC by Ghorai et al. [3], and MV-CNN by Liu et al. [17], respectively.
    4.6. Scenario 6: Feature selection rate