Selected article for: "cross validation and specificity sensitivity"
Author: Li, Chun; Zhao, Jialing; Wang, Changzhong; Yao, Yuhua
Title: Protein Sequence Comparison and DNA-binding Protein Identification with Generalized PseAAC and Graphical Representation
  • Document date: 2018_2_23
    • ID: u1imic5l_51
    Snippet: This experiment is made on DNASet itself. To obtain a reliable result with few error, the SVM model on DNASet is established by 5-fold cross-validation (5CV) with 3 runs. Here the 31-D feature vector of a protein sequence serves as the input for SVM. In a 5CV, the positive and negative samples are randomly distributed into five subsets or the socalled folds, and the test is repeated five times. In each of the five iterations, one subset is used a.....
    Document: This experiment is made on DNASet itself. To obtain a reliable result with few error, the SVM model on DNASet is established by 5-fold cross-validation (5CV) with 3 runs. Here the 31-D feature vector of a protein sequence serves as the input for SVM. In a 5CV, the positive and negative samples are randomly distributed into five subsets or the socalled folds, and the test is repeated five times. In each of the five iterations, one subset is used as the testing set, while the remaining four subsets are combined together and used to build a classifier (training). The predictions made for the test data instances in all the five iterations yield the final result. The sensitivity, specificity, ACC, MCC and F1M are calculated for each run, and the corresponding results and their average values are listed in Table 5 . As can be seen Fig. (4) . The relationship tree of 72 coronavirus spike proteins. T a lw a n T C 2 T a lw a n T C 1 T a lw a n T C 3 TW 1 TW 2 TW H TW J Urbani from this table, we achieve the accuracy (ACC) of 89.65%, with MCC of 0.776 and F1M of 84.91%. This result shows that our SVM model performs well on the benchmark dataset DNASet.

    Search related documents:
    Co phrase search for related documents
    • ACC accuracy and benchmark dataset: 1
    • ACC accuracy and cross validation: 1, 2, 3, 4, 5
    • ACC accuracy and SVM input: 1
    • ACC accuracy and SVM model: 1
    • average value and cross validation: 1, 2
    • average value and negative positive sample: 1
    • average value and protein sequence: 1
    • average value and spike protein: 1
    • average value and test data: 1, 2, 3
    • average value and testing set: 1
    • benchmark dataset and cross validation: 1, 2, 3, 4, 5, 6, 7, 8, 9
    • benchmark dataset and DNASet benchmark dataset: 1
    • benchmark dataset and experiment DNASet: 1
    • benchmark dataset and feature vector: 1
    • benchmark dataset and protein sequence: 1
    • benchmark dataset and subset testing set: 1
    • benchmark dataset and SVM model: 1, 2, 3
    • benchmark dataset and test data: 1, 2
    • benchmark dataset and testing set: 1