MVIAeval: a web tool for comprehensively evaluating the performance of a new missing value imputation algorithm

BMC Bioinformatics

Table 3 MVIAeval can provide the performance comparison results in many scenarios

Performance Index	Benchmark datasets	Ranking of USER using ORS	Ranking of USER using ONS
1/NRMSE	Five Time Series [37–41]	5	6
1/NRMSE	Five Non-time Series [27–31]	6	6
CPP	Five Time Series [37–41]	7	9
CPP	Five Non-time Series [27–31]	11	8
BLCI	Five Time Series [37–41]	3	4
BLCI	Five Non-time Series [27–31]	7	7
1/NRMSE + CPP + BLCI	Five Time Series [37–41]	6	7
1/NRMSE + CPP + BLCI	Five Non-time Series [27–31]	6	6

The performance comparison results of the user’s algorithm (denoted as USER) and various existing algorithms using different types of datasets (time series or non-time series), different performance indices (1/NRMSE, CPP or BLCI), and different overall performance scores (overall ranking score (ORS) or overall normalized score (ONS)) are shown. More details could be seen at http://cosbi.ee.ncku.edu.tw/MVIAeval/A_Case_Study

ISSN: 1471-2105