header
MartiRank 

Tag:
Edit edit   Starstar

Program Information

Name: MartiRank 
Domain: Machine learning
Functionality: Base on the historic data of past device failures as well as static and dynamic information about the current devices, predicting impending electrical device failures 
Input: T:The training data  D:The testing data 
Output: L:a ranking of the propensity of failure with respect to the testing data 

Reference

 Properties of Machine Learning Applications for Use in Metamorphic Testing
https://pdfs.semanticscholar.org/8b12/c5fd003efd52b798235d97a89a9c91dfd666.pdf?_ga=2.92592733.1914929612.1565157787-500444029.1561960669  

MR Information

MR1------

Description:
Property: $L_{1}=L_{2}$ 
Source input: $T_{1}$,D 
Source output: $L_{1}$ 
Follow-up input: $T_{2}$,D 
Follow-up output: $L_{2}$ 
Input relation: $T_{2}$: the values in any column of  $T_{1}$ are all increased by a constant 
Output relation: $L_{1}=L_{2}$ 
Pattern:

MR2------

Description:
Property: $L_{1}=L_{2}$ 
Source input: $T_{1}$,D 
Source output: $L_{1}$ 
Follow-up input: $T_{2}$,D 
Follow-up output: $L_{2}$ 
Input relation: $T_{2}$: the values in any column of  $T_{1}$ are all multiplied by a positive constant 
Output relation: $L_{1}=L_{2}$ 
Pattern:

MR3------

Description:
Property: $L_{1}=L_{2}$ 
Source input: $T_{1}$,D 
Source output: $L_{1}$ 
Follow-up input: $T_{2}$,D 
Follow-up output: $L_{2}$ 
Input relation: $T_2$: Permutation of $T_{1}$ 
Output relation: $L_{1}=L_{2}$ 
Pattern:

MR4------

Description:
Property: $L_{1}=L_{2}$, but in the opposite direction 
Source input: $T_{1}$,D 
Source output: $L_{1}$ 
Follow-up input: $T_{2}$,D 
Follow-up output: $L_{2}$ 
Input relation: $T_{2}$: the values in any column of  $T_{1}$ are all multiplied by a negative constant 
Output relation: $L_{1}=L_{2}$, but in the opposite direction 
Pattern:

MR5------

Description:
Property: the effect on the output is predictable 
Source input: $T_{1}$,D 
Source output: $L_{1}$ 
Follow-up input: $T_{2}$,D 
Follow-up output: $L_{2}$ 
Input relation: $T_{2}$:Include a new example in the $T_{1}$ 
Output relation: the effect on the output is predictable 
Pattern:

MR6------

Description:
Property: $L_{1}=L_{2}$(without the excluded example)  
Source input: $T_{1}$,D 
Source output: $L_{1}$ 
Follow-up input: $T_{2}$,D 
Follow-up output: $L_{2}$ 
Input relation:  $D_{2}$:exclude an example of $D_{1}$ 
Output relation: $L_{1}=L_{2}$(without the excluded example) 
Pattern:
Insert title here