This paper considers the problem faced by a reliability analyst who has detected faults in a system, which were caused by a combination of random and systematic factors. Such faults usually occur at random points in space or time. The analyst's challenge is to accurately gauge the scale of the problem, accepting the fact that an appropriate reliability estimate must also take into consideration the subjective nature of her assessment. In this paper, we introduce a reliability measure, which we called a gauge measure, which incorporates the randomness due to the locations of the faults as well as the imprecision caused by the subjective nature of the assessment. The randomness of the locations will be modeled by a point process and the subjective assessment of each fault by a random fuzzy mark. The mean and variance of a gauge measure will be obtained. Finally, through a generic example and several real world applications, we show how this measure can be applied to measure the reliability of many occurring working systems, especially software systems.
[1]
R. A. Vitale.
An alternate formulation of mean value for random geometric figures *
,
1988
.
[2]
Ralf Körner,et al.
On the variance of fuzzy random variables
,
1997,
Fuzzy Sets Syst..
[3]
D. Dubois,et al.
Operations on fuzzy numbers
,
1978
.
[4]
Panlop Zeephongsekul.
On the variability of fuzzy debugging
,
2001,
Fuzzy Sets Syst..
[5]
Panlop Zeephongsekul,et al.
On fuzzy debugging of software programs
,
1996,
Fuzzy Sets Syst..
[6]
M. Puri,et al.
Limit theorems for fuzzy random variables
,
1986,
Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.
[7]
Simon P. Wilson,et al.
Software Reliability Modeling
,
1994
.
[8]
N. N. Lyashenko,et al.
Limit theorems for sums of independent, compact, random subsets of euclidean space
,
1982
.
[9]
Huibert Kwakernaak,et al.
Fuzzy random variables - I. definitions and theorems
,
1978,
Inf. Sci..