International Conference and Workshop on Emerging Trends in Technology (ICWET 2010) – TCET, Mumbai, India
Software Reliability Assessment using Artificial Neural Network I Mandal CSE Dept SRSIT, Bangalore-562157, India Mobile: +919986635735
[email protected] ABSTRACT
2. RELIABILITY THEORY
It will show how to apply Backpropagation algorithm to predict software reliability by designing different elements of neural networks. Furthermore, we will use the neural network approach to build a dynamic weighted combinational model. The applicability of proposed model is demonstrated through software failure data sets. From experimental results, we can see that the proposed model significantly outperforms the traditional software reliability models.
CATEGORY DESCRIPTORS
AND
Reliability theory is the foundation of reliability engineering. For engineering purposes, reliability is defined as: The probability that a device will perform its intended function during a specified period of time under stated conditions. Mathematically, this may be expressed as,
SUBJECT where is the failure probability density function and t is the length of the period of time (which is assumed to start from time zero).
I.2 Artificial Intelligence
General Terms Performance, Experimentation, Theory, Verification.
KEYWORDS
3. PROPOSED WORK
Neural networks, Software Reliability Assessment, Back propagation algorithm, software failure data sets.
Backpropagation algorithm is used in the computation of software reliability.
1. INTRODUCTION
4. RESULTS OBTAINED
4.1. Case Study 1
Computers known as artificial neural networks have achieved considerable success. The success of computers lies in the fact that, any activity that can be represented in the form of steps (algorithmic form) can be solved with much faster time and efficiency than human beings. However, computers have proven relatively less successful in certain tasks such as picture recognition or voice recognition.
2. RELIABILITY THEORY Reliability theory is the foundation of reliability engineering. For engineering purposes, reliability is defined as: the probability that a device will perform its intended function during a specified period of time under stated conditions.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. ICWET’10, February 26–27, 2010, Mumbai, Maharashtra, India. Copyright 2010 ACM 978-1-60558-812-4…$10.00.
698
The case study one is done using standard data collected for Software Reliability. Around 80% of data is used for training purpose and rest 20% of data is used for the testing so that the result obtained can be compared with the standard data and the accuracy level of neural network can be assessed. Here inputs 1& 2 are inputs to simulator and expected and obtained are shown below table1: Table 1: Set of data sets Input1 Input2 expected result output obtained 0.029800 0.800000 0.977364 0.976441 0.029800 0.960000 0.976650 0.971797 0.629800 0.368900 0.792536 0.792681 0.329800 0.698900 0.796503 0.794138 0.929800 0.998900 0.408812 0.395036 0.699800 0.568900 0.665736 0.671583 0.589800 0.533900 0.727370 0.729866 0.454500 0.960000 0.646120 0.646411 0.404500 0.660000 0.767112 0.765696
Analysis: After training the neural network, the weights (case one) are generated which are summarized below. On the left most side integer numbers represent the layer number and
