Notes

Slide:2
Assalamaulaikum I am here to introduce to our topic which is Software defect prediction system.
Motivation for this topic is to find the reasons behind software defects using machine learning.
There are different types of software are implemented and published every day. Quality of the
software is the most important aspect of a software. The impact over the business of software
quality is huge. Without proper handling it may lead huge cost overruns and higher maintenance
costs. Any software can’t be 100% defect free or 100% testing can be achieved but a good
quality software has much smaller number of defects and is more reliable.
Slide:3
In the real world, problems are highly complex in nature. These problems are handled with some
machine learning approach according to their need. For every different problem it is almost
impossible to inventing new customized algorithms and also unrealistic. Machine learning is the
most beneficial technologies to have gained momentum in recent times. There are two types of
machine learning algorithms, supervised machine learning algorithms and unsupervised machine
learning algorithms.
In software testing and quality assurance, software defect prediction (SDP) has drawn a lot of
attention in recent times. It helps to diminish check cost, time and exertion by anticipating the
faulty modules productively. In software defect prediction (SDP), attribute characteristic
determination assumes a huge job. Nonetheless, choice of appropriate properties and their
portrayal in a productive way are exceptionally difficult because of the lacking of a standard
arrangement of properties. To address these issues, we present a Selection of Attribute with
Wrapper method to choose an appropriate arrangement of features.
Slide:4
A defect is an error or a bug, in the application which is created. A programmer while designing
and building the software can make mistakes or error. These mistakes or errors mean that there
are flaws in the software. These are called defects.
1. Planning- The foremost activity includes laying down a proper plan regarding how the
SQA will be carried out in our project.
2. Analysis- Are carried out by Analysts and which are a crucial part within software
development. They're tasked with testing programs to make sure they are reliable,
functioning properly, and user-friendly.
3. Design- Much like the planning process, having QA involved in the design phase can
save companies significant amounts of money. It can also result in a better end product,
which will bring in more money from happy customers. In this phase they can identify
aspects that can cause problems for users, it is basically design of user-friendly User
Interfaces.
4. Implementation- It is the completion of the designs. In programming, there’s almost
always more than one way to implement a new design. There are pros and cons to
different methods, some of which might end up having a negative effect on users.
5. Testing- It is the Writing of test cases and bug reports. This involves doing a heavy
walkthrough of each and every section, right down to the smallest details. Finally,
keeping track of all updates that come out and Prioritizing client-supported browsers and
devices.
6. Maintenance- Repetition of the for above steps. There are sometimes bugs that slip
through, even the best automation/manual testing can’t find 100% of bugs on 100% of
browsers/devices 100% of the time.
Slide:6
Our objectives of these projects are given below:
 Analyze existing defective methods

 Relation between attributes in software defects
 Find an effective approach to predict the software defects automatically
As software quality is the most important aspect of a software and it can directly affect the
quality of the software it has achieved significant popularity in recent years. So, our main
objective is to find the reasons behind the software defects.
Slide:7
Evaluation Matrix- Here we used confusion matrix for the evaluation.

A confusion matrix is a table that is often used to describe the performance of a classification
model or classifier on a set of test data for which the true values are known.
Classification-
SVM- A Support Vector Machine (SVM) is a discriminative classifier formally defined by a

separating hyperplane.
Logistic Regression- Logistic regression is the appropriate regression analysis to conduct when
the dependent variable is (binary). Like all regression analyses, the logistic regression is a
predictive analysis. Logistic regression is used to describe data and to explain the relationship
between one dependent binary variable and independent variables.
Decision trees- A decision tree is a decision support tool that uses a tree-like model of decisions
and their possible consequences.
K Nearest Neighbors, Naïve Bayes.

Notes

Uploaded by

Copyright:

Available Formats

Notes

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Notes

Uploaded by

Copyright:

Available Formats

Slide:2

Our objectives of these projects are given below:

 Analyze existing defective methods

Evaluation Matrix- Here we used confusion matrix for the evaluation.

SVM- A Support Vector Machine (SVM) is a discriminative classifier formally defined by a

K Nearest Neighbors, Naïve Bayes.

You might also like