Effort estimation for object-oriented system using artificial intelligence techniques

Software effort estimation is a vital task in software engineering. The importance of effort estimation becomes critical during early stage of the software life cycle when the details of the software have not been revealed yet. The effort involved in developing a software product plays an important role in determining the success or failure. With the proliferation of software projects and the heterogeneity in their genre, there is a need for efficient effort estimation techniques to enable the project managers to perform proper planning of the Software Life Cycle activates. In the context of developing software using object-oriented methodologies, traditional methods and metrics were extended to help managers in effort estimation activity. There are basically some points approach, which are available for software effort estimation such as Function Point, Use Case Point, Class Point, Object Point, etc. In this thesis, the main goal is to estimate the effort of various software projects using Class Point Approach. The parameters are optimized using various artificial intelligence (AI) techniques such as Multi-Layer Perceptron (MLP), K-Nearest Neighbor Regression (KNN) and Radial Basis Function Network(RBFN), fuzzy logic with various clustering algorithms such as the Fuzzy C-means (FCM) algorithm, K-means clustering algorithm and Subtractive Clustering (SC) algorithm, such as to achieve better accuracy. Furthermore, a comparative analysis of software effort estimation using these various AI techniques has been provided. By estimating the software projects accurately, we can have software with acceptable quality within budget and on planned schedules