Tirimula Rao Benala

A novel approach to image edge enhancement using Artificial Bee Colony optimization algorithm for hybridized smoothening filters

In this Modern era, image transmission and processing plays a major role. It would not be possible to retrieve information from satellite and medical images without the help of Image processing techniques. Image edge Enhancement is the art of examining images for identifying objects and judging their significance. The proposed work uses the concept of Artificial Bee Colony Algorithm which proved to be the most powerful unbiased optimization technique for sampling a large solution space. Because of its unbiased stochastic sampling, it was quickly adapted in image processing and thus for image edge enhancement as well. This paper deals with the techniques that help in improvising the quality of the image edges and in solving various complex image processing tasks such as segmentation, feature extraction, classification and image generation. The edge enhancement is done using hybridized smoothening filters by The Artificial Bee Colony optimization algorithm and compared it with the genetic algorithm.

Computational intelligence in software cost estimation: an emerging paradigm

One of the key features for the failure of project estimation techniques is the selection of inappropriate estimation models. Further, noisy data poses a challenge to build accurate estimation models. Therefore, the software cost estimation (SCE) is a challenging problem that has attracted many researchers over the past few decades. In the recent times,the use of computational intelligence methodologies for software cost estimation have gained prominence. This paper reviews some of the commonly used computational intelligence (CI) techniques and analyzes their application in software cost estimation and outlines the emerging trends in this area

Software Effort Estimation Using Data Mining Techniques

This paper describes an empirical study undertaken to investigate the quantitative aspects of application of data mining techniques to build models for Software effort estimation. The techniques chosen are Multi linear regression, Logistic regression and CART.Empirical evaluation using three fold cross validation procedure has been carried out using three bench marking datasets of software projects, namely, Nasa93, Cocomo81, and Bailey Basili. We observed that: (1) CART technique is suitable for Nasa93 and Nasa93_5. (2). Multiple Linear Regression is suitable for Nasa93_2, Cocomo81s, Cocomo81o and Basili Bailey. (3). Logistic Regression is suitable for Nasa93_1, Cocomo81 and Cocomo81e. It is concluded that data mining techniques tend to help estimating in the best way possible as they are objective and are applicable to unlimited sets of data.

Software effort prediction using fuzzy clustering and functional link artificial neural networks

We use the combined fuzzy C-Means (FCM) clustering algorithm and functional link artificial neural networks (FLANN) to achieve accurate software effort prediction. FLANN is a computationally efficient nonlinear network and is capable for complex nonlinear mapping between its input and output pattern space. The nonlinearity is introduced into the FLANN by passing the input pattern through a functional expansion unit. The proposed method uses three real time datasets. The Chebyshev polynomial has been used as choice of expansion to exhaustively study the performance. The simulation results show that it not only deals efficiently with noisy data but also proves to be a champion in producing promising results.

Genetic Algorithm for Optimizing Functional Link Artificial Neural Network Based Software Cost Estimation

As Software becomes more complex and its scope dynamically increases, the importance of research on developing methods for estimating software development efforts has perpetually increased. Such accurate estimation has a prominent impact on the success of projects.The proposed work uses Functional Link neural network (FLANN) based estimation, which is essentially a machine learning approach, is one of the most popular techniques. In this paper the author has proposed a 2 step process for software effort prediction. In first phase known as training phase the FLANN selects the matching class (datasets) for the given input, which is improved by optimizing the parameters of each individual dataset by Genetic algorithm. In second step known as testing phase, the prediction process is done by Functional Link Artificial Neural Networks. The proposed method uses COCOMO-II as base model. The experimental results show that our method could significantly improve prediction accuracy of conventional Functional Link Artificial Neural Networks (FLANN) and has potential to become an effective method for software cost estimation.

A Particle Swarm Optimized Functional Link Artificial Neural Network (PSO-FLANN) in Software Cost Estimation

We use particle swarm optimization (PSO) to train the functional link artificial neural network (FLANN) for software effort prediction. The combined framework is known as PSO-FLANN. This framework exploits the global classification capability of PSO and FLANN’s complex nonlinear mapping between its input and output pattern space by using functional expansion. The Chebyshev polynomial has been used as choice of expansion in FLANN to exhaustively study the performance in three real time datasets. The simulation results show that it not only deals efficiently with noisy data but achieves improved accuracy in prediction.

Genetic algorithm for optimizing neural network based software cost estimation

Software engineering cost models and estimation techniques are used for number of purposes. These include budgeting, tradeoff and risk analysis, project planning and control, software improvement and investment analysis. The proposed work uses neural network based estimation, which is essentially a machine learning approach, is one of the most popular techniques. In this paper the author has proposed a 2 step process for software effort prediction. In first phase known as training phase neural network selects the matching class (datasets) for the given input, which is improved by optimizing the parameters of each individual dataset by Genetic algorithm. In second step known as testing phase, the prediction process is done by adaptive neural networks. The proposed method uses COCOMO-II as base model. The experimental results show that our method could significantly improve prediction accuracy of conventional Artificial Neural Networks (ANN) and has potential to become an effective method for software cost estimation.

Software effort prediction using unsupervised learning (clustering) and functional link artificial neural networks

Software cost estimation continues to be an area of concern for managing of software development industry. We use unsupervised learning (e.g., clustering algorithms) combined with functional link artificial neural networks for software effort prediction. The unsupervised learning (clustering) indigenously divide the input space into the required number of partitions thus eliminating the need of ad-hoc selection of number of clusters. Functional link artificial neural networks (FLANNs), on the other hand is a powerful computational model. Chebyshev polynomial has been used in the FLANN as a choice for functional expansion to exhaustively study the performance. Three real life datasets related to software cost estimation have been considered for empirical evaluation of this proposed method. The experimental results show that our method could significantly improve prediction accuracy of conventional FLANN and has the potential to become an effective method for software cost estimation.

Software Effort Estimation Using Functional Link Neural Networks Tuned with Active Learning and Optimized with Particle Swarm Optimization

This paper puts forward a new learning model based on the collaborative effort of active learning and particle swarm optimization (PSO) in functional link artificial neural networks (FLANNs) to estimate software effort. The active learning uses quick algorithm to detect the essential content of the datasets by which the dataset is reduced and are processed through PSO optimized FLANN. The PSO uses the inertia weight, which is an important parameter in PSO that significantly affects the convergence and exploration-exploitation in the search space while training FLANN. The Chebyshev polynomial has been used for mapping the original feature space from lower to higher dimensional functional space. The method has been evaluated exhaustively on different test suits of PROMISE repository to study the performance. The computational results show that the active learning along with PSO optimized FLANN greatly improves the performance of the model and its variants for software development effort estimation.

Software Effort Estimation Using Functional Link Neural Networks Optimized by Improved Particle Swarm Optimization

This paper puts forward a new learning model based on improved particle swarm optimization (ISO) for functional link artificial neural networks (FLANN) to estimate software effort. The improved PSO uses the adaptive inertia to balance the tradeoff between exploration and exploitation of the search space while training FLANN. The Chebyshev polynomial has been used for mapping the original feature space from lower to higher dimensional functional space. The method has been evaluated exhaustively on different test suits of PROMISE repository to study the performance. The simulation results show that the ISO learning algorithm greatly improves the performance of FLANN and its variants for software development effort estimation.