Alaa Sheta

Development of software effort and schedule estimation models using Soft Computing Techniques

Accurate estimation of the software effort and schedule affects the budget computation. Bidding for contracts depends mainly on the estimated cost. Inaccurate estimates will lead to failure of making a profit, increased probability of project incompletion and delay of the project delivery date. In this paper, we explore the use of Soft Computing Techniques to build a suitable model structure to utilize improved estimations of software effort for NASA software projects. In doing so, we plan to use Particle Swarm Optimization (PSO) to tune the parameters of the famous COnstructive COst MOdel (COCOMO). We plan also to explore the advantages of Fuzzy Logic to build a set of linear models over the domain of possible software Line Of Code (LOC). The performance of the developed model was evaluated using NASA software projects data set [1]. A comparison between COCOMO tuned-PSO, Fuzzy Logic (FL), Halstead, Walston-Felix, Bailey-Basili and Doty models were provided.

Software Effort Estimation and Stock Market Prediction Using Takagi-Sugeno Fuzzy Models

In this paper, we use Takagi-Sugeno (TS) technique to develop fuzzy models for two nonlinear processes. They are the software effort estimation for a NASA software projects and the prediction of the next week S&P 500 for stock market. The development of the TS fuzzy model can be achieved in two steps 1) the determination of the membership functions in the rule antecedents using the model input data; 2) the estimation of the consequence parameters. We use least-square estimation to estimate those parameters. Detailed descriptions of the two applications are given. The results are promising.

Particle swarm optimisation enhancement approach for improving image quality

Particle Swarm Optimisation (PSO) algorithm represents a new approach to optimisation problems. In this paper, image enhancement is presented as an optimisation problem to which PSO is applied. This application is done within a nouvelle automatic image enhancement technique encompassing a real-coded particle swarms algorithm. The enhancement process is a non-linear optimisation problem with several constraints. Based upon a mathematical model of the social interactions of swarms, the algorithm has been shown to be effective at finding good solutions of the enhancement problem by adapting the parameters of a novel extension to a local enhancement technique similar to statistical scaling. This enhances the contrast and detail in the image according to an objective fitness criterion. The proposed algorithm has been compared with Genetic Algorithms (GAs) to a number of tested images. The obtained results using grey scale images indicate that PSO is better than GAs in terms of the computational time and both the objective evaluation and maximisation of the number of pixels in the edges of the tested images.

Analogue filter design using differential evolution

Although analogue circuits have been successfully used in a variety of real life applications, the design of such circuits is very challenging and a time-consuming task. Automating the design of analogue circuit using optimisation algorithms is urgently needed. Algorithms inspired from natural evolution called evolutionary algorithms (EAs) were successfully used to solve variety of engineering problem. EAs are capable of providing pioneer solutions because they are capable of handling multimodel function, deal with functional non-linearity and measurement noise. In this paper, we explore the advantages of using differential evolution (DE) algorithm to select the optimal elements of analogue electronic circuit and specially passive and active filters. The produced results show that DE can find the optimal values of the proposed circuit elements such as resistor, capacitor and inductor in an efficient way. The developed circuits were tested with significant results.

Identification of a chemical process reactor using soft computing techniques

This paper discusses the application of artificial neural networks (ANNs) in the area of identification and control of nonlinear dynamical systems. Since chemical processes are getting more complex and complicated, the need of schemes that can improve process operations is highly demanded. ANNs are capable of learning from examples, perform non-linear mappings, and have a special capacity to approximate the dynamics of nonlinear systems in many applications. This paper describe the application of neural network for modeling reactor level, reactor pressure, reactor cooling water temperature, and reactor temperature problems in the Tennessee Eastman (TE) chemical process reactor. The potential of neural network technology in the process industries is great. Its ability to model process dynamics makes it powerful tool for modeling and control processes. A comparison between the applications of ANNs to model the TE plant is compared with other soft computing techniques like fuzzy logic (FL) and adaptive neuro-fuzzy inference systems (ANFIS).

Minutiae extraction for fingerprint recognition

Automatic Personal Identification (API) represents a challenge for tremendous life applications such as in passports, cellular telephones, automatic teller machines, and driver licenses. It is important to achieve a high degree of confidence when handling such types of application. Biometrics is being more and more adopted in such cases. In the past years, the development of fingerprint identification systems has received a great deal of attention. The goal of this paper is to represent a complete identification process for fingerprint recognition throughout the extracting of matching minutiae. The performance of the proposed system is tested on a database with fingerprints from different people and experimental results are presented.

Utilizing Faults and Time to Finish Estimating the Number of Software Test Workers Using Artificial Neural Networks and Genetic Programming

Time, effort and the estimation of number of staff desired are critical tasks for project managers and particularly for software projects. The software testing process signifies about 40–50% of the software development lifecycle. Faults are detected and corrected during software testing. Accurate prediction of the number of test workers necessary to test a software before the delivery to a customer will save time and effort. In this paper, we present two models for estimating the number of test workers required for software testing using Artificial Neural Networks (ANN) and Genetic Programming (GP). We utilize the expected time to finish testing and the rate of change of fault observation as inputs to the proposed models. The proposed models were able to predict the required team size; thus, supporting project managers in allocating the team effort to various project phases. Both models yielded promising estimation results in real-time applications.

Landmind detection with IR sensors using Karhunen Loeve transformation and watershed segmentation

In this paper, we present our idea of using the Karhunen Loeve transformation (KLT) and watershed segmentation to detect landmine objects from infrared images. On doing this, we proposed a simplified process for reducing the computation in the Karhunen Loeve transformation using a smaller number of images than traditional methods do. We effectively used the marker based watershed segmentation to detect the mines with high performance detection rate. We tested our proposed method on three different mine fields with two different soil types. Our proposed method consists of four stages: feature extraction, enhancement, object segmentation, and object recognition. The results are promising.

Solving Capelin Time Series Ecosystem Problem Using Hybrid ANN‐GAs Model and Multiple Linear Regression Model

Development of accurate models is necessary in critical applications such as prediction. In this paper, a solution to the stock prediction problem of the Barents Sea capelin is introduced using Artificial Neural Network (ANN) and Multiple Linear model Regression (MLR) models. The Capelin stock in the Barents Sea is one of the largest in the world. It normally maintained a fishery with annual catches of up to 3 million tons. The Capelin stock problem has an impact in the fish stock development. The proposed prediction model was developed using an ANNs with their weights adapted using Genetic Algorithm (GA). The proposed model was compared to traditional linear model the MLR. The results showed that the ANN‐GA model produced an overall accuracy of 21% better than the MLR model.