Kürşat Ayan

Artificial bee colony algorithm solution for optimal reactive power flow

Artificial bee colony (ABC) algorithm is an optimization algorithm based on the intelligent foraging behavior of honeybee swarm. Optimal reactive power flow (ORPF) based on ABC algorithm to minimize active power loss in power systems is studied in this paper. The advantage of ABC algorithm is that it does not require these parameters, because it is very difficult to determine external parameters such as cross over rate and mutation rate as in case of genetic algorithm and differential evolution. The other advantage is that global search ability of the algorithm is implemented by introducing a neighborhood source production mechanism which is similar to mutation process. Because of these features, ABC algorithm attracts much attention in recent years and has been used successfully in many areas. ORPF problem is one of these areas. In this paper, proposed algorithm is tested on both standard IEEE 30-bus test system and IEEE 118-bus test system. To show the effectiveness of proposed algorithms, the obtained results are compared with different approaches as available in the literature.

Software defect prediction using cost-sensitive neural network

Software defect prediction model was built by Artificial Neural Network (ANN).ANN connection weights were optimized by Artificial Bee Colony (ABC).Parametric cost-sensitivity feature was added to ANN by using a new error function.Model was applied to five publicly available datasets from the NASA repository.Results were compared with other cost-sensitive and non-cost-sensitive studies. The software development life cycle generally includes analysis, design, implementation, test and release phases. The testing phase should be operated effectively in order to release bug-free software to end users. In the last two decades, academicians have taken an increasing interest in the software defect prediction problem, several machine learning techniques have been applied for more robust prediction. A different classification approach for this problem is proposed in this paper. A combination of traditional Artificial Neural Network (ANN) and the novel Artificial Bee Colony (ABC) algorithm are used in this study. Training the neural network is performed by ABC algorithm in order to find optimal weights. The False Positive Rate (FPR) and False Negative Rate (FNR) multiplied by parametric cost coefficients are the optimization task of the ABC algorithm. Software defect data in nature have a class imbalance because of the skewed distribution of defective and non-defective modules, so that conventional error functions of the neural network produce unbalanced FPR and FNR results. The proposed approach was applied to five publicly available datasets from the NASA Metrics Data Program repository. Accuracy, probability of detection, probability of false alarm, balance, Area Under Curve (AUC), and Normalized Expected Cost of Misclassification (NECM) are the main performance indicators of our classification approach. In order to prevent random results, the dataset was shuffled and the algorithm was executed 10 times with the use of n-fold cross-validation in each iteration. Our experimental results showed that a cost-sensitive neural network can be created successfully by using the ABC optimization algorithm for the purpose of software defect prediction.

Deriving thresholds of software metrics to predict faults on open source software

We empirically examined if there are effective thresholds for software metrics.Open-source software systems were used as benchmarking datasets.The learner model was created using logistic regression and the Bender method.Experimental results revealed that some metrics have effective threshold values. Object-oriented metrics aim to exhibit the quality of source code and give insight to it quantitatively. Each metric assesses the code from a different aspect. There is a relationship between the quality level and the risk level of source code. The objective of this paper is to empirically examine whether or not there are effective threshold values for source code metrics. It is targeted to derive generalized thresholds that can be used in different software systems. The relationship between metric thresholds and fault-proneness was investigated empirically in this study by using ten open-source software systems. Three types of fault-proneness were defined for the software modules: non-fault-prone, more-than-one-fault-prone, and more-than-three-fault-prone. Two independent case studies were carried out to derive two different threshold values. A single set was created by merging ten datasets and was used as training data by the model. The learner model was created using logistic regression and the Bender method. Results revealed that some metrics have threshold effects. Seven metrics gave satisfactory results in the first case study. In the second case study, eleven metrics gave satisfactory results. This study makes contributions primarily for use by software developers and testers. Software developers can see classes or modules that require revising; this, consequently, contributes to an increment in quality for these modules and a decrement in their risk level. Testers can identify modules that need more testing effort and can prioritize modules according to their risk levels.

A Feature Dependent Naive Bayes Approach and Its Application to the Software Defect Prediction Problem

Abstract Naive Bayes is one of the most widely used algorithms in classification problems because of its simplicity, effectiveness, and robustness. It is suitable for many learning scenarios, such as image classification, fraud detection, web mining, and text classification. Naive Bayes is a probabilistic approach based on assumptions that features are independent of each other and that their weights are equally important. However, in practice, features may be interrelated. In that case, such assumptions may cause a dramatic decrease in performance. In this study, by following preprocessing steps, a Feature Dependent Naive Bayes (FDNB) classification method is proposed. Features are included for calculation as pairs to create dependence between one another. This method was applied to the software defect prediction problem and experiments were carried out using widely recognized NASA PROMISE data sets. The obtained results show that this new method is more successful than the standard Naive Bayes approach and that it has a competitive performance with other feature-weighting techniques. A further aim of this study is to demonstrate that to be reliable, a learning model must be constructed by using only training data, as otherwise misleading results arise from the use of the entire data set.

Integrated AC/DC systems Load Flow using Genetic Algorithm

Although the Load Flow (LF) analysis of pure AC power systems is separately solved by both the numerical analysis methods and the heuristic methods, the load flow of integrated AC/DC power systems only has been implementing by numerical methods so far. There are many methods to implement load flow analysis of integrated AC/DC power systems in literature. Examples of these methods can be given as Newton-Raphson, Fast Decoupled and Broyden. In this paper, the sequential load flow analysis of AC/DC system is implemented by using Genetic Algorithm. The proposed method is tested on IEEE 9-bus test system. In this study, a heuristic method is used for load flow analysis of the integrated AC/DC power systems for the first time.

Risk analysis in cancer disease by using fuzzy logic

Thousands of people die every year because of cancer due to limitation of medical sources and unable to use the existing sources effectively. Loss of patients can be reduced by using the numerical (quantitative) techniques in the system of Medical and Health. Cancer is a genetic disease which is developed by the abnormal cell increase and cell growth as a result of DNA damage and cells being out of the Program. The earlier cancer is diagnosed, so the treatment would be that successful. In this study, the risks of getting cancer for selected pilot people will be discovered by applying the mamdani Fuzzy Logic Model and suggestions will be submitted to the persons to eliminate these risks. In order to resolve the problem, the available figures have been evaluated; leading method and sample have been presented together with fuzzy logic model as a new modality. The reason for selection of fuzzy logic model in this study is that the system uses fuzzy logic model enables to provide effective results depending on uncertain verbal knowledge just like logic of human being. When received good results from the study; our system will make a prediagnosis for the people who possibly can have risk of getting cancer due to working conditions or living standards therefore; this will enable these people to take precautions to the risk of cancer. Besides, the contribution of fuzzy logic model in the field of health and topics of artificial intelligence will also be examined in this study.

A new approach for optimal reactive power flow solution of multi-terminal HVDC systems using genetic algorithm

Optimal reactive power flow (ORPF) is one of the known problems of the power systems. Many numerical and heuristic methods were used to solve this problem so far. As seen from these studies in literature, heuristic methods are more effective and faster than numerical methods. This case is to make more attractive and mandatory the using of heuristic methods in optimal power flow solution of High Voltage Direct Current (HVDC) systems. In this study, ORPF solution of multi-terminal HVDC systems is accomplished by using the genetic algorithm (GA) that is one of the heuristic methods. A new approach is used in opposition to the current-balancing method used mostly in literature for the first time. The proposed approach is tested on the modified IEEE 14-bus test system. The obtained results are compared to that reported in the literature to show validity and effectiveness of the new approach.

Transient stability constrained optimal power flow solution of ac-dc systems using genetic algorithm

Optimal power flow (OPF) is one of the known problems of the power systems. Many numerical and heuristic methods were used to solve this problem so far. As seen from these studies in literature, heuristic methods are more effective and faster than numerical methods. This case is to make more attractive and mandatory the using of heuristic methods in optimal power flow solution of High Voltage Direct Current (HVDC) systems. In this study, transient stability constrained optimal power flow solution of alternating current-direct current (AC-DC) systems is accomplished by using the genetic algorithm (GA) that is one of the heuristic methods for the first time. The proposed approach is tested on modified New England 39-bus test system.

Comparison with Sugeno Model and Measurement Of Cancer Risk Analysis By New Fuzzy Logic Approach

Every year thousands of human mortality from cancer is due to limitation of medical sources and unable to use the existing sources effectively. Patient losses can be reduced by using the numerical (quantitative) techniques in the system of medical and health. Cancer is the leading life-threatening disease for people in today’s world. Although cancer formation is different for each type of cancer, it is determined in studies and research conducted that stress also triggers cancer types. Early precaution is very important for the people who have not been sick yet that have high mortality rate and expensive treatment such as cancer. With this type of study, the possibility of getting disease may decrease and people can take measures for the disease. In this study, for the three cancer types selected as pilot by introducing a new type of fuzzy logic model, the opportunity of revealing of risks for catching these cancer types of people and the opportunity of providing preliminary diagnosis to the person to remove this risk are presented. After the calculation of risk outcome, the effect of stress on cancer is discussed and calculated. Due to this type of study, people will have the chance to take measures against catching cancer and the rate of catching cancer can be decreased. Due to this study, the presentation of strong software is aimed, so that related techniques are used in the health field and sample studies are conducted. Furthermore, the performance status of the new technique was revealed by calculating performance measurements of the outcomes of the models developed by the new type of fuzzy logic technique for three cancer types selected as pilot within the study and Takagi-Sugeno type of fuzzy logic model. Key words : Fuzzy logic, artificial intelligence, cancer, risk analysis, preliminary diagnosis, soft computing, new fuzzy logic technique.