Muhammed Maruf Öztürk

Bio: Muhammed Maruf Öztürk is an academic researcher from Süleyman Demirel University. The author has contributed to research in topics: Computer science & Software. The author has an hindex of 6, co-authored 23 publications receiving 104 citations. Previous affiliations of Muhammed Maruf Öztürk include Sakarya University.

A novel defect prediction method for web pages using k-means++

Abstract: Presents a novel defect clustering method.Shed new light to defect prediction methods.Depicts the prominence of k-means++ for software testing.Unveils the density of error rates of web elements. With the increase of the web software complexity, defect detection and prevention have become crucial processes in the software industry. Over the past decades, defect prediction research has reported encouraging results for reducing software product costs. Despite promising results, these researches have hardly been applied to web based systems using clustering algorithms. An appropriate implementation of the clustering in defect prediction may facilitate to estimate defects in a web page source code. One of the widely used clustering algorithms is k-means whose derived versions such as k-means++ show good performance on large-data sets. Here, we present a new defect clustering method using k-means++ for web page source codes. According to the experimental results, almost half of the defects are detected in the middle of web pages. k-means++ is significantly better than the other four clustering algorithms in three criteria on four data set. We also tested our method on four classifiers and the results have shown that after the clustering, Linear Discriminant Analysis is, in general, better than the other three classifiers.

Which type of metrics are useful to deal with class imbalance in software defect prediction

Abstract: Context There are various ways to cope with class imbalance problem which is one of the main issues of software defect prediction. Sampling algorithms are implemented on both industrial and open-source software defect prediction data sets by practitioners to wipe out imbalanced data points. Sampling algorithms, up-to-date, have been employed either static or process code metrics. Objective In this study, sampling algorithms including Virtual, SMOTE, and HSDD (hybrid sampling for defect data sets) are explored using static code and quality metrics together. Our goal is not only to lead practitioners to decide the type of the metrics in defect prediction but also provide useful information for developers to design less defective software projects. Method We ran sampling experiments with three sampling algorithms on ten data sets (from GitHub). Feature selection is applied on large features of the data sets. Using five classifiers, the performance of the data sets after sampling is compared with initial data sets. Regression analyzes are implemented on quality metrics to find the most influential metrics for detecting defect proneness. Results Regardless of the type of the sampling, prediction performances are similar. Quality metrics surpassed static code metrics with respect to training times and prediction accuracies. Conclusion Using quality metrics yields better prediction results rather than static code metrics in imbalanced data sets. As the count of project cloning increases, the number of defects decreases. Thus, approaches, related to the class imbalance, should be evaluated not only in terms of static code metrics but also for quality metrics.

A bat-inspired algorithm for prioritizing test cases

Abstract: By ordering test cases, early fault detection is focused on test case prioritization. In this field, it is widely known that algorithm and coverage criteria focused works are common. Previous works, which are related to test case prioritization, showed that practitioners need a novel method that optimizes test cases according to the cost of each test case instead of regarding the total cost of a test suite. In this work, by utilizing local and global search properties of a bat algorithm, a new bat-inspired test cases prioritization algorithm (BITCP) is proposed. In order to develop BITCP, test case execution time and the number of faults were adapted to the distance from the prey and loudness, respectively. The proposed method is then compared with four methods which are commonly used in this field. According to the results of the experiment, BITCP is superior to the conventional methods. In addition, as the complexity of the code of test cases increases, the decline in average percentage of fault detection is less in BITCP than the other four comparison algorithms produced.

Introduction to Fractional Calculus

Abstract: In this chapter, fractional calculus is introduced. After a brief overview about this topic, some basic definitions and properties are presented. Moreover, some geometrical and physical interpretations of fractional operators are described, both in time and frequency domain.

Improving defect prediction with deep forest

Abstract: Context Software defect prediction is important to ensure the quality of software. Nowadays, many supervised learning techniques have been applied to identify defective instances (e.g., methods, classes, and modules). Objective However, the performance of these supervised learning techniques are still far from satisfactory, and it will be important to design more advanced techniques to improve the performance of defect prediction models. Method We propose a new deep forest model to build the defect prediction model (DPDF). This model can identify more important defect features by using a new cascade strategy, which transforms random forest classifiers into a layer-by-layer structure. This design takes full advantage of ensemble learning and deep learning. Results We evaluate our approach on 25 open source projects from four public datasets (i.e., NASA, PROMISE, AEEEM and Relink). Experimental results show that our approach increases AUC value by 5% compared with the best traditional machine learning algorithms. Conclusion The deep strategy in DPDF is effective for software defect prediction.

Chaotic chameleon: Dynamic analyses, circuit implementation, FPGA design and fractional-order form with basic analyses

Abstract: There are many recent investigations on chaotic systems with self-excited and hidden attractors. In this paper we introduce a chaotic system in which the attractor can change between hidden and self-excited attractor depending on the value of parameters. Dynamical properties of the proposed attractor are investigated. The attractor is then realized using off the shelf components. Also, for this new system electronic circuit is implemented and FPGA-based chaotic oscillator is designed. In the end, the fractional- order form is examined through bifurcation and stability analysis.