Problem statement: Predicting the value for missing attributes is an important data preprocessing problem in data mining and knowledge discovery tasks. Several methods have been proposed to treat missing data and the one used more frequently is deleting instances containing at least one missing value of a feature. When the dataset has minimum number of missing attribute values then we can neglect the instances. But if it is high, deleting those instances may neglect the essential information. Some methods, such as assigning an average value to the missing attribute, assigning the most common values make good use of all the available data. However the assigned value may not come from the information which the data originally derived from, thus noise is brought to the data. Approach: In this study, k-means clustering is proposed for predicting missing attribute values. The performance of the proposed approach is analyzed with nine different methods. The overall analysis shows that the k-means clustering can predict the missing attribute values better than other methods. After assigning the missing attributes, the feature selection is performed with Bees Colony Optimization (BCO) and the improved Genetic KNN is applied for finding the classification performance as discussed in our previous study. Results: The performance is analyzed with four different medical datasets; Dermatology, Cleveland Heart, Lung Cancer and Wisconsin. For all the datasets, the proposed k-means based missing attribute prediction achieves higher accuracy of 94.60 %, 90.45 %, 87.51 % and 95.70 % respectively. Conclusion: The greater classification accuracy shows the superior performance of the k-means based missing attribute value prediction.

No abstract

No abstract

The programmer has to understand the behavior of two similar programs and then identify the execution difference which produces difference in output. When two similar programs are executed under two different environments which shows different behavior in output. The main difference exists in the program behavior is due to two different types of input. This paper proposes differential slicing based on trace alignment algorithm which produces the execution differences and generates a casual difference graph. We implement differential slicing for C# programs and identify the execution difference. The results shows that differential slicing identifies the input difference and casual difference graph reduces the amount of time for the programmers to understand the execution difference. Our experimental results show the proposed differential slicing performs better than existing approach. KeywordsCasual Difference Graph (CDG), Program Dependence Graph (PDG) 1.Introduction:Differential program Analysis is the process of finding two similar programs to determine the behavioral difference between them.Programs are frequently maintained by the programmers who are far removed from software development process. The purpose of modifications in the program development is not always clear. The actual effect on the programs behavior is the presence of a particular part of the program may be unknown,a particular line may be crucial or it may have no effect at all. The previous research shows that difference in behavior is caused by the presence or absence of particular element would help the maintainers in understanding the program. A set of automated techniques is needed to analyze the effect of modifications. We use differential slicing to focus on differences between two similar programs [1]. We proposed a differential slicing for C# programs. It identifies the aligned and disaligned region and generates a casual difference graph. We compare the differential slicing and existing approach and the results are tabulated. Our results also show that differential slicing identifies the input difference and CDG decreases the time and effort needed for an analyst to understand the observed difference. The paper is organized as follows. Section 2 describes the existing differential slicing techniques. Section 3 explains about Dynamic slicing. Section 4 explains about differential slicing. Section 5 describes about slice alignment. Section 6 describes the performance result of differential slicing. Section 7 describes conclusion. Related WorkDifferential program analysis is the task of analyzing two related programs which identified the behavioral difference between them. Joel Winsted et al presents a technique to find an input for which the two programs will produce different outputs ,Thus illustrating the behavioral difference between the two programs [1]. A combination of static and dynamic techniques are used to find the differential inputs. Sumner and Zhang [4] finds the casual path of two executions by first patching the...

Nowadays due to the information overload the individual users did not obtaining their own relevant products which they are specified. So the recommendations to the individual users can reduce the load to the user whenever they are buying the products. However, certain algorithms where introduced to improve the quality of the aggregate diversity concept. By improving this concept the aggregate diversity of the certain products can be obtained. In this paper I have explored the aggregate diversity concepts which are obtained from the items that are individually ranked and displayed. This will be more effective in the application such as E-Commerce and E-Bay. In the proposed approach efficient recommendations are obtained to the user by which the aggregate diversity is achieved with the required products.