http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Introducing 'Meta-Network': A New Concept in Network Technology
Gaur, Deepti,Shastri, Aditya,Biswas, Ranjit The Korea Institute of Information and Commucation 2008 Journal of information and communication convergen Vol.6 No.4
A well-designed computer network technology produces benefits on several fields within the organization, between the organizations(suborganizations) or among different organizations(suborganizations). Network technology streamlines business processes, decision process. Graphs are useful data structures capable of efficiently representing a variety of networks in the various fields. Metagraph is a like graph theoretic construct introduced recently by Basu and Blanning in which there is set to set mapping in place of node to node as in a conventional graph structure. Metagraph is thus a new type of data structure occupying its popularity among the computer scientists very fast. Every graph is special case of Metagraph. In this paper the authors introduce the notion of Meta-Networking as a new network technological representation, which is having all the capabilities of crisp network as well as few additional capabilities. It is expected that the notion of meta-networking will have huge applications in due course. This paper will play the role of introducing this new concept to the network technologists and scientists.
Performance Evaluation by Validity Measures of HFC Algorithm
Deepti Gaur,Seema Gaur 한국정보통신학회 2014 2016 INTERNATIONAL CONFERENCE Vol.6 No.1
Hierarchical Fuzzy Clustering Algorithm (HFC) has wide range of applications in various classification areas. The HFC is put forward to overcome the limitations of Fuzzy C-Means (FCM) algorithm. HFC discovers the high concentrated data areas by the agglomerative hierarchical clustering method quickly, analyzes and merges the data areas, and then uses the evaluation function to find the optimum clustering scheme. HFC algorithm is faster than single linkage agglomerative clustering algorithm as it can merge more than two clusters in one iteration when the merging condition is satisfied. In this paper author measured the quality of the clusters obtained by HFC algorithm by calculating various validity measures such as partition coefficient, separation index and Xie and Beni"s index. Experimental results indicate that HFC algorithm gives accurate results comparatively better.
Reengineering Techniques for Object Oriented Legacy Systems
Aman Jatain,Deepti Gaur 보안공학연구지원센터 2015 International Journal of Software Engineering and Vol.9 No.1
Today’s software development is defined by continuous evolution of software products. These products are regularly updated during their usage. In most of the cases systems grow inevitably by adding new features or by changing the system architecture due to new technologies or business plans. It is more than a decade; objects oriented paradigm is adopted as the most efficient passage to build flexible software, and promptly supported by industry. Though, the benefits of object oriented paradigm are supported by many, but its usage does not necessarily result in general, adaptable systems. These huge systems are often suffering from improper use of object oriented techniques, like inheritance and the lack of object oriented methods being regulated towards the building of families of systems instead of developing single applications. These growing technologies make the systems more difficult to maintain and improve. So, there is growing demand for reengineering of object-based systems. The main intention of this paper is to discover important research directions in the area of reengineering of object oriented legacy systems, which necessitate further attention in order to build more effective and efficient reengineering technique for these systems. The paper first discusses the state of art in reengineering of legacy system and its need. Paper also discuss the benefits of component based system over object oriented system and later outlines the techniques for reengineering of object oriented legacy system. In this paper we presented statistical analysis based on more than a decade data.
ModifiedFAST: A New Optimal Feature Subset Selection Algorithm
Nagpal, Arpita,Gaur, Deepti The Korea Institute of Information and Commucation 2015 Journal of information and communication convergen Vol.13 No.2
Feature subset selection is as a pre-processing step in learning algorithms. In this paper, we propose an efficient algorithm, ModifiedFAST, for feature subset selection. This algorithm is suitable for text datasets, and uses the concept of information gain to remove irrelevant and redundant features. A new optimal value of the threshold for symmetric uncertainty, used to identify relevant features, is found. The thresholds used by previous feature selection algorithms such as FAST, Relief, and CFS were not optimal. It has been proven that the threshold value greatly affects the percentage of selected features and the classification accuracy. A new performance unified metric that combines accuracy and the number of features selected has been proposed and applied in the proposed algorithm. It was experimentally shown that the percentage of selected features obtained by the proposed algorithm was lower than that obtained using existing algorithms in most of the datasets. The effectiveness of our algorithm on the optimal threshold was statistically validated with other algorithms.
A New Alignment Free Method for Phylogenetic Tree Construction
Geetika Munjal,Madasu Hanmandlu,Deepti Gaur 보안공학연구지원센터 2015 International Journal of Database Theory and Appli Vol.8 No.6
In this paper various methods of sequence analysis which include the alignment based and alignment free methods of tree generation are reviewed and these find distance/similarity among the sequences of different species. Alignment free method based on tuple count and set theory is proposed and the results are compared with the guide tree obtained using alignment based method. The proposed method is tested on DNA sequence of length below 1000bp (dataset1) and Sequence of length above 16000bp (dataset2). It achieves the similar performance as that of the alignment based method but without the alignment phase.