Informatics Publishing Limited

D. Narmadha ¹, Appavu alias Balamurugan ², G. Naveen Sundar ¹, S. Jeba Priya ¹

Affiliations
1 School of CST, Karunya University, Coimbatore – 641114, Tamil Nadu, IN
2 Department of IT, KLN College of IT, Madurai – 630612, Tamil Nadu, IN

Abstract

Background/Objectives: This research work provides a survey on the various clustering algorithms such as k-means, K Harmonic means and Hybrid Fuzzy K Harmonic Means (HFKHM) for grouping similar items in large dataset. To improve the accuracy of clustering the large dataset HFKHM is used. Methods: The task of analyzing the issues in healthcare databases is extremely difficult since healthcare databases are multi-dimensional, comprising the attributes such as the categorization of tumor, radius, texture, smoothness and compactness of the tumor. This paper presents a related work on the existing clustering algorithms for categorizing the tumors as benign or malignant. Hence clustering algorithms are used to categorize the large dataset based on the diagnosis of the tumor. Findings: The efficiency of the various clustering algorithms is compared based on the accuracy and execution time. K means clustering algorithm produces 88% accuracy, 89% accuracy is obtained with the help of K Harmonic Means clustering approach, 90.5% accuracy is achieved using HFKHM clustering approach. Application: This model can be an efficient approach for categorizing similar patient records based on the symptoms, treatments and age.

Keywords

Clustering, Map Reduce

Full Text

   

D. Narmadha ¹, P. Padmakumari ¹, A. Umamakeswari ¹

Affiliations
1 School of Computing, SASTRA University, Thirumalaisamudram, Thanjavur - 613401, Tamilnadu, IN

Abstract

Background/Objectives: Cloud computing supports many enterprise and government organizations in business perspective due to its advantage such as high scalability and high flexibility. However, despite potential gains that can be achieved, security is fundamental issue. Denial of service attack attempted by attacker to exhausts the resources available to a network, application or service. The orchestrated flow of attack patterns by attacker affect the customers in terms of financial cost cause service inability to legitimate users, attacker overloads target system with massive amount of request, which results in loss of equipment resources affecting network bandwidth. Methods: To address this issue, the proposed lockout policy with access control list is applied to prevent the access to illegitimate user without affecting legal users. Findings: The proposed technique helps in differentiating legitimate and illegitimate users. The attack can be controlled by locking out malicious user access. Thereby the financial cost can be controlled by preventing the resource consumption by malicious node. Applications The proposed methodology can be applied in signature based analysis and strong user identification. There by providing security by building Anti-spam devices at customer site such as E-commerce application. Applications: The proposed methodology can be applied in the signature based analysis and strong user identification. Thus providing security by building Anti-spam devices at customer site, such as in an e-commerce application.

Keywords

Access Control List, Attack Pattern, DDoS, DoS, Lockout Policy, Service Inability.

Full Text