Qualification: 
M.E, BE

Kumaran U. currently serves as Assistant Professor (Senior Grade) in the Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Bengaluru. He has 10 years of experience in teaching. His areas of interest includes Data Mining, Network Security, Privacy Preserving Techniques and Machine Learning Concepts. He has guided number of final year M.Tech. Capstone projects. He has conducted many orientation and induction Programs and also acted as a resource person in motivation and career guidance programs.

Education

  • M. E.
    Arunai Engineering College, Tiruvannamalai, Affiliated to Anna University, Chennai.
  • B. E.
    Arunai College of Engineering, Tiruvannamalai, Affiliated to Anna University, Chennai.

Publications

Publication Type: Journal Article

Year of Publication Title

2018

Kumaran U. and Neelu Khare, “An Efficient and Secure Content Contribution and Retrieval Content in Online Social Networks Using Level by Level Security Optimization & Content Visualization Algorithm”, Indonesian Journal of Electrical Engineering and Computer Science, vol. 10, no. 2, pp. 807-816, 2018.[Abstract]


Online Social Networks (OSNs) is currently popular interactive media to establish the communication, share and disseminate a considerable amount of human life data. Daily and continuous communications imply the exchange of several types of content, including free text, image, audio, and video data. Security is one of the friction points that emerge when communications get mediated in Online Social Networks (OSNs). However, there are no content-based preferences supported, and therefore it is not possible to prevent undesired messages. Providing the service is not only a matter of using previously defined web content mining and security techniques. To overcome the issues, Level-level Security Optimization & Content Visualization Algorithm is proposed to avoid the privacy issues during content sharing and data visualization. It adopts level by level privacy based on user requirement in the social network. It evaluates the privacy compatibility in the online social network environment to avoid security complexities. The mechanism divided into three parts namely like online social network platform creation, social network privacy, social network within organizational privacy and network controlling and authentication. Based on the experimental evaluation, a proposed method improves the privacy retrieval accuracy (PRA) 9.13% and reduces content retrieval time (CRT) 7 milliseconds and information loss (IL) 5.33%.

More »»

2018

Kumaran U. and Neelu Khare, “PPHE – Automatic Detection of Sensitive Attribute in Privacy Preserved Hadoop Environment using Data Mining Techniques”, International Journal of Computer Aided Engineering and Technology, (Accepted), 2018.[Abstract]


Online Social Networks (OSN) has become highly popular, where users are more and more lured to reveal their private information. To balance privacy and utility, many privacy preserving approaches have been proposed which does not well meet users personalized requirements. Most social networks based data sources such as Twitter, Facebook etc., have unstructured data and no analytics or processing tools can work directly on this unstructured data. Commonly, users lack in data privacy and the access control mechanisms available to remove the risk of disclosure. Thus, the privacy preserving paradigm is required that automatically preserves the user privacy to find the sensitive attribute and reduce the risk of sensitive information leakage. In this paper, we present a Privacy Preserved Hadoop Environment (PPHE) which automatically detects sensitive attribute using data mining techniques. This work considers Twitter which enable users to post messages. The content of the posted tweets are wide ranging and contains private information such as email addresses, mobile numbers, physical addresses, and date of births. In this context, the purpose of our work is fourfold. First, we authenticate each twitter users using the integrated algorithm RSA and Elgamal Algorithm. Second, we categorize the tweets into private and non-private attributes based on Type-2 Fuzzy Logic System. Third, we apply data suppression technique for private tweets and finally sharing users content based on their similarity information. Content similarity has evaluated using Cosine Similarity. Finally we evaluate the system performance in terms of accuracy, precision, recall, and F-measure.

More »»

2018

Kumaran U. and Neelu Khare, “A Secure and Privacy Preserving Approach to Protect User Data Across Cloud Based Online Social Networks”, International Journal of Grid and High Performance Computing, ESCI journal (Accepted), 2018.

2017

Kumaran U. and Neelu Khare, “Feature Selection for Privacy Preserving in Data Mining with Linear Regression Using Genetic Algorithm”, Journal of Advanced Research in Dynamical and Control Systems, vol. 9, no. 02, pp. 1059-1067, 2017.[Abstract]


With the recent advancement in technology and supreme power to store large amounts of data invokes the endless possibilities of data mining and analysis using Data Warehouses and Cloud Storage.Peta bytes of data being generatedismaking the countries/companies/industries/organisations data driven which, decides the trends and finds the hidden patterns, with better visualisation. With data comes the important issue and aspect of maintenance its privacy. Privacy preserving in data mining is an upcoming field of research which is using various statistical and state of the art machine learning algorithm for preserving the very sensitive information about the firms from Data Miners while still allowing them to find the useful rules. In this paper we propose a way for maintaining our data secrecy using Linear Regression which uses Genetic Algorithm for deciding over the features for the most optimised accuracy and higher secrecy levels.

More »»

2017

Kumaran U. and Neelu Khare, “A Credential Data Privacy Preserving in Web Environment Using Secure Data Contribution Retrieval Algorithm”, International Journal of Intelligent Engineering and Systems, vol. 10, no. 3, pp. 363-370, 2017.[Abstract]


Preservation of privacy is a significant aspect of data mining and as the secrecy of sensitive information must be maintained while sharing the data among different untrusted parties. There are many application is suffering from vulnerable, data leakage, data misuse, and sensitive data disclosure issues. To protect the privacy of sensitive data without losing the usability of data, various techniques have been used in privacy-preserving data mining (PPDM). Some of the approaches are available to maintain the tight privacy, but they fail to minimize the execution time and error rate. The main objective of the article is to contribute and retrieve the data with minimal classification error and execution time with enhanced privacy. To overcome the issues, the paper introduces the Secure Data Contribution Retrieval algorithm (SDCRA) to fulfill the current issues. Proposed algorithms define a privacy policy and arrange the security based on requirements. This design applies the privacy based on the compatibility of applications. This approach is capable of satisfying the accuracy constraints for multiple datasets. It also considers the efficient data extraction with a good ranking of attributes in tables. Here, proposed SDCRA is compared with existing approaches namely as Perturbation, singular value decomposition (SVD), Singular Value Decomposition data Perturbation (SVD+DP), K-anonymity with Decision Tree (KA+DT)[] for Cancer, HIV, Diabetes dataset. Based on experimental result proposed approach performs well regarding success rate, error rate and system execution time compare than existing methods. Proposed approach improves Success Rate 1.83% reduces the Error Rate 2.33% and minimizes the system execution time 2 seconds.

More »»

2016

Neelu Khare, Kumaran U., and M. Mohan Vamsi, “Knowledge Acquisition and Privacy Preserving in Cloud using Simultaneous Diagonalization Algorithm”, International Journal of Advanced Research in Computer Science and Software Engineering, vol. 6, no. 9, 2016.[Abstract]


In the recent times the WWW (World Wide Web) has transformed from static collection of HTML data to a dynamic system that offered a platform for cloud technologies and distributed information systems. This paper describes how data mining is used in cloud computing while preserving its privacy. Data Mining is used for extracting potentially useful information from raw data. The integration of data mining techniques into normal day-to-day activities has become common place. Every day people are confronted with targeted advertising, and data mining techniques help businesses to become more efficient by reducing costs. Data mining techniques and applications are very much needed in the cloud computing paradigm. The implementation of data mining techniques through Cloud computing will allow the users to retrieve meaningful information from virtually integrated data warehouse that reduces the costs of infrastructure and storage.

More »»

2016

Kumaran U., Neelu Khare, and Sai Suraj A., “Privacy Preserving in Data Mining Technical: A Review”, Research Journal of Pharmacy and Technology, vol. 9, no. 11, pp. 2023-2026 , 2016.[Abstract]


Data mining produces a large amount of data that needs to be analyzed and prioritized in order to extract useful information from it and gain more knowledge from the data. The aim of data mining tools is to find useful patterns, techniques and models from the available of large data. Hence knowledge about various data mining techniques may contain private information about people or business. The data in data mining is vulnerable to data hackers and employees to take advantage of the situation and misuse data. Preservation of privacy is a significant aspect of data mining and as secrecy of sensitive information must be maintained while sharing the data among different un-trusted parties. To protect the privacy of sensitive data without losing the usability of data, various techniques have been used in privacy preserving data mining (PPDM) to achieve the goal. The aim of this paper is to present privacy preserving data mining techniques. Current application systems are suffering several data privacy during online. There is required some work for content privacy on web. This work plans to work on privacy of web content during data extraction and clustering.

More »»

2016

Kumaran U. and Neelu Khare, “An Empirical Study of Security in Text Mining”, International Journal of Control Theory and Applications, vol. 9, no. 6, pp. 2737-2743, 2016.

2016

Kumaran U. and Neelu Khare, “A Review on Privacy Preserving Data Mining using Secure Multiparty Computation”, Indian Journal of Science and Technology, vol. 9, no. 48, 2016.[Abstract]


With the widespread habituate of data mining technology in the entire available sectors (public and private) elevate concerns about the sensitiveness of data being mined. Data mining is an enormously powerful technology to extract information from raw data. With the growth of ease of handiness of digital data the possibility of misapply of the data and the mined information grows. A key challenge is to build up security and privacy methods suitable for data mining. This is the reason PPDM (Privacy Preserving Data Mining) has acquired a steam in recent times. In this paper we have addressed the issue of PPDM and moreover, we have considered a scenario where two different parties possesses confidential databases of their own and wish to run a data mining algorithm on the union of their databases, without disclosing any unnecessary information, where we have suggested different methodologies in order to preserve the privacy in the data mining process one among them is Secure Multiparty Computation which is a field of cryptography. PPDM looks at the job of applying data mining algorithms on secret (confidential) data i.e. not granted to be disclosed even to the trusted party who’s running the algorithm.

More »»

2014

Vikash Kumar Saw and Kumaran U., “An Optimal Approach for Mining Rare Causal Associations to Detect ADR Signal Pairs”, International Journal of Scientific and Research Publications, vol. 4, no. 5, 2014.[Abstract]


Adverse Drug Reaction (ADR) is one of the most important issues in the assessment of drug safety. In fact, many adverse drug reactions are not discovered during limited premarketing clinical trials; instead, they are only observed after long term post-marketing surveillance of drug usage. In light of this, the detection of adverse drug reactions, as early as possible, is an important topic of research for the pharmaceutical industry. Recently, large numbers of adverse events and the development of data mining technology have motivated the development of statistical and data mining methods for the detection of ADRs. These stand-alone methods, with no integration into knowledge discovery systems, are tedious and inconvenient for users and the processes for exploration are time-consuming. This paper proposes an interactive system platform for the detection of ADRs. By integrating an ADR data warehouse and innovative data mining techniques, the proposed system not only supports OLAP style multidimensional analysis of ADRs, but also allows the interactive discovery of associations between drugs and symptoms, called a drug-ADR association rule, which can be further, developed using other factors of interest to the user, such as demographic information. The experiments indicate that interesting and valuable drug-ADR association rules can be efficiently mined.

More »»