Qualification: 
MCA
hariag@asas.kh.amrita.edu

A. G. Hari Narayanan currently serves as Assistant Professor in the Department of Computer Science and I.T., School of Arts & Sciences, Amrita Vishwa Vidyapeetham, Kochi. 

Publications

Publication Type: Journal Article

Year of Publication Title

2019

S. G Gracious, Nandanan, G., R, D. K., and A. G. Hari Narayanan, “Big Data Security Analytics in Clinical Data using Cryptographic Algorithms”, International Journal of Recent Technology and Engineering (IJRTE) , vol. 8, no. 2, 2019.[Abstract]


With increasing apprehension and concerns of cloud computing and information security, awareness about the use of security algorithms in data systems and processes is
indispensable. The objective of this paper is to examine a set of cryptographic algorithms for cloud platforms to secure clinical data. The main benefits of cloud storage are scalability,
resilience, cost efficiency, high reliability and easy access to your knowledge anyplace, anytime. Because of these benefits every organization is moving its data to the cloud. So there is a
necessity to protect that data against unauthorized access, modification or denial of access etc. we analyzed the use of cryptography in securing clinical data sets using evaluation
parameters such as computing memory, encryption time and decryption time.

More »»

2019

A. M. M., D’cruz, A. Susan, and A. G. Hari Narayanan, “Big Data Analytics In Clinical Data using Multi Keyword Search”, International Journal of Recent Technology and Engineering (IJRTE), vol. 8, no. 1, pp. 1452-1456, 2019.[Abstract]


Due to rapidly increasing clinical data, clinics are increasingly outsourcing local data to to cloud servers online– this achieves convenience and also reduces data management expenditure. To
ensure privacy, data of a sensitive nature needs encryption before outsourcing. This renders impossible usual data recovery methods such as keyword - based document recovery. We study
Big Data Analytics in clinical data employing multi – keyword search, which also supports active update operations such as document removal and addition. To be more specific, we build
an index tree that is founded on the sculpture of vector space to search multi - keywords; this supports flexible update operations. In addition, cosine similarity measures are used to
support the precise ranking of results emerging from the search. We proceed to formulate a search algorithm – this relies on a Greedy Depth-first strategy -to improve search efficiency.
Clinical data experiments demonstrate the efficacy of the proposed scheme

More »»

2018

V. V. Sruthy, Saju, A., and A. G. Hari Narayanan, “Predictive Methodology for Child Behavior from Children Stories”, Journal of Engineering and Applied Sciences, vol. 13, no. 5, pp. 4597-4599, 2018.[Abstract]


Story reading brightens our child’s imagination and it develops curiosity in children. It helps them to develop brain. The graphics and rhyming style could help the children to understand the language patterns. They develop a difference between the real and make believe around the world and it helps to create their own ideas. Story reading and storytelling can emotionally impact children which help them to understand the change of different emotions according to the change of situations which is expressed through words. Seven basic categories of emotion (joy, fear, anger, disgust, surprise, sadness and neutral) of child are used here. The degree of these emotions depends upon the basic character of child. In this study, we applied SVM with the help of Hadoop MapReduce frame work environment to find out the child behavior according to the stories they read or listen. As per our analysis research, our system provides an efficient mechanism to select good stories for our child as well as developing an application in smartphone which does the same.

More »»

2018

M. Prabhakar, B. Priya, L., and A. G. Hari Narayanan, “Framework for Authenticating Smartphone Users Based on Touch Dynamics”, Journal of Engineering and Applied Sciences, vol. 13, no. 5, pp. 4604-4608, 2018.[Abstract]


Mobile phones have become an integral part of everyone’s personal and professional life. Besides providing all the basic functions of a phone, most of the smart phone devices are also used to store critical information regarding a user like passwords, photos, bank account information, etc. Storing and accessing critical information and identifying legitimate users is becoming a growing challenge these days. Hence, authentication should be enforced for all mobile devices to identify legitimate users. We have based our study on behavioral biometrics specifically, touch dynamics. It and can be used to provide increased level of security when authentication is concerned and protection of mobile devices. The objective is to develop an authentication framework which uses a hybrid classification algorithm to classify legitimate users and imposters and to analyze the efficiency of the framework with existing ones. The process is performed on a publicly available touch dynamics dataset and important feature extraction is performed on the same. The accuracy of the scheme is measured on the basis of Equal Error Rate (EER).

More »»

2018

A. G. Hari Narayanan, Prabhakar, M., Priya, L., and Singh, A. Pratap, “Comparative Study Between Classification Algorithms Based on Prediction Performance”, In: Mandal J., Sinha D. (eds) Social Transformation – Digital Way. CSI 2018. Communications in Computer and Information Science, vol. 836, 2018.[Abstract]


In todays “data-centric” world, the prevalence of vast and immeasurable amount of data pertaining to various fields of study has led to the need for properly analyzing and apprehending this information to yield knowledge that becomes useful in decision making. Among the many procedures for handling this multitude of data, “classification” is the one that aids in making decisions based on categorization of data and “feature selection” is the process of picking out attributes relevant to the study. Keeping classification as the central idea of our study, we aim at presenting a comparative analysis of prediction accuracies obtained by two chosen classification algorithms, namely, SVM and RBFN. We proceed to introduce feature selection using both filter and wrapper methods along with SVM and RBFN to showcase a detailed analytical report on variations in performance when using classification algorithms alone, and with application of feature selection. The four approaches used for feature selection in our study are; Information Gain, Correlation, Particle Swarm Optimization (PSO) and Greedy method. Performance of the algorithms under study is evaluated based on time, accuracy of prediction and area under ROC curve. Although time and accuracy are effective parameters for comparison, we propose to consider ROC area as the criterion for performance evaluation. An optimal solution will have the area under ROC curve value approaching 1.

More »»

2015

T. S. Sarika, Sreekumar, S., and A. G. Hari Narayanan, “Enhancement of speech recognition (Voice quest)”, International Journal of Applied Engineering Research, vol. 10, pp. 708-711, 2015.[Abstract]


Here in this paper, we have made a formal assessment of the current capabilities of Speech Recognition system and have taken efforts to show how they have been exploited in present day applications using Hidden Markov Model (HMM). Voice Quest is a huge leap in the world of digital communication. The objective of this paper is to analyse and explain the importance of Voice Quest. Voice quest aims to make searching more easy and simple. First of all, we have to create a database that can accommodate certain questions and their appropriate answers. Whenever user asks a question, this input question is first converted to its text format and tries to get a particular match from our database. After getting that match, the corresponding answer for that question, which is stored in the database in text format is converted to voice format and is given as the output to the user. Since the Voice Quest avoids typing and button presses, it makes searching quite a simpler task. © Research India Publications.

More »»
Faculty Research Interest: