Arul Kumar Natarajan

Dr. Arul Kumar Natarajan

orcid
Assistant Professor, Samarkand International University of T...

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 May 2021 in Soft Computing
Verified
Journal Article
Closed access
PDF file
Neelakandan SubramaniNeelakandan Subramani
Neelakandan Subramani
MBM. A. Berlin
M. A. Berlin
STSandesh Tripathi
Sandesh Tripathi
VDV. Brindha Devi
V. Brindha Devi
IBIndu Bhardwaj
Indu Bhardwaj
Arul Kumar NatarajanArul Kumar Natarajan
Arul Kumar Natarajan

20 January 2022 in International Journal of Modeling, Simulation, and Scientific Computing
Verified
Journal Article
Closed access
PDF file
SNS. Neelakandan
S. Neelakandan
JBJ. Rene Beulah
J. Rene Beulah
LPL. Prathiba
L. Prathiba
GMG. L. N. Murthy
G. L. N. Murthy
ERE. Fantin Irudaya Raj
E. Fantin Irudaya Raj
Arul Kumar NatarajanArul Kumar Natarajan
Arul Kumar Natarajan

10 March 2023 in Enterprise Information Systems
Verified
Journal Article
Closed access
PMPrakash Mohan
Prakash Mohan
SNS. Neelakandan
S. Neelakandan
Abbas MardaniAbbas Mardani
Abbas Mardani
SMSudhanshu Maurya
Sudhanshu Maurya
Arul Kumar NatarajanArul Kumar Natarajan
Arul Kumar Natarajan
KTK. Thangaraj
K. Thangaraj
Hyper automation is the group of approaches and software companies utilised to automate manual procedures. Financial Technology (FinTech) was processed as a distinctive classification that highly inspects the financial technology sector from a broader group of functions for enterprises with utilise of Information Technology (IT) application. Financial crisis prediction (FCP) is the most essential FinTech technique, defining institutions’ financial status. This study proposes an Eagle Strategy Arithmetic Optimisation Algorithm with Optimal Deep Convolutional Forest (ESAOA-ODCF) based FinTech Application for Hyperautomation. The ESAOA-ODCF technique has achieved exceptional performance with maximum accu y of 98.61%, and F score of 98.59%. Extensive experimental research revealed that the ESAOA-ODCF model beat more modern, cutting-edge approaches in terms of overall performance.

1 January 2022 in Intelligent Automation and Soft Computing
Verified
Journal Article
Open access
BJB. Jaishankar
B. Jaishankar
SVSantosh Vishwakarma
Santosh Vishwakarma
PMPrakash Mohan
Prakash Mohan
APAditya Kumar Singh Pundir
Aditya Kumar Singh Pundir
IPIbrahim Patel
Ibrahim Patel
Arul Kumar NatarajanArul Kumar Natarajan
Arul Kumar Natarajan
The Healthcare system is an organization that consists of important requirements corresponding to security and privacy, for example, protecting patients’ medical information from unauthorized access, communication with transport like ambulance and smart e-health monitoring. Due to lack of expert design of security protocols, the healthcare system is facing many security threats such as authenticity, data sharing, the conveying of medical data. In such situation, block chain protocol is used. In this manuscript, Efficient Block chain Network for securing Healthcare data using Multi-Objective Squirrel Search Optimization Algorithm (MOSSA) is proposed to generate smart and secure Healthcare system. In this the block chain is a decentralized and the distributed ledger device that consists of various blocks linked with digital signature schemes, consensus mechanisms and chain of hashing, offers highly reliable storage capabilities. Further the block chain parameters, such as block size, transaction size and number of block chain channels are optimized with the help of MOSSA. With the evolution of the MOSSA provide new features for enhancing security and scalability. The simulation process is executed in the JAVA platform. The experimental result of the proposed method shows higher throughput of 26.87%, higher efficiency of 34.67%, lowest delay of 22.97%, lesser computational overhead of 37.03%, higher storage cost of 34.29% when compared to the existing method such as Block chain-ECIES-HSO, Block chain-hybrid GO-FFO, Block chain-SDN-HSO algorithm for healthcare technologies.

28 April 2022
Verified
Conference Paper
Closed access
SASaleem Raja A
Saleem Raja A
MRMadhubala R
Madhubala R
RNRajesh N
Rajesh N
SLShaheetha L
Shaheetha L
Arul Kumar NatarajanArul Kumar Natarajan
Arul Kumar Natarajan
Crimes in the cyberspace are increasing day by day. Recent cyber threat defense reports states that 80.7% of the systems are compromised at least once in 2020. Cyber criminals taking the pandemic situation as an opportunity for the mass attack through malicious URL circulated by email or text messages in social media. Performing cyber-attacks through malicious URLs is the handy method for the cyber criminals. Protecting from such attacks requires proper awareness and solid defense system. Some of the common approaches followed by the cybercriminals to deceive the victims are 1. Phishing URLs which is very similar to the legitimate URLs. 2. Redirecting URLs 3. Using JavaScript, redirects to the phishing URL when user interacts with webpage 4. Social engineering etc. As soon as the novice internet users clicks on the malicious URL link, cyber criminals can easily steal personal information or install malware on their device to get additional access. Recently malicious URLs are generated algorithmically and uses URL shortening service to evade the existing security setup such as firewall and web filters. In literature, the researchers have proposed several ways to detect the malicious URLs but, new attack vectors that are introduced by the cyber criminals can easily bypass the security system. The purpose of this paper is to provide an overview of various malicious URL detection techniques which includes blacklist based, rules based, machine learning and deep learning-based techniques. Most importantly, the paper discusses the common features used by the detection system from webpages to classify the URL as malicious or benign and various performance metrics. This will encourage the new researchers to bring out the innovative solutions.

22 February 2019 in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
Verified
Journal Article
Closed access
ASAbhishek Sharma
Abhishek Sharma
YSYashvir Singh
Yashvir Singh
Arul Kumar NatarajanArul Kumar Natarajan
Arul Kumar Natarajan
To evaluate the performance and emissions of a diesel engine fuelled by biodiesel blends produced from polanga oil, the engine was run to investigate the effects of injection pressure and timing on engine operation with varying biodiesel blends concentrations. Consequently, commercial diesel fuel blended with different polanga biodiesel in different percentages (0%, 10%, 20%, 30%, and 40%). The average reduction in the thermal performance of the biodiesel fuels, was reduced proportionally with the biodiesel blends. B20 blend operates closest to that of diesel oil whereas, the engine operated with any higher injection timing, ranging from 27 to 31° bTDC, the emission constituents of CO, UHC, CO2, and smoke are the least and remains constant in the injection timing between 27 to 31°bTDC. Polanga based biodiesel blends provide a better result at an injection timing of 31°bTDC and injection pressure of 240 bar leading towards minimum emission. Up to 20% polanga biodiesel blends improvement in the engine performance and reduction in the emissions was observed without any modifications to CI engine.