Mohan Kumar

Dr. Mohan Kumar


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
27 April 2022 in IETE Journal of Research
Verified
Journal Article
Closed access
JDJesline Daniel
Jesline Daniel
RSR. Shyamala
R. Shyamala
RPR. Pugalenthi
R. Pugalenthi
MKMohan Kumar
Mohan Kumar
Agriculture is India's greatest wealth, which also contributes to the country's economic development and defines the standard of living for more than 50 percent of the Indian population. In addition to this conventional crop, more are grown and have high dependency, such as wheat and rice. Farmers face many problems where sustainability is of primary importance in agriculture. To solve the issue, we propose to develop a “RANC (Recommendation Analysis by Soil Nutrients of Crops) Crop Recommendation Tool” web application that will help farmers generate their high income with effective crop cultivation along with the suggestion of organic fertilizer by providing up-to - date stock information, Soil Test Report, crop yield time and nutritional value of each crop. The RANC algorithm is used to pick crops and the Deep Neural Network is used for price prediction to improve the farmer’s choice of crops for cultivation with a high benefit. In the case of crop selection, an existing model uses the Soil Test Report to generate the quantity of fertilizers needed to expand. We use SVM for linear data regressions and ANN, RNN, RBM for non-linear data in the case of price estimation in stock analysis. From the experimental results, the prediction accuracy over 90% has been achieved for the proposed approach.

16 June 2022 in Symmetry
Verified
Journal Article
Open access
PDF file
FEFenil Edwin
Fenil Edwin
MKMohan Kumar
Mohan Kumar
The distributed denial of service (DDoS) vulnerabilities have rapidly extended and have been given different possibilities for even more advanced assaults on specific targets in recent times, thanks to the growth of innovative technology such as the Internet of Things (IoT) and Software-Defined Networking (SDN). The attack patterns route comprises unprotected and susceptible IoT systems that are internet-connected, as well as denial of service weaknesses in the SDN controllers, such as southbound connection exhaustion. (1) Background: The review does not go into detail about the symmetry blockchain approaches used to mitigate DDoS attacks, nor does it classify them in IoT; (2) To overcome the privacy issues, a novel deep learning-based privacy preservation method was proposed named ShChain_3D-ResNet. This novel method combines Sharding, blockchain and Residual Network for securing the SDN. Under this network, the proposed efficient attention module jointly learns attention to enforce the symmetry on weights for various channels in spatial dimension as well as attention weights of multiple frames in temporal dimension assistance of pre-training, updating, and dense convolution process; (3) Results: the proposed ShChain_3D-ResNet achieves 95.6% of accuracy, 97.3% of precision, 95.2% of recall, 94.4% of F1-score, 32.5 ms of encryption time and 35.2 ms of decryption time for dataset-1. Further, it achieves 97.3% accuracy, 95.3% precision, 96.1% recall, 98.2% F1-score, 32.1 ms of encryption time, and 36.2 ms of decryption time for dataset-2; (4) Conclusions: The Sharding strategy can increase ShChain performance while simultaneously utilizing Multi User (MU) resources for SDN.

2 April 2016 in Journal of Applied Security Research
Verified
Journal Article
Closed access
MKMohan Kumar
Mohan Kumar
SGS. Gopalakrishnan
S. Gopalakrishnan
Mobile Ad hoc Network (MANET) is more vulnerable to various attacks since it has no centralized or any pre-existing network structure. In this research, we proposed an Attacker Identification using Region Splitting (AIRS) scheme for intrusion detection and attacker identification in MANET. In this scheme, the network is split into several regions for efficient detection. Our proposed AIRS scheme provides an effective response for attacks such as: jellyfish attack, neighbor attack, and location disclosure attack. Here, we calculate Degradation Performance (DP) and Trust of Attack and it provides three response schemes such as Full isolation, Partial isolation, and No reaction. We compare our proposed scheme with the existing Secure Routing Attacker Identification (SRAI) approach. Experimental results show the performance of response scheme on jellyfish attack, neighbor attack, and location disclosure attacks on various scenarios.

1 January 2012 in Information Security Journal: A Global Perspective
Verified
Journal Article
Closed access
MKMohan Kumar
Mohan Kumar
SHUNMUGANATHAN K LSHUNMUGANATHAN K L
SHUNMUGANATHAN K L
In modern electronic communication, ensuring security during transferring of data is crucial. Digital steganography is the technique that ensures the same, in which any secret data is hidden into the cover mediums such as images, audio or video files. Resistance to removal and invisibility of hidden data are the two important requirements of any steganographic system. This paper proposes a new approach to hide any secret data in images. Also, this paper proposes a new approach which hides an executable file in images. The executable files we have considered are Windows PE (Portable-Executable) files. Moreover from the experimental results, it is proven that the proposed approach is suitable for hiding all type of digital files including exe files. Also, comparing with the existing approaches, this approach shows better performance.

1 February 2024 in Big Data
Verified
Journal Article
Closed access
MAM. Ananthi
M. Ananthi
AGAnnapoorani Gopal
Annapoorani Gopal
KRK. Ramalakshmi
K. Ramalakshmi
MKMohan Kumar
Mohan Kumar
An accurate resource usage prediction in the big data streaming applications still remains as one of the complex processes. In the existing works, various resource scaling techniques are developed for forecasting the resource usage in the big data streaming systems. However, the baseline streaming mechanisms limit with the issues of inefficient resource scaling, inaccurate forecasting, high latency, and running time. Therefore, the proposed work motivates to develop a new framework, named as Gaussian adapted Markov model (GAMM)—overhauled fluctuation analysis (OFA), for an efficient big data streaming in the cloud systems. The purpose of this work is to efficiently manage the time-bounded big data streaming applications with reduced error rate. In this study, the gating strategy is also used to extract the set of features for obtaining nonlinear distribution of data and fat convergence solution, used to perform the fluctuation analysis. Moreover, the layered architecture is developed for simplifying the process of resource forecasting in the streaming applications. During experimentation, the results of the proposed stream model GAMM-OFA are validated and compared by using different measures.

3 December 2013 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
VSV. Ezhil Swanly
V. Ezhil Swanly
LSL. Selvam
L. Selvam
MKMohan Kumar
Mohan Kumar
JRJ. Arokia Renjith
J. Arokia Renjith
MAM. Arunachalam
M. Arunachalam
SHUNMUGANATHAN K LSHUNMUGANATHAN K L
SHUNMUGANATHAN K L
One third of the worlds population is thought to have been infected with mycobacterium tuberculosis (TB) with new infection occurring at a rate of about one per second. TB typically attacks the lungs. Indication of cavities in upper lobes of lungs shows the high infection. Traditionally, it has been detected manually by physicians. But the automatic technique proposed in this paper focuses on accurate detection of disease by computed tomography (CT) using computer-aided detection (CAD) system. The various steps of the detection process include the following: (i) image preprocessing, which is done by techniques such as resizing, masking, and Gaussian smoothening, (ii) image egmentation that is implemented by using mean-shift model and gradient vector flow (GVF) model, (iii) feature extraction that can be achieved by Gradient inverse coefficient of variation and circularity measure, and (iv) classification using Bayesian classifier. Experimental results show that its perfection of detecting cavities is very accurate in low false positive rate (FPR).