Subbiah Janakiraman

Subbiah Janakiraman

Auto-generated profile, based on publicly available information

Subbiah Janakiraman

Pondicherry University

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
1 September 2016 in Expert Systems with Applications
Verified
Journal Article
Closed access
SGS. Gunasundari
S. Gunasundari
SJS. Janakiraman
S. Janakiraman
SMS. Meenambal
S. Meenambal

1 December 2018 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Closed access
GSGunasundari S
Gunasundari S
SJS. Janakiraman
S. Janakiraman
SMS. Meenambal
S. Meenambal

7 July 2016 in SpringerPlus
Verified
Journal Article
Open access
PDF file
GDGayathri Dhananjayan
Gayathri Dhananjayan
JSJanakiraman Subbiah
Janakiraman Subbiah
Secure data transfer against the malicious attacks is an important issue in an infrastructure-less independent network called mobile ad-hoc network (MANET). Trust assurance between MANET nodes is the key parameter in the high-security provision under dynamic topology variations and open wireless constraints. But, the malicious behavior of nodes reduces the trust level of the nodes that leads to an insecure data delivery. The increase in malicious attacks causes the excessive energy consumption that leads to a reduction of network lifetime. The lack of positional information update of the nodes in ad-hoc on-demand vector (AODV) protocol during the connection establishment offers less trust level between the nodes. Hence, the trust rate computation using energy and mobility models and its update are the essential tasks for secure data delivery. This paper proposes a trust-aware ad-hoc routing (T2AR) protocol to improve the trust level between the nodes in MANET. The proposed method modifies the traditional AODV routing protocol with the constraints of trust rate, energy, mobility based malicious behavior prediction. The packet sequence ID matching from the log reports of neighbor nodes determine the trust rate that avoids the malicious report generation. Besides, the direct and indirect trust observation schemes utilization increases the trust level. Besides, the received signal strength indicator utilization determines the trusted node is within the communication range or not. The comparative analysis between the proposed T2AR with the existing methods such as TRUNCMAN, RBT, GR, FBR and DICOTIDS regarding the average end-to-end delay, throughput, false positives, packet delivery ratio shows the effectiveness of T2AR in the secure MANET environment design.

27 August 2021 in Wireless Personal Communications
Verified
Journal Article
Closed access
PDF file
KTKalaipriyan Thirugnanasambandam
Kalaipriyan Thirugnanasambandam
RRRaghav RS
Raghav RS
DADinesh Kumar Anguraj
Dinesh Kumar Anguraj
DSD. Saravanan
D. Saravanan
SJS. Janakiraman
S. Janakiraman

8 October 2022 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
SJS. Janarthanan
S. Janarthanan
TKT. Ganesh Kumar
T. Ganesh Kumar
SJS. Janakiraman
S. Janakiraman
Rajesh Kumar DhanarajRajesh Kumar Dhanaraj
Rajesh Kumar Dhanaraj
MSMohd Asif Shah
Mohd Asif Shah
A significant amount of effort and cost is required to collect training samples for remote sensing image classifications. The study of remote sensing and how to read multispectral images is becoming more important. High-dimensional multispectral images are created by the various bands that show how materials behave. The need for more information about things and the improvement of sensor resolutions have led to the creation of multispectral data with a higher size. In recent years, it has been shown that the high dimensionality of these data makes it hard to preprocess them in multiple ways. Recent research has demonstrated that one of the most crucial methods to address this issue is by adopting a variety of learning strategies. But as the data gets more complicated, these methodologies are not adequate to support. The proposed methodology shows that the classification experiment using remote sensing images indicates the maximum likelihood classifier with different deep learning models; weight vector (WV) AdaBoost and ADAM can greatly limit overfitting, and it obtains high classification accuracy. Proposed VGG16 and Inception v3 increase classification accuracy along with optimization process produce 96.08.

26 February 2019 in Journal of Testing and Evaluation
Verified
Journal Article
Closed access
DSD. Saravanan
D. Saravanan
SJS. Janakiraman
S. Janakiraman
KCK. Chandraprabha
K. Chandraprabha
TKT. Kalaipriyan
T. Kalaipriyan
RRR. S. Raghav
R. S. Raghav
SVS. Venkatesan
S. Venkatesan
Following an investigation undertaken by the publisher, we have determined that this paper was accepted on the basis of a compromised peer review process. We hereby retract the paper. The corresponding author has been notified of the retraction. The retraction statement can be found here: https://doi.org/10.1520/JTE20259998. This article focuses on roadside unit (RSU) deployment based on the analysis of aggregation delay causes between the accident-occurring location and the nearby RSU. Information aggregation in vehicular ad hoc networks using RSU is one of the phenomenal concepts that look ahead in today’s recent advancements, since the consistency in aggregation and dissemination of data in a volatile network is high when compared with vehicle to vehicle communications. Deploying the RSU as appropriate in rural areas is cost-sensitive since the collection of information is not up to the mark when compared with urban regions. A mathematical model called Powell’s Method and a bioinspired algorithm, namely krill herd algorithm, have been hybridized and proposed in this research article for effective RSU deployment. The proposed algorithm has been tested under three different road maps, and the consistency of the algorithm has been evaluated under appropriate performance measures.