Ganesh E.N.

Dr. Ganesh E.N.

Department of Electronics and communication engineering, Sri Venkateswara College of Engineering, Chennai, Tamil Nādu, International
orcid

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
1 June 2024 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
MAMalothu Amru
Malothu Amru
RKRaju Jagadeesh Kannan
Raju Jagadeesh Kannan
Ganesh E.N.Ganesh E.N.
Ganesh E.N.
SMSurulivelu Muthumarilakshmi
Surulivelu Muthumarilakshmi
KPKuppan Padmanaban
Kuppan Padmanaban
SMSubbiah Murugan
Subbiah Murugan
The exponential advancements in recent technologies for surveillance become an important part of life. Though the internet of things (IoT) has gained more attention to develop smart infrastructure, it also provides a large attack surface for intruders. Therefore, it requires identifying the attacks as soon as possible to provide a secure environment. In this work, the network intrusion detection system, by applying the ensemble model (NIDSE) for Smart Homes is designed to identify the attacks in the smart home devices. The problem of classifying attacks is considered a classification predictive modeling using eXtreme gradient boosting (XGBoosting). It is an ensemble approach where the models are added sequentially to correct the errors until no further improvements or high performance can be made. The performance of the NIDSE is tested on the IoT network intrusion (IoT-NI) dataset. It has various types of network attacks, including host discovery, synchronized sequence number (SYN), acknowledgment (ACK), and hypertext transfer protocol (HTTP) flooding. Results from the cross-validation approach show that the XGBoosting classifier classifies the nine attacks with micro average precision of 94% and macro average precision of 85%.

21 June 2022 in Connection Science
Verified
Journal Article
Open access
RSR. Sudharsan
R. Sudharsan
Ganesh E.N.Ganesh E.N.
Ganesh E.N.
Owing to saturated markets, fierce competition, dynamic criteria, along with introduction of new attractive offers, the considerable issue of customer churn was faced by the telecommunication industry. Thus, an efficient Churn Prediction (CP) model is required for monitoring customer churn. Therefore, this work proposes a novel framework to predict customer churn through a deep learning model namely Swish Recurrent Neural Network (S-RNN). Finally, SRNN is adapted to classify the Churn Customer (CC) and a normal customer. If the result is a churn customer, network utilisation history is analysed for retention process. Whereas, the number of churn customers based on the area network usage is not recognised in this frameworkOwing to saturated markets, fierce competition, dynamic criteria, along with introduction of new attractive offers, the considerable issue of customer churn was faced by the telecommunication industry. Thus, an efficient Churn Prediction (CP) model is required for monitoring customer churn. Therefore, this work proposes a novel framework to predict customer churn through a deep learning model namely Swish Recurrent Neural Network (S-RNN). Finally, S-RNN is adapted to classify the Churn Customer (CC) and a normal customer. If the result is a churn customer, network utilisation history is analysed for retention process.

28 August 2024
Verified
Conference Paper
Closed access
CRChitra Sabapathy Ranganathan
Chitra Sabapathy Ranganathan
RSRajeshkumar Sampathrajan
Rajeshkumar Sampathrajan
MVM. Venkatesh
M. Venkatesh
Nilamadhab MishraNilamadhab Mishra
Nilamadhab Mishra
Ganesh E.N.Ganesh E.N.
Ganesh E.N.
SMS. Murugan
S. Murugan
Optimizing the building performance and component future has never been easier than integrating Internet of Things (IoT) sensors in building infrastructure. This technology has transformed fault detection and prognosis. This research provides a thorough method for defect identification and prognostics using Bayesian network (BN) modeling approaches and IoT sensors. Deploying a network of IoT sensors across the building's infrastructure is the first step in the method. These sensors will continually monitor metrics such as temperature, humidity, energy usage, and equipment health. Anomalies and deviations from typical operating circumstances may be detected by these sensors via their real-time data streams. Second, the data collected by the sensors will be analyzed using BN, which are a probabilistic graphical model to determine the potential of building infrastructure failures. To effectively diagnose and predict failures, BN makes it possible to describe complicated correlations among variables. The proposed method identifies problems, including equipment malfunctions, BVAC system breakdowns, and energy inefficiencies, by merging data from IoT sensors with BN analysis. It can predict when faults will arise, which helps with preventive maintenance and less downtime. It also includes a case study that shows how the method worked in a real-life situation involving building infrastructure, demonstrating how operating efficiency was improved and maintenance costs were reduced.

11 October 2023
Verified
Conference Paper
Closed access
RRRamakrishnan Raman
Ramakrishnan Raman
JPJohn Benito Jesudasan Peter
John Benito Jesudasan Peter
AGAtul A Gokhale
Atul A Gokhale
JMJ. Manikandan
J. Manikandan
Ganesh E.N.Ganesh E.N.
Ganesh E.N.
CSC. Srinivasan
C. Srinivasan
Distributed systems cannot achieve consistency, availability, and partition tolerance, according to Brewer's Rule (CAP theorem). Brewer's Rule affects distributed data warehouses. Brewer's Rule improves data warehouse architecture, according to this study. Database research Brewer's Rule reliability, accessibility, and tolerance for partitions. Consistency—the condition that all distributed system nodes access the same data simultaneously—is examined. Distributed transactions, two-phase commit, and consensus methods let data warehouses achieve consistency. A distributed system must be available even if some nodes fail, the study says. Replication, load balancing, and failover provide high availability in data warehouses. Finally, partition tolerance—the need for a distributed system to operate after network partitions—is examined. Data sharding, distributed caching, and data replication help data warehousing systems achieve partition tolerance. Brewer's Rule helps improve data warehouse architecture for use cases and business needs. The study also discusses trade-offs companies must make when improving consistency, availability, and partition tolerance. To maintain dependable and performant data warehousing solutions, organizations must balance these trade-offs. Organizations designing and implementing distributed data warehouses must consider Brewer's Rule. Organizations may construct high-performing, dependable data warehouse systems that fulfill their business needs by understanding how consistency, availability, and partition tolerance affect data warehouse architecture.

30 December 2015 in Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine
Verified
Journal Article
Open access
SKSenthilkumar Krishnamurthy
Senthilkumar Krishnamurthy
Ganesh E.N.Ganesh E.N.
Ganesh E.N.
URUmamaheswari Rengasamy
Umamaheswari Rengasamy
The three-dimensional analysis on lung computed tomography scan was carried out in this study to detect the malignant lung nodules. An automatic three-dimensional segmentation algorithm proposed here efficiently segmented the tissue clusters (nodules) inside the lung. However, an automatic morphological region-grow segmentation algorithm that was implemented to segment the well-circumscribed nodules present inside the lung did not segment the juxta-pleural nodule present on the inner surface of wall of the lung. A novel edge bridge and fill technique is proposed in this article to segment the juxta-pleural and pleural-tail nodules accurately. The centroid shift of each candidate nodule was computed. The nodules with more centroid shift in the consecutive slices were eliminated since malignant nodule’s resultant position did not usually deviate. The three-dimensional shape variation and edge sharp analyses were performed to reduce the false positives and to classify the malignant nodules. The change in area and equivalent diameter was more for malignant nodules in the consecutive slices and the malignant nodules showed a sharp edge. Segmentation was followed by three-dimensional centroid, shape and edge analysis which was carried out on a lung computed tomography database of 20 patient with 25 malignant nodules. The algorithms proposed in this article precisely detected 22 malignant nodules and failed to detect 3 with a sensitivity of 88%. Furthermore, this algorithm correctly eliminated 216 tissue clusters that were initially segmented as nodules; however, 41 non-malignant tissue clusters were detected as malignant nodules. Therefore, the false positive of this algorithm was 2.05 per patient.

18 August 2023
Verified
Conference Paper
Closed access
SSS. Srinivasan
S. Srinivasan
TST R Saravanan
T R Saravanan
JIJ. Vimala Ithayan
J. Vimala Ithayan
Ganesh E.N.Ganesh E.N.
Ganesh E.N.
ADA. Sangeerani Devi
A. Sangeerani Devi
This study investigates the potentially revolutionary role that the Internet of Things (IoT) may play in combating the urgent ocean pollution problem and promoting the growth of ecologically sound marine ecosystems. An approach that is data-driven has become essential in light of the fact that pollution poses a risk to the delicate balance of marine life and puts the future of the seas in jeopardy. The user can get real-time data on water quality, pollutant levels, and plastic trash dispersion if the user installs sensors and devices that the IoT enables. This will allow us to gain a greater knowledge of the patterns and causes of pollution. Using the plethora of information at people’s disposal, the system can develop innovative intervention tactics that successfully and efficiently combat ocean pollution. In addition, early warning systems powered by the Internet of Things might make it easier to respond quickly to oil spills, reducing the negative effects on the environment. This research highlights the importance of cooperation among stakeholders and underlines the need for public awareness and education to create changes in behavioral patterns. The adoption of technologies related to the Internet of Things is the most important step that can be taken to protect marine biodiversity and to create a brighter, more sustainable future for seas.