E. Poovammal

Prof. Dr. E. Poovammal


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
14 October 2016 in Indian Journal of Science and Technology
Verified
Journal Article
Open access
PDF file
VSV. Sellam
V. Sellam
EPE. Poovammal
E. Poovammal
Prediction of Crop Yield using Regression Analysis

19 January 2022 in IEEE Access
Verified
Journal Article
Open access
RDR. Durga
R. Durga
EPE. Poovammal
E. Poovammal
RKRamana Kadiyala
Ramana Kadiyala
RJRutvij H. Jhaveri
Rutvij H. Jhaveri
Saurabh SinghSaurabh Singh
Saurabh Singh
Byungun YoonByungun Yoon
Byungun Yoon
With the advent of the Internet of Things (IoT), smart devices have now changed their dimensions to provide applications in different domains such as medical, agriculture, and Industry 4.0. Although IoT provides more diversified applications, enhancing the security in IoT remains on the darker side of the research. Traditional IoT systems involve a third party to secure sensitive data during transmission in an IoT environment which can lead to complex and serious problems. To overcome security issues and eradicate third-party involvement, Blockchain technology is the modern-day solution in an IoT environment. In the context of a Secured IoT system, we proposed a novel chaotic encryption-based blockchain-IoT architecture to clinch the security and privacy of data. Since smart sensors and image sensors are used widely in an IoT environment, the proposed scheme was tested with different image sets to evaluate performance metrics such as Number of Pixel Change Rate (NPCR), Unified Averaged Changed Intensity (UACI), Correlation Coefficients, and entropy under different attack scenarios. We obtained an NPCR of 99.65%, a UACI of 34%, and an entropy value close to 8. These values incite that the novel chaotic encryption-based blockchain-IoT architecture will be safe from IoT attacks. Results showed that integrating chaotic encrypted blockchain architecture with IoT could be more effective in defending attacks.

1 January 2016 in Procedia Computer Science
Verified
Journal Article
Open access
JDJ. Chitra Devi
J. Chitra Devi
EPE. Poovammal
E. Poovammal
In the field of research, Social Network Analysis is prevalent domain which pulls the attention of many data mining experts. Social network analysis is the specific field of sociology and anthropology. It shares a number of characteristics common to real network. Some real networks like Facebook, Twitter exhibit the concept of community structure within the network. Social network is represented as a network graph. Detecting the communities involves finding the densely connected nodes. Overlapping communities are possible if a node is a member of more than one community. This paper discusses various modularity based approaches on detecting the overlapping communities in the social networks. This work aims in providing the characteristics and limitations of modularity based overlapping community detection algorithms

23 September 2021 in IEEE Access
Verified
Journal Article
Open access
BSB. Sowmiya
B. Sowmiya
EPE. Poovammal
E. Poovammal
RKRamana Kadiyala
Ramana Kadiyala
Saurabh SinghSaurabh Singh
Saurabh Singh
Byungun YoonByungun Yoon
Byungun Yoon
Cloud computing is a continuously evolving technology that can enhance agility, availability, collaboration and scalability of data. Blockchain has a secure, immutable ledger which maintains all the transactions along with the timestamp. The blockchain framework and cloud computing technology jointly provides different ways of computational cost reduction. The existing methods help to identify the anonymous documents which are given in the form of requests from the cloud server. If the anonymized document requests are from the authorized users, then cloud provides better security and hence documents are not available for unauthorized users. But the main issue is access rights available for authorized users on sensitive data of the owner. To maintain the privacy the sensitive data are hidden using cryptographic techniques even for authorized users. The method adopted is Linear Elliptical Curve Digital Signature (LECDS) with Hyperledger blockchain, to prevent private data loss. The Linear regression method is used to classify the user information into two classes namely sensitive and non-sensitive. The non-sensitive data is encrypted using RSA and sensitive data is encrypted using LECC method. Modified Spider optimization search Algorithm (MSOA) is used to verify the integrity of outsourced data and search user query information in a cloud server. The hyper ledger blockchain verifies the user policy to create a private network through which the user communicates the cloud. In the analysis of the proposed method, the results are evaluated using various performance metrics such as security, throughput, classification accuracy and error rate.

30 August 2019 in International Journal of Engineering and Advanced Technology
Verified
Journal Article
Closed access
ADAditi
Aditi
MNMayank Kumar Nagda
Mayank Kumar Nagda
EPE. Poovammal
E. Poovammal
This work elaborates on the integration of the rudimentary Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM), resulting in a new paradigm in the well-explored field of image classification. LSTM is one kind of Recurrent Neural Network (RNN) which has the potential to memorize long-term dependencies. It was observed that LSTMs are able to complement the feature extraction ability of CNN when used in a layered order. LSTMs have the capacity to selectively remember patterns for a long duration of time and CNNs are able to extract the important features out of it. This LSTM-CNN layered structure, when used for image classification, has an edge over conventional CNN classifier. The model which has been proposed is based on the sets of Artificial Neural Network like Recurrent and Convolutional neural network; hence this model is robust and suitable to a wide spectrum of classification tasks. To validate these results, we have tested our model on two standard datasets. The results have been compared with other classifiers to establish the significance of our proposed model.

2 October 2021 in Water
Verified
Journal Article
Open access
PDF file
ACAswathy K. Cherian
Aswathy K. Cherian
EPE. Poovammal
E. Poovammal
NPNinan Sajeeth Philip
Ninan Sajeeth Philip
RKRamana Kadiyala
Ramana Kadiyala
Saurabh SinghSaurabh Singh
Saurabh Singh
IRIn-Ho Ra
In-Ho Ra
Under-water sensing and image processing play major roles in oceanic scientific studies. One of the related challenges is that the absorption and scattering of light in underwater settings degrades the quality of the imaging. The major drawbacks of underwater imaging are color distortion, low contrast, and loss of detail (especially edge information). The paper proposes a method to address these issues by de-noising and increasing the resolution of the image using a model network trained on similar data. The network extracts frames from a video and filters them with a trigonometric–Gaussian filter to eliminate the noise in the image. It then applies contrast limited adaptive histogram equalization (CLAHE) to improvise the image contrast, and finally enhances the image resolution. Experimental results show that the proposed method could effectively produce enhanced images from degraded underwater images.