Kanimozhi Soundararajan
@kanimozhi@auist.net
Faculty and Department of Information Science and Technology
CEG Campus, Anna University, Chennai-25
EDUCATION
Ph.D (ICT)
M.Tech(IT)
B.Tech(IT)
RESEARCH INTERESTS
Machine Intelligence,
Computer Vision,
Image Processing,
Data Science,
Mobile Application Development
Scopus Publications
Scopus Publications
K. Muthulakshmi, N. Krishnaraj, R. S. Ravi Sankar, A. Balakumar, S. Kanimozhi, and B. Kiruthika
Computers, Materials and Continua (Tech Science Press)
S. Kanimozhi, N. Arun, A.Madhan Singh, S Shanthosh Kumar, and Tharanidharan T
IEEE
Preventive medical care relies on vaccinations to provide significant health benefits. Vaccination is an important and effective preventive health measure. There is no better way to reduce the risk of pandemic spread of SARS-CoV-2/COVID-19 than vaccination. As a preventive measure, the government has begun vaccinating Indians against Corona infection. It is therefore important, in addition to developing and supplying vaccines, that enough people are willing to obtain vaccines. However, of the populations worldwide, there are concerning proportions that are reluctant to get vaccinated. In order to end the pandemic, it is highly essential to deal with another omnipresent issue: outright rejection of vaccinations. To achieve population immunity first we have to find the non-vaccinated population should be detected and to this end, this project proposed an Aadhaar-based facial recognition system is used to find non-vaccinated citizen and alert them using Artificial Intelligence. Deep learning which is in the form of Convolutional Neural Networks (CNNs) are used to carry out the face recognition process and it is also proven to be an efficient method to carry out face recognition due to its high fidelity. A CNN is a Deep Neural Network (DNN), which is designed to perform challenging tasks like image processing, which is crucial for facial recognition. The CNN structure is composed of numerous layers of neurons that connect the neurons: an input layer, an output layer, and layers between these two layers. In the midst of the epidemic coronavirus outbreak (COVID-19), a person's current inoculation status will be updated based on face recognition to safeguard him/her from COVID-19 and it may also serve as proof of vaccination for other purposes. Facial recognition technology (FRT) along with the Aadhaar helps to authenticate people before entering into any types of service. This project provides COVID-19 immunization status, which is determined by observing at their face, and certify that they have been vaccinated.
S. Kanimozhi, T. Mala, A. Kaviya, M. Pavithra, and P. Vishali
Springer Singapore
Kanimozhi S, Anbarasi S, and Mythili M
IOS Press
Recognizing human action in sports is difficult task as various sequences of activities involved in every scene. Identifying each action individually without overlapping of movements is a tedious process due to continuous change of frames within short duration. So proper tracking of human movements for each action is important. Hence new structure-based human action recognition and tracker technique (HART) is proposed. It uses joint trajectory images and visual feature to design each human action. At first, a structural based method employed to extract human skeleton data points from RGB (Red Green Blue) videos. Next, a Multitude Object Tracker (MOT) is proposed which uses the trajectory of human skeleton joints in an image space for identification of actions. Then, Histogram of Oriented Gradients (HOG) combined with Support Vector Machine (SVM) is applied to extract physical body shape and action information. Finally, the action label and interconnected keypoints in humans is jointly detected as end result. The proposed HART technique effectively performed well with the accuracy of about 82% over the other activity recognition methods.
R. Velumadhava Rao, K. Selvamani, S. Kanimozhi, and A. Kannan
Wiley
In cloud environment, the importance of security for the outsourced data has increased much, since the data is maintained and controlled by the semi‐trusted third‐party cloud providers. Data Security is one of the major factors to be considered in group data sharing. Using the secret key, the entire file is encrypted directly in a conventional security framework; however, in a cloud‐based environment for group mechanism, this framework cannot be applied as there is a problem of key distribution. This research paper proposes an efficient hierarchical‐based group key mechanism for a cloud‐based environment. This proposed system relies on Key Distribution Server (KDS), which performs cryptographic key operations for securing the data in the cloud. Also, this system uses logical key hierarchy (LKH) protocol to maintain hierarchical tree for scalability. The group key is generated using the group member secret values and a secret value assigned by the KDS server. Performance analysis of this system shows that the proposed key management system is more efficient and much suitable for cloud environment.
S. Kanimozhi, A. Kannan, K. Suganya Devi, and K Selvamani
Wiley
There are lot of research works carried out in the field of Information Technology (IT), which have more impact on the education throughout the world. The main contribution from IT in today's education world is e‐learning. There are several institutions implemented the mechanism and several technologies of e‐learning in different countries. E‐learning provides more flexibility in education. Although there are several organizations and institutions had come up with the e‐learning system, the cost of investment involved for the infrastructure setup is much higher for e‐learning applications. Cloud Computing is one of the important technology, which provides different services, which plays a vital role in the education domain and e‐learning mechanism. In addition, the security factor in sharing the content is also much important nowadays as the content is shared among different countries with multiple source environments. In this paper, cloud‐based e‐learning is implemented using access control mechanism, which prevents the cloud resources from illegal user access. The key management schemes combined with access control technique is discussed for secure content sharing and to protect the e‐learning environment. The traditional e‐learning mechanism is compared with the cloud e‐learning for the better understanding of the cloud usage and advantages. Findings indicate that cloud‐based e‐learning utilizes cloud services in a secure way and also more flexible and scalable in accessing the e‐learning content.
S Kanimozhi, G Gayathri, and T Mala
IEEE
Real time object detection is one of the challenging task as it need faster computation power in identifying the object at that time. However the data generated by any real time system are unlabelled data which often need large set of labeled data for effective training purpose. This paper proposed a faster detection method for real time object detection based on convolution neural network model called as Single Shot Multi-Box Detection(SSD).This work eliminates the feature resampling stage and combined all calculated results as a single component. Still there is a need of a light weight network model for the places which lacks in computational power like mobile devices( eg: laptop, mobile phones, etc). Thus a light weight network model which use depth-wise separable convolution called MobileNet is used in this proposed work. Experimental result reveal that use of MobileNet along with SSD model increase the accuracy level in identifying the real time household objects.
M. Sindhuja, K. Selvamani, A. Kannan, and S. Kanimozhi
Elsevier BV
S. Kanimozhi, A. Kannana, K. Selvamani, and A. Vijay Kumar
Elsevier BV
M. Sindhuja, K. Selvamani, A. Kannan, and S. Kanimozhi
Elsevier BV
S. Chakaravarthi, K. Selvamani, S. Kanimozhi, and Pradeep Kumar Arya
IEEE
Web Service (WS) plays an important role in today's word to provide effective services for humans and these web services are built with the standard of SOAP, WSDL & UDDI. This technology enables various service providers to register and service sender their intelligent agent based privacy preserving modelservices to utilize the service over the internet through pre established networks. Also accessing these services need to be secured and protected from various types of attacks in the network environment. Exchanging data between two applications on a secure channel is a challenging issue in today communication world. Traditional security mechanism such as secured socket layer (SSL), Transport Layer Security (TLS) and Internet Protocol Security (IP Sec) is able to resolve this problem partially, hence this research paper proposes the privacy preserving named as HTTPI to secure the communication more efficiently. This HTTPI protocol satisfies the QoS requirements, such as authentication, authorization, integrity and confidentiality in various levels of the OSI layers. This work also ensures the QoS that covers non functional characteristics like performance (throughput), response time, security, reliability and capacity. This proposed intelligent agent based model results in excellent throughput, good response time and increases the QoS requirements.
R Elakkiya, K Selvamani, and S Kanimozhi
IEEE
Notice of Violation of IEEE Publication Principles “Hand Gesture Recognition Framework for Recognizing Sign Gestures and Handling Movement Epenthesis Using Level Building Nested Dynamic Programming Approach” by Elakkiya A., Selvamani K., Kanimozhi S. in the Proceedings of the IEEE 27th Canadian Conference on Electrical and Computer Engineering (CCECE), May 2014 After careful and considered review of the content and authorship of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE’s Publication Principles. This paper duplicated extensive amounts of text from the paper cited below. The original text was copied without attribution (including appropriate references to the original author(s) and/or paper title) and without permission. A. Elakkiya was solely responsible for the copied material. Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper, and future references should be made to the following article: “Enhanced Level Building Algorithm for the Movement Epenthesis Problem in Sign Language Recognition” by Ruiduo Yang, Sudeep Sarkar, Barbara Loeding in the Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2007 In this research paper, two crucial problems in continuous sign language recognition from unaided video sequences are considered. At the feature level, the problem of hand segmentation and grouping is considered and at the sentence level, the movement epenthesis problem is considered. A framework that can handle both of these problems based on an enhanced, nested version of the dynamic programming approach is constructed. To handle movement epenthesis problem, a nested version of a dynamic programming framework, called Level Building is used to simultaneously segment and to match signs from continuous sign language sentences. This approach is then coupled with a trigram grammar model to optimally segment and label sign language sentences. This approach will show improvement over past approaches in terms of the frame labeling rate and also our approach shows the flexibility when handling a changing context. The proposed approach is novel since it does not need explicit any models for movement epenthesis.
Elakkiya R, Selvamani K, and Kanimozhi S
IEEE
This paper proposes a new approach to solve the problem of real-time vision-based hand gesture recognition with the combination of hand posture and hand gesture analyses. The main objective of this is to divide the recognition problem into two levels according to the hierarchical property of hand gestures. This approach implements the posture detection with a statistical method based on Haar-like features and the dynamic approach for recognizing hand gestures using AdaBoost learning algorithm. With this proposed method, a group of hand postures is detected in dynamic video sequence with high recognition accuracy using boosted learning algorithm.
Pradeep Kumar Arya, K Selvamani, and S Kanimozhi
IEEE
Authentication and data privacy is an important aspect in Cloud computing. In this research work to ensure authentication and data privacy a Group Key Authentication (GKA) protocol is proposed and implemented. This defined protocol provides authentication and data privacy with reasonable authentication time and data reduce data traffic in the Cloud computing and simultaneously increases the Quality of Service (QoS). In addition, this work also aims in providing an access control based on group signatures in cloud based services. To achieve this access control scheme, a dual grand access control mechanism is formulated. This scheme will manage multi-groups and validate the group certificates of users in the cloud environment. Extensive evaluations have been carried out on the analytical model to verify the effectiveness and the correctness of the proposed system.
R. Elakkiya, K. Selvamani, and S. Kanimozhi
IEEE
The problem of vision-based sign language recognition, which is used to translate signs to English sentence, is addressed in this paper. A fully automatic system to recognize signs that starts with breaking up signs into manageable subunits is proposed. A framework for segmenting and tracking skin objects from signing videos is described. A boosting algorithm to learn a subset of weak classifiers for extracted features to combine them into a strong classifier for each sign is then applied. A joint learning strategy to share subunits across sign classes is adopted, which leads to a more efficient classification of sign gestures. Experimental results shown by the system demonstrate that the proposed approach is promising to build an effective and scalable system on real-world hand gesture recognition from continuous video sequences.
P.K. Arya, K. Selvamani, A. Kannan, and S. Kanimozhi
Institution of Engineering and Technology
The authentication is one of the important problems in Cloud computing environment. In this paper, a new Group Key Authentication (GKA) protocol is proposed. This protocol reduces the authentication time and data traffic in the Cloud computing and simultaneously increases the Quality of Service (QoS). Two additional aspects need to be addressed in cloud computing environment are load balancing and robustness. To solve these problems, mathematic grouping and heuristic grouping strategies are also proposed in this paper. In addition, it also describes a new access control policy based on group signatures in cloud service. To build this access control policy scheme, a double center access control model is designed. This scheme is able to manage multi-groups and validate the group certificates of users. Extensive evaluations have been conducted on the analytical model to verify the effectiveness and the correctness of our strategies.
Selvamani K, Anbuchelian S, Kanimozhi S, Elakkiya R, Bose S, and Kannan A
IEEE
The rapid proliferation of wireless ad-hoc networks and mobile computing applications has changed the landscape of network security. In this paper, we use hybrid approach that have both misuse and anomaly intrusion detection system using cross feature analysis for obtaining the trained data and test data from the trace file and to model the intrusion detection pattern. Apart from detection based on trace data, we proposed an innovative technique which operates through the implementation of battery consumption based detection on wireless ad-hoc networks by correlating attacks with their impact on device power consumption on the fly. The proposed system monitors power behavior to detect potential intrusions by noting irregularities of power consumption. This proposed and implemented work of the IDS using Network Simulator (NS-2) has achieved high detection rate and low false positive rate.
R. Elakkiya, K. Selvamani, S. Kanimozhi, Rao. Velumadhava, and A. Kannan
Elsevier BV
R. Elakkiya, K. Selvamani, S. Kanimozhi, Rao. Velumadhava, and J. Senthilkumar
Elsevier BV
RECENT SCHOLAR PUBLICATIONS
Publications
Kanimozhi, S., Gayathri, G., & Mala, T. (2019, February). Multiple Real-time object identification using Single shot Multi-Box detection. In 2019 International Conference on Computational Intelligence in Data Science (ICCIDS) (pp. 1-5). IEEE.
Kanimozhi, S., Mala, T., Kaviya, A., Pavithra, M., & Vishali, P. (2022). Key Object Classification for Action Recognition in Tennis Using Cognitive Mask RCNN. In Proceedings of International Conference on Data Science and Applications (pp. 121-128). Springer, Singapore.
Soundararajan, K. (2022). Sports highlight recognition and event detection using rule inference system. Concurrent Engineering, 1063293X221088353.
Sulthana, T., Soundararajan, K., Mala, T., Narmatha, K., & Meena, G. (2021, March). Captioning of Image Conceptually Using BI-LSTM Technique. In International Conference on Computational Intelligence in Data Science (pp. 71-77). Springer, Cham.