Kalpana Devi S
@rvu.edu.in
Assistant Professor , School of Computer Science and Engineering
RV University
EDUCATION
B.E(CSE) - 2004
M.Tech (CSE) - 2008
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Networks and Communications, Computer Engineering, Computer Science Applications, Artificial Intelligence
FUTURE PROJECTS
Networking
Applications Invited
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
S Kalpana Devi, R. Thenmozhi, and D. Sathish Kumar
IEEE
Developing Internet of Things (IoT) sensor networks across various use cases calls for effective failure detection and recovery systems. This research uses the Isolation Forest algorithm to provide a new method for autonomous defect detection and recovery in IoT sensor networks. The Isolation Forest algorithm, originally designed for anomaly detection, has been modified to locate and fix network problems. The suggested system can minimize downtime and provide continuous data collection by automatically recognizing abnormalities in sensor data and quickly initiating recovery methods. Intelligent decision-making procedures that dynamically rearrange the network to lessen the effect of errors enable self-healing capabilities. The results of the experiments show that the suggested method effectively improves the robustness of IoT sensor networks, opening up a viable path for autonomous fault management in the real world. This architecture significantly impacts the development of self-repairing IoT systems by responding to the pressing need for automatic fault diagnosis and repair in highly dynamic, hardly-resourced settings.
A.B. Feroz Khan, S. Kalpana Devi, and K. Rama Devi
ITMO University
In the recent years, the devices in Internet of Things (IoT) are growing exponentially due to the emergence of many sophisticated applications. This tremendous growth leads to serious security challenges and the devices of Wireless Sensor Networks should be protected from various attacks. IoT can be configured dynamically without fixed infrastructure and the devices are communicated with one another in an Ad-hoc manner. The work presents the classification of various DDoS attacks in the IoT environment and provides a solution for replay attack. All variations of DDoS attacks are modeled using UML based activity modeling. This clearly understands the behavior of each version of attacks and their performance in the environment. The modeling also helps to construct a solution to prevent this attack from its execution. The work also proposed a trust based protocol for replay attacks which allows the attack inside the network and blocks it after identifying the attack based on its specific behavior. The network performance is improved after implementing this proposed protocol inside the network with help of simulation under realistic conditions. The performance metrics considered in the work are energy, packet loss, computational time and throughput. The paper compares the performance with the state-of-the-art schemes such as Efficient Distributed Deterministic Key and Hash-based Message Authentication Code. The experimental analysis proved that the proposed scheme outperforms the other state-of-the-works in terms of computational cost, throughput, and delay.
A.B. Feroz Khan, Mohammed Muzaffar Hussain, S. Kalpana Devi, and M.A. Gunavathie
Elsevier BV
D. Sathish Kumar, R. Thenmozhi, and Kalpana Devi. S
IEEE
When vehicles in an ad hoc network are able to exchange data with one another and with infrastructure units along the road (V-V communication) via their driver information systems and internet connection, this improves overall road safety. The fast-paced nature of vehicle movement, the scarcity of available wireless resources, and the instability of the wireless channel make it difficult to establish successful multi-hop communication in a VANET. The authors of this work propose a strategy for intelligent forward routing that takes into account many criteria using fuzzy logic. “Our proposed method selects the greedy next node for data forwarding based on a combination of node stability cost and positive progress value.” In this case, For effective data transmission toward the destination, the node stability cost has been constantly analyzed using fuzzy logic based multi-criteria to choose the next hop ahead vehicle or road side units (RSUs). Criteria: Vehicle traffic density, Path link quality, Communication Range from current relay to neighbor, Vehicle Speed Difference, In order to choose the best next hop node for the relay, the link's expiry time and the node's positive movement toward the destination have been analyzed using fuzzy logic. For the purpose of framework evaluation, a fuzzy next hop forwarding system based on artificial intelligence has been made available. The simulation results have shown that the provided approach outperforms the currently used protocol. Improved packet delivery ratio, less need for next-hop selection, and shorter overall delays are the results.
A.B. Feroz Khan, Hannah Lalitha R, Kalpana Devi S, and Rajalakshmi CN
Elsevier BV
D. Sathish Kumar, R. Thenmozhi, and Kalpana Devi. S
IEEE
Modern Intelligent Transportation Systems (ITS) employ state-of-the-art technology to make possible an array of useful new services designed to improve the flow of people and products. For an ITS to be fully functional, in-vehicle ad hoc networks are an essential component (VANETs). In order to actualize the ITS services, every vehicle and Road Side Unit (RSU) in a Vehicular Ad-hoc network takes part in a communication. Considering that VANET nodes may be any sort of vehicle moving at any speed, the network's creation will be more dynamic, and the network's scalability will change continually. Routing is more difficult in urban areas than in rural areas because to the high traffic density, many impediments, and the dynamic nature of VANETs. We present a brief review of Delay and Non Delay tolerant protocols and taxonomy of routing to provide a broad understanding of VANETs. Lastly, we compare and evaluate a number of position-based routing systems to round off the paper.
Kalpana Devi S, Sharmila R, Soundharya S, and Suganthi R
IEEE
A safety system is necessary for the parents to take care of their infants in their work time too. This purpose caused the approach of the child care centers. Though they sense insecurity in those kinds of centers, the parents have no different way to proceed. So, we came up with a system to make certain the protection of the kids inside the toddler care centers or preschools. This system guarantees the children's safety with the help of a clever wearable card with the assistance of the Internet of things sensor network. It also offers a way to track the youngster within the school or child care areas. This wearable card design allows it to be handy and calls for little technological knowledge from the consumer. This device's goal is to assist parents track the youngster and ensure their safety even as they're under the control of the faculties or baby caretakers. This gadget works through the usage of sensor nodes to reveal the environment and handing over concurrent records to the database that was connected to the server within the cloud. An internet-based interface permits customers to get the data saved at the server. The system may also transmit emergency notifications to the person through a software application developed whenever an unauthorized person comes to pick up the child from these centers. Its cause is to allow verbal exchange among the parent or caretaker and the kid by way of knowing their real-time location. The kid's position has been traced with the usage of RFID in real-time. We reviewed relevant literature and tested the strategies used to reap similar but wonderful consequences.
S Kalpana Devi, K Samy Durai, Karthik M Shri Balaji, and J Ravi Kumar
IEEE
Blockchain has gotten a lot of publicity recently, and there are a lot of applications that have come out of it. The cryptocurrency, Bitcoin is a well-known Blockchain technology which effectively solves the double-spending issue, can validate the validity of transactional history without depending on a centralised framework to do the same. As a result, the application which uses Blockchain technology as its foundation guarantees that the data is tamper-free. The paper employs a decentralised Blockchain based proposal to verify that customers do not solely depend on retailers to decide whether or not goods are original. We define a decentralised Blockchain framework without fake goods, so that producers can use it to produce legitimate products without directly handling stores, lowering product quality assurance costs significantly.
S. Kalpana Devi, Amirthavarshini D, Anbukani R S, and Harini T K
IEEE
Due to the pandemic by the spread of the COVID virus, there has been a mandatory demand to screen patients. Predominantly RTPCR test is used to detect the virus. The RTPCR test is the most commonly used technique to detect COVID - 19 viruses. The test takes a minimum of 12 hours which is time-consuming and might put a patient's life at stake. This detection method for COVID screening is said to have a false detection rate. CT scans have been used for COVID-19 screening and using CT has several challenges especially since their radiation dose is considerably higher than x-rays. Hence, CXRs are a better choice for the initial assessment. Detection of COVID-19 pneumonia is a fine-grained problem as doctors cannot detect it just by looking at the x-ray images. Moreover, the radiologists visit many patients every day and the diagnosis process take significant time, which may increase errors in screening notably. Therefore, a medical decision support system for screening COVID-19 patients is of utmost importance. Our proposed system is a web application that helps to screen COVID-19 patients effectively.
S Kalpana Devi, D Amirthavarshini, RS Anbukani, and S Bhavatha Ranjanni
IEEE
Alzheimer’s disease is a gradual brain disorder and an irremediable disease that slowly destroys memory and thinking skills. The contemporary solution for this disease includes forums for discussion, behavioural monitoring, and path sensing. The proposed solution is to create an application that acts as personal assistance to the patients. The features include face recognition, wandering and fainting detection, assistance to find a way home, reminders to daily chores and past life, organizing , and planning jobs. This can be implemented by using the sensors and GPS in smartphones to sense the actions of the patients. Deep learning and machine learning using python can be applied in android studio along with google maps. The games in the application that are specifically designed for the patient help them in the initial stage of the disease. Memory is improved by learning and making the brain engaged in some activity as it connects brain cells. The new feature in the application is face recognition, where the patient gets a reminder of persons they have met. This helps the patient to overcome the difficulties in recognizing people.
Ms. Geetha A, , Dr. S. Sobitha Ahila, Ms. V.S.Vidhya Lakshmi, Ms. S. Kalpana Devi, , , and
Blue Eyes Intelligence Engineering and Sciences Engineering and Sciences Publication - BEIESP
Cloud computing is the on-demand availability of computer system resources, particularly data storage and computing power, without direct active management by the user. Here an online organ donation system is developed with the help of the aforementioned technologies. The main aim of the paper is to make sure that the organs of the people, who have come forward to donate, reach the respective individual in need of the particular organ. Since everything is stored in the cloud, anybody can access it anytime, which in turn puts the data at risk. The secured sharing of donor detail is necessary. Encryption is done at two levels to provide security, one while the data is entered and the other done by a third party providing proxy re-encryption. Now, whenever a brain-dead patient is in the hospital, after thorough verification for any complications, the deciding parameters such as the organs that can be transplanted, blood group, presence of HIV positive and location, is compared with the cloud database using query filtering, which results in the nearest organ donor available meeting the requirements. The performance enhancement of cloud data using encryption schemes is of high potential.