KKKavitha Kanagaraj

Kavitha Kanagaraj

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kavitha Kanagaraj has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hybrid MWGSO: Developing Hybrid Heuristic Algorithm for Energy Efficient D2D Communication System with Optimal Resource Allocation

    by K. Jasmine, K. Kavitha

    Device-to-Device (D2D) communication is said to be a highly demanded network technology to efficiently cope with content sharing between network users. It is used to provide direct communication among the devices and enhances spectral efficiency with the reuse of licensed cellular spectrum. Simultaneously, the respective communication spectrum is changing to be less in amount and observed as scarcer. The complex and heterogeneous ability of the system having various technological scenarios leads to vital difficulties for managing the wireless resource that enables the researchers to focus on the radio resource optimization as the significant perspective in D2D communication systems. In addition, the challenges related to energy consumption and spectrum resource shortage occurred at the time of communication. To combat all the issues, a novel energy-efficient model is proposed using a hybrid algorithm for D2D communication. The key scope of the developed method is to allocate the resources appropriately which will increase energy efficiency. In the Non-Orthogonal Multiple Access (NOMA), the resources are required to be allocated for performing the communication. Here, the resources are optimized by infusing the hybrid-based optimization algorithm. The hybrid algorithm is developed and named Modified Whale Glowworm Swarm Optimization (MWGSO). While optimizing the resources, the developed methodology helps to maximize energy efficiency. Thus, an energy efficiency optimization scheme is deployed to provide better D2D pairs of wireless communication. Finally, the result shows the proposed model achieves the enhancement of energy efficiency by using optimal resource allocation. Hence, it offers the desired results when compared with classical methodologies.

  • Real-Time Anomalous Event (Crime) Detection Using MGFN and YOLO

    by R. Dhivya Praba, K. Kavitha, S. N. Shivappriya, P. Karthik, P. Kausik, E. Dhaneshvar

  • Hybrid AI‐Driven Bio‐Inspired Wearable Sensors With Aquasense AI Technology for Multimodal Health Monitoring and Rehabilitation in Dynamic Environments

    by J. Poongodi, K. Kavitha, S. Sathish, R. Lakshmana Kumar

    AquaSense AI is a bio‐inspired, wearable sensor system that enables a paradigmatic shift in healthcare and physiotherapy, emulating nature's sensory capabilities of aquatic animals. Flexible, waterproof sensors are used to detect human motion, balance, and posture on land and in water. AquaSense AI is perfect for application in swimming pools and hydrotherapy sessions. AquaSense AI delivers real‐time, high‐precision feedback to enable effective rehabilitation, fall prevention, and fitness monitoring. In Under water, these sensors follow a person's posture and the coordination of their limbs through the detection of pressure changes, while on land, they monitor gait, posture, and balance. The sophisticated AI algorithms within the system, including Hierarchical Adaptive Neural Network (HANN) and Multimodal Self‐Learning Framework, adjust sensor sensitivity to the environment and provide personalized feedback over time, continuously adapting to the movements and rehabilitation progress of the user. The bio‐inspired design, adaptive AI, and real‐time predictive analytics can provide dual functionality at clinical and fitness applications, improving safety, rehabilitation outcomes, and general health monitoring in diverse environments.


  • Open Access

    Implementation Challenges and Opportunities in the Outcome-Based Education (OBE) for Teaching Engineering Courses: A Case Study

    by K. Kavitha, K. Karthika

    Outcome-based education is a closed-loop control system accepted globally for enhancing the teaching-learning processes. However, the success of the system is not prominently visible in fresh graduates. Hence detailed research and optimal process to implement OBE is necessary. This paper aims to investigate the challenges in implementing Outcome-based education and explores opportunities for improvement. Further, pedagogic planning for the analytical subjects has been proposed and the performance of the proposed method is analyzed using a case study. Performance improvement in Course Outcome attainments of the course Antennas and Wave Propagation, offered for undergraduate engineering (ECE) students have been investigated and evaluated in this paper. The investigation shows that dynamically adapting the teaching-learning and assessment methods during the course based on the assessments of the student’s capabilities results in improved performance. The following changes in the system have been suggested for the optimal implementation of OBE. The CO targets for the current semester course should be fixed based on the CO attainment of the previous semester courses of the same batch instead of the traditional way of fixing CO attainment targets. The microanalysis of the end-semester marks and students’ feedback at the ratio of 5:1 may be considered for overall CO attainment computation at the end of the course.


  • Open Access

    Healthcare internet of things (HIoT) data management using block chain technology for enhanced security

    by J. Poongodi, K. Kavitha, S. Sathish

    Data security on the basis of block chains is one among the most intensively researched fields in the recent age. Using blockchain platform, the security associated with the HIoT data may be improved. Nevertheless, various security measures for distinct services necessitate the use of keys in order to complete the procedure. To circumvent this restriction, this research paper presents a HIoT block chain platform that uses Ethereum block chain technology to assure data security. The suggested approach combines low-power HIoT devices with block chain to ensure that medical personnel have safe access to data. The data acquired from IoT devices is sent to an Ethereum node, while the user data is sent to the cloud. So that after the data access request has been received from the client, the user information can be validated using cloud data, and healthcare data may be accessed from the Ethereum node. Extra cryptography approaches are avoided, and data security is improved, thanks to the easy and quick process.

  • Open Access

    Ultra-Low Power Memory Circuit Unit for Space Application

    by S.P. Karthi, K. Kavitha, Ganesh Babu, J R Dinesh Kumar, C Visvesvaran, N Girinath

    In VLSI design power dissipation is an important factor in micro and nano VLSI design. For Space applications, Circuits with Ultralow power (ULP) operation is a good solution because of its limited options of energy sources. This Ultralow power operation will pay the way to small and low-cost satellites where the heavy battery and power supplies can be replaced. One of the effective way to implement ULP operations are by restricting the VDD and make the circuit to work in sub threshold region. But at the same time this low voltage circuits have some challenges like delay, temperature fluctuations needs to be addressed. The most complicated area of these circuits are memory arrays which cover large areas of the silicon die which often store critical data. Large bit cells leads to hardening of embedded memory block cells and this limits the low power operation of the entire system. In this paper, radiation-hardened static random access memory (SRAM) bit cell targeted at low-voltage functionality is proposed. The proposed method employs 5T RAM cell bears changes in charge deposits as high as 500 fC at a scaled 500-mV supply voltage.


  • Multilevel spatial modulation

    by K. Kavitha, H. Mangalam

    In this paper, a new Multilevel Spatial Modulation technique is proposed. It combines computationally efficient multilevel oding and spatial modulation based on trellis codes to increase coding gain, diversity gain, and bandwidth efficiency. The trellis complexity of the single-stage system increases exponentially, whereas in the proposed multilevel system the complexity increases linearly. The proposed system is analyzed with optimal Viterbi and suboptimal sequential decoding algorithms. The results show that sequential decoding saves 75% of the computational power with a loss of 2 dB SNR approximately, when compared with optimal Viterbi decoding, over both fast- and slow-fading channel conditions. Since the antenna index is used as a source of information in spatial modulation, the number of antennae required increases with the throughput and packing a large number of antennas make cross-correlation unavoidable. In this paper, a low complexity modified decoding technique is also proposed for the multilevel spatial modulation system, in which the correlated received signals are equally combined and decoded by the multistage decoder using the Viterbi algorithm. This technique exploits the receiver antenna correlation and makes the decoding complexity independent of number of antennas. The simulation results indicate that the proposed low complexity algorithm gives approximately 8–10 dB gain when compared with optimal Viterbi decoder with equivalent computational complexity when the eight highly correlated signals are equally combined. This may be a suitable solution for mobile handsets where size and computational complexity are the major issues.