Dr. Prajna Parimita Dash

@bitmesra.ac.in

Assistant Professor, Department of Electronics and Communication Engineering
birla institute of technology

Dr. Prajna Parimita Dash


                  Download Compact PDF  
https://researchid.co/prajnaparimitadash

EDUCATION

Qualification Name of The School/Institute/Board/University Year of passing Percentage of Mark
PhD National Institute of Technology , Rourkela Oct-2017 8.6 CGPA
M-Tech S ‘O’ A University,Bhubaneswar, 2009 8.13 CGPA
BTech J.I.E.T, Cuttack, BPUT, Orissa 2005 72 %
C.H.S.E Women’s college, Bargarh 2000 60%
H.S.C Govt. Girl’s High School, Bargarh,Orissa 1998 78%

RESEARCH, TEACHING, or OTHER INTERESTS

Signal Processing, Artificial Intelligence, Electrical and Electronic Engineering, Computer Vision and Pattern Recognition
30

Scopus Publications

Scopus Publications

  • Development of a Neurofeedback System for Movement Imagery-Based BCI
    Manoj Kumar Mukul, Ayush Chandra, Prajna Parimita Dash, Aminul Islam
    Ssrg International Journal of Electronics and Communication Engineering, 2026
    In recent decades, Brain Research–Computer Interfaces (BCIs) based on Electroencephalograms (EEGs) have become a crucial area of study, particularly for enabling real-time control of electric wheelchairs for individuals with disabilities. A most commonly used approach for this purpose is Movement Imagery (MI). Researchers have proposed various techniques to improve classification accuracy, focusing on effective preprocessing and feature extraction methods for real-time classification of movement imagery. This paper investigates the effectiveness of Empirical Mode Decomposition (EMD) as a preprocessing technique to decompose raw EEG signals into Intrinsic Mode Functions (IMFs) and evaluates suitable power spectrum estimation methods. Different rhythmic bands of the raw EEG signals are selected for EMD decomposition. The resulting IMFs are then used to estimate power spectral density using parametric (Burg method) and non-parametric (Welch method) approaches. The analyzed feature is the average power within the rhythmic bands of the selected IMFs. The outcomes of this study have multiple observations. The reported results indicate that the Welch method outperforms the Burg method, achieving overall classification accuracy that is more than 1% higher. Additionally, the proposed methods achieve good classification accuracy on standard movement imagery datasets but fail to match the performance of BCI-illiterate subjects. Based on this analysis, the authors conclude that signal processing and feature extraction methods alone are insufficient to achieve high classification accuracy, emphasizing that users of BCI technology require proper training.
  • Deep learning approaches for detecting malignant melanoma in dermoscopic imagery
    Abhishek Thakur, Sudhansu Kumar Mishra, Monica Bhutani, Prajna Parimita Dash, Prabhat Kumar Upadhyay, Sitanshu Sekhar Sahu
    International Journal of Information Technology Singapore, 2026
  • Enhancing non-orthogonal multiple access systems: A reconfigurable Machine Learning classification approach
    Saurabh Srivastava, Rampravesh Kumar, Prajna Parimita Dash
    Engineering Applications of Artificial Intelligence, 2025
    Non-Orthogonal Multiple Access (NOMA) is being considered as a Multiple Access (MA) technique for the next-generation systems, due to factors such as a high per-user spectral resource allocation, grant-free transmission, support for millimeter Waves (mmWaves) and massive-MIMO (mMIMO). A practical limitation of the NOMA systems is imperfect Successive Interference Cancellation (SIC); and the involved decoding delay. This work develops a data-driven Machine Learning (ML) model providing the functionality of a SIC receiver. While most of the Deep Learning (DL) algorithms have high complexity and training times, the given ML approach utilizes the received symbol as the only primary predictor. The other two predictors are derived from the primary predictor, and utilized for the Power-Domain (PD)-NOMA symbol-decoding process. The model utilizes a developed low-complexity NOMA-ML-based Decoder (MLbD) dataset for the same. The extensive test simulations confirm the reconfigurable ML-based receiver to be at par with the existing Maximum Likelihood (MLH) decoder in terms of decoding accuracy. Still, the former supports its integration into the next-generation systems due to its reconfigurable nature and removes the drawbacks related to SIC in the NOMA systems.
  • Secure Image Encryption with Optimized Chaotic Sequences and Multi-layer Cryptographic Operations
    Jagannath Sethi, Sudhansu Kumar Mishra, Prajna Parimita Dash, Monica Bhutani
    SN Computer Science, 2025
  • GAN-CNN based Structure-Preserving Mixed Noise Removal Model for Enhancing Medical Image
    Vishal H Shah, Prajna Parimita Dash
    Journal of Scientific and Industrial Research, 2025
    The current era of the Internet of Medical Things (IoMT) and Medical Artificial Intelligence (MAI) makes medical imaging a prominent mode of providing effective solutions in diagnosis and prognosis. The main issue with these images is the presence of noise that requires enhancement through effective edge preservation and noise reduction. The proposed work introduces a two-stage Deep Learning (DL) model, utilizing Generative Adversarial Networks (GANs) and Convolutional Neural Networks (CNN) for jointly reducing speckle, impulse, and Gaussian noise while preserving edge information in noisy medical images. The work also explores the probabilistic evaluation of generators and discriminators for compensating lossy patches to ensure image quality. The performance of the proposed model is investigated by considering three different performance metrics, namely, PSNR, FSIM, and SSIM. Moreover, non-parametric statistical tests like the Sign test, Wilcoxon Signed rank tests and Friedman tests are also conducted to assess the dominance of the proposed model over other state-of-the-art approaches. Two-stage GAN-based models generate realistic, high-quality images by effectively suppressing inherently present spurious noise in medical images and simultaneously preserving the edge information.
  • Global perspectives on digital twin adoption in healthcare
    Saurabh Srivastava, Prajna Parimita Dash
    Digital Twin Technology for Better Health A Healthcare Odyssey, 2025
    Digital twins (DTs) represent a cutting-edge technological advancement, creating virtual models of physical objects, systems, or any processes that mirror their real-world counterparts throughout their lifecycle. Initially developed by NASA for space exploration, DT technology has since expanded into various industries, notably healthcare, where it is revolutionizing patient care, hospital management, and medical device optimization. Chapter 11 explores the evolution, application, and prospects of DTs within the healthcare sector. This chapter begins by tracing the origins of DTs, from their early use in the Apollo-13 mission to their formal conceptualization in the mid-2000s. It then delves into the current applications of DTs in healthcare, highlighting their role in enhancing operational efficiency, personalizing treatment plans, and predicting patient outcomes. The integration of the Internet of Things (IoT), artificial intelligence (AI), and big data analytics is highlighted as a key enabler of DT technology, allowing for real-time data collection, processing, and analysis. Despite their transformative potential, the implementation of DTs in healthcare is not without challenges. This chapter addresses key obstacles such as data integration, regulatory and ethical concerns, and the need for interoperability among diverse healthcare systems. It also examines the resource-intensive nature of DT development and the importance of clinical validation to gain the trust of healthcare professionals. Looking ahead, this chapter identifies exciting opportunities for DTs in personalized medicine, early disease detection, virtual clinical trials, and remote patient monitoring. It concludes with an analysis of global adoption trends, projecting significant market growth and increased investment in DT technology over the coming decade. As the healthcare industry continues to evolve, DTs are poised to become indispensable tools in improving patient outcomes and optimizing healthcare delivery.
  • Entropy Enhanced Bilateral Filter for Denoising Medical Images with Variable Region of Interest
    Dikshant Vats, Sunny Kumar, Tanmay Arora, Vishal H. Shah, Prajna Parimita Dash
    Lecture Notes in Networks and Systems, 2025
  • Low Resolution Medical Image Enhancement using Generative Artificial Intelligence
    Vishal H Shah, Abhishek Kumar Mishra, Nilanshu Chandra, Shivam Kumar, Prajna Parimita Dash
    3rd International Conference on Intelligent Data Communication Technologies and Internet of Things Idciot 2025, 2025
    Accurate diagnosis through medical image data is the base of proper prognosis in healthcare, which requires high-quality medical image. Enhancement of various low-resolution medical images in healthcare needs attention. The research addresses the challenge of generating high-resolution images from low-resolution inputs, a critical difficulty in picture super-resolution. Super-Resolution GAN (SRGAN), which enhances image quality through perceptual loss to produce visually realistic and high-resolution outputs, has been employed. Through experiments and evaluation, we demonstrated the effectiveness of SRGAN compared to other variants of GAN in producing realistic, high-resolution images, showcasing the advancements made in image generation tasks using GANs.
  • Constellation design for PD-NOMA-based mmWave inter-satellite communication
    Saurabh Srivastava, Prajna Parimita Dash, Deepak Kumar Rout, Dinesh Madhukar Chandwadkar, Sunita Pandit Ugale
    Computers and Electrical Engineering, 2024
  • Two stage self-adaptive cognitive neural network for mixed noise removal from medical images
    Vishal H Shah, Prajna Parimita Dash
    Multimedia Tools and Applications, 2024
  • GP-based fair power allocation for 6G multi-user power domain NOMA network
    Saurabh Srivastava, Prajna Parimita Dash
    Journal of Ambient Intelligence and Humanized Computing, 2024
  • ML-based reconfigurable symbol decoder: An alternative for next-generation communication systems
    Saurabh Srivastava, Prajna Parimita Dash
    Engineering Applications of Artificial Intelligence, 2022
  • Decisive Analysis of Fixed Power Allocation Coefficients in a PD-NOMA Network
    Saurabh Srivastava, Prajna Parimita Dash, Sanjay Kumar
    Proceedings of 4th International Conference on Cybernetics Cognition and Machine Learning Applications Icccmla 2022, 2022
  • Coefficient-Scaling-Based Fair Power Allocation for Multi-User Power-Domain Nonorthogonal Multiple Access Network
    Saurabh Srivastava, Prajna Parimita Dash
    Journal of Circuits Systems and Computers, 2021
  • Interactive teaching learning based optimization technique for multiple object tracking
    Prajna Parimita Dash, Sudhansu Kumar Mishra, Kishore Kumar Senapati, Ganapati Panda
    Multimedia Tools and Applications, 2021
  • Capacity analysis of non-orthogonal multiple access for uplink and downlink
    Saurabh Srivastava, Prajna Parimita Dash, Sanjay Kumar
    Journal of Mobile Multimedia, 2021
  • Non-Orthogonal Multiple Access: Procession towards B5G and 6G
    Saurabh Srivastava, Prajna Parimita Dash
    IEEE 2nd International Conference on Applied Electromagnetics Signal Processing and Communication Aespc 2021 Proceedings, 2021
  • Identification of real-time maglev plant using long-short term memory network based deep learning technique
    Journal of Scientific and Industrial Research, 2020
  • An efficient hybrid framework for visual tracking using Exponential Quantum Particle Filter and Mean Shift optimization
    Prajna Parimita Dash, Dipti Patra
    Multimedia Tools and Applications, 2020
  • Analysis of NOMA: In capacity domain
    International Symposium on 5g Beyond for Rural Upliftment 2020 in Twinning Activity Between BIT Sindri Iit Ism Dhanbad Jointly with the IEEE 5g Summit and 35th Gisfi Standardization Series Meeting Gssm, 2020
  • Animal tracking in wildlife footage with quantum particle filter (QPF)
    Prajna Parimita Dash, Sudhansu Kumar Mishra, Dipti Patra
    Proceedings 2019 International Conference on Information Technology Icit 2019, 2019
  • Mutation based self regulating and self perception particle swarm optimization for efficient object tracking in a video
    Prajna Parimita Dash, Dipti Patra
    Measurement Journal of the International Measurement Confederation, 2019
  • Efficient visual tracking using multi-feature regularized robust sparse coding and quantum particle filter based localization
    Prajna Parimita Dash, Dipti Patra
    Journal of Ambient Intelligence and Humanized Computing, 2019
  • Moment Invariant Based Weed/Crop Discrimination for Smart Farming
    Sabiha Fatma, Prajna Parimita Dash
    2019 International Conference on Computer Electrical and Communication Engineering Iccece 2019, 2019
  • GCD Based Blind Super-Resolution for Remote Sensing Applications
    Neerav Sharma, Praina Parimita Dash, Priyank Saxena
    2nd International Conference on Energy Power and Environment Towards Smart Technology Icepe 2018, 2018
  • Efficient object tracking using local tetra pattern based texture feature
    Prajna Parimita Dash, Dipti Patra
    2015 IEEE International Conference on Computer Graphics Vision and Information Security Cgvis 2015, 2016
  • Local binary pattern as a texture feature descriptor in object tracking Algorithm
    Prajna Parimita Dash, Dipti Patra, Sudhansu Kumar Mishra
    Advances in Intelligent Systems and Computing, 2014
  • Robust detection & tracking of object by particle filter using color information
    Ashwani Kumar, Sudhanshu Kumar Mishra, Pranjna Parimita Dash
    2013 4th International Conference on Computing Communications and Networking Technologies Icccnt 2013, 2013
  • Ohta based covariance technique for tracking object in video scene
    Prajna Parimita Dash, Santhosh Aitha, Dipti Patra
    2012 IEEE Students Conference on Electrical Electronics and Computer Science Innovation for Humanity Sceecs 2012, 2012
  • Evolutionary neural network for noise cancellation in image data
    Prajna Parimita Dash, Dipti Patra
    International Journal of Computational Vision and Robotics, 2011