Prasad Sarappadi Narasimha

Dr. Prasad Sarappadi Narasimha


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
18 January 2024 in Engineering Proceedings
Verified
Conference Paper
Open access
PDF file
KSKavya B S
Kavya B S
PNPrasad Sarappadi Narasimha
Prasad Sarappadi Narasimha
Neurological disorders are a significant health challenge globally, affecting millions of individuals and imposing a considerable economic burden on healthcare systems. Early and accurate diagnosis plays a crucial role in improving patient outcomes and managing these disorders effectively. This abstract presents a novel approach that combines blockchain technology with deep learning algorithms to enhance the detection of neurological disorders. The proposed system leverages the decentralized and transparent nature of blockchain to securely store and share medical data, enabling seamless collaboration among healthcare providers, researchers, and patients. This infrastructure ensures data integrity, privacy, and accessibility, addressing critical concerns in medical data management. Furthermore, the deep learning approach employs advanced neural network architectures, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), to analyze large-scale neurological data, including medical images, electroencephalograms (EEGs), and clinical records. By leveraging the power of deep learning, the system can automatically extract relevant features and patterns from complex neurological data, enabling accurate diagnosis and early detection of various disorders. The integration of blockchain and deep learning offers several advantages. Firstly, it facilitates secure and decentralized storage of medical data, ensuring patient privacy and data integrity. Secondly, it enables seamless data sharing and collaboration among multiple stakeholders, promoting knowledge exchange and enhancing research capabilities. Lastly, deep learning algorithms improve the accuracy and efficiency of neurological disorder detection, enabling timely interventions and personalized treatment plans. The proposed system holds great potential in revolutionizing the field of neurological disorder diagnosis and management. By leveraging the combined power of blockchain and deep learning, healthcare providers can enhance their diagnostic capabilities, leading to improved patient outcomes, reduced healthcare costs, and accelerated research advancements. However, further research and development are necessary to address technical challenges, scalability issues, and regulatory considerations to realize the full potential of this innovative approach.

22 September 2025 in IEEE Access
Verified
Journal Article
Open access
HSH A Sharath
H A Sharath
JVJayavrinda Vrindavanam
Jayavrinda Vrindavanam
SDSaswati Dana
Saswati Dana
PNPrasad Sarappadi Narasimha
Prasad Sarappadi Narasimha
The rapid advancement of quantum computing is poised to disrupt the foundations of classical cryptography, calling into question the long-term security of widely used algorithms. Classical cryptographic techniques, including symmetric key algorithms like DES, 3DES and AES, asymmetric schemes such as RSA and ECC, and essential primitives like hash functions and the One-Time Pad (OTP), have been the cornerstone of secure digital communication since their inception. However, the progress of quantum algorithms, spearheaded by Shor and Grover, poses serious threats to these schemes, necessitating a shift in cryptographic design. This paper presents an all-encompassing review of classical cryptographic techniques, along with emerging post-quantum cryptographic (PQC) algorithms that have been developed to provide quantum-resistant security while maintaining compatibility with classical infrastructure. Concurrently, the quantum key distribution (QKD) introduces a radical shift, leveraging quantum mechanics principles to attain unconditional security. This paper elaborates both Discrete Variable (DV-QKD) and Continuous Variable (CV-QKD) approaches, highlighting their operational principles and security models. By providing a relative analysis of classical cryptographic methods, PQC, and quantum cryptography, including QKD protocols and quantum-safe primitives, this work targets to provide a consolidated insight into modern cryptographic landscape and further research toward secure communication in the quantum era.

1 September 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
SSSugandha Saxena
Sugandha Saxena
PNPrasad Sarappadi Narasimha
Prasad Sarappadi Narasimha
Despite the existence of numerous models for detecting lung cancer, there is still room for achieving higher levels of accuracy. In this paper, a maximum sensitivity neural network (MSNN) has been proposed. As the name suggests, the model aims to achieve high sensitivity and offers a viable remedy to minimize the number of false positive in oder to improve the overall accuracy for lung cancer detection. The MSNN model is a promising model since it can efficiently interpret grayscale lung computed tomography (CT) scan images as inputs and can be trained using just a few images also. This model has surpassed previous deep learning models by obtaining a remarkable sensitivity of 94.6% and an accuracy of 96.9%. A sensitivity map is created, offering important insights into the critical regions for finding malignant nodules. This innovative method has shown outstanding performance in identifying lung cancer with a low false positive rate which can increase the accuracy of medical diagnoses.

1 February 2024 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
RKRaghavendra Mandara Shetty Kirimanjeshwara
Raghavendra Mandara Shetty Kirimanjeshwara
PNPrasad Sarappadi Narasimha
Prasad Sarappadi Narasimha
This research provides a strategy for enhancing the precision of face sketch identification through adversarial sketch-photo transformation. The approach uses a generative adversarial network (GAN) to learn to convert sketches into photographs, which may subsequently be utilized to enhance the precision of face sketch identification. The suggested method is evaluated in comparison to state-of-the-art face sketch recognition and synthesis techniques, such as sketchy GAN, similarity-preserving GAN (SPGAN), and super-resolution GAN (SRGAN). Possible domains of use for the proposed adversarial sketch-photo transformation approach include law enforcement, where reliable face sketch recognition is essential for the identification of suspects. The suggested approach can be generalized to various contexts, such as the creation of creative photographs from drawings or the conversion of pictures between modalities. The suggested method outperforms state-of-the-art face sketch recognition and synthesis techniques, confirming the usefulness of adversarial learning in this context. Our method is highly efficient for photo-sketch synthesis, with a structural similarity index (SSIM) of 0.65 on The Chinese University of Hong Kong dataset and 0.70 on the custom-generated dataset.

19 November 2024 in IEEE Access
Verified
Journal Article
Open access
NVN. A. Vinay
N. A. Vinay
KVK. N. Vidyasagar
K. N. Vidyasagar
RSROHITH SHIVASHANKAR
ROHITH SHIVASHANKAR
SSS Supreeth
S Supreeth
PNPrasad Sarappadi Narasimha
Prasad Sarappadi Narasimha
SBS. H. Bharathi
S. H. Bharathi
Dysfluency refers to discontinuity in speech due to noise or speech disorder, this dysfluency has unique features in terms of pitch, time based on these characteristics the dysfluent speech is categorized into: repetition, prolongation, or blocking of words or phrases and because of this uneven structure in speech it named unstructured speech. The recognition and classification of such unstructured speech requires an effective algorithm to boost the process of Automatic Speech Recognition in real time and it is a challenging task because the system will take more time to extract the features like: pitch, frequency or time, energy. From past few decades many researchers have proposed their own algorithms to address the mentioned, but still there is a gap in recognizing the endpoint of each frames based on mentioned which helps to robust the recognition accuracy dysfluent speech. So, in this proposed work the to extract the desired and unique features of dysfluent speech the samples are decomposed into different sub-signals by using two advanced methods of Empirical mode decomposition (EMD), they are Variational Mode Decomposition (VMD) and Complete Ensemble Empirical Mode Decomposition (CEEMD). These two techniques overcome the one major disadvantage of EMD that is the EMD techniques uses different decomposition levels to produce the oscillation of same time series signal. Hence combination of VMD and CEEMD decomposes the input speech sample into 5 sub-signals to classify the different classes of dysfluency using New Gate Control Unit (NGCU) based on Recurrent Neural Networks (RNN).

1 February 2024 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
ARAnupama Rajanna
Anupama Rajanna
SKSrimannarayana Kulkarni
Srimannarayana Kulkarni
PNPrasad Sarappadi Narasimha
Prasad Sarappadi Narasimha
Recognition of signals is a spectrum sensing challenge requiring simultaneous detection, temporal and spectral localization, and classification. In this approach, we present the convolution neural network (CNN) architecture, a powerful portrayal of the cyclo-stationarity trademark, for remote range detection and sign acknowledgment. Spectral correlation function is used along with CNN. In two scenarios, method-1 and method-2, the suggested approach is used to categorize wireless signals without any previous knowledge. Signals are detected and classified simultaneously in method-1. In method-2, the sensing and classification procedures take place sequentially. In contrast to conventional spectrum sensing techniques, the proposed CNN technique need not bother with a factual judgment process or past information on the signs’ separating qualities. The method beats both conventional sensing methods and signal-classifying deep learning networks when used to analyze real-world, over-the-air data in cellular bands. Despite the implementation’s emphasis on cellular signals, any signal having cyclo-stationary properties may be detected and classified using the provided approach. The proposed model has achieved more than 90% of testing accuracy at 15 dB.