Thirumala Narasimha Naidu Korrapati

Mr. Thirumala Narasimha Naidu Korrapati

Computer Science and Engineering, vishnu institute of technology, Bhīmavaram, Andhra Pradesh, International
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
21 January 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
Mahaboob Hussain ShaikMahaboob Hussain Shaik
Mahaboob Hussain Shaik
BABalakrishna Akula
Balakrishna Akula
Thirumala Narasimha Naidu KorrapatiThirumala Narasimha Naidu Korrapati
Thirumala Narasimha Naidu Korrapati
Prakash PareekPrakash Pareek
Prakash Pareek
NMNishit Malviya
Nishit Malviya
Manuel José Cabral dos Santos ReisManuel José Cabral dos Santos Reis
Manuel José Cabral dos Santos Reis
A recent study by the Food and Agriculture Organization (FAO) reveals that approximately 40% of India’s food production is wasted each year due to inefficient and fragmented supply chain management. An effective supply chain is essential to ensure the efficient use of resources and to maximize profitability. A platform is required to enhance communication, facilitate contract agreements, and streamline collaboration among stakeholders to reach their target destinations. In some cases, suppliers of raw materials often struggle to find buyers, which create gaps in the system. To address these issues, we have developed a unique methodology. We designed a platform that connects all stakeholders in the supply chain through a transparent, two-way communication channel, while ensuring high levels of authenticity and trust. Additionally, we created a comprehensive framework that includes profiles for farmers, retailers, manufacturers, and distributors. This application aims to bridge communication gaps and improve the overall efficiency of the system. To ensure the application’s integrity with the database, we conducted tests with various databases for optimal performance and authentication. During our evaluation, one of our observations on databases was that the Postgres database system utilized 48.3% of the total processing time and a latency of 10,941.3 milliseconds. At the same time, PgBouncer used 5.4% of the time consumed and required 1230.75 milliseconds before data processing started. Considering the authentication as a parameter, we also considered the Firebase (NoSQL) database for our application. It optimizes database operations to enhance the platform’s speed and efficiency, which has the potential for performance improvements in the supply chain management system.
1

6 February 2026
Verified
Conference Paper
Closed access
KVK Vishnu Vardhan
K Vishnu Vardhan
Mahaboob Hussain ShaikMahaboob Hussain Shaik
Mahaboob Hussain Shaik
KPK Lokesh Surya Prakash
K Lokesh Surya Prakash
Thirumala Narasimha Naidu KorrapatiThirumala Narasimha Naidu Korrapati
Thirumala Narasimha Naidu Korrapati
CPChukka Abhishek Mahin Prabhas
Chukka Abhishek Mahin Prabhas
Sickle Cell Disease (SCD) is a life-threatening genetic condition that causes red blood cells to become sickleshaped, leading to serious health complications. Current diagnostic methods rely on manual inspection of microscopic blood images, which can be slow, subjective, and error-prone. This study presents a comparative analysis of deep learning architectures to automate SCD diagnosis. Using a publicly available image dataset, we applied preprocessing techniques including data augmentation, class balancing, and PCA visualization. We systematically trained and evaluated both Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) models to classify red blood cells as healthy or sickle-affected. Our comparative evaluation revealed significant performance differences between the architectures. The CNN model achieved superior results with 100 % training accuracy, 96.12 % validation accuracy, 93.85 % test accuracy, and an AUC score of 0.94, while the LSTM model demonstrated lower performance across all metrics. The CNN also showed better balanced performance across both classes, effectively addressing class imbalance challenges. This comparative study demonstrates that CNN-based approaches provide faster, more consistent, and scalable solutions for SCD detection compared to LSTM models, particularly valuable in resource-limited healthcare settings. By optimizing architecture selection through systematic comparison, this work supports automated early detection and reduces dependency on manual diagnosis, ultimately bringing reliable SCD screening closer to patients who need it most.