S Ranjith Reddy

S Ranjith Reddy

Auto-generated profile, based on publicly available information

S Ranjith Reddy

GIFT Autonomous, BPUT,Department of Computer Science and Engineering,Bhubaneswar,India

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
1 March 2024
Verified
Conference Paper
Closed access
CGChilukuri Sai Ganesh
Chilukuri Sai Ganesh
RKRoyyala Sai Kishore
Royyala Sai Kishore
KGK. Varshith Goud
K. Varshith Goud
BKBhaskerreddy Kethireddy
Bhaskerreddy Kethireddy
Saroja Kumar RoutSaroja Kumar Rout
Saroja Kumar Rout
SRS Ranith Reddy
S Ranith Reddy
The usage of machine learning techniques has been instrumental in the healthcare industry to a great extent for the past few years. The rise in disease rates highlights the urgent need for quick medical attention. Hospitals often struggle with efficiently sorting and prioritizing patients due to the overwhelming influx of individuals seeking care. The time-consuming manual review of patient records to identify their specific conditions has become a bottleneck in healthcare delivery. To tackle this challenge, artificial intelligence (AI) has emerged as a crucial tool in the healthcare sector. AI utilizes data from diagnostic procedures not only to deepen our understanding of diseases but also to significantly enhance treatment success rates. The proposed healthcare system, we employ various machine learning algorithms like logistic regression, linear regression, Support Vector Machine, and K Nearest Neighbors to offer precise and personalized predictions and insights. The Support Vector Classifier (SVC) achieves 87.2% accuracy for diabetes prediction, while the random forest model excels in breast cancer prediction with 95.98% accuracy. For heart disease, Support Vector Machine (SVM) attains 86.38% accuracy, and linear regression achieves 96.46% accuracy for caloric expenditure prediction, illustrating machine learning's versatility in healthcare. The research work serves as a user-friendly platform for disease prediction and health monitoring, aiming to empower individuals to actively manage their health. Ultimately, the integration of AI-driven machine learning models into healthcare applications represents a significant advancement. It streamlines patient prioritization and equips individuals with the knowledge to make informed health decisions. Data mining techniques coupled with machine learning techniques can further increase the accuracy of disease prediction.

24 August 2025
Verified
Book Chapter
Closed access
PDF file
SRS Ranjith Reddy
S Ranjith Reddy
Saroja Kumar RoutSaroja Kumar Rout
Saroja Kumar Rout
Kottu Santosh KumarKottu Santosh Kumar
Kottu Santosh Kumar
RSRuchismita Sahu
Ruchismita Sahu
KAKachi Anvesh
Kachi Anvesh
KNKailash Chandra Nayak
Kailash Chandra Nayak

18 December 2025
Verified
Conference Paper
Closed access
SRS Ranjith Readdy
S Ranjith Readdy
Saroja Kumar RoutSaroja Kumar Rout
Saroja Kumar Rout
SPSujit Kumar Panda
Sujit Kumar Panda
PMPradyumna Mohapatra
Pradyumna Mohapatra
MJMuhammed Basheer Jasser
Muhammed Basheer Jasser
Wireless Sensor Networks support agriculture, surveillance, and monitoring, but face energy issues. LEACH helps conserve energy but suffers from random cluster head selection and inefficiencies.LEACH conserves energy by rotating cluster head roles but suffers from random selection. This study proposes an improved LEACH using a hybrid of Spider Wasp Optimization and Special Forces Algorithm. The proposed SFA+SWO-LEACH method enhances CH selection by considering residual energy, node density, and distance to the base station. A Python-based simulation compared the hybrid model with LEACH, PSO-LEACH, and GWO-LEACH using 100 nodes over 100 rounds. The first node died at Round 36 in the hybrid model, outperforming LEACH (21), PSO (28), and GWO (30), while the last node died at Round 98 compared to 76 in LEACH. The hybrid model outperformed others with longer node lifespan, higher residual energy (28.4 J), 35% better data delivery, and improved energy efficiency and reliability in WSNs.