DR.C.UMARANI

@caias.in

Head-Department of Computer Science and Applications
Christ Academy Institute for advanced studies

DR.C.UMARANI


                  Download Compact PDF  
https://researchid.co/umacrani
Head Department of Computer Science and Applications
Dr. C. Umarani is a distinguished academic and professional with over 21 years of experience in cybersecurity, information security, and network security. Her expertise spans several cutting-edge fields, including blockchain-based supply chain management and AI-driven process optimization, areas in which she has contributed innovative patents. Throughout her career, Dr. Umarani has published extensively in both national and international journals, covering topics such as intrusion detection systems and encryption techniques.

In addition to her research and publications, Dr. Umarani has held several key leadership positions, including Head of the Department, Head In-charge, PG Coordinator, Placement Coordinator, and Mentoring Head. Her involvement in organizing conferences, workshops, and faculty development programs has earned her recognition as a respected resource person, particularly in the field of information security. As an ed

EDUCATION

MCA, MPhil, PhD

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Computer Networks and Communications, Information Systems, Computer Science Applications
11

Scopus Publications

89

Scholar Citations

3

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • Uncovering Hidden Patterns: Association Rule Mining for Disease Detection and Treatment Planning in Healthcare
    Arun Agrawal, Md Imtiyaz Ali, Mohsin Shaikh, Sujatha Somesula, C. Umarani, Amol L. Mangrulkar, Deepak Gupta
    AI Techniques for Association Rule Mining in Medical Data Trends and Practical Applications, 2026
    Association Rule Mining (ARM) has become an important tool for uncovering hidden patterns and clinically meaningful relationships in large healthcare datasets. With the growth of electronic health records, administrative claims, and patient monitoring systems, ARM helps identify disease co-occurrences, multimorbidity patterns, medication risks, and factors influencing patient outcomes. This review examines key ARM algorithms, recent methodological advances, and their applications in diagnosis support, drug safety, and precision medicine. It also highlights ongoing challenges related to data quality, integration, and clinical interpretability, while outlining future opportunities for improving patient management.
  • Innovations in Disease Forecasting and Modelling
    Deepak Gupta, Apoorva Dwivedi, C. Umarani, Rakhi Chawla, S. M. Karpagavalli, Someshwar Siddi, Abduraimova Nigora
    Plant Disease Management for Sustainable Agriculture, 2026
    Plant diseases pose significant threats to global food security, causing substantial crop losses worldwide. Traditional disease management approaches, primarily reactive in nature, are increasingly inadequate to meet the challenges of modern agriculture. The integration of machine learning (ML), deep learning (DL), and advanced predictive modeling technologies has revolutionized plant disease forecasting, offering proactive, accurate, and scalable solutions for disease prediction and management. This chapter provides a comprehensive review of innovative approaches to disease forecasting and modeling, examining the evolution from traditional epidemiological models to advanced machine learning-based predictive systems including temporal neural networks, ensemble forecasting methods, and hybrid climate-disease models. We analyze current forecasting methodologies, predictive datasets, validation frameworks, and real-world implementations while addressing key challenges such as uncertainty quantification, model interpretability, and long-term prediction accuracy.
  • Forensic Audit Trails and Biometric-Based Authentication
    Deepak Gupta, Raghu Nangunuri, Srinivasan Nagaraj, S. Keerthi, Pratish Rawat, C. Umarani, Someshwar Siddi
    Exploring the Intersection of Forensics and Biometrics, 2026
    Forensic audit trails combined with biometric-based authentication represent a critical convergence in modern cybersecurity infrastructure. This chapter examines the technical implementation, forensic methodologies, and investigative frameworks for biometric authentication systems. The integration of immutable audit trails with biometric verification creates comprehensive forensic evidence chains essential for digital investigations. We analyze forensic challenges including spoofing attacks, presentation attacks, and biometric template security. The chapter explores multimodal biometric systems, liveness detection mechanisms, and blockchain-based audit trail implementations. Critical examination of privacy-preserving forensic techniques, GDPR compliance, and admissibility of biometric evidence in legal proceedings provides practical guidance. Real-world case studies demonstrate forensic analysis of compromised biometric systems.
  • Separating Operator Hippopotamus Optimization Algorithm with Support Vector Machine for Optimizing Intrusion Detection in Internet of Things
    Zainab Alassedi, Raheleh Ghadami, Srinath Chandramohan, R. Vijayarangan, C. Umarani
    4th IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics Icdcece 2025, 2025
    An Intrusion Detection System (IDS) is considered to identify system attacks and distinguish between normal and abnormal activities. Machine Learning (ML) techniques are enabled to IDS which is significant role identifying Intrusions. This research presents the system design of an IDS, minimize false alarm rate and increase accuracy to detect intrusion. However, enhancing volume of network traffic in Internet of Things (IoT) system makes it difficult to detect cyberattacks accurately because of huge number of features which most are redundant led to inefficiencies in detection performance. To overcome these challenges, Separating Operator-Hippopotamus Optimization Algorithm with Support Vector Machine (SOHOA-SVM) is proposed for enhancing attack detection, which eliminates redundant features and improve accuracy level. In preprocessing, numerical data then labeled data used for normalizations. The SOHOA-SVM achieves accuracy of 99.99% and 99.97% for NSL-KDD and TON-IoT when compared to SVM and Grey Wolf Optimization (GWO) and XGBoost + Mutual Information Thresholding.
  • Fault Detection using Opposition-based Learning Orca Predator Algorithm with Random Forest
    C. Umarani, Mohammed I. Habelalmateen, Sujata N Patil, Rekha Phadke, Srinath Chandramohan
    4th IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics Icdcece 2025, 2025
    Machinery equipment stability and safety operations heavily depend on the implementation of intelligent fault detection systems. The system enhances production efficiency while decreasing maintenance costs together with its most significant benefit of preventing safety accidents. Intelligent compound fault detection methods require additional research regarding their interpretability features. The detection results prove difficult to understand which impedes their general acceptance for industrial use in the real world. Therefore, this research proposes an Opposition-based Learning Orca Predator Algorithm (OLOPA) with Random Forest (RF) for fault detection. The OLOPA exploration-exploitation control improves worldwide search performance while reducing convergence time thus enhancing both accuracy and stability in feature extraction. High-dimensional data management and strong generalization abilities characterize the RF classifier during its performance. The combined hybrid method provides dependable and interpretable fault detection capabilities which enables its use in complex industrial environments. Furthermore, this research extracts meaningful features from signals through time-domain and frequency domain to enhance the feature detection and signal quality maintenance. The OLOPA-RF achieves 99.91% accuracy for CWRU dataset which is better than state-of-the-art methods.
  • Decision-Making Frameworks for AI-Enabled Cyber Risk Assessments in Financial Institutions
    Kafila, C. Umarani, Mettu Jhansi Rani, Kawerinder Singh Sidhu, Uthanda Karthick U, Joshuva Arockia Dhanraj
    2025 World Skills Conference on Universal Data Analytics and Sciences Worldsuas 2025, 2025
    The perpetually increasing crop of cyber threats forces financial institutions to improve their capacity for measuring and managing cyber risks. This research proposes a structured AI-based method of cyber risk assessment that is tailored to meet the particular needs of the financial institutions. Through use of probabilistic risk frameworks, current threat feeds, and decision-making tools that measure multiple criteria, the framework is developed. Examining the practices of a Tier-1 bank, we show how the framework increases the accuracy of 0.96 % using the machine learning classifiers. Our framework consists of a 5-layer system for data collection, risk assessment, impact evaluation, and mitigation suggestions in addition to immediate decision guidance based on AI and Bayesian networks. After increases in performance observed upon testing the framework against simulated threat vectors, we get to know the proposed approach improvement. Within this research, we demonstrate how AI-enriched frameworks enable flexible and data-driven governance strategies that can successfully adjust to the current transformation of the regulatory requirements as well as the operational needs in finance.
  • Security and Privacy Challenges in IoT-Enabled Educational Ecosystems
    Ramesh Chandra Aditya Komperla, Alpana A. Borse, C. Umarani, Christabell Joseph, Rashmi Gupta, Kuldeep Chouhan
    2025 5th International Conference on Advancement in Electronics and Communication Engineering Aece 2025, 2025
    The accelerated usage of Internet of Things (IoT) devices in schools and colleges has changed the learning environment, however, has created major security and privacy threats. In this research paper, the secondary data, such as the reports on cybersecurity incidents and datasets, are used to assess these challenges. Conducting quantitative risk analysis and calculating privacy risk with entropy, the study determines weak authentication $(24.5 \%)$ as the most prominent security problem and biometric data exposure as the greatest privacy risk (9.5/10). Security cameras and access control systems are presented as vulnerable with more than $8.5 / 10$. The most effective mitigation strategy is discovered to be Zero Trust Architecture ($88.7 \%$), which can provide an insight into secure and efficient IoT implementation in education.
  • Dynamic Graph Convolutional Networks for Time-Series Customer Behavior Modeling
    Kotla Lakshmaji, Pallavi Jha, TulasiRaju Nethala, C. Umarani, Tamanna Agarwal, Chanakya Kumar Jha
    2025 5th Asian Conference on Innovation in Technology Asiancon 2025, 2025
    Understanding and predicting customer behavior patterns is crucial for modern e-commerce platforms and recommendation systems. This paper presents a novel Dynamic Graph Convolutional Network (DGCN) framework for modeling temporal customer behavior through graph-structured representations. We introduce a temporal attention mechanism that captures evolving customer-product interactions over time while preserving the structural properties of the customer relationship graph. Our approach dynamically updates graph topology based on behavioral patterns and employs multi-scale temporal convolutions to capture both short-term and long-term dependencies. Experimental results on three real-world datasets (Taobao, Amazon, and RetailRocket) demonstrate that our DGCN model achieves significant improvements over state-of-the-art baselines, with 12.3% increase in prediction accuracy and 15.7% improvement in F1-score for customer churn prediction. The model also shows robust performance in session-based recommendation tasks, achieving NDCG@10 scores of 0.784 on Taobao dataset.
  • Optimizing Sentiment Analysis on Twitter for Improved Customer Insights: Integrating Bagged CNN and Flamingo Search
    C. Umarani, Jyoti Metan, Piyush Kumar Pareek, Mahantesh Mathapati
    International Conference on Distributed Systems Computer Networks and Cybersecurity Icdscnc 2024, 2024
    Twitter helps you understand public opinion by revealing what people think, feel, and believe. This study provides a framework for businesses, particularly food delivery companies, to analyse social media data competitively and gain actionable insights. A novel combination of Flamingo Search Optimisation (FSA) and a one-dimensional bagged CNN is applied to Twitter data to improve customer satisfaction research. Our method uses advanced machine learning to analyse and interpret consumer attitudes and trends using Twitter's massive, real-time customer feedback stream. We found that sentiment analysis can now better predict consumer preferences and satisfaction. The study suggests developing more advanced optimisation algorithms, cross-platform sentiment analysis, real-time processing, and natural language processing techniques. Average kappa score: 0.9941, sensitivity: 0.9969, specificity: 0.9972, accuracy: 0.9971, precision: 0.9973. This study prepares companies to improve customer engagement and respond quickly to digital consumer sentiments.
  • Enhancing DDoS Detection in SDNs: Integrating AFSOA with BiLSTM for Real-Time Threat Management
    C. Umarani, Jyoti Metan, Piyush Kumar Pareek, Mahantesh Mathapati
    International Conference on Distributed Systems Computer Networks and Cybersecurity Icdscnc 2024, 2024
    Software-defined networking (SDN) has emerged as a popular solution to the inherent difficulties of traditional dispersed networks. The primary focus of this work is the early identification of anomalous assaults. We investigate the efficacy of combining a Bidirectional Long Short-Term Memory (BiLSTM) network with an Artificial Fish Swarm Optimization Algorithm (AFSOA) to detect Distributed Denial of Service (DDoS) attacks in an SDN environment. For dimensionality reduction, we combine information gain (IG) with principal component analysis (PCA), allowing for a more effective and economic analysis of complex, high-dimensional datasets. The AFSOA optimizes the BiLSTM model's parameters to improve its ability to detect patterns in network traffic indicative of DDoS attacks. The proposed solution leverages the programmable and dynamic nature of SDNs to build and test the detection system, enabling adaptive threat management in accuracy of 95.20%, precision of 97.64%, recall of 98.20%, and an F-measure of 98.67%, significantly outperforming existing methods. This approach opens up new possibilities for enhancing network security in the future.
  • Intrusion detection system using hybrid tissue growing algorithm for wireless sensor network
    C. Umarani, S. Kannan
    Peer to Peer Networking and Applications, 2020

RECENT SCHOLAR PUBLICATIONS

  • Intelligent Cost Governance in Projects: Machine Learning-Driven Forecasting, Anomaly Detection, and Value Leakage Prevention
    A Agrawal, V Sudharsan, MK Saranya, M Adusumilli, C Umarani, ...
    AI-Driven Project Planning, Decision Intelligence, and Risk Management, 175-204 , 2026
    2026
  • Uncovering Hidden Patterns: Association Rule Mining for Disease Detection and Treatment Planning in Healthcare
    A Agrawal, MI Ali, M Shaikh, S Somesula, C Umarani, AL Mangrulkar, ...
    AI Techniques for Association Rule Mining in Medical Data: Trends and … , 2026
    2026
  • Forensic Audit Trails and Biometric-Based Authentication
    D Gupta, R Nangunuri, S Nagaraj, S Keerthi, P Rawat, C Umarani, S Siddi
    Exploring the Intersection of Forensics and Biometrics, 31-60 , 2026
    2026
  • Innovations in Disease Forecasting and Modelling
    D Gupta, A Dwivedi, C Umarani, R Chawla, SM Karpagavalli, S Siddi, ...
    Plant Disease Management for Sustainable Agriculture, 91-118 , 2026
    2026
  • Deep Learning Powered Data Aggregation and Communication in Wireless Sensor Networks
    BA Kumar, C Umarani, V Trinadha, K Sridevi, VS Goud
    2025 IEEE 1st International Conference on Recent Trends in Computing and … , 2025
    2025
  • Security and Privacy Challenges in IoT-Enabled Educational Ecosystems
    RCA Komperla, AA Borse, C Umarani, C Joseph, R Gupta, K Chouhan
    2025 5th International Conference on Advancement in Electronics … , 2025
    2025
  • Decision-Making Frameworks for AI-Enabled Cyber Risk Assessments in Financial Institutions
    C Umarani, MJ Rani, KS Sidhu, JA Dhanraj
    2025 World Skills Conference on Universal Data Analytics and Sciences … , 2025
    2025
  • Dynamic Graph Convolutional Networks for Time-Series Customer Behavior Modeling
    K Lakshmaji, P Jha, TR Nethala, C Umarani, T Agarwal, CK Jha
    2025 5th Asian Conference on Innovation in Technology (ASIANCON), 1-5 , 2025
    2025
  • Separating Operator Hippopotamus Optimization Algorithm with Support Vector Machine for Optimizing Intrusion Detection in Internet of Things
    Z Alassedi, R Ghadami, S Chandramohan, R Vijayarangan, C Umarani
    2025 4th International Conference on Distributed Computing and Electrical … , 2025
    2025
    Citations: 1
  • Fault Detection using Opposition-based Learning Orca Predator Algorithm with Random Forest
    C Umarani, MI Habelalmateen, SN Patil, R Phadke, S Chandramohan
    2025 4th International Conference on Distributed Computing and Electrical … , 2025
    2025
  • Advanced Signal Processing For IoT Device Communication In Smart Homes
    M Malini, MB Jashva, MS Banu, N Jayanthi, C Umarani, TH Babu
    2025 International Conference on Automation and Computation (AUTOCOM), 1537-1542 , 2025
    2025
  • An hybrid machine learning and improved social spider optimization based clustering and routing protocol for wireless sensor network
    C UmaRani, S Ramalingam, S Dhanasekaran, K Baskaran
    Wireless Networks 31 (2), 1885-1910 , 2025
    2025
    Citations: 35
  • Optimizing Sentiment Analysis on Twitter for Improved Customer Insights: Integrating Bagged CNN and Flamingo Search
    C Umarani, J Metan, PK Pareek, M Mathapati
    2024 International Conference on Distributed Systems, Computer Networks and … , 2024
    2024
    Citations: 1
  • Enhancing DDoS Detection in SDNs: Integrating AFSOA with BiLSTM for Real-Time Threat Management
    C Umarani, J Metan, PK Pareek, M Mathapati
    2024 International Conference on Distributed Systems, Computer Networks and … , 2024
    2024
  • A GAN-based Hybrid Deep Learning Approach for Enhancing Intrusion Detection in IoT Networks.
    S Balaji, G Dhanabalan, C Umarani, J Naskath
    International Journal of Advanced Computer Science & Applications 15 (6) , 2024
    2024
    Citations: 8
  • Smart Contracts for Automated Compliance in Supply Chain Management Using Blockchain - January 2024.
    C Umarani
    2024
  • Cold Chain Monitoring with Blockchain - January 2024.
    C Umarani
    2024
  • 1. Secure System for Supply Chain Management using Blockchain - January 2024.
    C Umarani
    2024
  • AI-Driven Process Optimization System for Small Software Firms - December 2023
    C Umarani
    2023
  • Research Paper on Detection and Prevention of Data Leakage
    D Gupta, U Chellapandy
    International Journal for Research in Applied Science and Engineering … , 2022
    2022
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • An hybrid machine learning and improved social spider optimization based clustering and routing protocol for wireless sensor network
    C UmaRani, S Ramalingam, S Dhanasekaran, K Baskaran
    Wireless Networks 31 (2), 1885-1910 , 2025
    2025.0
    Citations: 35
  • Intrusion detection system using hybrid tissue growing algorithm for wireless sensor network
    C Umarani, S Kannan
    Peer-to-Peer Networking and Applications 13 (3), 752-761 , 2020
    2020.0
    Citations: 28
  • A GAN-based Hybrid Deep Learning Approach for Enhancing Intrusion Detection in IoT Networks.
    S Balaji, G Dhanabalan, C Umarani, J Naskath
    International Journal of Advanced Computer Science & Applications 15 (6) , 2024
    2024.0
    Citations: 8
  • Steganography Using Python
    R Sengupta, C Umarani
    IITM Journal of Management and IT 12 (1), 40-43 , 2021
    2021.0
    Citations: 3
  • Research Paper on Detection and Prevention of Data Leakage
    D Gupta, U Chellapandy
    International Journal for Research in Applied Science and Engineering … , 2022
    2022.0
    Citations: 2
  • Criminal Investigation Tracker with Suspect Prediction
    G Kushwaha, C Umarani
    IITM Journal of Management and IT, 78-80 , 2021
    2021.0
    Citations: 2
  • Embedded Based Deaf Mute Communication System
    C Umarani, J Naskath, M Banu, JU Shanthi
    International Journal for Scientific Research and Development 5 (1), 694-700 , 2017
    2017.0
    Citations: 2
  • A Study on Applying Reinforcement Learning in Intrusion Detection and Prevention System
    R Arunraj, C Umarani
    2017.0
    Citations: 2
  • Intrusion detection system using hybrid tissue growing algorithm for wireless sensor network. Peer-to-Peer Netw. Appl. 13, 752–761 (2020)
    C Umarani, S Kannan
    Citations: 2
  • Integrating AI With Remote Sensing For Mineral Prospectivity Mapping
    M Cherukuri, B Kumar, C Umarani, KS Kumar, S Sachin, NR Patel
    International Journal of Environmental Sciences 11 (20s), 2025 , 0
    Citations: 2
  • Separating Operator Hippopotamus Optimization Algorithm with Support Vector Machine for Optimizing Intrusion Detection in Internet of Things
    Z Alassedi, R Ghadami, S Chandramohan, R Vijayarangan, C Umarani
    2025 4th International Conference on Distributed Computing and Electrical … , 2025
    2025.0
    Citations: 1
  • Optimizing Sentiment Analysis on Twitter for Improved Customer Insights: Integrating Bagged CNN and Flamingo Search
    C Umarani, J Metan, PK Pareek, M Mathapati
    2024 International Conference on Distributed Systems, Computer Networks and … , 2024
    2024.0
    Citations: 1
  • A REFEREED JOURNAL OF THE DEPARTMENT OF COMPUTER SCIENCE
    H Rajesh, RAH Sathish, BA Vincent, N Srinivas, SS Erady, ...
    Journal of Physical Science September 4 , 2015
    2015.0
    Citations: 1
  • Intelligent Cost Governance in Projects: Machine Learning-Driven Forecasting, Anomaly Detection, and Value Leakage Prevention
    A Agrawal, V Sudharsan, MK Saranya, M Adusumilli, C Umarani, ...
    AI-Driven Project Planning, Decision Intelligence, and Risk Management, 175-204 , 2026
    2026.0
  • Uncovering Hidden Patterns: Association Rule Mining for Disease Detection and Treatment Planning in Healthcare
    A Agrawal, MI Ali, M Shaikh, S Somesula, C Umarani, AL Mangrulkar, ...
    AI Techniques for Association Rule Mining in Medical Data: Trends and … , 2026
    2026.0
  • Forensic Audit Trails and Biometric-Based Authentication
    D Gupta, R Nangunuri, S Nagaraj, S Keerthi, P Rawat, C Umarani, S Siddi
    Exploring the Intersection of Forensics and Biometrics, 31-60 , 2026
    2026.0
  • Innovations in Disease Forecasting and Modelling
    D Gupta, A Dwivedi, C Umarani, R Chawla, SM Karpagavalli, S Siddi, ...
    Plant Disease Management for Sustainable Agriculture, 91-118 , 2026
    2026.0
  • Deep Learning Powered Data Aggregation and Communication in Wireless Sensor Networks
    BA Kumar, C Umarani, V Trinadha, K Sridevi, VS Goud
    2025 IEEE 1st International Conference on Recent Trends in Computing and … , 2025
    2025.0
  • Security and Privacy Challenges in IoT-Enabled Educational Ecosystems
    RCA Komperla, AA Borse, C Umarani, C Joseph, R Gupta, K Chouhan
    2025 5th International Conference on Advancement in Electronics … , 2025
    2025.0
  • Decision-Making Frameworks for AI-Enabled Cyber Risk Assessments in Financial Institutions
    C Umarani, MJ Rani, KS Sidhu, JA Dhanraj
    2025 World Skills Conference on Universal Data Analytics and Sciences … , 2025
    2025.0