Faculty Profile

About

**Dr. Renukadevi M.N.** is an accomplished academician and researcher with over 12 years of teaching and research experience in Computer Science and Engineering. She received her Ph.D. from Visvesvaraya Technological University (VTU) in 2021, with her doctoral research focused on the characterization and detection of behavioral patterns using video data from TED Talks. She began her academic career at PES Institute of Technology (PESIT), Bangalore South Campus, where she served as an Assistant Professor in the Department of Information Science and Engineering from 2011 to 2016. She subsequently served at BNMIT, Bengaluru, and at Dayananda Sagar University, Bengaluru, from 2020 to 2026. Since July 2026, she has been serving as an Associate Professor in the Department of Artificial Intelligence and Data Science (AI & DS) at BMS College of Engineering (BMSCE), Bengaluru. Her teaching expertise encompasses Data Structures, Digital Logic Design, Artificial Intelligence, Computer Vision, Digital Image Processing, MATLAB, Python Programming, Database Management Systems, Computer Networks and Computer Organization.

Her research interests span Artificial Intelligence, Deep Learning, Computer Vision, Multimedia Computing, Image and Video Processing, Medical Image Analysis, and AI-driven healthcare systems. She has contributed to Scopus-indexed research publications, patents, funded research projects, and interdisciplinary research collaborations in areas including medical imaging, cardiac arrhythmia detection, stroke analysis, cancer detection, and multimodal behavioral analysis. Her notable academic achievements include receiving the **Best Project of the Year Award at the KSCST State-Level Student Project Competition in 2025** for mentoring the project *“Cardiac Arrhythmia Detection.”* She has also been conferred the **InSc Young Researcher Award** and a **Best Paper Award** for her research contributions. Her academic interests are complemented by a strong commitment to quality education, student mentoring, interdisciplinary research, and the development of innovative AI-based solutions addressing real-world healthcare and societal challenges.

Education

• Ph. D - Computer Science and Engineering
  VTU
  Passed Year: 2021 | Program Type: FullTime
• M.Tech - Computer Science and Engineering
  NITTE
  Passed Year: 2011 | Program Type: FullTime
• Bachelor of Engineering - Computer Science and Engineering
  PESU
  Passed Year: 2009 | Program Type: FullTime

Selected Publications

• Patents | Published On : 26-09-2026
  Dr. Rajesh T M, Dr. Renukadevi M N, Dr. Jessica Minal, Dr. Archana Shetty, Dr. Praveen Kulkarni, Dayananda Sagar University, Dr. Santosh Kumar J
  5. Title: A Robust Multi-Model Computational Framework for Automatic Detection of Malignancy in Ovarian Ascitic Fluid Cytology Applicants: Santosh Kumar Jankatti, Dayananda Sagar University Inventors: Dr. Rajesh T M, Dr. Renukadevi M N, Dr. Jessica Minal, Dr. Archana Shetty, Dr. Praveen Kulkarni, Dayananda Sagar University, Dr. Santosh Kumar J Published Date: 26/09/2025 Patent Application Number: 202541083246 A Details: This patent presents a multi-model computational framework for automated malignancy detection in ovarian ascitic fluid cytology images. The proposed system integrates image enhancement, nuclei segmentation, handcrafted feature extraction, CNN-based deep learning, and decision fusion techniques for accurate cancer diagnosis and stage prediction.
• Journal | Published On : 17-06-2026
  S. Debnath, D. Willson, R. M. N. Renukadevi, S. H. Shreenidhi, J. Kishore, et al., “An AI-driven framework for diabetic foot ulcer classification, segmentation, and depth estimation,” Scientific Reports, vol. 16, Art. no. 18861, 2026
  This paper proposes an AI-driven framework for automated diabetic foot ulcer analysis, integrating classification, segmentation, and wound depth estimation techniques. The framework utilizes advanced deep learning and image processing methods to accurately identify ulcer regions, assess severity, and estimate wound depth from clinical images. The proposed system aims to support early diagnosis, treatment planning, and improved healthcare management for diabetic foot ulcer patients.
  Weblink
• Journal | Published On : 16-06-2026
  M. N. Renukadevi, T. M. Rajesh, S. G. Shaila, P. Kulkarni, T. Babu, R. R. Nair, and S. Yogarayan, “Modeling audio dynamics using hierarchical assisted K-means model for structured speaker profiling in TED talks,” Scientific Reports
  Explanation: This paper presents a hierarchical assisted K-means framework for modeling audio dynamics and structured speaker profiling in TED Talks. The study analyzes speech characteristics, audio patterns, and speaker behavior to identify structured communication profiles. The proposed approach supports intelligent multimodal analysis for applications in public speaking assessment, behavioral analytics, and inclusive educational technologies.
  Weblink
• Journal | Published On : 06-06-2026
  T. M. Rakesh, G. S. Girisha, and M. N. Renukadevi, “AURORA-OCR: A Neuroevolutionary Framework with LLM-Guided Correction for Robust Text Recognition Under Degraded Imaging Conditions,” Engineering, Technology & Applied Science Research, vol. 16, no. 3, pp. 36617–36623, 2026. DOI: 10.48084/etasr.18219
  This paper introduces AURORA-OCR, a neuroevolutionary OCR framework integrated with Large Language Model (LLM)-guided correction for accurate text recognition under degraded imaging conditions. The proposed system enhances OCR robustness against noise, blur, low illumination, and distorted images by combining adaptive feature optimization with intelligent post-processing correction mechanisms.
  Weblink
• Conference | Published On : 31-01-2026
  M. N. Renukadevi, Kavyashree I. Pattan, and T. M. Rajesh, “Comparative Analysis of Machine Learning Algorithms for Water Region Classification in Flood-Affected Images,” in Communications in Computer and Information Science (CCIS), Springer Nature Switzerland
  This paper presents a comparative study of machine learning algorithms, including Support Vector Machine (SVM), Random Forest, and K-means clustering, for water region classification in flood-affected aerial and satellite images. The proposed methodology utilizes NDWI-based feature extraction and image segmentation techniques to distinguish flooded and non-flooded regions. Experimental results demonstrate that the Random Forest classifier achieved superior performance with 99.99% accuracy, supporting efficient flood monitoring and disaster management applications.
  Weblink
• Journal | Published On : 31-12-2025
  ]. D. Sandhya Rani, K. Mohiuddin, N. Vasudha, K. Swapna, P. Kulkarni, P. Naresh, T. M. Rajesh, and M. N. RenukaDevi, “Churn prediction analysis in the telecom industry using PCA and bagging techniques,” Mathematical Modelling of Engineering Problems, vol. 12, no. 12, 2025
  This paper presents a telecom customer churn prediction framework using Principal Component Analysis (PCA) and bagging-based machine learning techniques. The study focuses on improving prediction accuracy by reducing dimensionality and combining ensemble learning methods, thereby enabling telecom providers to identify potential customer attrition more effectively.
  Weblink
• Journal | Published On : 30-11-2025
  P. Naresh, P. Kulkarni, T. M. Rajesh, K. I. Pattan, and Y. S. Gupta, “MedGRU-SVC: A hybrid ConvGRU and support vector clustering framework for interpretable anomaly detection in medical radiographs,” Mathematical Modelling of Engineering Problems, vol. 12, no. 11, pp. 3879–3886, 2025.
  The paper presents a hybrid deep learning and clustering model for detecting anomalies in radiographic images. The approach improves interpretability and supports medical diagnostic systems.
  Weblink
• Journal | Published On : 11-11-2025
  T. M. Rakesh, G. S. Girisha, and M. N. Renukadevi, “Hybrid OCR with LLM-enhanced post processing for robust text recognition for extreme illumination condition,” International Journal of Intelligent Engineering and Systems, vol. 18, no. 11, pp. 1049–1064, 2025.
  This paper proposes a hybrid OCR framework combined with large language model post-processing. The approach improves text recognition accuracy in images captured under poor or extreme lighting conditions.
  Weblink
• Patents | Published On : 27-07-2025
  Dr. Renukadevi M N,
  4. Title: AI-Powered Multi-Modal Deep Learning System for Real-Time Cardiac Arrhythmia Detection Using Enhanced ECG Signal Representation and Temporal Context Modeling Applicants: Santosh Kumar Jankatti, Dr. Renukadevi M N, Dayananda Sagar University Inventors: Santosh Kumar Jankatti, Dr. Renukadevi M N Published Date: 27/06/2025 Patent Application Number: 202541058076 Details: This invention introduces an AI-driven multimodal deep learning framework for real-time cardiac arrhythmia detection using ECG signal analysis and temporal context modeling. The system enhances arrhythmia classification accuracy and supports intelligent cardiovascular monitoring for early diagnosis and preventive healthcare.
• Conference | Published On : 03-06-2025
  P. Kulkarni, T. M. Rajesh, and M. N. Renuka Devi, “Predicting cardiac disease using stacked refinement combination machine learning models,” in Lecture Notes in Networks and Systems, vol. 1354, 2025, pp. 515–525.
  This research proposes a stacked ensemble machine learning framework for predicting cardiac diseases. Multiple models are combined to improve prediction accuracy and clinical decision support.
  Weblink
• Patents | Published On : 30-05-2025
  Dr. Renukadevi M N, Dr. Rajesh T M, Dr. Shaila S G, Dr. Praveen Kulkarni, Santosh Kumar Jankatti
  Title: SmartMentor: Deep Learning System for Classroom Behavior Intelligence and Pedagogical Enhancement Applicants: Santosh Kumar Jankatti, Dayananda Sagar University Inventors: Dayananda Sagar University, Dr. Renukadevi M N, Dr. Rajesh T M, Dr. Shaila S G, Dr. Praveen Kulkarni, Santosh Kumar Jankatti Published Date: 30/05/2025 Patent Application Number: 202541044612 A Details: This patent introduces a deep learning-based classroom behavior intelligence framework that analyzes synchronized video, audio, and textual classroom data to evaluate teaching effectiveness and student engagement. The system uses multimodal behavioral analysis to support pedagogical enhancement, classroom communication assessment, and AI-assisted educational analytics.

Other Information

Experienced in teaching, research supervision, curriculum development, scientific writing, peer review, interdisciplinary collaboration, and industry/healthcare-oriented research. Published in Scopus-indexed journals/conferences and contributed to patents and collaborative AI-healthcare projects.

Download Resume