REKHA SHARMILY R

@bharathuniv.ac.in

Assistant Professor, Electronics and Communication Engineering
Bharath Institute of Higher Education and Research

REKHA SHARMILY R


               Download Compact PDF  
https://researchid.co/rekhasharmily
Assistant Professor in ECE department

EDUCATION

BE, MTech, pursuing PhD

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Vision and Pattern Recognition, Artificial Intelligence, Signal Processing, Biomedical Engineering
4

Scopus Publications

13

Scholar Citations

2

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Developing a Hybrid Framework for Brain Tumor Multi Classification from MRI Images Using LSTM
    R. Rekha Sharmily, B. Karthik, T. Vijayan
    Proceedings of the 2025 12th International Conference on Computing for Sustainable Global Development Indiacom 2025, 2025
    Globally, brain cancers create a serious threaten to public health. The class of tumor and early prognosis have a major impact on the patients' survival. Traditional Machine Learning (ML) models, rely on handcrafted feature extraction but often struggle with complex spatial patterns. Deep learning-based approaches, such as VGG16, excel at extracting hierarchical spatial features, while Long Short-Term Memory (LSTM) approaches can model sequential dependencies within feature representations. In this research, a hybrid approach integrating VGG16, LSTM, and ML classifiers for improved brain tumor classification is proposed. VGG16 serves as a feature extractor, generating deep spatial representations, which are then passed to an LSTM network to capture sequential dependencies. Additionally, ML techniques such as SVM, DT, XGB, NB and KNN are deployed for classification. The efficacy of the hybrid deep learning approach is compared with related approaches, demonstrating superior accuracy and robustness. This study highlights the advantages of combining CNNs, LSTMs, and ML classifiers to enhance brain tumor classification, providing an efficient and interpretable framework for medical diagnosis. The most notable enhancement occurred when SVM was combined with the hybrid VGG16-LSTM approach achieving an accuracy of 98.76%. This approach improves both categorization performance and computational efficiency, making it an efficient approach for forecasting multiclass brain tumors.
  • Improved MRI based Automatic Brain Tumor Categorization Employing Deep Learning Techniques
    R Rekha Sharmily, B Karthik, T Vijayan
    2024 4th Asian Conference on Innovation in Technology Asiancon 2024, 2024
    Accurately identifying and categorizing brain tumor is necessary for the lifesaving therapy. They allow the computational networks to perform in a dynamic manner. For brain tumor categorization the traditional classifiers require large dataset, more computational time and suffer from vanishing and exploding gradient problems. In this research three pretrained deep learning models namely ResNet152, VGG19 and EfficientNetB1 have been employed for categorizing the Magnetic Resonant Images into two classes. The Kaggle dataset is applied to our pretrained models. The evaluation metrics used for vali-dating the model are the accuracy, precision, Recall, F1score, ROC-AUC, Cohen Kappa score and confusion matrix. The VGG19 model has attained the highest scores such as 99% of accuracy, 99% of precision, 99% of Recall, 98.99% of F1 score, 0.9998 as ROC-AUC e and 0.98 as Cohen Kappa score.
  • MRI Brain Tumor Medical Images Multi Classification Using Deep Neural Networks
    R Rekha Sharmily, B Karthik, T Vijayan
    Proceedings of the 2024 3rd Edition of IEEE Delhi Section Flagship Conference Delcon 2024, 2024
    Detecting brain tumors accurately remains challenging due to the diverse appearances of tumors, their variable sizes, shapes, and structures. In light of the tumor's size, form, position, and category, prediction of the tumor its extremely complex and challenging. Deep Neural networks enhance the prognosis and categorization of the brain tumor. In this research, three highly efficient architectures such as InceptionResnet V2, Mobilenet V2 and Densenet 201 architectures are employed to differentiate the classes of brain tumor. The outcomes are progressive and analogous for the three architectures, while the Mobilenet V2 attained the highest accuracy, Precision, recall and F1 score about, 97%. 98%, 100%, 99%. The developed models are finetuned by tuning the hyperparameters to perform on less data, mitigating vanishing gradient issues. These models can assist the clinicians for detecting and categorizing the brain tumors automatically with less computational resources.
  • Brain Tumour Detection and Classification using Deep Learning And Transfer Learning Techniques
    R Rekha Sharmily, B Karthik, T Vijayan
    2023 Intelligent Computing and Control for Engineering and Business Systems Iccebs 2023, 2023
    Identifying a brain tumor in its early stages is crucial, as the condition can become severe and incurable once it progresses. A precise diagnosis of a brain tumor is pivotal in initiating proper treatment, ultimately improving the patient's chances of survival. The examination specifically focuses on techniques rooted in deep learning and transfer learning, such as CNN, ResNet, U Net, and capsule networks. ResNet, an innovative deep learning architecture, has been recently developed to address the limitations of CNNs. Capsule networks are not affected by rotations and translations. Moreover, it explores essential matters and lingering challenges, bringing attention to constraints while proposing intriguing directions for future research. We expect this overview to act as a valuable launchpad for additional inquiries in this domain.

RECENT SCHOLAR PUBLICATIONS

  • A novel MRI based deep learning ensemble approach for the prognosis of multiclass brain tumor
    RR Sharmily, B Karthik, T Vijayan
    Artificial Intelligence and Sustainable Innovation, 628-633 , 2026
    2026
  • Developing a Hybrid Framework for Brain Tumor Multi Classification from MRI Images Using LSTM
    RR Sharmily, B Karthik, T Vijayan
    2025 12th International Conference on Computing for Sustainable Global … , 2025
    2025
    Citations: 1
  • MRI Brain Tumor Medical Images Multi Classification Using Deep Neural Networks
    RR Sharmily, B Karthik, T Vijayan
    2024 3rd Edition of IEEE Delhi Section Flagship Conference (DELCON), 1-5 , 2024
    2024
  • Improved MRI based automatic brain tumor categorization employing deep learning techniques
    RR Sharmily, B Karthik, T Vijayan
    2024 4th Asian Conference on Innovation in Technology (ASIANCON), 1-5 , 2024
    2024
    Citations: 2
  • Brain tumour detection and classification using deep learning and transfer learning techniques
    RR Sharmily, B Karthik, T Vijayan
    2023 Intelligent Computing and Control for Engineering and Business Systems … , 2023
    2023
    Citations: 10

MOST CITED SCHOLAR PUBLICATIONS

  • Brain tumour detection and classification using deep learning and transfer learning techniques
    RR Sharmily, B Karthik, T Vijayan
    2023 Intelligent Computing and Control for Engineering and Business Systems … , 2023
    2023
    Citations: 10
  • Improved MRI based automatic brain tumor categorization employing deep learning techniques
    RR Sharmily, B Karthik, T Vijayan
    2024 4th Asian Conference on Innovation in Technology (ASIANCON), 1-5 , 2024
    2024
    Citations: 2
  • Developing a Hybrid Framework for Brain Tumor Multi Classification from MRI Images Using LSTM
    RR Sharmily, B Karthik, T Vijayan
    2025 12th International Conference on Computing for Sustainable Global … , 2025
    2025
    Citations: 1
  • A novel MRI based deep learning ensemble approach for the prognosis of multiclass brain tumor
    RR Sharmily, B Karthik, T Vijayan
    Artificial Intelligence and Sustainable Innovation, 628-633 , 2026
    2026
  • MRI Brain Tumor Medical Images Multi Classification Using Deep Neural Networks
    RR Sharmily, B Karthik, T Vijayan
    2024 3rd Edition of IEEE Delhi Section Flagship Conference (DELCON), 1-5 , 2024
    2024

Publications

R. R. Sharmily, B. Karthik and T. Vijayan, "Improved MRI based Automatic Brain Tumor Categorization Employing Deep Learning Techniques," 2024 4th Asian Conference on Innovation in Technology (ASIANCON), Pimari Chinchwad, India, 2024, pp. 1-5, doi: 10.1109/.,
R. R. Sharmily, B. Karthik and T. Vijayan, "Brain Tumour Detection and Classification using Deep Learning And Transfer Learning Techniques," 2023 Intelligent Computing and Control for Engineering and Business Systems (ICCEBS), Chennai, India, 2023, pp. 01-05, doi: 10.1109/.,
MRI Brain Tumor Medical Images Multi Classification Using Deep Neural Networks
RR Sharmily, B Karthik, T Vijayan - 2024 3rd Edition of IEEE …, 2024 - ,
A novel MRI based deep learning ensemble approach for the prognosis of multiclass brain tumor
RR Sharmily, B Karthik… - Artificial Intelligence and …, 2026 - ,
Developing a Hybrid Framework for Brain Tumor Multi Classification from MRI Images Using LSTM
RR Sharmily, B Karthik, T Vijayan - 2025 12th International …, 2025 -