Deepa Bammidi

@anits.edu.in

Assistant Professor, Department of ECE, ANITS
Anil Neerukonda Institute of Technology and Sciences

Deepa Bammidi


            Download Compact PDF  
https://researchid.co/deeparesearchworks

RESEARCH INTERESTS

Antennas, Machine Learning, ANN, Deep Learning, IOT
20

Scopus Publications

Scopus Publications

  • A Hybrid Quantum Framework for Ultra-Secure Communication and Anomaly Detection in IoT Systems
    Bharathi Deepa, M. Murugappan, G. Jashwanth Kumar, S. Iswariya
    Lecture Notes in Electrical Engineering, 2026
    The rapid expansion of the Internet of Things (IoT) has produced a highly linked digital environment together with a growing number of complex cyber threats. This work presents a Quantum-Enhanced Hybrid Anomaly Detection Framework combining two advanced Quantum Machine Learning (QML) models: Quantum Support Vector Machine (QSVM) and Quantum Neural Network (QNN) to address these challenges. By projecting data into high-dimensional quantum spaces, QSVM efficiently classifies non-linear and low-frequency threats such as User to Root (U2R) and Probe attacks using quantum kernel functions. Concurrently, QNN models utilize Variational Quantum Circuits (VQCs) to detect large-scale threats like Denial of Service (DoS) and Remote to Local (R2L) attacks by offering superior generalization. Both models produce a final, high-confidence prediction by combining their outputs using a soft voting ensemble approach. The proposed framework guarantees scalability and resilience while ensuring compatibility with present simulation systems. The experimental results obtained indicate that the hybrid QSVM + QNN model significantly outperforms standalone models and conventional methods, providing a future-ready security solution for next-generation IoT infrastructures. In addition, this model delivers a robust, adaptable, and quantum-resilient security solution, well-suited for safeguarding future IoT ecosystems.
  • Multi-scale Image Decomposition Approach with Improved Filtering Techniques
    S. Kannadhasan, B. Deepa, S. Prasad Jones Christydass, C. V. Vennila, Lakshmi Kanthan Narayanan, Harishchander Anandaram
    Lecture Notes in Electrical Engineering, 2026
  • Miniaturized monopole antenna with dual inverted L shape slot and shorting pins for biotelemetry applications
    Palanisamy Ramya, Bharathi Deepa, Rengaraj Bharathi, Suriyan Kannadhasan
    Journal of Industrial Textiles, 2025
    This research shows how a small, low-profile monopole antenna was designed, built, and tested for performance in the medical field for Internet of Things applications. The suggested antenna is especially designed for integration into wearable and implantable medical devices, and it runs in the 2.45 GHz ISM (Industrial, Scientific, and Medical) frequency range. The antenna uses shorting pins and stub structures for improved impedance matching and downsizing. It is appropriate for biomedical applications with limited space since it is made on a flame-resistant FR4 substrate and has small dimensions of 22 mm × 15 mm × 1 mm. To evaluate the antenna’s performance, extensive computer simulations and experimental tests are carried out. The antenna has excellent impedance matching with a low return loss of −35 dB. In the 2.2–2.6 GHz frequency band, the gain and directivity are measured at 2.279 dB and 2.546 dBi, respectively. With a radiation efficiency of 80.27%, the design guarantees dependable wireless signal transmission. Testing the antenna in liquid phantoms that look like human tissue to make sure it works in real life proves that it is suitable for both in-body and on-body applications. In addition to standard antennas, this study looks at different types of biomedical antennas, such as circularly polarized in-body antennas for next-generation implants, Yagi antennas and SIW-based designs for wearable applications, and dipole antennas with polarization diversity for capsule endoscopy. The suggested antenna works well with Internet of Things-based medical monitoring devices, which makes sending real-time health data easier. It also offers a very sensitive, non-invasive, and affordable way to keep an eye on patients and make diagnoses. The experimental findings and manufactured prototypes show this antenna’s potential for smart implants, wireless medical telemetry, and real-time patient monitoring. This study improves connection in healthcare applications and advances wireless medical IoT technology by resolving current design issues.
  • Smart Detection and Repulsive System for Animal Intrusion
    Deepa Bharathi, Ramya Palanisamy, Leeban Moses, Karthikeyan Shanmugam, Nirmala Rangasamy
    Aip Conference Proceedings, 2024
  • A Novel Approach for Sign Language Video Generation Using Deep Networks
    Sachin Kumar, Deepa B, Kavitha T, Tamilselvi M, Sathiyapriya V, Natarajan B
    2nd IEEE International Conference on Data Science and Network Security Icdsns 2024, 2024
    Sign language enhances the communication capabilities of the deaf-mute community, allowing for a deeper understanding of their needs and emotions. These languages are highly structured and visual, using gestures and various upper body movements such as those of the hands, face, eyes, and gaze. Researchers face numerous challenges in recognizing and translating the diverse variations in sign movements, which requires specialized expertise in computer vision and artificial intelligence. Sign language recognition and translation research has garnered global attention. This research work introduces a novel methodology for generating sign gesture videos from text inputs by integrating various intelligent techniques. The proposed model employs an enhanced generative adversarial network (GAN) to create sign videos from input sentences. Experiments with the proposed VideoGAN model using diverse sign language datasets from multiple countries have demonstrated its effectiveness. The research outcomes highlight its contribution to high-quality video production, with improved evaluation metrics underscoring the model's superior performance.
  • HNNLS: Robust Design to Identify Textile Fabric Defects Using Hybrid Neural Network Assisted Learning Strategy
    Madasamy Raja. G., B.Deepa, Rajesh. S, Kurakula Sai Satish, D. Baburao, Sreedhar Burada
    4th International Conference on Power Energy Control and Transmission Systems Harnessing Power and Energy for an Affordable Electrification of India Icpects 2024, 2024
    The rising cost of labor combined with increased automation in the textile sector has made studying methods for detecting flaws in fabrics an area of intense interest in recent years. In this study, we present a machine-learning technique for automatic fabric defect identification that employs deep neural network models that have already been pretrained. Pre-processing the fabric pictures using standard image processing techniques yields improved data that is then used to train the networks. In order to train and categorize many fabric flaws, the Deep Convolutional Neural Network (DCNN) is utilized. In the performed simulations, the existing textile dataset allows for a maximum categorization accuracy of 97.34%. This classifier model-based detection and categorization system may help humans locate manufacturing flaws in fabric with a high degree of accuracy.
  • Automated Computer-Aided Detection and Classification of Intracranial Hemorrhage Using Ensemble Deep Learning Techniques
    Snekhalatha Umapathy, Murugappan Murugappan, Deepa Bharathi, Mahima Thakur
    Diagnostics, 2023
    Diagnosing Intracranial Hemorrhage (ICH) at an early stage is difficult since it affects the blood vessels in the brain, often resulting in death. We propose an ensemble of Convolutional Neural Networks (CNNs) combining Squeeze and Excitation–based Residual Networks with the next dimension (SE-ResNeXT) and Long Short-Term Memory (LSTM) Networks in order to address this issue. This research work primarily used data from the Radiological Society of North America (RSNA) brain CT hemorrhage challenge dataset and the CQ500 dataset. Preprocessing and data augmentation are performed using the windowing technique in the proposed work. The ICH is then classified using ensembled CNN techniques after being preprocessed, followed by feature extraction in an automatic manner. ICH is classified into the following five types: epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural. A gradient-weighted Class Activation Mapping method (Grad-CAM) is used for identifying the region of interest in an ICH image. A number of performance measures are used to compare the experimental results with various state-of-the-art algorithms. By achieving 99.79% accuracy with an F-score of 0.97, the proposed model proved its efficacy in detecting ICH compared to other deep learning models. The proposed ensembled model can classify epidural, intraventricular, subarachnoid, intra-parenchymal, and subdural hemorrhages with an accuracy of 99.89%, 99.65%, 98%, 99.75%, and 99.88%. Simulation results indicate that the suggested approach can categorize a variety of intracranial bleeding types. By implementing the ensemble deep learning technique using the SE-ResNeXT and LSTM models, we achieved significant classification accuracy and AUC scores.
  • A Machine Learning based Accurate Localization Technique for 5G Networks
    Praveen Chakkravarthy S, Humaira Nishat, Deepa B, Ramya P, Pon Bharathi A
    Proceedings of the 3rd International Conference on Artificial Intelligence and Smart Energy Icais 2023, 2023
    To cater the needs of network scalability and improved performance, 5G networks are set to achieve accurate localization in Indoor/Outdoor environment. This capability can be imparted in the network by training it to behave like a Real Dynamic Network (RDN). The proposed Accurate localization algorithm enable network nodes with self learning capability based on local observations. The decision making of the network is clearly autonomous and due to its self-learning capability, it behaves like a Heterogeneous network. With Ultra-Wide Band communication, the following measurements include Time of Arrival (TOA), Channel State Information (CSI) and Time Difference of Arrival (TDOA) are calculated for the network to justify the accuracy of the proposed algorithm. The Q learning model enhances the decision-making capability of nodes and base stations, which in turn enhance the localization of the proposed network. Simulation results prove that the Q learning model outperforms conventional approaches in terms of matching the performance requirements of 5G networks.
  • Internet of Things (IoT) Assisted Smart Agriculture Monitoring and Summarization System using NodeMCU and Efficient Sensor Unit
    Madasamy Raja. G., B. Deepa, Nijanthan, B. Swapna, B.Sai Divya, Parinita J Chate
    IEEE 9th International Conference on Smart Structures and Systems Icsss 2023, 2023
    The Internet of Things (IoT) has catalyzed transformative advancements across various industries, and agriculture is no exception. This paper introduces an innovative IoT-assisted Smart Agriculture Monitoring and Summarization System designed to enhance farming practices. The system seamlessly integrates NodeMCU, agricultural drones, and an array of sensors, including optical sensors, soil moisture sensors, motion sensors, and temperature and humidity sensors. Monthly crop yield, soil health parameters, and environmental conditions are meticulously monitored and processed through cloud-based analytics. The user-friendly dashboard provides real-time insights, alerts, and actionable recommendations to empower farmers in decision-making. This sophisticated amalgamation of cutting-edge technologies not only addresses the inefficiencies of traditional farming but also paves the way for a more sustainable and efficient agricultural future. The presented system serves as a blueprint for leveraging IoT in agriculture, fostering data-driven precision farming and contributing to global food security.
  • Multimode Textile Array Antenna for Millimeter Wave Wearable Applications
    P. Ramya, , B. Deepa, R. Nirmala, Malathi Murugesan, K. Rama Abirami, S. Kannadhasan
    Journal of Communications, 2022
    The development of a multimode textile array antena for wearable applications is discussed in this study. For fabrication, copper sheet and conductive copper materials are employed. Because the body wear antenna is intended to function close to the human body, it should be lightweight and low profile. The performance of the suggested antenna is examined for different textile materials, which serve as its substrate. Additionally, a 1 x 4 antenna array is made to increase gain and bandwidth. According to the results, the designed antenna has high gain and directivity of 14dB and 10dB, respectively. Future 5G wireless devices may employ the frequencies obtained—27.08GHz, 30.16GHz, 38.62GHz, and 45.59GHz—as well as the reflection coefficients—-24.57dB, -13.735dB, -23.61dB, and -10.912dB, respectively. An excellent radiation pattern, good gain of 10.35 dB, and high directivity of 14.206 dB are all shown by the suggested patch antenna. Due to its very low profile, the antenna architecture is easily adaptable to systems where limited space is a major consideration. The antenna may be used for wearable applications and will be efficient for the next 5G applications since it is made of cotton.
  • Pattern Descriptors Orientation and MAP Firefly Algorithm Based Brain Pathology Classification Using Hybridized Machine Learning Algorithm
    B. Deepa, M. Murugappan, M. G. Sumithra, Mufti Mahmud, Mabrook S. Al-Rakhami
    IEEE Access, 2022
  • Weiner Filter based Hough Transform and Wavelet feature extraction with Neural Network for Classifying Brain Tumor
    B. Deepa, M.G. Sumithra, R. Mahesh Kumar, M. Suriya
    Proceedings of the 6th International Conference on Inventive Computation Technologies Icict 2021, 2021
  • Recital Study of Different Segmentation Techniques for Brain Tumor Detection
    B. Deepa, M. G. Sumithra, V. Chandran
    Lecture Notes in Electrical Engineering, 2021
  • An intensity factorized thresholding based segmentation technique with gradient discrete wavelet fusion for diagnosing stroke and tumor in brain MRI
    B. Deepa, M. G. Sumithra
    Multidimensional Systems and Signal Processing, 2019
  • Fusion-based segmentation technique for improving the diagnosis of MRI brain tumor in CAD applications
    Bharathi Deepa, Manimegalai Govindan Sumithra, Venkatesan Chandran, Varadan Gnanaprakash
    Lecture Notes in Computational Vision and Biomechanics, 2019
  • MRI Medical Image Fusion Using Gradient Based Discrete Wavelet Transform
    B. Deepa, M.G. Sumithra, T. Divya Bharathi, Soundarya Rajesh
    2017 IEEE International Conference on Computational Intelligence and Computing Research Iccic 2017, 2018
  • Performance analysis of various segmentation techniques for detection of brain abnormality
    M.G. Sumithra, B. Deepa
    IEEE Region 10 Annual International Conference Proceedings TENCON, 2017
  • MRI medical image denoising by combined spectral subtraction and wavelet based methods
    Arpn Journal of Engineering and Applied Sciences, 2015
  • A new hybrid approach for denoising medical images
    Deepa Bharathi, Sumithra Manimegalai Govindan
    Advances in Intelligent Systems and Computing, 2013
  • A new robust hybrid approach to enhance speech in mobile communication systems
    Sumithra
    American Journal of Applied Sciences, 2011