Subha K J

@srmist.edu.in

Assistant Professor and Department of Networking and Communications
SRM Institute of Science and Technology, Kattankulathur

Subha K J


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Vision and Pattern Recognition, Artificial Intelligence, Signal Processing
12

Scopus Publications

47

Scholar Citations

4

Scholar h-index

1

Scholar i10-index

Scopus Publications

  • Deepfake Detection Utilizing Enhanced Silicon-Based Physically Unclonable Functions Integrated with Photonic Crystal Fiber Sensor
    V. Suresh Babu, M. Sathya, R. Uma Maheshwari, K. J. Subha
    Silicon, 2025
  • An improved ensemble deep learning framework for glaucoma detection
    K. J. Subha, R. Rajavel, B. Paulchamy
    Multimedia Tools and Applications, 2025
  • Design and Performance Analysis of a Low-Profile Spiral Antenna for C-Band Cognitive Radio Applications
    Josephine Pon Gloria Jeyaraj, M. Anto Bennet, K. J. Subha, Jebasingh Kirubakaran S J
    Proceedings of the 4th International Conference on Ubiquitous Computing and Intelligent Information Systems Icuis 2024, 2024
    This paper presents the design of a low-profile spiral antenna specifically for C-band cognitive radio applications. Spiral antennas, while traditionally recognized for their broad frequency response, can be optimized for narrowband use, maintaining consistent polarization and radiation patterns within a targeted frequency range. The design process, executed using CST Microwave Studio Suite, involves detailed analysis and optimization of the antenna's geometric parameters. Key performance metrics-including return loss, radiation pattern, voltage standing wave ratio (VSWR), gain, and directivity-are systematically evaluated. The proposed spiral antenna achieves a return loss of −25.307 dB, a VSWR of 1.1148, a gain of 5.38 dBi, and a directivity of 6.621 dBi, centered at a narrow bandwidth of 6.864 GHz. These results highlight the antenna's suitability for effective long-range communication in fixed satellite service applications, emphasizing its role in enhancing spectrum utilization in cognitive radio networks.
  • Performance Enhancement Strategies for Remaining Useful Life Estimation Using Advanced Recurrent Neural Network Models
    K.J. Subha, Josephine Pon Gloria Jeyaraj, M. Anto Bennet, T.R. Dinesh Kumar
    2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things Icoici 2024 Proceedings, 2024
    This research focuses on utilizing Artificial Intelligence with Recurrent Neural Networks (RNNs) for estimating the Remaining Useful Life (RUL) of bearings. Predictive Maintenance (PDM) techniques are employed to minimize unplanned downtime and associated costs. A data-driven approach is presented, specifically addressing bearing failures and emphasizing the importance of health indicators. The proposed RNN-based health indicator aims to predict the RUL by analyzing acceleration signals, overcoming challenges posed by interference from other machine components. Envelope spectrum analysis and spectral kurtosis are demonstrated as effective methods for diagnosing bearing faults. The project compares various engineered features and their corresponding RUL outputs obtained from the RNN.
  • Performance and Analysis of Skin Cancer Detection Using Deep Learning
    P. Hemanth, L. Dhanujay, G. Girinadh, M. Anto Bennet, K. J. Subha, Josephine Pon Gloria Jeyaraj
    2024 IEEE International Conference on Intelligent Techniques in Control Optimization and Signal Processing Incos 2024 Proceedings, 2024
    Skin cancer is notably one of the most dangerous expressions of this ailment, originating from DNA damage in skin cells that results in the formation of genetic abnormalities or mutations on the skin. The insidious characteristic of skin cancer lies in its inclination to gradually spread to other parts of the body, underscoring the importance of early detection for successful treatment. Given the increasing prevalence of skin cancer, its elevated mortality rate, and the significant expenses associated with medical interventions, prompt diagnosis becomes imperative. Acknowledging the severity of these challenges, researchers have developed various methods for the early identification of skin cancer. Parameters such as the symmetry, color, size, and shape of lesions are utilized to distinguish skin cancer and differentiate benign cases from melanoma. This paper explores deep learning approaches applied to the early detection of skin cancer, presenting the study's findings through tools, graphs, tables, techniques, and frameworks. This enhances comprehension and contributes to the body of knowledge in this critical field.
  • Alzheimer's Disease Recognition and Detection using Machine Learning
    M. Anto Bennet, Josephine Pon Gloria Jeyaraj, K. J. Subha, Ch. Sri Vidhya, K. Yamini, P. Laljan Pasha
    Proceedings of the 5th International Conference on Smart Electronics and Communication Icosec 2024, 2024
    Alzheimer’s disease is a neurological disorder marked by memory loss, diminished cognitive function, and difficulties with day-to-day activities. As the world’s population ages, Alzheimer’s disease has become a major public health concern. This review looks at what is now known about Alzheimer’s disease, including its causes, diagnosis techniques, and therapies. Amyloid plaques and tau neurofibrillary tangles are examples of abnormal protein clumps that accumulate in Alzheimer’s disease pathogenesis and cause synaptic dysfunction, neuronal death, and eventually cognitive impairment. Familial forms of Alzheimer’s disease have been linked to genetic mutations, including those in the APP, PSEN1, and PSEN2 genes.
  • Improved ensemble deep learning based retinal disease detection using image processing
    K.J. Subha, R. Rajavel, B. Paulchamy
    Journal of Intelligent and Fuzzy Systems, 2023
    The Retinal image analysis has received significant attention from researchers due to the compelling need of early detection systems that aid in the screening and treatment of diseases. Several automated retinal disease detection studies are carried out as part of retinal image processing. Heren an Improved Ensemble Deep Learning (IEDL) model has been proposed to detect the various retinal diseases with a higher rate of accuracy, having multiclass classification on various stages of deep learning algorithms. This model incorporates deep learning algorithms which automatically extract the properties from training data, that lacks in traditional machine learning approaches. Here, Retinal Fundus Multi-Disease Image Dataset (RFMiD) is considered for evaluation. First, image augmentation is performed for manipulating the existing images followed by upsampling and normalization. The proposed IEDL model then process the normalized images which is computationally intensive with several ensemble learning strategies like heterogeneous deep learning models, bagging through 5-fold cross-validation which consists of four deep learning models like ResNet, Bagging, DenseNet, EfficientNet and a stacked logistic regression for predicting purpose. The accuracy rate achieved by this method is 97.78%, with a specificity rate of 97.23%, sensitivity of 96.45%, precision of 96.45%, and recall of 94.23%. The model is capable of achieving a greater accuracy rate of 1.7% than the traditional machine learning methods.
  • Assessment and Evaluation of Deep Brain Stimulation Surgery Utilizing Convolutional Neural Networks in the Context of Adversarial Attack Strategies
    Josephine Pon Gloria Jeyaraj, M. Anto Bennet, K. J. Subha, M. Manimaraboopathy
    1st International Conference on Emerging Research in Computational Science Icercs 2023 Proceedings, 2023
    Deep brain stimulation is a widely employed treatment method for conditions like Parkinson’s disease, movement disorders, glaucoma, and psychological disorders. Authentication mechanisms within these systems are of paramount importance as they wield substantial influence over an individual’s immediate psychological, physical, and emotional well-being. The specially devised system proves to be effective in identifying diverse forms of replicated attack patterns and alerting medical professionals to potential threats. This research employs a combination of long short-term memory and convolutional neural networks to predict the majority of tremor rates, distinguishing between simulated and authentic stimulation.
  • Performance and Analysis of Optical Flow Techniques for Moving Object Segmentation & Detection in Infrared Tracking Method
    M. Anto Bennet, Subha KJ, S. Vinod, M. Shruthi, T. Sri Lakshmi
    Proceedings of the 4th International Conference on Smart Electronics and Communication Icosec 2023, 2023
    For the detection of small targets using video infrared (IR), Between video sequences, the spatio-temporal information is crucial. In order to estimate motion and identify tiny targets in IR, optical flow is frequently used correction in order to efficiently utilise the additional temporal information. The standard optical Nevertheless, the broad viewing distance and poor IR imaging speed cause the target's spatial location to vary often between two frames, which reduces the effectiveness of optical flow-based detection techniques. Our solution, an end-to-end video infrared microscopic target identification system is one that is more resistant to significant motion and capable of more precise motion compensation. Flow-based detection techniques are only able to detect very slight motion in video sequences. Nevertheless, the broad viewing distance and poor IR imaging speed cause the target's spatial location to vary often between two frames, which reduces the effectiveness of optical flow-based detection techniques. The end-to-end video infrared microscopic target identification system we propose is more robust to large motion and capable of more precise motion compensation. To do motion estimates in a more accurate manner, we first advise employing an optical flow reconstruction network with many scales. Finally, the neighbouring frames are synchronised to the reference frame using the generated optical flows. The detection network is then given the concatenated neighbourhood frames to obtain the detection results.
  • Analysis of Deep Learning based Optimization Techniques for Oral Cancer Detection
    K J Subha, M.Anto Bennet, Gaddam Pranay, Ketham Bharadwaj, Polu Vikram Reddy
    2023 4th International Conference on Electronics and Sustainable Communication Systems Icesc 2023 Proceedings, 2023
    The main aim is to examine the application of deep learning technique in detecting oral cancer at an early stage. The focus is on evaluating the performance of various optimization techniques to deep learning technique through analyzing images of the mouth and throat for oral cancer detection. The goal is to determine the most effective method for identifying oral cancer and gain insights into potential improvements. The importance of early detection of oral cancer cannot be overstated, as it plays a crucial role in improving patient outcomes through earlier treatment and higher survival rates. The findings have the potential to contribute to the development of more accurate and efficient methods for oral cancer diagnosis and make a positive impact in the field.
  • An Effective Method for Distinguishing Breathing and Infant Sleep Apnea Detection and Prevention using Python
    M. Anto Bennet, K.J. Subha, R. Kumutha, V. Rajmohan
    2022 1st International Conference on Computer Power and Communications Iccpc 2022 Proceedings, 2022
  • Deep Learning-Based Automatic Glaucoma Assessment Using Fundus Images
    KJ Subha, M. Anto Bennet, M. Manimaraboopathy, M.R. Arun
    2022 1st International Conference on Computer Power and Communications Iccpc 2022 Proceedings, 2022

RECENT SCHOLAR PUBLICATIONS

  • Non-Invasive Skin Cancer Classification Using a Machine Learning-Assisted Compact Terahertz Metamaterial Absorber
    JPG Jeyaraj, KJ Subha, A Vinayagam, MA Bennet, PK Devi
    2026 Third International Conference on Networking and Communications (ICNWC … , 2026
    2026
  • Performance Improvement in Video Processing using Quantum Computation
    JJP Gloria, A Vijayaprabhu, KJ Subha, MA Bennet, A Thanam, ...
    2025 IEEE International Conference on Compute, Control, Network & Photonics … , 2025
    2025
  • An improved ensemble deep learning framework for glaucoma detection
    KJ Subha, R Rajavel, B Paulchamy
    Multimedia Tools and Applications 84 (22), 25309-25323 , 2025
    2025
    Citations: 8
  • Design and Performance Analysis of a Low-Profile Spiral Antenna for C-Band Cognitive Radio Applications
    JPG Jeyaraj, MA Bennet, KJ Subha, JK SJ
    2024 4th International Conference on Ubiquitous Computing and Intelligent … , 2024
    2024
  • Alzheimer’s disease recognition and detection using machine learning
    MA Bennet, JPG Jeyaraj, KJ Subha, CS Vidhya, K Yamini, PL Pasha
    2024 5th international conference on smart electronics and communication … , 2024
    2024
    Citations: 2
  • Performance enhancement strategies for remaining useful life estimation using advanced recurrent neural network models
    KJ Subha, JPG Jeyaraj, MA Bennet, TRD Kumar
    2024 Second International Conference on Intelligent Cyber Physical Systems … , 2024
    2024
    Citations: 2
  • Performance and Analysis of Skin Cancer Detection Using Deep Learning
    P Hemanth, L Dhanujay, G Girinadh, MA Bennet, KJ Subha, JPG Jeyaraj
    2024 Third International Conference on Intelligent Techniques in Control … , 2024
    2024
    Citations: 1
  • Assessment and Evaluation of Deep Brain Stimulation Surgery Utilizing Convolutional Neural Networks in the Context of Adversarial Attack Strategies
    JPG Jeyaraj, MA Bennet, KJ Subha, M Manimaraboopathy
    2023 International Conference on Emerging Research in Computational Science … , 2023
    2023
    Citations: 1
  • Performance and Analysis of Optical Flow Techniques for Moving Object Segmentation & Detection in Infrared Tracking Method
    MA Bennet, KJ Subha, S Vinod, M Shruthi, TS Lakshmi
    2023 4th International Conference on Smart Electronics and Communication … , 2023
    2023
  • Analysis of deep learning based optimization techniques for oral cancer detection
    KJ Subha, MA Bennet, G Pranay, K Bharadwaj, PV Reddy
    2023 4th International Conference on Electronics and Sustainable … , 2023
    2023
    Citations: 4
  • Improved ensemble deep learning based retinal disease detection using image processing
    KJ Subha, R Rajavel, B Paulchamy
    Journal of Intelligent & Fuzzy Systems 45 (1), 1119-1130 , 2023
    2023
    Citations: 15
  • Deep learning-based automatic glaucoma assessment using fundus images
    KJ Subha, MA Bennet, M Manimaraboopathy, MR Arun
    2022 International Conference on Computer, Power and Communications (ICCPC … , 2022
    2022
    Citations: 6
  • An effective method for distinguishing breathing and infant sleep apnea detection and prevention using Python
    MA Bennet, KJ Subha, R Kumutha, V Rajmohan
    2022 International Conference on Computer, Power and Communications (ICCPC … , 2022
    2022
    Citations: 2
  • A study of segmentation and glaucoma diagnosis through fundus images using deep convolution neural network with transfer learning techniques
    K Subha, SK Mohideen
    International Journal of Mechanical Engineering 7 (1), 5395-5407 , 2022
    2022
    Citations: 4
  • An Effective Retinal Image Analysis To Diagnose Stargardt Disease Using Automated Algorithm
    KJ Subha, C Anu
    International Journal of Engineering Research & Technology (IJERT), RTICCT … , 2018
    2018
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • Improved ensemble deep learning based retinal disease detection using image processing
    KJ Subha, R Rajavel, B Paulchamy
    Journal of Intelligent & Fuzzy Systems 45 (1), 1119-1130 , 2023
    2023
    Citations: 15
  • An improved ensemble deep learning framework for glaucoma detection
    KJ Subha, R Rajavel, B Paulchamy
    Multimedia Tools and Applications 84 (22), 25309-25323 , 2025
    2025
    Citations: 8
  • Deep learning-based automatic glaucoma assessment using fundus images
    KJ Subha, MA Bennet, M Manimaraboopathy, MR Arun
    2022 International Conference on Computer, Power and Communications (ICCPC … , 2022
    2022
    Citations: 6
  • Analysis of deep learning based optimization techniques for oral cancer detection
    KJ Subha, MA Bennet, G Pranay, K Bharadwaj, PV Reddy
    2023 4th International Conference on Electronics and Sustainable … , 2023
    2023
    Citations: 4
  • A study of segmentation and glaucoma diagnosis through fundus images using deep convolution neural network with transfer learning techniques
    K Subha, SK Mohideen
    International Journal of Mechanical Engineering 7 (1), 5395-5407 , 2022
    2022
    Citations: 4
  • Alzheimer’s disease recognition and detection using machine learning
    MA Bennet, JPG Jeyaraj, KJ Subha, CS Vidhya, K Yamini, PL Pasha
    2024 5th international conference on smart electronics and communication … , 2024
    2024
    Citations: 2
  • Performance enhancement strategies for remaining useful life estimation using advanced recurrent neural network models
    KJ Subha, JPG Jeyaraj, MA Bennet, TRD Kumar
    2024 Second International Conference on Intelligent Cyber Physical Systems … , 2024
    2024
    Citations: 2
  • An effective method for distinguishing breathing and infant sleep apnea detection and prevention using Python
    MA Bennet, KJ Subha, R Kumutha, V Rajmohan
    2022 International Conference on Computer, Power and Communications (ICCPC … , 2022
    2022
    Citations: 2
  • An Effective Retinal Image Analysis To Diagnose Stargardt Disease Using Automated Algorithm
    KJ Subha, C Anu
    International Journal of Engineering Research & Technology (IJERT), RTICCT … , 2018
    2018
    Citations: 2
  • Performance and Analysis of Skin Cancer Detection Using Deep Learning
    P Hemanth, L Dhanujay, G Girinadh, MA Bennet, KJ Subha, JPG Jeyaraj
    2024 Third International Conference on Intelligent Techniques in Control … , 2024
    2024
    Citations: 1
  • Assessment and Evaluation of Deep Brain Stimulation Surgery Utilizing Convolutional Neural Networks in the Context of Adversarial Attack Strategies
    JPG Jeyaraj, MA Bennet, KJ Subha, M Manimaraboopathy
    2023 International Conference on Emerging Research in Computational Science … , 2023
    2023
    Citations: 1
  • Non-Invasive Skin Cancer Classification Using a Machine Learning-Assisted Compact Terahertz Metamaterial Absorber
    JPG Jeyaraj, KJ Subha, A Vinayagam, MA Bennet, PK Devi
    2026 Third International Conference on Networking and Communications (ICNWC … , 2026
    2026
  • Performance Improvement in Video Processing using Quantum Computation
    JJP Gloria, A Vijayaprabhu, KJ Subha, MA Bennet, A Thanam, ...
    2025 IEEE International Conference on Compute, Control, Network & Photonics … , 2025
    2025
  • Design and Performance Analysis of a Low-Profile Spiral Antenna for C-Band Cognitive Radio Applications
    JPG Jeyaraj, MA Bennet, KJ Subha, JK SJ
    2024 4th International Conference on Ubiquitous Computing and Intelligent … , 2024
    2024
  • Performance and Analysis of Optical Flow Techniques for Moving Object Segmentation & Detection in Infrared Tracking Method
    MA Bennet, KJ Subha, S Vinod, M Shruthi, TS Lakshmi
    2023 4th International Conference on Smart Electronics and Communication … , 2023
    2023