Murukessan Perumal

@srmist.edu.in

Assistant Professor, Engineering & Technology
SRM IST Kattankulathur Chennai

Murukessan Perumal


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Science, Computer Vision and Pattern Recognition
15

Scopus Publications

285

Scholar Citations

5

Scholar h-index

4

Scholar i10-index

Scopus Publications

  • Segmentation Studies on Al-Si-Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions
    Abeyram M. Nithin, Murukessan Perumal, M. J. Davidson, M. Srinivas, C. S. P. Rao, Katika Harikrishna, Jayant Jagtap, Abhijit Bhowmik, A. Johnson Santhosh
    Engineering Reports, 2025
    Segmenting metallographic pictures is being done in material science and related domains in order to detect the features within them. Therefore, it becomes crucial to find grains and secondary phase particles. It is necessary to label every pixel in order to obtain satisfactory segmentation outcomes. However, labeling takes a lot of time and is physically taxing. Therefore, in order to obtain higher performance, we have suggested a semi‐supervised deep learning technique in the current study that uses fewer labeled images. Other deep learning algorithms, such as Segnet, Resnet, and FCN, were compared with the Unet approach that was suggested. Additional comparisons have been made using the Dice score (0.85), IOU score (0.74), F1 (0.85), and recall (0.96) measures. Different loss functions were also compared, including binary, SS loss, and Tversky. Furthermore, the dataset was expanded, and these datasets were also subjected to result analysis. The trials show that, both numerically and qualitatively, the suggested approach can produce superior outcomes with fewer labeled photos.
  • PCNNTB: Pre-Activated Deep Convolutional Neural Networks Based Tuberculosis Severity Classification
    K Jenni, Murukessan Perumal, M. Srinivas
    Proceedings 2024 Rivf International Conference on Computing and Communication Technologies Rivf 2024, 2024
    Tuberculosis (TB) is a infection disease and mainly it affects the human lungs. As stated by the World Health Organization, 10.6 million population of the whole world is affected with Tuberculosis. If we diagnose TB at an early stage, then we can control this disease. Tuberculosis is a major challenge problem for immunocompromised HIV/AIDS patients. In this paper, we proposes a novel technique to automatically detect and classify the Tuberculosis using the Preactivated Deep Convolutional Neural Networks Based Tuberculosis Learner method (PCNNTB). The proposed deep learning model provides more discriminate information to more accurately classify the positive or negative images. In this work, the performance of the proposed method is evaluated on the standard ImageClef 2019 dataset. The experimental results demonstrate the proposed method provides promising results on ImageClef 2019 challenging dataset.
  • DeYOLO: A CNN Based Novel Approach for Classification and Localization of Pneumonia in Chest Radiographs
    Murukessan Perumal, E. Goutham, Debraj Das, M. Srinivas
    Communications in Computer and Information Science, 2024
  • USE_Res2Net:Automatic Plant Image Classification Using Squeeze and Excitation
    Murukessan Perumal, K Jenni, Lahari Karimajji, M Srinivas
    Proceedings 2024 Rivf International Conference on Computing and Communication Technologies Rivf 2024, 2024
    Recent approaches and advances in computer vision have paved the way for employing deep and neural networks in wide-reaching image recovery tasks. One of the applications includes automated plant leaf disease classification. Crop diseases are a one of the important threat to the steady food supply for billions of people, and a substantial fragment of the crop fields are affected with the different type of diseases each and every year and thus are lost to them, leading to an immense loss in agricultural yield to millions of smallholder farmers around the globe. The main aim of this work is to predict or classify the most probable plant species (either with an affected disease or a healthy crop if no disease is diagnosed) for each and every observation of the images taken by the farmers with mobile. The proposed approach is named the USE_Res2Net model, which identifies different diseases. The input images collected from the PlantVillage dataset were few in number for some classes of crop diseases. In this proposed method, various image based data augmentation methods are used to avoid the over-fitting problem and improve the classification accuracy. The proposed model USE_Res2Net achieves an accuracy of 99% on standard dataset.
  • FResFormer: Leukemia Detection Using Fusion-Enabled CNN and Attention
    Murukessan Perumal, E. Goutham, U. Shivani Sri Varshini, M. Srinivas, R. B. V. Subramanyam
    Communications in Computer and Information Science, 2024
  • DenSplitnet: Classifier-invariant neural network method to detect COVID-19 in chest CT data
    Murukessan Perumal, M Srinivas
    Journal of Visual Communication and Image Representation, 2023
  • CSA-BERT: Video Question Answering
    Kommineni Jenni, M Srinivas, Roshni Sannapu, Murukessan Perumal
    IEEE Workshop on Statistical Signal Processing Proceedings, 2023
    Convolutional networks are a key component of many computer vision applications. However, convolutions have a serious flaw. It only works in a small area, hence it lacks global information. The Attention method, on the other hand, is a new improvement in capturing long range interactions that has mostly been used to sequence modeling and generative modeling tasks. As an alternative to convolutions, we investigate the use of convolutions with an attention mechanism in a video question answering task. We present a unique self-attention mechanism based on convolutions that outperforms convolutions in the video question answering task. We discovered that combining convolutions with self-attention produces the greatest outcomes in experiments. As a result, we propose a hybrid idea, which combines convolutional operators with the self-attention mechanism. We combine convolutional feature maps with self-attention feature maps. Experiments show that convolution with self-attention improves video question answering tasks on the MSRVTT-QA dataset.
  • HF-Detect A Hybrid Detector for Manipulated Face Detection
    Ankit Shakya, K. Jenni, Murukessan Perumal, M. Srinivas
    IEEE Region 10 Annual International Conference Proceedings TENCON, 2023
    The recent advancement of fake face creation and fake face generation motivates the development of an excellent fake face detection method that can effectively detect the difference between fake and real. Various fake detection methods are available with adequate performance, but the limitation of those available methods is they are not performing well with highly compressed images with degraded quality. Manipulation of face images is getting advanced, and becoming difficult to trust the content over the media, and generating and detection should go parallelly to balance society. Therefore we are proposing a novel approach to solve this problem which uses the hybrid model HF-Detect, which combines the advantage of the Xception network along with the F<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup>Net.
  • IFSI:Identification of Forged and Stego Images using Deep Learning Method
    E Goutham, U. Shivani Sri Varshini, Murukessan Perumal, M Srinivas
    2023 IEEE 20th India Council International Conference Indicon 2023, 2023
    This research signifies our present in opting out Forged files and segregation of Steganographic content using a set of algorithms which were based after human brains which we termed as convolutional neural network(CNN’s). These networks are elucidating the sensational data through clustered raw supplements and machine cognizance. CNN’s are sketched for extracting consequential and insightful and sensitive features which are pertinent to classification. We have considered the two distinct tasks: 1) Recognition of images that have been forged has been carried out which is exposing the altered images that incorporates both extension and signatures. In parallel to this, we have predicted the original essence of counterfeited files by using the AmoebaNet that have been segregating them which are useful for extensive image classification by increasing the ConvNet depth. 2) We have conceded the stego images by applying EfficientNet which is used for classifying stego and non stego images. We have highly prioritized these networks over VGG16 and ResNet as widening the network should helps in making the network to classify more efficiently. In our research, we have used ImageCLEF 2019 data set for rooting out modified images and for recognizing the steganographic content.
  • Attention-based Deep Neural Network for Wind Power and Solar Radiation Prediction
    U. Shivani Sri Varshini, Murukessan Perumal, M. Srinivas, R.B.V. Subramanyam
    2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen Technologies Globconht 2023, 2023
    Renewable energy is essential in day-to-day human life where we focus on two renewable energies such as solar, and wind energies. Solar and Wind power changes dynamically, depends on location, and it is important to predict the energy in the future to manage the load requirement in various applications. Predicting energy accurately in the presence of noisy or missing values is difficult. To accurately predict the energy, we proposed a BiLSTM with masked attention where the masked values are predicted by the model and learnt better vector representations for the data. We evaluated the proposed model on two datasets Hi-SEAS and California-ISO. From the results obtained, we can conclude that the proposed model outperforms the state-of-the-art models with the lowest MSE value of 0.002863 for Hi-SEAS solar radiation prediction and 0.001141 for California-ISO wind power energy prediction.
  • MSMVAN: Multi Step Multi Variate Deep Attention Network for Renewable Energy Forecast
    U. Shivani Sri Varshini, R. Praneetha Sree, Murukessan Perumal, M. Srinivas, R. B. V. Subramanyam
    IEEE Transactions on Industry Applications, 2023
  • INASNET: Automatic identification of coronavirus disease (COVID-19) based on chest X-ray using deep neural network
    Murukessan Perumal, Akshay Nayak, R. Praneetha Sree, M. Srinivas
    ISA Transactions, 2022
  • Facial expression recognition using fusion of deep learning and multiple features
    M. Srinivas, Sanjeev Saurav, Akshay Nayak, A. P. Murukessan
    Machine Learning Algorithms and Applications, 2021
  • Automate Allocation of Secure Slice in Future Mobile Networks using Machine Learning
    Muddu Krishnama Naidu Immadisetti, Murukessan A P, M. Srinivas
    2021 12th International Conference on Computing Communication and Networking Technologies Icccnt 2021, 2021
  • Analysis on novel coronavirus (COVID-19) using machine learning methods
    Milind Yadav, Murukessan Perumal, M Srinivas
    Chaos Solitons and Fractals, 2020

RECENT SCHOLAR PUBLICATIONS

  • FMed-Diffusion Federated Learning on Medical Image Diffusion
    M Perumal, M Srinivas
    bioRxiv, 2025.04. 22.649958 , 2025
    2025
    Citations: 1
  • Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions
    AM Nithin, M Perumal, MJ Davidson, M Srinivas, CSP Rao, K Harikrishna, ...
    Engineering Reports 7 (4), e70119 , 2025
    2025
    Citations: 4
  • USE_Res2Net: Automatic Plant Image Classification Using Squeeze and Excitation
    M Perumal, K Jenni, L Karimajji, M Srinivas
    2024 RIVF International Conference on Computing and Communication … , 2024
    2024
  • PCNNTB: Pre-Activated Deep Convolutional Neural Networks Based Tuberculosis Severity Classification
    K Jenni, M Perumal, M Srinivas
    2024 RIVF International Conference on Computing and Communication … , 2024
    2024
  • MSMVAN: Multi Step Multi Variate Deep Attention Network for Renewable Energy Forecast
    USS Varshini, RP Sree, M Perumal, M Srinivas, RBV Subramanyam
    IEEE Transactions on Industry Applications 60 (2), 2462-2470 , 2023
    2023
    Citations: 10
  • IFSI: Identification of Forged and Stego Images using Deep Learning Method
    E Goutham, USS Varshini, M Perumal, M Srinivas
    2023 IEEE 20th India Council International Conference (INDICON), 1336-1340 , 2023
    2023
    Citations: 1
  • DenSplitnet: Classifier-invariant neural network method to detect COVID-19 in chest CT data
    M Perumal, M Srinivas
    Journal of Visual Communication and Image Representation 97, 103949 , 2023
    2023
    Citations: 5
  • DeYOLO: A CNN Based Novel Approach for Classification and Localization of Pneumonia in Chest Radiographs
    M Perumal, E Goutham, D Das, M Srinivas
    International Conference on Computer Vision and Image Processing, 382-393 , 2023
    2023
    Citations: 1
  • FResFormer: Leukemia Detection Using Fusion-Enabled CNN and Attention
    M Perumal, E Goutham, U Shivani Sri Varshini, M Srinivas, ...
    International Conference on Computer Vision and Image Processing, 137-146 , 2023
    2023
    Citations: 1
  • HF-Detect A Hybrid Detector for Manipulated Face Detection
    A Shakya, K Jenni, M Perumal, M Srinivas
    TENCON 2023-2023 IEEE Region 10 Conference (TENCON), 1-5 , 2023
    2023
    Citations: 2
  • CSA-BERT: Video Question Answering
    K Jenni, M Srinivas, R Sannapu, M Perumal
    2023 IEEE Statistical Signal Processing Workshop (SSP), 532-536 , 2023
    2023
    Citations: 2
  • Attention-based deep neural network for wind power and solar radiation prediction
    USS Varshini, M Perumal, M Srinivas, RBV Subramanyam
    2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen … , 2023
    2023
    Citations: 2
  • INASNET: Automatic identification of coronavirus disease (COVID-19) based on chest X-ray using deep neural network
    M Perumal, A Nayak, RP Sree, M Srinivas
    ISA transactions 124, 82-89 , 2022
    2022
    Citations: 30
  • Facial expression recognition using fusion of deep learning and multiple features
    M Srinivas, S Saurav, A Nayak, AP Murukessan
    Machine Learning Algorithms and Applications, 229-246 , 2021
    2021
    Citations: 2
  • Automate allocation of secure slice in future mobile networks using machine learning
    MKN Immadisetti, AP Murukessan, M Srinivas
    2021 12th International Conference on Computing Communication and Networking … , 2021
    2021
    Citations: 11
  • Analysis on novel coronavirus (COVID-19) using machine learning methods
    M Yadav, M Perumal, M Srinivas
    Chaos, Solitons & Fractals 139, 110050 , 2020
    2020
    Citations: 213

MOST CITED SCHOLAR PUBLICATIONS

  • Analysis on novel coronavirus (COVID-19) using machine learning methods
    M Yadav, M Perumal, M Srinivas
    Chaos, Solitons & Fractals 139, 110050 , 2020
    2020
    Citations: 213
  • INASNET: Automatic identification of coronavirus disease (COVID-19) based on chest X-ray using deep neural network
    M Perumal, A Nayak, RP Sree, M Srinivas
    ISA transactions 124, 82-89 , 2022
    2022
    Citations: 30
  • Automate allocation of secure slice in future mobile networks using machine learning
    MKN Immadisetti, AP Murukessan, M Srinivas
    2021 12th International Conference on Computing Communication and Networking … , 2021
    2021
    Citations: 11
  • MSMVAN: Multi Step Multi Variate Deep Attention Network for Renewable Energy Forecast
    USS Varshini, RP Sree, M Perumal, M Srinivas, RBV Subramanyam
    IEEE Transactions on Industry Applications 60 (2), 2462-2470 , 2023
    2023
    Citations: 10
  • DenSplitnet: Classifier-invariant neural network method to detect COVID-19 in chest CT data
    M Perumal, M Srinivas
    Journal of Visual Communication and Image Representation 97, 103949 , 2023
    2023
    Citations: 5
  • Segmentation Studies on Al‐Si‐Mg Metallographic Images Using Various Different Deep Learning Algorithms and Loss Functions
    AM Nithin, M Perumal, MJ Davidson, M Srinivas, CSP Rao, K Harikrishna, ...
    Engineering Reports 7 (4), e70119 , 2025
    2025
    Citations: 4
  • HF-Detect A Hybrid Detector for Manipulated Face Detection
    A Shakya, K Jenni, M Perumal, M Srinivas
    TENCON 2023-2023 IEEE Region 10 Conference (TENCON), 1-5 , 2023
    2023
    Citations: 2
  • CSA-BERT: Video Question Answering
    K Jenni, M Srinivas, R Sannapu, M Perumal
    2023 IEEE Statistical Signal Processing Workshop (SSP), 532-536 , 2023
    2023
    Citations: 2
  • Attention-based deep neural network for wind power and solar radiation prediction
    USS Varshini, M Perumal, M Srinivas, RBV Subramanyam
    2023 IEEE IAS Global Conference on Renewable Energy and Hydrogen … , 2023
    2023
    Citations: 2
  • Facial expression recognition using fusion of deep learning and multiple features
    M Srinivas, S Saurav, A Nayak, AP Murukessan
    Machine Learning Algorithms and Applications, 229-246 , 2021
    2021
    Citations: 2
  • FMed-Diffusion Federated Learning on Medical Image Diffusion
    M Perumal, M Srinivas
    bioRxiv, 2025.04. 22.649958 , 2025
    2025
    Citations: 1
  • IFSI: Identification of Forged and Stego Images using Deep Learning Method
    E Goutham, USS Varshini, M Perumal, M Srinivas
    2023 IEEE 20th India Council International Conference (INDICON), 1336-1340 , 2023
    2023
    Citations: 1
  • DeYOLO: A CNN Based Novel Approach for Classification and Localization of Pneumonia in Chest Radiographs
    M Perumal, E Goutham, D Das, M Srinivas
    International Conference on Computer Vision and Image Processing, 382-393 , 2023
    2023
    Citations: 1
  • FResFormer: Leukemia Detection Using Fusion-Enabled CNN and Attention
    M Perumal, E Goutham, U Shivani Sri Varshini, M Srinivas, ...
    International Conference on Computer Vision and Image Processing, 137-146 , 2023
    2023
    Citations: 1
  • USE_Res2Net: Automatic Plant Image Classification Using Squeeze and Excitation
    M Perumal, K Jenni, L Karimajji, M Srinivas
    2024 RIVF International Conference on Computing and Communication … , 2024
    2024
  • PCNNTB: Pre-Activated Deep Convolutional Neural Networks Based Tuberculosis Severity Classification
    K Jenni, M Perumal, M Srinivas
    2024 RIVF International Conference on Computing and Communication … , 2024
    2024