Murukessan Perumal

Murukessan Perumal

Auto-generated profile, based on publicly available information

Murukessan Perumal

National Institute of Technology

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2020 in Chaos, Solitons & Fractals
Verified
Journal Article
Closed access
MYMilind Yadav
Milind Yadav
MPMurukessan Perumal
Murukessan Perumal
MSM Srinivas
M Srinivas

3 March 2022 in ISA Transactions
Verified
Journal Article
Closed access
MPMurukessan Perumal
Murukessan Perumal
ANAkshay Nayak
Akshay Nayak
RSR. Praneetha Sree
R. Praneetha Sree
MSM. Srinivas
M. Srinivas

25 December 2023 in IEEE Transactions on Industry Applications
Verified
Journal Article
Closed access
UVU. Shivani Sri Varshini
U. Shivani Sri Varshini
RSR. Praneetha Sree
R. Praneetha Sree
MPMurukessan Perumal
Murukessan Perumal
MSM. Srinivas
M. Srinivas
RSR. B. V. Subramanyam
R. B. V. Subramanyam
The importance of renewable energy in our everyday lives cannot be overstated, specifically highlighting solar and wind energies as two crucial sustainable power sources. Nevertheless, it is crucial to acknowledge that the amount of energy derived from renewable sources is subjected to variability, being influenced by environmental conditions. To ensure efficient management of energy load demands in diverse applications and enhance the performance of storage grids, precise energy production forecasting is vital. However, existing models doesn't recognise the important variables for forecasting and fails in the presence of noisy or missing data. To address these issues, we proposed a MultiStep Multi Variate Deep Attention Network (MSMVAN) model with masked attention and dilated Fourier convolutions. The proposed approach utilizes a sequential model to analyze non-linear relationships in time series data. Further, dilated fourier convolutions are incorporated to capture multistep spatial and cross correlations, while attention mechanisms are employed to identify significant variables. As a result, the model acquires improved vector representations, leading to enhanced energy forecasting power. We evaluated our model on three standard datasets and from the experimental results we conclude that our proposed model outperforms the state-of-the-art models in forecasting solar and wind energy.

4 October 2023 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
MPMurukessan Perumal
Murukessan Perumal
MSM Srinivas
M Srinivas

23 April 2025 in bioRxiv
Verified
Preprint
Open access
PDF file
MPMurukessan Perumal
Murukessan Perumal
MSM Srinivas
M Srinivas
Medical data is not available for public access due to privacy concerns of the patients and the stakeholders’ trust-worthiness. However, Artificial Intelligence, especially all deeplearning models, is data-hungry and fails to produce clinically relevant results without much data. Moreover, augmentation strategies are deployed to overcome the less data hurdle. The promising future in this direction is generative AI-augmented data. The chat-GPT and DALLE-2 have become commercial products leveraging the generative AI in Natural Language Processing and Computer Vision. The diffusion models have started giving many promising results in the generative AI in computer vision. And in medical imaging, they can potentially create synthetic data to augment the scarce dataset. Diffusion models coupled with federated learning can create synthetic data on a large scale without the need to violate data privacy. This synthetic dataset could be used for further training of deep learning models without the issues of patients’ identity theft from reverse engineering data. A Federated Learning paradigm of diffusion models has been proposed to overcome this hurdle and its related challenges. Our work focuses on diffusion models in federated learning settings. We named our novel model FMed-Diffusion or Federated Learning on Medical Image Diffusion. We trained our model under distributed federated settings imitating real-world clinical settings. We have achieved impressive results over three medical image datasets, APTOS 2019 Blindness Detection, Retinal OCT Detection, and COVID-CT Detection in the federated setting on par with the traditional training. Our model FMed-Diffusion has achieved an FID score of 7.1821 on the APTOS 2019 Blindness Detection dataset, an FID score of 8.8154 on the Retinal OCT Detection dataset, and an FID score of 7.4486 on the COVID-CT Detection dataset.

3 July 2024
Verified
Book Chapter
Closed access
PDF file
MPMurukessan Perumal
Murukessan Perumal
EGE. Goutham
E. Goutham
UVU. Shivani Sri Varshini
U. Shivani Sri Varshini
MSM. Srinivas
M. Srinivas
RSR. B. V. Subramanyam
R. B. V. Subramanyam