Energy-Efficient Cognitive MIMO Framework for Bedridden Patient Monitoring Using Deep Learning

International Journal of Electronics and Communication Engineering

© 2026 by SSRG - IJECE Journal

Volume 13 Issue 3

Year of Publication : 2026

Authors : G. Kalaimagal, M.S.Vasanthi

10.14445/23488549/IJECE-V13I3P119

How to Cite?

G. Kalaimagal, M.S.Vasanthi, "Energy-Efficient Cognitive MIMO Framework for Bedridden Patient Monitoring Using Deep Learning," SSRG International Journal of Electronics and Communication Engineering, vol. 13,  no. 3, pp. 227-240, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I3P119

Abstract:

In this article, a new approach for monitoring the temperature of bedridden patients is presented, which continues to pose a challenge. To solve this problem, a proposed Optimized MSE and Energy Efficiency Enhancement (Opti-MSEEE) algorithm, which uses underlay cognitive Multiple-Input Multiple-Output (MIMO) to send thermal images and a U-Net method to restore the images. This proposed work facilitates reliable thermal image transmission, restoration, and temperature prediction using an underlay cognitive MIMO system. The work incorporates a closed-form mathematical model based on the Optimized MSE and Energy Efficiency Enhancement (Opti-MSEEE) algorithm, which jointly minimizes the Sum Minimum Mean Square Error (Sum-MSE) and maximizes Energy Efficiency (EE) for transmission strategies. Simulation findings show that Opti MSEEE outperforms other schemes, which proves that it has better EE. To ensure image integrity, the work integrates a deep learning–based dynamic channel selection mechanism at the Cognitive Base Station (CBS) transmitter and employs a lightweight deep learning model, the Nonlinear Activation Free Network–lite version (NAFNet-lite), at the receiver for accurate image restoration. Comparative evaluation shows that NAFNet-lite achieved the highest Peak Signal-to-Noise Ratio (PSNR) of 31.2 dB and a Structural Similarity Index Measure (SSIM) of 0.794. Crucially, the deep learning model preserves thermal consistency, maintaining maximum and minimum temperatures closest to the original values, which is essential for diagnostic reliability. The full proposed work, the Thermal Image Cognitive Radio (TMCR) framework, was tested and confirmed using a specialized Raspberry Pi-based hardware testbed. Experimental results confirm that the reconstructed thermal images preserve fine structural details and accurate temperature information, highlighting the framework’s suitability for resource-constrained medical thermal image applications.

Keywords:

Underlay cognitive, Energy Efficiency, Peak Signal-to-Noise Ratio, Sum Minimum Mean Square Error, Structural Similarity Index Measure.

References:

[1] G. Premalatha, and V. Thulasi Bai, “Design and Implementation of Intelligent Patient in-House Monitoring System based on Efficient XGBoost-CNN Approach,” Cognitive Neurodynamics, vol. 16, pp. 1135-1149, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] David Gertsvolf et al., “A U-net Convolutional Neural Network Deep Learning Model Application for Identification of Energy Loss in Infrared Thermographic Images,” Applied Energy, vol. 360, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Himanshu Singh, and Millie Pant, “Auto-Minimum Resolvable Temperature Difference Method for Thermal Imagers,” Journal of Optics, vol. 50, pp. 689-700, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[4] S. Esakki Rajavel et al., “Energy Efficient Relay Selection Framework for 5G Communication using Cognitive Radio Networks,” Scientific Reports, vol. 15, pp. 1-12, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Umar Ghafoor, and Adil Masood Siddiqui, “Maximizing Energy Efficiency in 6G Cognitive Radio Network,” Digital Communications and Networks, vol. 11, no. 5, pp. 1356-1369, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Jianbin Liao et al., “Correction: Optimal Resource Allocation Method for Energy Harvesting Based Underlay Cognitive Radio Networks,” Plos one, vol. 18, no. 1, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Ramnaresh Yadav, Keshav Singh, and Ashwani Kumar, “Optimal Power Allocation for Achieving Secure Green Cognitive Radio Networks,” Electronics, vol. 11, no. 13, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Kai Zhang et al., “Learning Deep CNN Denoiser Prior for Image Restoration,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3929-3938, 2017.
[Google Scholar] [Publisher Link]
[9] Guanyu Liu et al., “A Lightweight Convolutional Network based on Pruning Algorithm for Yolo,” Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022), vol. 12705, pp. 302-311, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Ruiheng Zhang et al., “Graph-Based Few-Shot Learning with Transformed Feature Propagation and Optimal Class Allocation,” Neurocomputing, vol. 470, pp. 247-256, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Kai Zhang et al., “Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising,” IEEE Transactions on Image Processing, vol. 26, no. 7, pp. 3142-3155, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Kai Zhang, Wangmeng Zuo, and Lei Zhang, “FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising,” IEEE Transactions on Image Processing, vol. 27, no. 9, pp. 4608-4622, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zhendong Wang et al., “Uformer: A General U-Shaped Transformer for Image Restoration,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17683-17693, 2022.
[Google Scholar] [Publisher Link]
[14] Nipuni Ginige et al., “Efficient Channel Prediction for Beyond Diagonal RIS-Assisted MIMO Systems With Channel Aging,” IEEE Transactions on Vehicular Technology, vol. 74, no. 8, pp. 12658-12672, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ozan Oktay et al., “Attention U-Net: Learning Where to Look for the Pancreas,” arXiv preprint, pp. 1-10, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Zongwei Zhou et al., “UNet++: A Nested U-Net Architecture for Medical Image Segmentation,” Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Granada, Spain, pp. 3-11, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Siddharth Rawat., “Holographic Microscopy of Complex Fluids,” PhD Thesis, University of New South Wales (Australia), pp. 1-171, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Xinyi Gao, “A Method for Face Image Inpainting Based on Generative Adversarial Networks,” PhD Dissertation, Auckland University of Technology, New Zealand, pp. 1-95, 2022.
[Google Scholar] [Publisher Link]
[19] Emil Björnson, Jakob Hoydis, and Luca Sanguinetti, “Massive MIMO Networks: Spectral, Energy, and Hardware Efficiency,” Foundations and Trends® in Signal Processing, vol. 11, no. 3-4, pp. 154-655, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Mahmoud Zaher et al., “Learning-Based Downlink Power Allocation in Cell-Free Massive MIMO Systems,” IEEE Transactions on Wireless Communications, vol. 22, no. 1, pp. 174-188, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Huan Zhang et al., “Rate Maximization of Wireless-Powered Cognitive Massive MIMO Systems,” IEEE Internet of Things Journal, vol. 8, no. 7, pp. 5632-5644, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Neji Mensi, and Danda B. Rawat, “On the Performance of Partial RIS Selection vs. Partial Relay Selection for Vehicular Communications,” IEEE Transactions on Vehicular Technology, vol. 71, no. 9, pp. 9475-9489, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Mohamed A. Abdel-Moneim et al., “CNN-Based Modulation Classification using Image Processing Techniques for OFDM Underwater Acoustic Communication System,” Journal of Electrical Systems and Information Technology, vol. 12, pp. 1-29, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Jin Wang et al., “Pilot Optimization and Power Allocation for OFDM-Based Full-Duplex Relay Networks with IQ-Imbalances,” IEEE Access, vol. 5, pp. 24344-24352, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Xingxiang Peng, Peiran Wu, and Minghua Xia, “Optimization for Multicarrier MIMO SWIPT Systems under MSE QoS Constraint,” 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, pp. 1-5, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[26] R. Kanmani, and S. Mary Praveena, “Bio Inspired Multi Agent System for Distributed Power and Interference Management in MIMO OFDM Networks,” Scientific Reports, vol. 15, pp. 1-25, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[27] H. Yu et al., “Regularized Zero-Forcing Aided Hybrid Beamforming for Millimeter-Wave Multiuser MIMO Systems,” IEEE Transactions on Wireless Communications, vol. 22, no. 5, pp. 3280-3295, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Zhangliang Chen, “Power Allocation and Massive Mimo Channel Modeling for 5G Wireless Communications,” Dissertation University of Texas at Arlington, pp. 1-121, 2022.
[Google Scholar] [Publisher Link]
[29] Nasim Reza et al., “Thermal Imaging and Computer Vision Technologies for the Enhancement of Pig Husbandry: A Review,” Journal of Animal Science and Technology, vol. 66, no. 1, pp. 31-56, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[30] J. Zuluaga-Gomez et al., “A CNN-based Methodology for Breast Cancer Diagnosis using Thermal Images,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 9, no. 2, pp. 131-145, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[31] L.A. Bezerra et al., “An Empirical Correlation to Estimate Thermal Properties of the Breast and of the Breast Nodule using Thermographic Images and Optimization Techniques,” International Journal of Heat and Mass Transfer, vol. 149, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Massive MIMO Spatial Channel Model Dataset, Qualcomm Developer Network. [Online]. Available: https://www.qualcomm.com/developer/software/massive-mimo-spatial-channel-model-dataset
[33] Hu Cao et al., “Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation,” Computer Vision – ECCV 2022 Workshops, Tel Aviv, Israel, pp. 205-218, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[34] Yaopeng Peng, Danny Z. Chen, and Milan Sonka, “U-Net V2: Rethinking the Skip Connections of U-Net for Medical Image Segmentation,” 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), Houston, TX, USA, pp. 1-5, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[35] Agnesh Chandra Yadav, Maheshkumar H. Kolekar, and Mukesh Kumar Zope, “Modified Recurrent Residual Attention U-Net Model for MRI-based Brain Tumor Segmentation,” Biomedical Signal Processing and Control, vol. 102, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Giuseppe Nunnari, and Sonia Calvari, “Exploring Vision Transformers and Convolution Neural Networks for the Thermal Image Classification of Volcanic Activity,” Applied Sciences, vol. 15, no. 5, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Houssem Habbouche et al., “A Wavelet Transform-Based Transfer Learning Approach for Enhanced Shaft Misalignment Diagnosis in Rotating Machinery,” Electronics, vol. 14, no. 2, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[38] Dario Scilla et al., “Computer Vision Corrections Enhance UAV-Based Retrievals in Shallow Waters,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 18134-18149, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Tomas Vicar et al., “Cell Segmentation Methods for Label-free Contrast Microscopy: Review and Comprehensive Comparison,” BMC Bioinformatics, vol. 20, pp. 1-25, 2019.
[CrossRef] [Google Scholar] [Publisher Link]