Citation :

R. Venkatesan, A. Saravanan, "IOMT Source- Fuse: Cross-Attention Driven Latent Multi-Source Integration Framework," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 8, pp. 37-49, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I8P103

Abstract

IoMT systems are in high demand in the global market as the healthcare domain is a critically important factor in national development and citizens' well-being. Growing need requires optimisation in various stages of IoMT systems, which makes the system scalable and economical in practical deployment. One of the primary concerns in the IoMT systems is the data handling capacity of the overall system. In the IoMT system, prediction of the patient's condition is the primary criterion that requires high accuracy and precision. The accuracy and precision highly rely on the amount of data that the analysis provides, for efficient results. Therefore, it is a prime notion to consider the vast amount of patient data with dimensionality reduction without the loss of information. Data fusion is an efficient model that ensures data integrity by providing dimensionality reduction of information without compromising the original data. The proposed work utilises the data fusion approach for the IoMT system by fusing the input data at the feature level using the Variational Autoencoder and fusing the latent representation by the Multi-Head Cross-Attention model, which overcomes the limitations of conventional concatenation. The proposed work is validated using the EHR, Imaging, and IoT sensor data from Kaggle, achieving 94.6% accuracy with a high AUC score of 97.3%. The proposed work compared the prediction results with a single modality, where the data fusion predicted 2.2% higher compared to other single modality predictions.

Keywords

IoMT, Data Fusion, Variational Autoencoder, Good Health and Well-Being (SDG 3), Multi-Head Attention.

References

[1] Ali Ghubaish et al., “Recent Advances in the Internet-of-Medical-Things (IoMT) Systems Security,” IEEE Internet of Things Journal, vol. 8, no. 11, pp. 8707-8718, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Tahir Abbas et al., “IoMT-based Healthcare Systems: A Review,” Computer Systems Science and Engineering, vol. 48, no. 4, pp. 871-895, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Amirhossein Adavoudi Jolfaei, Seyed Farhad Aghili, and Dave Singelee, “A Survey on Blockchain-based IoMT Systems: Towards Scalability,” IEEE Access, vol. 9, pp. 148948-148975, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Muhammad Shafiq et al., “Advances in IoMT for Healthcare Systems,” Sensors, vol. 24, no. 1, pp. 1-6, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Imran Ahmed, Eulalia Balestrieri, and Francesco Lamonaca, “IoMT-based Biomedical Measurement Systems for Healthcare Monitoring: A Review,” Acta IMEKO, vol. 10, no. 2, pp. 174-184, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Shams Forruque Ahmed et al., “Insights into Internet of Medical Things (IoMT): Data Fusion, Security Issues and Potential Solutions,” Information Fusion, vol. 102, pp. 1-20, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Taher M. Ghazal et al., “IoMT-Enabled Fusion-based Model to Predict Posture for Smart Healthcare Systems,” Computers, Materials and Continua, vol. 71, no. 2, pp. 2579-2597, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Mian Ahmad Jan et al., “Lightweight and Smart Data Fusion Approaches for Wearable Devices of the Internet of Medical Things,” Information Fusion, vol. 103, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Hemant Ghayvat et al., “Revolutionising Healthcare: IoMT-Enabled Digital Enhancement via Multimodal ADL Data Fusion,” Information Fusion, vol. 111, pp. 1-14, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Fan Yang et al., “Internet-of-Things-Enabled Data Fusion Method for Sleep Healthcare Applications,” IEEE Internet of Things Journal, vol. 8, no. 21, pp. 15892-15905, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Xuhui Ding et al., “A Feasibility Study of Multi-Mode Intelligent Fusion Medical Data Transmission Technology of Industrial Internet of Things Combined with Medical Internet of Things,” Internet of Things, vol. 21, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[12] MD. Mobin Akhtar et al., “IoMT-based Smart Healthcare Monitoring System using Adaptive Wavelet Entropy Deep Feature Fusion and Improved RNN,” Multimedia Tools and Applications, vol. 82, no. 11, pp. 17353-17390, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Veselin Atanasov, and Yordan Sivkov, “Data Fusion for IoMT in Shipping,” 2020 21^st International Symposium on Electrical Apparatus and Technologies (SIELA), Bourgas, Bulgaria, pp. 1-6, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Hui Lin et al., “Privacy-Enhanced Data Fusion for COVID-19 Applications in Intelligent Internet of Medical Things,” IEEE Internet of Things Journal, vol. 8, no. 21, pp. 15683-15693, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Fei Zhao, Chengcui Zhang, and Baocheng Geng, “Deep Multimodal Data Fusion,” ACM Computing Surveys, vol. 56, no. 9, pp. 1-36, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Xuezhu Lin et al., “Multi-Sensor Data Fusion Method based on Self-Attention Mechanism,” Applied Sciences, vol. 13, no. 21, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Silvana M. Azcarate et al., “Data Handling in Data Fusion: Methodologies and Applications,” TrAC Trends in Analytical Chemistry, vol. 143, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Federico Castanedo, “A Review of Data Fusion Techniques,” The Scientific World Journal, vol. 2013, no. 1, pp. 1-19, 2013.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Yunhao Gao et al., “Cross-Scale Mixing Attention for Multisource Remote Sensing Data Fusion and Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-15, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[20] Zilong Huang et al., “CCNET: Criss-Cross Attention for Semantic Segmentation,” Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 603-612. 2019.
[Google Scholar] [Publisher Link]

[21] Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda, “CrossVIT: Cross-Attention Multi-Scale Vision Transformer for Image Classification,” 2021 IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 347-356, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[22] Hezheng Lin et al., “Cat: Cross Attention in Vision Transformer,” 2022 IEEE International Conference on Multimedia and Expo (ICME), Taipei, Taiwan, pp. 1-6, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[23] Mozhdeh Gheini, Xiang Ren, and Jonathan May, “Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation,” Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics,
Online and Punta Cana, Dominican Republic, pp. 1754-1765, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[24] Hui Li, and Xiao-Jun Wu, “CrossFuse: A Novel Cross Attention Mechanism based Infrared and Visible Image Fusion Approach,” Information Fusion, vol. 103, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[25] Wenjuan Han, Ge Wang, and Kewei Tu, “Latent Variable Autoencoder,” IEEE Access, vol. 7, pp. 48514-48523, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[26] Junhai Zhai et al., “Autoencoder and its Various Variants,” 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, pp. 415-419, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[27] Fei Yang et al., “Variable Rate Deep Image Compression with Modulated Autoencoder,” IEEE Signal Processing Letters, vol. 27, pp. 331-335, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[28] Jinwon An, and Sungzoon Cho, “Variational Autoencoder based Anomaly Detection using Reconstruction Probability,” Special Lecture on IE, vol. 2, no. 1, pp. 1-18, 2015.
[Google Scholar]

[29] Lucas Pinheiro Cinelli et al., Variational Autoencoder, Variational Methods for Machine Learning with Applications to Deep Networks, Springer, Cham, pp. 111-149, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[30] Abdullah Ayub Khan et al., “Blockchain-Enabled Secure Internet of Medical Things (IoMT) Architecture for Multi-Modal Data Fusion in Precision Cancer Diagnosis and Continuous Monitoring,” Journal of Cloud Computing, vol. 14, no. 1, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link]

[31] Sekione Reward Jeremiah et al., “Multi-View Learning and Model Fusion Framework for Threat Detection in Multi-Protocol IoMT Networks,” Information Fusion, vol. 125, 2026.
[CrossRef] [Google Scholar] [Publisher Link]

[32] Tongyue He et al., “Enhanced Detection of Early Parkinson’s Disease through Multi-Sensor Fusion on Smartphone-based IoMT Platforms,” Information Fusion, vol. 117, 2025.
[CrossRef] [Google Scholar] [Publisher Link]