A Hybrid Noise Reduction And Normalization Framework For Improving Multimodal Sensor Data Quality In Real-Time Systems

Kim Sa Ram; Park Ji Hoon; Hong Jae  Yeon

doi:10.51903/jtie.v4i3.440

Authors

Kim Sa Ram Dongguk University, Seoul, South Korea, 04620
Park Ji Hoon Dongguk University, Seoul, South Korea, 04620
Hong Jae Yeon Dongguk University, Seoul, South Korea, 04620

DOI:

https://doi.org/10.51903/jtie.v4i3.440

Keywords:

Multimodal sensor data, Wavelet denoising, Kalman filter, Adaptive normalization

Abstract

Multimodal sensor data, integrating signals such as RGB, LiDAR, and IMU, plays a pivotal role in enabling intelligent decision-making in real-time Internet of Things (IoT) systems. However, these data streams are inherently prone to complex noise patterns, cross-sensor inconsistencies, and scaling disparities that conventional preprocessing techniques often fail to address comprehensively. This paper presents a hybrid data preprocessing framework that unifies advanced denoising and adaptive normalization in a single, context-aware pipeline. The framework leverages wavelet-based denoising for high-frequency noise suppression, Kalman filtering for dynamic state estimation, and a real-time adaptive normalization mechanism that calibrates data scaling based on temporal and environmental contexts. Evaluations on synchronized multimodal IoT datasets comprising RGB, LiDAR, and IMU recordings under low-light, high-noise, and adverse-weather conditions (≈ 18,000 aligned samples; 30 Hz, 10 Hz, 100 Hz) show significant performance gains. Results indicate a 30.4% RMSE reduction (p < 0.05), 33% faster convergence, and only 34% computational overhead, while maintaining real-time feasibility with a 41 ms latency per frame. These findings confirm that combining complementary denoising paradigms with adaptive, context-driven normalization enhances signal fidelity and responsiveness in dynamic sensing environments. This contribution presents a reproducible, statistically validated hybrid preprocessing framework for enhancing the quality of multimodal sensor data, enabling more reliable deployments in industrial automation, environmental monitoring, and intelligent transport systems.

References

Baldazzi, G., Solinas, G., Valle, J. Del, Barbaro, M., Micera, S., Raffo, L., & Pani, D. (2020). Systematic analysis of wavelet denoising methods for neural signal processing. Journal of Neural Engineering, 17(6). https://doi.org/10.1088/1741-2552/abc741

Bijelic, M., Gruber, T., Mannan, F., Kraus, F., Ritter, W., Dietmayer, K., & Heide, F. (2020). Seeing Through Fog Without Seeing Fog: Deep Multimodal Sensor Fusion in Unseen Adverse Weather.

Bnou, K., Raghay, S., & Hakim, A. (2020). A wavelet denoising approach based on unsupervised learning model. Eurasip Journal on Advances in Signal Processing, 2020(1). https://doi.org/10.1186/s13634-020-00693-4

Cao, R., Wang, Y., Lin, Y., & Zhang, Y. (2022). An Efficient Preprocessing Approach for Airborne Hybrid SAR and ISAR Imaging of Ship Target Based on Kernel Distribution. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 5147–5162. https://doi.org/10.1109/JSTARS.2022.3183196

Chen, W., Zheng, M., Gao, Q., Deng, C., Ma, Y., & Ji, G. (2021). Simulation of surface runoff control effect by permeable pavement. Water Science and Technology, 83(4), 948–960. https://doi.org/10.2166/wst.2021.027

Duan, S., Shi, Q., & Wu, J. (2022). Multimodal Sensors and ML‐Based Data Fusion for Advanced Robots. Advanced Intelligent Systems, 4(12). https://doi.org/10.1002/aisy.202200213

Fan, X., Wang, Q., Ke, J., Yang, F., Gong, B., & Zhou, M. (2021). Adversarially Adaptive Normalization for Single Domain Generalization.

Faye, B., Azzag, H., Lebbah, M., & Bouchaffra, D. (2024). Adaptative Context Normalization: A Boost for Deep Learning in Image Processing. http://arxiv.org/abs/2409.04759

Faye, B., Azzag, H., Lebbah, M., & Fang, F. (2024). Unsupervised Adaptive Normalization. http://arxiv.org/abs/2409.04757

Feng, S., Li, X., Zhang, S., Jian, Z., Duan, H., & Wang, Z. (2023). A review: state estimation based on hybrid models of Kalman filter and neural network. In Systems Science and Control Engineering (Vol. 11, Issue 1). Taylor and Francis Ltd. https://doi.org/10.1080/21642583.2023.2173682

Gao, J., Li, P., Chen, Z., & Zhang, J. (2020). A survey on deep learning for multimodal data fusion. In Neural Computation (Vol. 32, Issue 5, pp. 829–864). MIT Press Journals. https://doi.org/10.1162/neco_a_01273

Greenberg, I., Yannay, N., & Mannor, S. (2023). Optimization or Architecture: How to Hack Kalman Filtering.

He, D., Xu, W., & Zhang, F. (2021). Kalman Filters on Differentiable Manifolds. http://arxiv.org/abs/2102.03804

Huang, J. J., & Dragotti, P. L. (2022). WINNet: Wavelet-Inspired Invertible Network for Image Denoising. IEEE Transactions on Image Processing, 31, 4377–4392. https://doi.org/10.1109/TIP.2022.3184845

Huang, L., Qin, J., Zhou, Y., Zhu, F., Liu, L., & Shao, L. (2020). Normalization Techniques in Training DNNs: Methodology, Analysis and Application. http://arxiv.org/abs/2009.12836

Huang, M.-H., & Rust, R. T. (2020). A strategic framework for artificial intelligence in marketing. https://doi.org/10.1007/s11747-020-00749-9/Published

Jagadesh, B. N., Mantena, S. V., Sathe, A. P., Prabhakara Rao, T., Lella, K. K., Pabboju, S. S., & Vatambeti, R. (2025). Enhancing food recognition accuracy using hybrid transformer models and image preprocessing techniques. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-90244-4

Jayan, B., Tamilarasi Ganesan, G., & Kurup, B. B. (2024). ENHANCING IOT NETWORK SECURITY THROUGH ADVANCED DATA PREPROCESSING AND HYBRID FIREFLY-SALP SWARM OPTIMIZED DEEP CNN-BASED INTRUSION DETECTION. Journal of Engineering and Technology for Industrial Applications, 10(47), 73–82. https://doi.org/10.5935/jetia.v10i47.1096

Kim, Y., Woong, J., Gu, S., Park, Y., & Cho, N. I. (2020). Transfer Learning from Synthetic to Real-Noise Denoising with Adaptive Instance Normalization.

Kumar, A., Tomar, H., Mehla, V. K., Komaragiri, R., & Kumar, M. (2021). Stationary wavelet transform based ECG signal denoising method. ISA Transactions, 114, 251–262. https://doi.org/10.1016/j.isatra.2020.12.029

Ling, J., Xue, H., Song, L., Xie, R., & Gu, X. (2021). Region-aware Adaptive Instance Normalization for Image Harmonization. https://github.com/junleen/RainNet.

Mehmood, M., Javed, T., Nebhen, J., Abbas, S., Abid, R., Bojja, G. R., & Rizwan, M. (2021). A hybrid approach for network intrusion detection. Computers, Materials and Continua, 70(1), 91–107. https://doi.org/10.32604/cmc.2022.019127

Mu, S., Cui, M., & Huang, X. (2020). Multimodal data fusion in learning analytics: A systematic review. In Sensors (Switzerland) (Vol. 20, Issue 23, pp. 1–27). MDPI AG. https://doi.org/10.3390/s20236856

Panday, V., Wadhvani, R., & Gyanchandani, M. (2022). Selective Review on Adaptive Normalization Techniques.

Rahimnejad, A., Gadsden, S. A., & Al-Shabi, M. (2021). Lattice Kalman Filters. IEEE Signal Processing Letters, 28, 1355–1359. https://doi.org/10.1109/LSP.2021.3089935

Revach, G., Shlezinger, N., Locher, T., Ni, X., van Sloun, R. J. G., & Eldar, Y. C. (2021). Unsupervised Learned Kalman Filtering. http://arxiv.org/abs/2110.09005

Revach, G., Shlezinger, N., Ni, X., Escoriza, A. L., van Sloun, R. J. G., & Eldar, Y. C. (2022). KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics. https://doi.org/10.1109/TSP.2022.3158588

Sahoo, G. R., Freed, J. H., & Srivastava, M. (2024). Optimal Wavelet Selection for Signal Denoising. IEEE Access, 12, 45369–45380. https://doi.org/10.1109/ACCESS.2024.3377664

Sharma, K., & Giannakos, M. (2020). Multimodal data capabilities for learning: What can multimodal data tell us about learning? In British Journal of Educational Technology (Vol. 51, Issue 5, pp. 1450–1484). Blackwell Publishing Ltd. https://doi.org/10.1111/bjet.12993

Shlezinger, N., Revach, G., Ghosh, A., Chatterjee, S., Tang, S., Imbiriba, T., Dunik, J., Straka, O., Closas, P., & Eldar, Y. C. (2025). AI-Aided Kalman Filters. http://arxiv.org/abs/2410.12289

Sun, M., Davies, M. E., Proudler, I. K., & Hopgood, J. R. (2023). Adaptive Kernel Kalman Filter. https://doi.org/10.1109/TSP.2023.3250829

Tian, C., Zheng, M., Zuo, W., Zhang, B., Zhang, Y., & Zhang, D. (2022). Multi-stage image denoising with the wavelet transform. http://arxiv.org/abs/2209.12394

Urrea, C., & Agramonte, R. (2021). Kalman Filter: Historical Overview and Review of Its Use in Robotics 60 Years after Its Creation. In Journal of Sensors (Vol. 2021). Hindawi Limited. https://doi.org/10.1155/2021/9674015

Vinayak Jha, K., Pandey, S., & Basu, A. (2025). HyCache: Hybrid Caching for Accelerating DNN Input Preprocessing Pipelines. www.usenix.org/conference/atc25/presentation/jha

Zhao, F., Zhang, C., & Geng, B. (2024). Deep Multimodal Data Fusion. ACM Computing Surveys, 56(9). https://doi.org/10.1145/3649447

Zhu, P., Abdal, R., Qin, Y., & Wonka, P. (2020). SEAN: Image Synthesis with Semantic Region-Adaptive Normalization. https://github.com/ZPdesu/SEAN