What question did this study set out to answer?

Develop a hybrid underwater data analytics framework combining wavelet transforms, autoencoders, and transformer networks to mitigate sensor noise and capture long-range temporal dependencies.

August 19, 2026IETE Journal of Research

Advanced Underwater Data Analytics with IoT-Enabled Systems and Hybrid Wavelet-AI Modeling Techniques Using Autoencoders and Transformer Networks

View Full Paper

Ask AI

Bookmark

Authors

MLMohamed Loey PVPrema V SASoniya Agrawal

Discussion

Member takes

Overview

Computational study demonstrates high predictive accuracy in underwater IoT monitoring, suggesting robust analytics for sustainable aquaculture.

Key Points

Develop a hybrid underwater data analytics framework combining wavelet transforms, autoencoders, and transformer networks to mitigate sensor noise and capture long-range temporal dependencies.
Decomposed non-stationary underwater signals across multiple scales using Wavelet Packet Transform (WPT).
Extracted compact, denoised latent representations with autoencoders and modeled sequential temporal dependencies using self-attention mechanisms in Transformer Networks.
Evaluated predictive performance against baseline architectures including ResNet, YOLOv7, and MLCNN across dynamic underwater conditions.
Achieved an overall predictive accuracy of approximately 99.5% in dynamic underwater scenarios.
Attained a precision of ≈98.9%, recall of ≈98.7%, and an F1-score of ≈98.8%, demonstrating superior performance over ResNet, YOLOv7, and MLCNN.

Cite This Study

Loey et al. (2026) studied this question.

synapsesocial.com/papers/6a85634f03308d306e2d656b https://doi.org/10.1080/03772063.2026.2710344

View Full Paper

Ask AI

Bookmark

August 19, 2026IETE Journal of Research

Advanced Underwater Data Analytics with IoT-Enabled Systems and Hybrid Wavelet-AI Modeling Techniques Using Autoencoders and Transformer Networks

View Full Paper

Ask AI

Bookmark

Authors

MLMohamed Loey PVPrema V SASoniya Agrawal

Discussion

Member takes

Overview

Computational study demonstrates high predictive accuracy in underwater IoT monitoring, suggesting robust analytics for sustainable aquaculture.

Key Points

Develop a hybrid underwater data analytics framework combining wavelet transforms, autoencoders, and transformer networks to mitigate sensor noise and capture long-range temporal dependencies.
Decomposed non-stationary underwater signals across multiple scales using Wavelet Packet Transform (WPT).
Extracted compact, denoised latent representations with autoencoders and modeled sequential temporal dependencies using self-attention mechanisms in Transformer Networks.
Evaluated predictive performance against baseline architectures including ResNet, YOLOv7, and MLCNN across dynamic underwater conditions.
Achieved an overall predictive accuracy of approximately 99.5% in dynamic underwater scenarios.
Attained a precision of ≈98.9%, recall of ≈98.7%, and an F1-score of ≈98.8%, demonstrating superior performance over ResNet, YOLOv7, and MLCNN.

Cite This Study

Loey et al. (2026) studied this question.

synapsesocial.com/papers/6a85634f03308d306e2d656b https://doi.org/10.1080/03772063.2026.2710344

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark