Explainable AI for gait speed analysis from multimodal data fusion

Abdullah Alharthi; Abdulrahman Al Ayidh; Ahmed Alqurashi; Mohammed Alammar; Shoaib Shahriar Mohammad; Houssem R. E. H. Bouchekara; Yusuf Abubakar Sha’aban; Turki E. A. Alharbi

doi:10.1371/journal.pone.0341067

February 27, 2026PLoS ONEOpen Access

Explainable AI for gait speed analysis from multimodal data fusion

View Full Paper

Ask AI

Bookmark

Share

Key Points

The aim is to develop a robust framework for accurate gait speed analysis using multimodal data and deep learning techniques.
Developed a hybrid model combining CNN and LSTM.
Benchmarked against various neural network architectures and statistical classifiers.
Employed three distinct cross-validation strategies for training and validation.
Applied Layer-wise Relevance Propagation for feature relevance evaluation.
Achieved highest F1 scores with the Multi-stream Quads CNN (up to 98% accuracy).
Outperformed traditional gait analysis methods across all experiments.
Demonstrated robustness through comprehensive performance evaluations including ROC curves and perturbation analyses.

No abstract yet

We only have this paper's title and publication details.

Read it at the source

Implication

Demonstrates enhanced gait speed classification in injury-free adults via multimodal data fusion, indicating strong implications for healthcare and robotics.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Alharthi et al. (2026) studied this question.

synapsesocial.com/papers/69a3d887ec16d51705d2f850 https://doi.org/10.1371/journal.pone.0341067

View Full Paper

Ask AI

Bookmark

Share

Explainable AI for gait speed analysis from multimodal data fusion

Key Points

No abstract yet

Implication

Discussion

Cite This Study

Explainable AI for gait speed analysis from multimodal data fusion

Key Points

No abstract yet

Implication

Discussion

Cite This Study

Keep reading

Keep reading