Interpretable AI for Time-Series: Multi-Model Heatmap Fusion with Global Attention and NLP-Generated Explanations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Francis, Jiztom Kavalakkatt, Darr, Matthew J
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913919957729280
author Francis, Jiztom Kavalakkatt
Darr, Matthew J
author_facet Francis, Jiztom Kavalakkatt
Darr, Matthew J
contents In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem of spatial-temporal misalignment in existing interpretability methods, where convolutional networks fail to capture global context and Transformers lack localized precision - a limitation that impedes actionable insights in safety-critical domains like healthcare and industrial monitoring. Our method merges gradient-weighted activation maps (ResNet) and Transformer attention rollout into a unified visualization, achieving full spatial-temporal alignment while preserving real-time performance. Empirical evaluations on clinical (ECG arrhythmia detection) and industrial (energy consumption prediction) datasets demonstrate significant improvements: the hybrid framework achieves 94.1% accuracy (F1 0.93) on the PhysioNet dataset and reduces regression error to RMSE = 0.28 kWh (R2 = 0.95) on the UCI Energy Appliance dataset-outperforming standalone ResNet, Transformer, and InceptionTime baselines by 3.8-12.4%. An NLP module translates fused heatmaps into domain-specific narratives (e.g., "Elevated ST-segment between 2-4 seconds suggests myocardial ischemia"), validated via BLEU-4 (0.586) and ROUGE-L (0.650) scores. By formalizing interpretability as causal fidelity and spatial-temporal alignment, our approach bridges the gap between technical outputs and stakeholder understanding, offering a scalable solution for transparent, time-aware decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00234
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Interpretable AI for Time-Series: Multi-Model Heatmap Fusion with Global Attention and NLP-Generated Explanations
Francis, Jiztom Kavalakkatt
Darr, Matthew J
Machine Learning
Artificial Intelligence
Computation and Language
In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem of spatial-temporal misalignment in existing interpretability methods, where convolutional networks fail to capture global context and Transformers lack localized precision - a limitation that impedes actionable insights in safety-critical domains like healthcare and industrial monitoring. Our method merges gradient-weighted activation maps (ResNet) and Transformer attention rollout into a unified visualization, achieving full spatial-temporal alignment while preserving real-time performance. Empirical evaluations on clinical (ECG arrhythmia detection) and industrial (energy consumption prediction) datasets demonstrate significant improvements: the hybrid framework achieves 94.1% accuracy (F1 0.93) on the PhysioNet dataset and reduces regression error to RMSE = 0.28 kWh (R2 = 0.95) on the UCI Energy Appliance dataset-outperforming standalone ResNet, Transformer, and InceptionTime baselines by 3.8-12.4%. An NLP module translates fused heatmaps into domain-specific narratives (e.g., "Elevated ST-segment between 2-4 seconds suggests myocardial ischemia"), validated via BLEU-4 (0.586) and ROUGE-L (0.650) scores. By formalizing interpretability as causal fidelity and spatial-temporal alignment, our approach bridges the gap between technical outputs and stakeholder understanding, offering a scalable solution for transparent, time-aware decision-making.
title Interpretable AI for Time-Series: Multi-Model Heatmap Fusion with Global Attention and NLP-Generated Explanations
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2507.00234