Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures

• URL: http://arxiv.org/abs/2411.03714v1
• Date: Wed, 06 Nov 2024 07:28:57 GMT
• Title: Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures
• Authors: Felix Tempel, Espen Alexander F. Ihlen, Lars Adde, Inga Strümke,
• Abstract summary: This study uses SHapley Additive exPlanations to explain the decision-making process of Graph Convolution Networks (GCNs) We employ SHAP to explain two real-world datasets: one for cerebral palsy (CP) classification and the widely used NTU RGB+D 60 action recognition dataset. Results on both datasets show that body key points identified as important through SHAP have the largest influence on the accuracy, specificity, and sensitivity metrics.
• Score: 0.1398098625978622
• License:
• Abstract: In Human Activity Recognition (HAR), understanding the intricacy of body movements within high-risk applications is essential. This study uses SHapley Additive exPlanations (SHAP) to explain the decision-making process of Graph Convolution Networks (GCNs) when classifying activities with skeleton data. We employ SHAP to explain two real-world datasets: one for cerebral palsy (CP) classification and the widely used NTU RGB+D 60 action recognition dataset. To test the explanation, we introduce a novel perturbation approach that modifies the model's edge importance matrix, allowing us to evaluate the impact of specific body key points on prediction outcomes. To assess the fidelity of our explanations, we employ informed perturbation, targeting body key points identified as important by SHAP and comparing them against random perturbation as a control condition. This perturbation enables a judgment on whether the body key points are truly influential or non-influential based on the SHAP values. Results on both datasets show that body key points identified as important through SHAP have the largest influence on the accuracy, specificity, and sensitivity metrics. Our findings highlight that SHAP can provide granular insights into the input feature contribution to the prediction outcome of GCNs in HAR tasks. This demonstrates the potential for more interpretable and trustworthy models in high-stakes applications like healthcare or rehabilitation.

Related papers

• DEL-Ranking: Ranking-Correction Denoising Framework for Elucidating Molecular Affinities in DNA-Encoded Libraries [43.47251247740565]
  DNA-encoded library (DEL) screening has revolutionized the detection of protein-ligand interactions through read counts. noise in read counts, stemming from nonspecific interactions, can mislead this exploration process. We present DEL-Ranking, a distribution-correction denoising framework that addresses these challenges.
  arXiv  Detail & Related papers  (2024-10-19T02:32:09Z)
• Physics Inspired Hybrid Attention for SAR Target Recognition [61.01086031364307]
  We propose a physics inspired hybrid attention (PIHA) mechanism and the once-for-all (OFA) evaluation protocol to address the issues. PIHA leverages the high-level semantics of physical information to activate and guide the feature group aware of local semantics of target. Our method outperforms other state-of-the-art approaches in 12 test scenarios with same ASC parameters.
  arXiv  Detail & Related papers  (2023-09-27T14:39:41Z)
• QXAI: Explainable AI Framework for Quantitative Analysis in Patient Monitoring Systems [9.29069202652354]
  An Explainable AI for Quantitative analysis (QXAI) framework is proposed with post-hoc model explainability and intrinsic explainability for regression and classification tasks. We adopted the artificial neural networks (ANN) and attention-based Bidirectional LSTM (BiLSTM) models for the prediction of heart rate and classification of physical activities based on sensor data.
  arXiv  Detail & Related papers  (2023-09-19T03:50:30Z)
• Explainable AI and Machine Learning Towards Human Gait Deterioration Analysis [0.0]
  We objectively analyze gait data and associate findings with clinically relevant biomarkers. We achieve classification accuracies of 98% F1 sc ores for each PhysioNet.org dataset and 95.5% F1 scores for the combined PhysioNet dataset.
  arXiv  Detail & Related papers  (2023-06-12T14:53:00Z)
• Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models [0.7829352305480283]
  In this work, we employ established gaze event detection algorithms for fixations and saccades. We quantitatively evaluate the impact of these events by determining their concept influence.
  arXiv  Detail & Related papers  (2023-04-12T10:15:31Z)
• Dataset Bias in Human Activity Recognition [57.91018542715725]
  This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance. We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR.
  arXiv  Detail & Related papers  (2023-01-19T12:33:50Z)
• Learning Neural Causal Models with Active Interventions [83.44636110899742]
  We introduce an active intervention-targeting mechanism which enables a quick identification of the underlying causal structure of the data-generating process. Our method significantly reduces the required number of interactions compared with random intervention targeting. We demonstrate superior performance on multiple benchmarks from simulated to real-world data.
  arXiv  Detail & Related papers  (2021-09-06T13:10:37Z)
• Towards Unbiased Visual Emotion Recognition via Causal Intervention [63.74095927462]
  We propose a novel Emotion Recognition Network (IERN) to alleviate the negative effects brought by the dataset bias. A series of designed tests validate the effectiveness of IERN, and experiments on three emotion benchmarks demonstrate that IERN outperforms other state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-07-26T10:40:59Z)
• How Knowledge Graph and Attention Help? A Quantitative Analysis into Bag-level Relation Extraction [66.09605613944201]
  We quantitatively evaluate the effect of attention and Knowledge Graph on bag-level relation extraction (RE) We find that (1) higher attention accuracy may lead to worse performance as it may harm the model's ability to extract entity mention features; (2) the performance of attention is largely influenced by various noise distribution patterns; and (3) KG-enhanced attention indeed improves RE performance, while not through enhanced attention but by incorporating entity prior.
  arXiv  Detail & Related papers  (2021-07-26T09:38:28Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)
• Feature Importance Estimation with Self-Attention Networks [0.0]
  Black-box neural network models are widely used in industry and science, yet are hard to understand and interpret. Recently, the attention mechanism was introduced, offering insights into the inner workings of neural language models. This paper explores the use of attention-based neural networks mechanism for estimating feature importance, as means for explaining the models learned from propositional (tabular) data.
  arXiv  Detail & Related papers  (2020-02-11T15:15:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.