X-CHAR: A Concept-based Explainable Complex Human Activity Recognition Model
X-CHAR: A Concept-based Explainable Complex Human Activity Recognition Model
复制标题
DOI：
10.1145/3580804
复制
发表时间：
2022-03
影响因子：
--
通讯作者：
J. Jeyakumar;Ankur Sarker;L. Garcia;Mani Srivastava
中科院分区：
文献类型：
--
作者：
J. Jeyakumar;Ankur Sarker;L. Garcia;Mani Srivastava
端到端深度学习模型越来越多地应用于安全关键型人类活动识别（HAR）应用中，例如医疗保健监测和智能家居控制，以减轻开发人员的负担并提高预测模型的性能和稳健性。然而，在安全关键型应用中集成HAR模型需要信任，并且近期的方法旨在平衡深度学习模型的性能与复杂活动识别的可解释决策。先前的工作利用了复杂HAR的组合性（即由较低级别活动组成的较高级别活动）来形成具有符号接口的模型，例如概念瓶颈架构，这有助于形成本质上可解释的模型。然而，符号概念的特征工程以及概念之间的关系需要领域专家对较低级别活动进行精确标注，通常具有固定的时间窗口，所有这些都会给领域专家带来繁重且容易出错的工作量。在本文中，我们介绍了X - CHAR，一种可解释的复杂人类活动识别模型，它不需要对低级活动进行精确标注，以人类可理解的高级概念形式提供解释，同时保持端到端深度学习模型对时间序列数据的稳健性能。X - CHAR学习以一系列概念的形式对复杂活动识别进行建模。对于每次分类，X - CHAR输出一系列概念和一个反事实示例作为解释。我们表明，可以使用连接主义时序分类（CTC）损失对概念的序列信息进行建模，而无需在训练数据集中具有低级标注的准确开始和结束时间——这大大减轻了开发人员的负担。我们在几个复杂活动数据集上评估了我们的模型，并证明与基线模型相比，我们的模型在提供解释的同时不会影响预测准确性。最后，我们进行了一项亚马逊土耳其机器人（Mechanical Turk）研究，以表明我们的模型提供的解释比现有复杂活动识别方法提供的解释更易于理解。
End-to-end deep learning models are increasingly applied to safety-critical human activity recognition (HAR) applications, e.g., healthcare monitoring and smart home control, to reduce developer burden and increase the performance and robustness of prediction models. However, integrating HAR models in safety-critical applications requires trust, and recent approaches have aimed to balance the performance of deep learning models with explainable decision-making for complex activity recognition. Prior works have exploited the compositionality of complex HAR (i.e., higher-level activities composed of lower-level activities) to form models with symbolic interfaces, such as concept-bottleneck architectures, that facilitate inherently interpretable models. However, feature engineering for symbolic concepts-as well as the relationship between the concepts-requires precise annotation of lower-level activities by domain experts, usually with fixed time windows, all of which induce a heavy and error-prone workload on the domain expert. In this paper, we introduce X-CHAR, an eXplainable Complex Human Activity Recognition model that doesn't require precise annotation of low-level activities, offers explanations in the form of human-understandable, high-level concepts, while maintaining the robust performance of end-to-end deep learning models for time series data. X-CHAR learns to model complex activity recognition in the form of a sequence of concepts. For each classification, X-CHAR outputs a sequence of concepts and a counterfactual example as the explanation. We show that the sequence information of the concepts can be modeled using Connectionist Temporal Classification (CTC) loss without having accurate start and end times of low-level annotations in the training dataset-significantly reducing developer burden. We evaluate our model on several complex activity datasets and demonstrate that our model offers explanations without compromising the prediction accuracy in comparison to baseline models. Finally, we conducted a mechanical Turk study to show that the explanations provided by our model are more understandable than the explanations from existing methods for complex activity recognition.