[论文解读] Context-driven Active and Incremental Activity Recognition

Gabriele Civitarese, Riccardo Presotto+1 more|arXiv (Cornell University)|Jun 7, 2019

Context-Aware Activity Recognition Systems参考文献 37被引用 9

一句话总结

本文提出 CAVIAR，一种上下文感知的半监督主动增量活动识别系统，通过结合上下文数据（如位置、时间、交通工具）的本体论推理与增量分类器，提升识别准确率并减少用户查询。通过利用语义上下文优化统计预测，并仅在不确定时查询用户，而利用置信预测进行自训练，CAVIAR 在识别率和查询次数方面均优于将上下文作为原始特征的方法。

ABSTRACT

Human activity recognition based on mobile device sensor data has been an active research area in mobile and pervasive computing for several years. While the majority of the proposed techniques are based on supervised learning, semi-supervised approaches are being considered to significantly reduce the size of the training set required to initialize the recognition model. These approaches usually apply self-training or active learning to incrementally refine the model, but their effectiveness seems to be limited to a restricted set of physical activities. We claim that the context which surrounds the user (e.g., semantic location, proximity to transportation routes, time of the day) combined with common knowledge about the relationship between this context and human activities could be effective in significantly increasing the set of recognized activities including those that are difficult to discriminate only considering inertial sensors, and the ones that are highly context-dependent. In this paper, we propose CAVIAR, a novel hybrid semi-supervised and knowledge-based system for real-time activity recognition. Our method applies semantic reasoning to context data to refine the prediction of a semi-supervised classifier. The context-refined predictions are used as new labeled samples to update the classifier combining self-training and active learning techniques. Results on a real dataset obtained from 26 subjects show the effectiveness of the context-aware approach both on the recognition rates and on the number of queries to the subjects generated by the active learning module. In order to evaluate the impact of context reasoning, we also compare CAVIAR with a purely statistical version, considering features computed on context data as part of the machine learning process.

研究动机与目标

• 解决纯统计活动识别在区分依赖上下文或运动相似活动（如步行与爬楼梯、站立与乘电梯）方面的局限性。
• 通过结合主动学习与上下文感知优化的半监督学习，减轻手动标注负担。
• 提升真实场景中动态且不完整上下文数据下活动识别系统的可扩展性与鲁棒性。
• 评估基于知识的上下文推理是否优于将上下文作为机器学习模型中直接特征的方法。
• 证明上下文感知推理可实现对复杂、依赖上下文活动的识别，超越基本运动模式。

提出的方法

• 增量分类器处理惯性传感器数据，生成可能活动的概率分布。
• 基于知识的推理引擎利用上下文本体（如语义位置、一天中的时间、接近交通工具）过滤掉在语义上不合理的统计预测活动。
• 经上下文推理优化后的预测结果——结合传感器数据与上下文推理——成为系统的输出。
• 当系统对优化后的预测结果具有高置信度时，将其作为新标注样本，通过自训练更新分类器。
• 当置信度较低时，系统向用户查询真实标签，用于进一步训练分类器。
• 系统通过扩展本体动态集成新上下文源，避免重新训练，保持模型适应性。

实验结果

研究问题

• RQ1 上下文感知推理是否能显著提升复杂、依赖上下文活动的识别准确率，超越仅依赖惯性传感器的水平？
• RQ2 通过语义推理使用上下文数据是否优于在机器学习流程中将其作为原始特征？
• RQ3 基于知识的推理集成在主动学习中在多大程度上减少了用户查询次数？
• RQ4 系统在识别活动复杂度与多样性增加时的可扩展性如何？
• RQ5 系统能否在最小化用户交互的同时维持高性能，并在无需重新训练的情况下适应新上下文源？

主要发现

• CAVIAR 在识别率上显著优于将上下文作为原始特征的基线方法，尤其在复杂且依赖上下文的活动（如“乘电梯”或“乘车移动”）中表现更优。
• 由于更精确的上下文过滤，CAVIAR 的主动学习模块触发的用户查询次数相比上下文作为特征的方法大幅减少。
• 系统在不同活动集合上均保持高性能，展现出良好的可扩展性与对活动复杂度增加的鲁棒性。
• 上下文感知推理使系统能够识别仅靠惯性传感器难以区分的活动，如步行与爬楼梯。
• 本体论推理减少了对完整且一致上下文数据的依赖，缺失值不会导致系统失效，而基于特征的方法则易受此影响。
• 与基于特征的上下文集成相比，该方法更具可扩展性与可维护性，因为可通过扩展本体添加新上下文源，而无需重新训练模型。