[论文解读] Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art

Artur Jordão, Antonio C. Nazaré+2 more|arXiv (Cornell University)|Jun 13, 2018

Context-Aware Activity Recognition Systems参考文献 27被引用 80

一句话总结

本文通过分析样本生成和验证协议来标准化可穿戴传感器人类活动识别的评估，揭示常见方法中的偏差，并提出两种新的样本生成方法以及数据集标准化。

ABSTRACT

Human activity recognition based on wearable sensor data has been an attractive research topic due to its application in areas such as healthcare and smart environments. In this context, many works have presented remarkable results using accelerometer, gyroscope and magnetometer data to represent the activities categories. However, current studies do not consider important issues that lead to skewed results, making it hard to assess the quality of sensor-based human activity recognition and preventing a direct comparison of previous works. These issues include the samples generation processes and the validation protocols used. We emphasize that in other research areas, such as image classification and object detection, these issues are already well-defined, which brings more efforts towards the application. Inspired by this, we conduct an extensive set of experiments that analyze different sample generation processes and validation protocols to indicate the vulnerable points in human activity recognition based on wearable sensor data. For this purpose, we implement and evaluate several top-performance methods, ranging from handcrafted-based approaches to convolutional neural networks. According to our study, most of the experimental evaluations that are currently employed are not adequate to perform the activity recognition in the context of wearable sensor data, in which the recognition accuracy drops considerably when compared to an appropriate evaluation approach. To the best of our knowledge, this is the first study that tackles essential issues that compromise the understanding of the performance in human activity recognition based on wearable sensor data.

研究动机与目标

• 识别在可穿戴传感器活动识别评估中影响性能偏差的因素。
• 评估样本生成和验证协议如何影响报告的准确性。
• 在标准化评估下实现并比较多种高性能方法（从手工特征到卷积神经网络）。
• 提出两种新颖的数据样本生成过程以减少偏差并实现公平比较。
• 标准化公开可用的可穿戴传感器数据集以促进可重复评估。

提出的方法

• 实现并评估多种最先进的活动识别方法，涵盖从手工特征到卷积神经网络。
• 分析数据样本生成过程对识别性能与偏差的影响。
• 提出全非重叠窗口（Full-Non-Overlapping-Window）和留一试验（Leave-One-Trial-Out）样本生成过程以解决偏差与数据稀缺问题。
• 标准化具有不同传感器配置的数据集以实现统一评估。
• 使用10折交叉验证和留一受试者验证来考察验证协议对性能的影响。
• 进行统计验证以比较方法并评估等效性。

实验结果

研究问题

• RQ1 样本生成过程如何偏置可穿戴传感器数据中的报道活动识别准确性？
• RQ2 哪些验证协议在跨数据集时能够产生稳健、偏差较小的性能估计？
• RQ3 在标准化评估下，手工特征方法与基于卷积网络的方法仍然具备竞争力吗？
• RQ4 新的数据样本生成方案能否在不大幅降低样本量的情况下减少偏差？
• RQ5 应如何对公开数据集进行标准化以实现可重复的基准测试？

主要发现

• 来自半重叠窗口采样的偏差会通过训练和测试的重叠而提高准确性；去除偏差后性能下降。
• 全非重叠窗口减少偏差，但样本数量减少，可能降低准确性。
• 留一试验法（Leave-One-Trial-Out）在保持交叉验证结构的同时防止试验内的重叠，从而减轻偏差。
• 在标准化评估下，与偏差化设置相比，许多方法的准确率平均下降约10个百分点。
• 基于卷积网络的方法需要谨慎的架构选择（通道分离、核尺寸等），在低采样率数据集上可能不实用。
• 跨数据集的标准化揭示方法鲁棒性差异，并强调需要可重复的基准测试。