Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models
Self-Adaptive Multi-Sensor Activity Recognition Systems Based on Gaussian Mixture Models
复制标题
DOI：
10.3390/informatics5030038
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Martin Jänicke;B. Sick;Sven Tomforde
中科院分区：
文献类型：
--
作者：
Martin Jänicke;B. Sick;Sven Tomforde
智能手机或智能手表等个人可穿戴设备在日常生活中的使用越来越多。通常，在这些设备上执行活动识别以估计当前用户状态并根据用户需求触发自动操作。在本文中，我们专注于创建一个基于IMU的自适应活动识别系统，该系统在运行时包含新的传感器。该方法从基于GMM的分类器入手，利用正态分布的边际化性质，使密度模型完全自主地适应新的传感器数据。为了从中创建分类器，基于初始分类器或基于训练数据进行标签推理。为了进行评估，我们使用了来自公开可用的PAMAP2基准数据集的超过10小时的带注释的活动数据。使用这些数据，我们证明了我们方法的可行性，并进行了9720个实验，以获得有弹性的数字。其中一种方法执行得相当好，导致了系统的平均改进，F-Score增加了0.0053，而另一种方法由于在标签推理过程中信息的高度丢失而显示出明显的缺陷。此外，与最先进技术的比较表明，有必要在这一领域进行进一步的实验。
Personal wearables such as smartphones or smartwatches are increasingly utilized in everyday life. Frequently, activity recognition is performed on these devices to estimate the current user status and trigger automated actions according to the user’s needs. In this article, we focus on the creation of a self-adaptive activity recognition system based on IMU that includes new sensors during runtime. Starting with a classifier based on GMM, the density model is adapted to new sensor data fully autonomously by issuing the marginalization property of normal distributions. To create a classifier from that, label inference is done, either based on the initial classifier or based on the training data. For evaluation, we used more than 10 h of annotated activity data from the publicly available PAMAP2 benchmark dataset. Using the data, we showed the feasibility of our approach and performed 9720 experiments, to get resilient numbers. One approach performed reasonably well, leading to a system improvement on average, with an increase in the F-score of 0.0053, while the other one shows clear drawbacks due to a high loss of information during label inference. Furthermore, a comparison with state of the art techniques shows the necessity for further experiments in this area.