arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1701.08528cs.CVcs.LGstat.ML
收藏

活动识别系统对新传感器的自适应

Self-Adaptation of Activity Recognition Systems to New Sensors

Bonsai Systems GmbH(Bonsai Systems有限公司);ETH Zürich(苏黎世联邦理工学院);University of Kassel(卡塞尔大学);German Research Center for Artificial Intelligence(德国人工智能研究中心)

David Bannach, Martin Jänicke, Vitor F. Rey, Sven Tomforde, Bernhard Sick, Paul Lukowicz

摘要:

传统的活动识别系统在训练的基础上工作,考虑到一组固定的传感器。在本文中,我们关注的问题是模式识别如何在没有任何用户输入或用户输入最少的情况下利用新的信息源。因此,我们提出了一种机会主义活动识别的方法,无处不在的传感器导致动态变化的输入空间。我们的方法是机器学习的成熟原则的变体,依赖于无监督聚类来发现数据中的结构,并以半监督的方式从少量标记的数据中推断聚类标签。阐述的挑战,超过3000个传感器组合的评估,从三个多用户实验详细介绍,并显示我们的方法的潜在好处。

英文摘要:

Traditional activity recognition systems work on the basis of training, taking a fixed set of sensors into account. In this article, we focus on the question how pattern recognition can leverage new information sources without any, or with minimal user input. Thus, we present an approach for opportunistic activity recognition, where ubiquitous sensors lead to dynamically changing input spaces. Our method is a variation of well-established principles of machine learning, relying on unsupervised clustering to discover structure in data and inferring cluster labels from a small number of labeled dates in a semi-supervised manner. Elaborating the challenges, evaluations of over 3000 sensor combinations from three multi-user experiments are presented in detail and show the potential benefit of our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑