Using unlabeled data in a sparse-coding framework for human activity recognition
Using unlabeled data in a sparse-coding framework for human activity recognition
复制标题
DOI：
10.1016/j.pmcj.2014.05.006
复制
发表时间：
2014-12-01
影响因子：
4.3
通讯作者：
Poeltz, Thomas
中科院分区：
文献类型：
--
作者：
Bhattacharya, Sourav;Nurmi, Petteri;Poeltz, Thomas
我们提出了一个稀疏编码框架，用于无处不在和移动计算中的活动识别，缓解了当前监督学习方法的两个基本问题。(i)自动提取传感器数据的紧凑，稀疏和有意义的特征表示，不依赖于先前的专家知识，并且可以很好地跨领域边界进行推广。（ii）它利用未标记的样本数据来引导有效的活动识别器，即大大减少了模型估计所需的基础真值注释的数量。这种未标记的数据很容易获得，例如，通过用户在日常活动中携带的现代智能手机。基于自学范例，我们从未标记的数据中自动获得一组超完整的基向量，这些基向量捕获了活动数据中存在的固有模式。通过将原始传感器数据投影到由这些过完备基向量集定义的特征空间中，实现有效的特征提取。给定这些学习到的特征表示，然后使用少量标记的训练数据训练分类后端。我们使用两个在识别任务和传感器模式方面不同的数据集详细研究了新方法。我们主要关注交通模式分析任务，这是基于移动电话的传感中的一个流行任务。稀疏编码框架比最先进的监督学习方法表现出更好的性能。更重要的是，我们通过考虑流行的机遇数据集，成功评估了新方法在域和传感器模式上的泛化能力，展示了新方法的实际潜力。我们的特征学习方法在分析日常生活活动方面优于最先进的方法。(C) 2014 Elsevier B.V.版权所有
We propose a sparse-coding framework for activity recognition in ubiquitous and mobile computing that alleviates two fundamental problems of current supervised learning approaches. (i) It automatically derives a compact, sparse and meaningful feature representation of sensor data that does not rely on prior expert knowledge and generalizes well across domain boundaries. (ii) It exploits unlabeled sample data for bootstrapping effective activity recognizers, i.e., substantially reduces the amount of ground truth annotation required for model estimation. Such unlabeled data is easy to obtain, e. g., through contemporary smartphones carried by users as they go about their everyday activities.Based on the self-taught learning paradigm we automatically derive an over-complete set of basis vectors from unlabeled data that captures inherent patterns present within activity data. Through projecting raw sensor data onto the feature space defined by such over-complete sets of basis vectors effective feature extraction is pursued. Given these learned feature representations, classification backends are then trained using small amounts of labeled training data.We study the new approach in detail using two datasets which differ in terms of the recognition tasks and sensor modalities. Primarily we focus on a transportation mode analysis task, a popular task in mobile-phone based sensing. The sparse-coding framework demonstrates better performance than the state-of-the-art in supervised learning approaches. More importantly, we show the practical potential of the new approach by successfully evaluating its generalization capabilities across both domain and sensor modalities by considering the popular Opportunity dataset. Our feature learning approach outperforms state-of-the-art approaches to analyzing activities of daily living. (C) 2014 Elsevier B.V. All rights reserved.