Memory-Aware Active Learning in Mobile Sensing Systems.
Memory-Aware Active Learning in Mobile Sensing Systems.
复制标题
DOI：
10.1109/tmc.2020.3003936
复制
发表时间：
2022-01-01
影响因子：
7.9
通讯作者：
Ghasemzadeh H
中科院分区：
文献类型：
--
作者：
Ashari ZE;Chaytor NS;Cook DJ;Ghasemzadeh H
我们提出了一种新的主动学习框架，使用可穿戴传感器的活动识别。我们的工作是独一无二的，因为它考虑到甲骨文的局限性时，选择传感器数据的注释由甲骨文。我们的方法受到了人类对移动终端上提示的有限响应能力的启发。这种能力限制不仅表现在一个人在给定的时间范围内可以响应的查询数量上，而且还表现在查询发布和oracle响应之间的时间间隔上。我们引入了正念主动学习的概念，并提出了一个计算框架，称为EMMA，以最大限度地提高主动学习性能，同时考虑到传感器数据的信息量，查询预算和人类记忆。我们制定这个优化问题，提出了一种方法来模拟内存保留，讨论了问题的复杂性，并提出了一个贪婪的启发式算法来解决优化问题。此外，我们设计了一种方法来执行有意识的主动学习在批处理中，多个传感器的观察同时选择查询的预言。我们证明了我们的方法使用三个公开的活动数据集，并通过模拟具有各种内存强度的神谕的有效性。我们发现，活动识别的准确率范围从21%到97%，这取决于记忆强度，查询预算和机器学习任务的难度。我们的研究结果还表明，EMMA实现的准确性水平，平均而言，13.5%的情况下，只有信息的传感器数据被认为是主动学习。此外，我们表明，我们的方法的性能最多比实验上限低20%，比实验下限高80%。为了评估EMMA在批量主动学习中的性能，我们设计了两个EMMA实例来在批量模式下执行主动学习。我们表明，这些算法提高了算法的训练时间在性能的准确性降低的成本。我们工作中的另一个发现是，将聚类集成到为批量主动学习选择传感器观测值的过程中，平均可以提高11.1%的主动学习性能，这主要是由于减少了所选传感器观测值之间的冗余。我们观察到，有意识的主动学习是最有益的，当查询预算是小的和/或甲骨文的内存是薄弱的。这一观察结果强调了在移动的健康环境中利用有意识的主动学习策略的优势，这些健康环境涉及与老年人和其他认知障碍人群的互动。
We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes limitations of the oracle into account when selecting sensor data for annotation by the oracle. Our approach is inspired by human-beings’ limited capacity to respond to prompts on their mobile device. This capacity constraint is manifested not only in the number of queries that a person can respond to in a given time-frame but also in the time lag between the query issuance and the oracle response. We introduce the notion of mindful active learning and propose a computational framework, called EMMA, to maximize the active learning performance taking informativeness of sensor data, query budget, and human memory into account. We formulate this optimization problem, propose an approach to model memory retention, discuss the complexity of the problem, and propose a greedy heuristic to solve the optimization problem. Additionally, we design an approach to perform mindful active learning in batch where multiple sensor observations are selected simultaneously for querying the oracle. We demonstrate the effectiveness of our approach using three publicly available activity datasets and by simulating oracles with various memory strengths. We show that the activity recognition accuracy ranges from 21% to 97% depending on memory strength, query budget, and difficulty of the machine learning task. Our results also indicate that EMMA achieves an accuracy level that is, on average, 13.5% higher than the case when only informativeness of the sensor data is considered for active learning. Moreover, we show that the performance of our approach is at most 20% less than the experimental upper-bound and up to 80% higher than the experimental lower-bound. To evaluate the performance of EMMA for batch active learning, we design two instantiations of EMMA to perform active learning in batch mode. We show that these algorithms improve the algorithm training time at the cost of a reduced accuracy in performance. Another finding in our work is that integrating clustering into the process of selecting sensor observations for batch active learning improves the activity learning performance by 11.1% on average, mainly due to reducing the redundancy among the selected sensor observations. We observe that mindful active learning is most beneficial when the query budget is small and/or the oracle’s memory is weak. This observation emphasizes advantages of utilizing mindful active learning strategies in mobile health settings that involve interaction with older adults and other populations with cognitive impairments.
登录
查看更多内容
影响因子：
1.4
作者：
Barshan, Billur;Yuksek, Murat Cihan
通讯作者：
Yuksek, Murat Cihan
影响因子：
4.3
作者：
Ma, Yuchao;Ashari, Zhila Esna;Ghasemzadeh, Hassan
通讯作者：
Ghasemzadeh, Hassan
影响因子：
8
作者：
Altun, Kerem;Barshan, Billur;Tuncel, Orkun
通讯作者：
Tuncel, Orkun
通过查询信息丰富且具有代表性的示例进行主动学习
DOI：
10.1109/tpami.2014.2307881
发表时间：
2014-10-01
影响因子：
23.6
作者：
Huang, Sheng-Jun;Jin, Rong;Zhou, Zhi-Hua
通讯作者：
Zhou, Zhi-Hua
影响因子：
--
作者：
Redmond, S J;Lovell, N H;Marschollek, M
通讯作者：
Marschollek, M