Mindful active learning

Zhila Esna Ashari Esfahani

doi:10.7273/000004188

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 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 mode. We demonstrate the effectiveness of our approach using three publicly available activity datasets. 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. Moreover, we show that the performance of our approach is at most 20% less than experimental upper-bound and up to 80% higher than experimental lower-bound. To evaluate the performance of EMMA for batch active learning, we design two instantiations of EMMA to perform active learning in a batch mode. We show that these algorithms improve the algorithm training time at the cost of a reduced accuracy in performance. Also, 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 query budget is small and/or oracle's memory is weak.

Mindful active learning

Files and links (1)

Abstract

Metrics

Details