Active learning enabled activity recognition

Abstract

Activity recognition in smart environment has been investigated rigorously in recent years. Researchers are enhancing the underlying activity discovery and recognition process by adding various dimensions and functionalities. But one significant barrier still persists which is collecting the ground truth information. Ground truth is very important to initialize a supervised learning of activities. Due to a large variety in number of Activities of Daily Living (ADLs), acknowledging them in a supervised way is a non-trivial research problem. Most of the previous researches have referenced a subset of ADLs and to initialize their model, they acquire a vast amount of informative labeled training data. On the other hand to collect ground truth and differentiate ADLs, human intervention is indispensable. As a result it takes an immense effort and raises privacy concerns to collect a reasonable amount of labeled data. In this paper, we propose to use active learning to alleviate the labeling effort and ground truth data collection in activity recognition pipeline. We investigate and analyze different active learning strategies to scale activity recognition and propose a dynamic k-means clustering based active learning approach. Experimental results on real data traces from a retirement community-(IRB #HP-00064387) help validate the early promise of our approach.

Implementation Analysis of Curriculum 2013 Towards Interactive Learning Aspects and Multimedia-Based Learning

“…Interactive learning is a learning process that allows active students to engage themselves in the learning process, both mentally and physically (Hossain et al, 2017;Rodríguez et al, 2018;Walters et al, 2017). Therefore, to implement interactive learning the teacher must involve students during learning.…”

“…Learning that is done with a variety of teaching methods can create interaction patterns. The optimal pattern of interaction between teachers and students, students and teachers, and between students and students is a multi-purpose communication that is in accordance with the concepts of active students (Hossain et al, 2017).…”

Stratified Transfer Learning for Cross-domain Activity Recognition

“…Conventional machine learning approaches have made tremendous progress on HAR by adopting machine learning algorithms such as similarity-based approach [16], [17], active learning [18], crowdsourcing [19], and other semi-supervised methods [20], [21]. Those methods typically treat HAR as a standard time series classification problem.…”

ActiveHARNet

“…Incorporating AL for obtaining ground truth in mobile sensing systems has been addressed in few previous works discussed as follows. Hossain et al [6] incorporate a dynamic k-means clustering approach with AL in HAR tasks. However, this work was before the ubiquitousness of deep learning algorithms, thereby making the model dependent on heuristic hand-picked features.…”

“…A special interest in bringing deep learning to mobile and wearable devices (incorporating deep learning on the edge) has been an active area of research owing to its automatic feature extraction capabilities, in contrast to conventional machine learning models which mandate domain knowledge to craft shallow heuristic features. One of the unexplored areas involving deep learning for such HAR tasks is Active Learning -a technique which gives a model, the ability to learn from real-world unlabeled data by querying an oracle [6]. The integration of Bayesian techniques with deep learning provide us a convenient way to represent model uncertainties by linking Bayesian Neural Networks (BNNs) with Gaussian processes using Dropout [4] (Section 3.1).…”