A detailed human activity transition recognition framework for grossly labeled data from smartphone accelerometer
- PDF / 2,527,344 Bytes
- 22 Pages / 439.642 x 666.49 pts Page_size
- 33 Downloads / 165 Views
A detailed human activity transition recognition framework for grossly labeled data from smartphone accelerometer Jayita Saha1 · Chandreyee Chowdhury2 Sanghamitra Bandyopadhyay3
· Dip Ghosh3 ·
Received: 18 November 2019 / Revised: 24 September 2020 / Accepted: 7 October 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Smartphone based human activity monitoring and recognition play an important role in several medical applications, such as eldercare, diabetic patient monitoring, post-trauma recovery after surgery. However, it is more important to recognize the activity sequences in terms of transitions. In this work, we have designed a detailed activity transition recognition framework that can identify a set of activity transitions and their sequence for a time window. This enables us to extract more meaningful insight about the subject’s physical and behavioral context. However, precise labeling of training data for detailed activity transitions at every time instance is required for this purpose. But, due to non uniformity of individual gait, the labeling tends to be error prone. Accordingly, our contribution in this work is to formulate the activity transition detection problem as a multiple instance learning problem to deal with imprecise labeling of data. The proposed human activity transition recognition framework forms an ensemble model based on different MIML-kNN distance metrics. The ensemble model helps to find both the activity sequence as well as multiple activity transition. The framework is implemented for a real dataset collected from 8 users. It is found to be working adequately (average precision 0.94). Keywords Detailed activity · MIML · Smartphone · Activity transition · Activity sequence
Jayita Saha
[email protected] Chandreyee Chowdhury [email protected] 1
Department of Artificial Intelligence and Data Science, Koneru Lakshmaiah Education Foundation Deemed to be University, Hyderabad, India
2
Department of CSE, Jadavpur University, Kolkata, India
3
Machine Intelligence Unit, Indian Statistical Institute, Kolkata, India
Multimedia Tools and Applications
1 Introduction The idea of solving the problem of Human Activity Recognition (HAR) using Smartphone accelerometer data started with the recognition of primitive classes of activities such as sit, stand, walk etc. which are performed in everyday life as described in [21, 27, 30]. Few recent works can also be found on detailed activities such as slow walk, brisk walk etc. that evidently gives us more information about the subject’s context and behavioral patterns as in [5, 28]. Even with wearable accelerometers and/or cameras, HAR systems are built to recognize complete action such as “cooking”, “working on a Desktop” etc. Such HAR systems are generally concerned with detecting one activity or action being performed at a time as in [33]. The precise labeling of such actions for every time instant is difficult because the action duration varies and requires huge data collection and la
Data Loading...
