ActiLabel: A Combinatorial Transfer Learning Framework for Activity Recognition
By Parastoo Alinia, Seyed Iman Mirzadeh, Hassan Ghasemzadeh. 2020
11 citations recorded by the source corpus.
Sensor-based human activity recognition has become a critical component of many emerging applications ranging from behavioral medicine to gaming. However, an unprecedented increase in the diversity of sensor devices in the Internet-of-Things era has limited the adoption of activity recognition models for use across different domains. We propose ActiLabel a combinatorial framework that learns structural similarities among the events in an arbitrary domain and those of a different domain. The structural similarities are captured through a graph model, referred to as the it dependency graph, which abstracts details of activity patterns in low-level signal and feature space. The activity labels are then autonomously learned by finding an optimal tiered mapping between the dependency graphs. Extensive experiments based on three public datasets demonstrate the superiority of ActiLabel over state-of-the-art transfer learning and deep learning methods.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Seyed Iman Mirzadeh
- Mehrdad Farajtabar
- Hassan Ghasemzadeh
- Liyuan Wang
- Thang Van Doan
- Xingxing Zhang
- Jaehong Yoon
- Dong Yin
Citations in the corpus
- Dropout as an Implicit Gating Mechanism For Continual Learning (2020, methodology): “One interesting research direction is to modify the dropout method to gain more control over the gating mechanism, possibly by exploiting the structural similarity between sequential tasks and neural activation patterns, the same as proposed ideas in the transfer learning literature [1].”