HarMI: Human Activity Recognition via Multi-modality Incremental Learning

2021 ◽  
pp. 1-1
Author(s):  
Xiao Zhang ◽  
Hongzheng Yu ◽  
Yang Yang ◽  
Jingjing Gu ◽  
Yujun Li ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Incremental Learning ◽  
Human Activity Recognition

A Novel Feature Incremental Learning Method for Sensor-Based Activity Recognition

2019 ◽  
Vol 31 (6) ◽  
pp. 1038-1050 ◽  
Author(s):  
Chunyu Hu ◽  
Yiqiang Chen ◽  
Xiaohui Peng ◽  
Han Yu ◽  
Chenlong Gao ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Incremental Learning ◽  
Learning Method ◽  
Incremental Learning Method

scholarly journals Context-aware incremental learning-based method for personalized human activity recognition

2021 ◽  
Author(s):  
Pekka Siirtola ◽  
Juha Röning
Keyword(s):  
Discriminant Analysis ◽  
Activity Recognition ◽  
Human Activity ◽  
Error Rate ◽  
Incremental Learning ◽  
Body Position ◽  
Human Activity Recognition ◽  
Streaming Data ◽  
Linear Discriminant ◽  
Independent Model

AbstractThis study introduces an ensemble-based personalized human activity recognition method relying on incremental learning, which is a method for continuous learning, that can not only learn from streaming data but also adapt to different contexts and changes in context. This adaptation is based on a novel weighting approach which gives bigger weight to those base models of the ensemble which are the most suitable to the current context. In this article, contexts are different body positions for inertial sensors. The experiments are performed in two scenarios: (S1) adapting model to a known context, and (S2) adapting model to a previously unknown context. In both scenarios, the models had to also adapt to the data of previously unknown person, as the initial user-independent dataset did not include any data from the studied user. In the experiments, the proposed ensemble-based approach is compared to non-weighted personalization method relying on ensemble-based classifier and to static user-independent model. Both ensemble models are experimented using three different base classifiers (linear discriminant analysis, quadratic discriminant analysis, and classification and regression tree). The results show that the proposed ensemble method performs much better than non-weighted ensemble model for personalization in both scenarios no matter which base classifier is used. Moreover, the proposed method outperforms user-independent models. In scenario 1, the error rate of balanced accuracy using user-independent model was 13.3%, using non-weighted personalization method 13.8%, and using the proposed method 6.4%. The difference is even bigger in scenario 2, where the error rate using user-independent model is 36.6%, using non-weighted personalization method 36.9%, and using the proposed method 14.1%. In addition, F1 scores also show that the proposed method performs much better in both scenarios that the rival methods. Moreover, as a side result, it was noted that the presented method can also be used to recognize body position of the sensor.

Human Activity Recognition-Oriented Incremental Learning with Knowledge Distillation

2020 ◽  
pp. 2150096
Author(s):  
Caijuan Chen ◽  
Kaoru Ota ◽  
Mianxiong Dong ◽  
Chen Yu ◽  
Hai Jin
Keyword(s):  
Activity Recognition ◽  
Incremental Learning ◽  
Sample Selection ◽  
Sensor Data ◽  
Storage Space ◽  
Knowledge Distillation ◽  
Space Limitation ◽  
Recognition Systems ◽  
Public Datasets ◽  
Specific Number

Recently, a variety of different machine learning methods improve the applicability of activity recognition systems in different scenarios. For many current activity recognition models, it is assumed that all data are prepared well in advance and the device has no storage space limitation. However, the process of the sensor data collection is dynamically changing over time, the activity category may be continuously increasing, and the device has limited storage space. Therefore, in this study, we propose a novel class incremental learning comprehensive solution towards activity recognition with knowledge distillation. Besides, we develop the representative sample selection method to select and update a specific number of preserved old samples. When new activity classes samples arrive, we only need the new classes samples and the representative old samples to preserve the network’s performance for old classes while identifying the new classes. Finally, we carry out experiments using two different public datasets, and they show good accuracy for old and new categories. Besides, the method can significantly reduce the space required to store old classes samples.

Sign in / Sign up

Export Citation Format

Share Document