Data Augmentation and Dense-LSTM for Human Activity Recognition Using WiFi Signal

Abstract

Recent research have devoted significant efforts on the utilization of WiFi signals to recognize various human activities. An individual's limb motions in the WiFi coverage area could interfere wireless signal propagation, that manifested as unique patterns for activities recognition. Existing approaches though yielding reasonable performance in certain cases, are ignorant of two major challenges. The performed activities of the individual normally have inconsistent speed in different situations and time. Besides that the wireless signal reflected by human bodies normally carry substantial information that is specific to that subject. The activity recognition model trained on a certain individual may not work well when being applied to predict another individual's activities. Since only recording activities of limited subjects in certain speed and scale, recent works commonly have moderate amount of activity data for training the recognition model. The small-size data could often incur the overfitting issue that negative affect the traditional classification model. To address these challenges, we propose a WiFi based human activity recognition system that synthesize variant activities data through 8 CSI transformation methods to mitigate the impact of activity inconsistency and subjectspecific issues, and also design a novel deep learning model that cater to the small-size WiFi activity data. We conduct extensive experiments and show synthetic data improve performance by up to 34.6% and our system achieves around 90% of accuracy with well robustness in adapting to small-size CSI data.

Gate-ID: WiFi-Based Human Identification Irrespective of Walking Directions in Smart Home

“…We employ the label-preserving transformation method that the augmented training samples are to preserve their class labels (i.e. individuals' identities) [40][41] [42]. The original feature dataset together with the augmented dataset form the synthetic training dataset which helps the following deep learning model to identify individuals in whichever orientations.…”

Towards Activity Recognition through Multidimensional Mobile Data Fusion with a Smartphone and Deep Learning

“…e framework of activity recognition based on CNN is developed [38]. When training human activity data, the activity recognition model trained on one person may not work well when it is applied to predict another person's activity [39,40]. In order to meet this challenge, data enhancement for human activity recognition is also a research hotspot.…”

A Deep Learning-Based Human Identification System With Wi-Fi CSI Data Augmentation

“…They generated probable data and maintained their labels. Many deep learning-based works [22][23][24] have used the data augmentation to improve accuracy, generalization, and prevent overfitting. [22] augments CSI spectrum data through nine different data transformation processes.…”

“…Many deep learning-based works [22][23][24] have used the data augmentation to improve accuracy, generalization, and prevent overfitting. [22] augments CSI spectrum data through nine different data transformation processes. This work aims at applying human behavior recognition, and CSI amplitude change is less than that of human identification.…”