Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition.

Sensors (Basel) 2018 Nov 13;18(11). Epub 2018 Nov 13.

Department of Computer Science and Engineering, Kyung Hee University, (Global Campus), 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do 17104, Korea.

The most significant barrier to success in human activity recognition is extracting and selecting the right features. In traditional methods, the features are chosen by humans, which requires the user to have expert knowledge or to do a large amount of empirical study. Newly developed deep learning technology can automatically extract and select features. Among the various deep learning methods, convolutional neural networks (CNNs) have the advantages of local dependency and scale invariance and are suitable for temporal data such as accelerometer (ACC) signals. In this paper, we propose an efficient human activity recognition method, namely Iss2Image (Inertial sensor signal to Image), a novel encoding technique for transforming an inertial sensor signal into an image with minimum distortion and a CNN model for image-based activity classification. Iss2Image converts real number values from the , , and axes into three color channels to precisely infer correlations among successive sensor signal values in three different dimensions. We experimentally evaluated our method using several well-known datasets and our own dataset collected from a smartphone and smartwatch. The proposed method shows higher accuracy than other state-of-the-art approaches on the tested datasets.

Download full-text PDF

Source
http://www.mdpi.com/1424-8220/18/11/3910
Publisher Site
http://dx.doi.org/10.3390/s18113910DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6263516PMC
November 2018

Publication Analysis

Top Keywords

sensor signal
12
human activity
12
activity recognition
12
signal image
8
deep learning
8
inertial sensor
8
suitable temporal
4
acc signals
4
values three
4
invariance suitable
4
scale invariance
4
signal values
4
accelerometer acc
4
successive sensor
4
three dimensions
4
data accelerometer
4
correlations successive
4
temporal data
4
dimensions experimentally
4
method well-known
4

Similar Publications