Next Article in Journal
High-Efficiency Automatic Recharging Mechanism for Cleaning Robot Using Multi-Sensor
Previous Article in Journal
Particle Filter Based Monitoring and Prediction of Spatiotemporal Corrosion Using Successive Measurements of Structural Responses
Open AccessArticle

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

1
Department of Computer Science and Engineering, Kyung Hee University, (Global Campus), 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do 17104, Korea
2
Department of Smart ICT Convergence, Konkuk University, 120 Neungdong-ro, Gwangjin-gu, Seoul 05029, Korea
*
Authors to whom correspondence should be addressed.
Sensors 2018, 18(11), 3910; https://doi.org/10.3390/s18113910
Received: 31 August 2018 / Revised: 5 November 2018 / Accepted: 12 November 2018 / Published: 13 November 2018
(This article belongs to the Section Physical Sensors)
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 X, Y, and Z 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. View Full-Text
Keywords: human activity recognition; convolutional neural network; encoder; signal transformation; smartphone; smartwatch; accelerometer human activity recognition; convolutional neural network; encoder; signal transformation; smartphone; smartwatch; accelerometer
Show Figures

Figure 1

MDPI and ACS Style

Hur, T.; Bang, J.; Huynh-The, T.; Lee, J.; Kim, J.-I.; Lee, S. Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition. Sensors 2018, 18, 3910. https://doi.org/10.3390/s18113910

AMA Style

Hur T, Bang J, Huynh-The T, Lee J, Kim J-I, Lee S. Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition. Sensors. 2018; 18(11):3910. https://doi.org/10.3390/s18113910

Chicago/Turabian Style

Hur, Taeho; Bang, Jaehun; Huynh-The, Thien; Lee, Jongwon; Kim, Jee-In; Lee, Sungyoung. 2018. "Iss2Image: A Novel Signal-Encoding Technique for CNN-Based Human Activity Recognition" Sensors 18, no. 11: 3910. https://doi.org/10.3390/s18113910

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop