Next Article in Journal
Habit Representation Based on Activity Recognition
Next Article in Special Issue
Wi-Fi CSI-Based Outdoor Human Flow Prediction Using a Support Vector Machine
Previous Article in Journal
Legodroid: A Type-Driven Library for Android and LEGO Mindstorms Interoperability
Previous Article in Special Issue
Intelligent Lecturer Tracking and Capturing System Based on Face Detection and Wireless Sensing Technology
Article

Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process

1
Department of Electronics and Control Engineering, Hanbat National University, Dajeon 34158, Korea
2
Department of Computer Science, University of Southern California, Los Angeles, CA 90089, USA
3
Agency for Defense Development, Daejeon 34186, Korea
4
TnB Radio Tech., Seoul 08511, Korea
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(7), 1927; https://doi.org/10.3390/s20071927
Received: 5 February 2020 / Revised: 12 March 2020 / Accepted: 27 March 2020 / Published: 30 March 2020
Although various linear log-distance path loss models have been developed for wireless sensor networks, advanced models are required to more accurately and flexibly represent the path loss for complex environments. This paper proposes a machine learning framework for modeling path loss using a combination of three key techniques: artificial neural network (ANN)-based multi-dimensional regression, Gaussian process-based variance analysis, and principle component analysis (PCA)-aided feature selection. In general, the measured path loss dataset comprises multiple features such as distance, antenna height, etc. First, PCA is adopted to reduce the number of features of the dataset and simplify the learning model accordingly. ANN then learns the path loss structure from the dataset with reduced dimension, and Gaussian process learns the shadowing effect. Path loss data measured in a suburban area in Korea are employed. We observe that the proposed combined path loss and shadowing model is more accurate and flexible compared to the conventional linear path loss plus log-normal shadowing model. View Full-Text
Keywords: wireless sensor network; path loss; machine learning; artificial neural network (ANN); principle component analysis (PCA); Gaussian process; multi-dimensional regression; shadowing; feature selection wireless sensor network; path loss; machine learning; artificial neural network (ANN); principle component analysis (PCA); Gaussian process; multi-dimensional regression; shadowing; feature selection
Show Figures

Figure 1

MDPI and ACS Style

Jo, H.-S.; Park, C.; Lee, E.; Choi, H.K.; Park, J. Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process. Sensors 2020, 20, 1927. https://doi.org/10.3390/s20071927

AMA Style

Jo H-S, Park C, Lee E, Choi HK, Park J. Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process. Sensors. 2020; 20(7):1927. https://doi.org/10.3390/s20071927

Chicago/Turabian Style

Jo, Han-Shin, Chanshin Park, Eunhyoung Lee, Haing K. Choi, and Jaedon Park. 2020. "Path Loss Prediction Based on Machine Learning Techniques: Principal Component Analysis, Artificial Neural Network, and Gaussian Process" Sensors 20, no. 7: 1927. https://doi.org/10.3390/s20071927

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
Back to TopTop