Abstract
In this paper, we propose a convolutional neural network (CNN) model for device-free fingerprinting indoor localization based on Wi-Fi channel state information (CSI). Besides, we develop an interpretation framework to understand the representations learned by the model. By quantifying and visualizing CNN in comparison with the fully-connected feedforward deep neural network (DNN) (or multilayer perceptron), we observe that each model can automatically identify location-specific patterns, which are however different across models and are linked to the respective performance of each model. Furthermore, we quantify how features, relevant or otherwise, as deemed by the adopted quantifying metrics (i.e., relevance scores, calculated by relevance propagation techniques), determine or affect the performance results. Interpretation of learning models for wireless applications is challenging due to the lack of human sensory intuition and reference. The results presented in this paper provide visually perceivable evidence and plausible explanations for the performance advantages of CNN in this important application.
Highlights
Wireless indoor localization is a key enabling technology for the Internet of Things (IoT) [1]
Fingerprinting refers to building an offline database (‘‘fingerprints’’) of wireless signal measurements and matching the online measurements with the offline database to determine the location of the target
We showed that the convolutional neural network (CNN) classifier achieves better statistical performance as compared to the k-NN, SVM, and deep neural network (DNN), and has fewer trainable parameters as compared to the DNN
Summary
Wireless indoor localization is a key enabling technology for the Internet of Things (IoT) [1]. Precise location information is crucial for many futuristic IoT applications, such as smart cities and smart homes [2], disaster management and droneassisted rescue services [3], [4], health care and assisted living [5], vehicle-to-everything (V2X) services [6]–[8], etc. Fingerprinting-based techniques with Wi-Fi measurements are a widely adopted solution for indoor localization. Fingerprinting refers to building an offline database (‘‘fingerprints’’) of wireless signal measurements and matching the online measurements with the offline database to determine the location of the target. A commonly used measurement parameter is the received signal strength (RSS). For orthogonal frequency-division multiplexing (OFDM)-based Wi-Fi radios, channel state information (CSI) carries advantageous potential as the measurement parameter, as it provides fine-grained link information in the granularity
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have