CSI-Based Fingerprinting for Indoor Localization: A Deep Learning Approach

By Xuyu Wang, Lingjun Gao, Shiwen Mao, Santosh Pandey. IEEE Transactions on Vehicular Technology, 2016

992 citations recorded by the source corpus.

With the fast-growing demand of location-based services in indoor environments, indoor positioning based on fingerprinting has attracted significant interest due to its high accuracy. In this paper, we present a novel deep-learning-based indoor fingerprinting system using channel state information (CSI), which is termed DeepFi. Based on three hypotheses on CSI, the DeepFi system architecture includes an offline training phase and an online localization phase. In the offline training phase, deep learning is utilized to train all the weights of a deep network as fingerprints. Moreover, a greedy learning algorithm is used to train the weights layer by layer to reduce complexity. In the online localization phase, we use a probabilistic method based on the radial basis function to obtain the estimated location. Experimental results are presented to confirm that DeepFi can effectively reduce location error, compared with three existing methods in two representative indoor environments.

Subfields: Electrical and Electronic Engineering, Ocean Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/4016403a62b587a675198415b93b903e2a66264a

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

In Ocean Engineering

In Signal Processing

Citations in the corpus

The Integrated Sensing and Communication Revolution for 6G: Vision, Techniques, and Applications (2024, positive): “…the angle–delay domain channel power matrix [140], [141], a weighted average of CSI values over multiple antennas [142], the CSI per sub-carrier [143], [144], or a decimated delay-domain CSI representation followed by autocorrelation to extract features invariant to the system impairments…”
Application of Machine Learning in Wireless Networks: Key Techniques and Open Issues (2018, methodology): “Moreover, ideas similar to [133] are adopted in [134] and [135].”
Wireless Sensing for Human Activity: A Survey (2020, background): “[89], [90] propose to use deep learning techniques to facilitate indoor localization.”
CSI Phase Fingerprinting for Indoor Localization With a Deep Learning Approach (2016, methodology): “To improve localization accuracy based on CSI values, DeepFi [11], [24] system leverages a large amount of CSI”
Deep Learning Based Transmit Power Control in Underlaid Device-to-Device Communication (2019, background): “, the classification of communication signals [10], channel estimation and signal detection [12], indoor localization [15], and the optimization of constellation mapping and demapping of symbols on each sub-carrier of orthogonal frequency division multiplexing systems [16].”
Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks (2019, neutral): “In [314]–[316], Wang et al.”
Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems (2017, methodology): “Historically, researchers have developed many channel models for CSI that well describe the real channels in terms of channel statistics.”
A Survey of Multi-Access Edge Computing in 5G and Beyond: Fundamentals, Technology Integration, and State-of-the-Art (2019, background): “networks can be used for channel estimation and signal detection [350], [351], localization based on channels state information [352], [353], and channel decoding [354], which all show that ML is a promising tool in wireless communications.”
Applications of Deep Reinforcement Learning in Communications and Networking: A Survey (2018, methodology): “Deep learning that is able to learn useful features from complicated environments can be used for the user localization as proposed in [189].”
Earthquake Prediction Based on Spatio-Temporal Data Mining: An LSTM Network Approach (2020, methodology): “Recently, deep learning methods like RNNs are shown to be able to capture the nonlinear correlations among data [16], [17].”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “The same group of authors extend their work in [274], [275], [314], and [315], where they update the localization system, such that it can work with calibrated phase information of CSI [274], [275], [325].”
PhaseBeat: Exploiting CSI Phase Data for Vital Sign Monitoring with Commodity WiFi Devices (2017, background): “CSI reveals the channel characteristics experienced by the received signal such as the multipath effect, shadow fading, and distortion [26], [27].”