Xu Feng

Mr. Xu Feng

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 September 2021 in Journal of Information and Telecommunication
Verified
Journal Article
Open access
XFXu Feng
Xu Feng
Khuong An NguyenKhuong An Nguyen
Khuong An Nguyen
ZLZhiyuan Luo
Zhiyuan Luo
One of the most popular approaches for indoor positioning is WiFi fingerprinting, which has been intrinsically tackled as a traditional machine learning problem since the beginning, to achieve a few metres of accuracy on average. In recent years, deep learning has emerged as an alternative approach, with a large number of publications reporting sub-metre positioning accuracy. Therefore, this survey presents a timely, comprehensive review of the most interesting deep learning methods being used for WiFi fingerprinting. In doing so, we aim to identify the most efficient neural networks, under a variety of positioning evaluation metrics for different readers. We will demonstrate that despite the new emerging WiFi signal measures (i.e. CSI and RTT), RSS produces competitive performances under deep learning. We will also show that simple neural networks outperform more complex ones in certain environments.

29 November 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XFXu Feng
Xu Feng
Khuong An NguyenKhuong An Nguyen
Khuong An Nguyen
ZLZhiyuan Luo
Zhiyuan Luo
The emerging WiFi Round Trip Time measured by the IEEE 802.11mc standard promised sub-meter-level accuracy for WiFi-based indoor positioning systems, under the assumption of an ideal line-of-sight path to the user. However, most workplaces with furniture and complex interiors cause the wireless signals to reflect, attenuate, and diffract in different directions. Therefore, detecting the non-line-of-sight condition of WiFi Access Points is crucial for enhancing the performance of indoor positioning systems. To this end, we propose a novel feature selection algorithm for non-line-of-sight identification of the WiFi Access Points. Using the WiFi Received Signal Strength and Round Trip Time as inputs, our algorithm employs multi-scale selection and Machine Learning-based weighting methods to choose the most optimal feature sets. We evaluate the algorithm on a complex campus WiFi dataset to demonstrate a detection accuracy of 93% for all 13 Access Points using 34 out of 130 features and only 3 s of test samples at any given time. For individual Access Point line-of-sight identification, our algorithm achieved an accuracy of up to 98%. Finally, we make the dataset available publicly for further research.

12 November 2024 in IEEE Access
Verified
Journal Article
Open access
XFXu Feng
Xu Feng
Khuong An NguyenKhuong An Nguyen
Khuong An Nguyen
ZLZhiyuan Luo
Zhiyuan Luo
WiFi fingerprinting is one of the most widely used techniques for indoor positioning systems. However, existing fingerprinting datasets came in different shapes and forms with varying levels of information without any standardised format. They were also dispersed across multiple platforms, making it challenging for new researchers to identify and access a suitable dataset to evaluate their own positioning systems. To address this challenge, this paper provides a comprehensive review of more than 50 publicly available WiFi fingerprinting datasets. We examine the most critical elements for fingerprinting, including the size and location of the testbed, the WiFi signal input, the number of locations, the temporal and spatial intervals of data collection, the positioning performance, and more. Surprisingly, it was observed that a large number of reference and access points, the use of 3D coordinates, denser sampling grid, and higher data collection frequencies do not always guarantee improved performance as often reported in the literature. The paper also outlines current challenges, and proposes guidelines for creating new WiFi fingerprint datasets.

5 April 2024 in IEEE Journal of Indoor and Seamless Positioning and Navigation
Verified
Journal Article
Open access
XFXu Feng
Xu Feng
Khuong An NguyenKhuong An Nguyen
Khuong An Nguyen
ZLZhiyuan Luo
Zhiyuan Luo
The advances in WiFi technology have encouraged the development of numerous indoor positioning systems. However, their performance varies significantly across different indoor environments, making it challenging in identifying the most suitable system for all scenarios. To address this challenge, we propose an algorithm that dynamically selects the most optimal WiFi positioning model for each location. Our algorithm employs a Machine Learning weighted model selection algorithm, trained on raw WiFi RSS, raw WiFi RTT data, statistical RSS & RTT measures, and Access Point line-of-sight information. We tested our algorithm in four complex indoor environments, and compared its performance to traditional WiFi indoor positioning models and state-of-the-art stacking models, demonstrating an improvement of up to 1.8 meters on average.

9 June 2025 in IEEE Sensors Reviews
Verified
Journal Article
Open access
XFXu Feng
Xu Feng
Khuong An NguyenKhuong An Nguyen
Khuong An Nguyen
ZLZhiyuan Luo
Zhiyuan Luo
WiFi fingerprinting has been a prominent solution for indoor positioning, yet its dependence on labour-intensive data collection and susceptibility to environmental dynamics are on-going major challenges. Thus, this paper presents a comprehensive survey and analysis of the data augmentation techniques designed to enhance WiFi fingerprinting datasets, focusing on the efficiency in data construction and the robustness in positioning accuracy. We reviewed over 70 studies, and proposed a novel taxonomy that categorises existing methods into 6 groups: traditional (e.g., interpolation, perturbation), propagation models, machine learning, deep learning, hybrid approaches, and other emerging techniques. Our quantitative analysis correlates key metrics, such as input data size, synthetic data volume, and augmentation ratios, with positioning performance. We found that traditional methods achieved notable performance enhancements with minimal computational overhead. Surprisingly, deep learning models became less efficient when generating more data, particularly when the synthetic data exceeded an threefold ratio over the input samples. Our findings provide actionable guidance for selecting data augmentation strategies and bridge the gap between theoretical advancements and practical deployment for WiFi fingerprinting dataset enhancement.

11 August 2023 in Journal of Location Based Services
Verified
Journal Article
Open access
XFXu Feng
Xu Feng
Khuong An NguyenKhuong An Nguyen
Khuong An Nguyen
ZLZhiyuan Luo
Zhiyuan Luo