Zhiyuan Luo

Prof. Zhiyuan Luo


Research Focus & Metrics

Academic Career Length

21Years (2006-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.

11 July 2020 in Brain Sciences
Verified
Journal Article
Open access
PDF file
YWYou Wang
You Wang
MZMing Zhang
Ming Zhang
RWRumeng Wu
Rumeng Wu
HGHan Gao
Han Gao
MYMeng Yang
Meng Yang
GLGuang Li
Guang Li
Silent speech decoding is a novel application of the Brain–Computer Interface (BCI) based on articulatory neuromuscular activities, reducing difficulties in data acquirement and processing. In this paper, spatial features and decoders that can be used to recognize the neuromuscular signals are investigated. Surface electromyography (sEMG) data are recorded from human subjects in mimed speech situations. Specifically, we propose to utilize transfer learning and deep learning methods by transforming the sEMG data into spectrograms that contain abundant information in time and frequency domains and are regarded as channel-interactive. For transfer learning, a pre-trained model of Xception on the large image dataset is used for feature generation. Three deep learning methods, Multi-Layer Perception, Convolutional Neural Network and bidirectional Long Short-Term Memory, are then trained using the extracted features and evaluated for recognizing the articulatory muscles’ movements in our word set. The proposed decoders successfully recognized the silent speech and bidirectional Long Short-Term Memory achieved the best accuracy of 90%, outperforming the other two algorithms. Experimental results demonstrate the validity of spectrogram features and deep learning algorithms.

2 September 2010 in Sensors
Verified
Journal Article
Open access
PDF file
ZPZhifu Pei
Zhifu Pei
Xingfa (or X.) MaXingfa (or X.) Ma
Xingfa (or X.) Ma
PDPengfei Ding
Pengfei Ding
WZWuming Zhang
Wuming Zhang
ZLZhiyuan Luo
Zhiyuan Luo
GLGuang Li
Guang Li
Sensitive, selective and fast detection of chemical warfare agents is necessary for anti-terrorism purposes. In our search for functional materials sensitive to dimethyl methylphosphonate (DMMP), a simulant of sarin and other toxic organophosphorus compounds, we found that zinc oxide (ZnO) modification potentially enhances the absorption of DMMP on a manganese dioxide (MnO2) surface. The adsorption behavior of DMMP was evaluated through the detection of tiny organophosphonate compounds with quartz crystal microbalance (QCM) sensors coated with ZnO-modified MnO2 nanofibers and pure MnO2 nanofibers. Experimental results indicated that the QCM sensor coated with ZnO-modified nanostructured MnO2 film exhibited much higher sensitivity and better selectivity in comparison with the one coated with pure MnO2 nanofiber film. Therefore, the DMMP sensor developed with this composite nanostructured material should possess excellent selectivity and reasonable sensitivity towards the tiny gaseous DMMP species.

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.

3 August 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
LLLi Liu
Li Liu
XZXianghao Zhan
Xianghao Zhan
RWRumeng Wu
Rumeng Wu
XGXiaoqing Guan
Xiaoqing Guan
ZWZhan Wang
Zhan Wang
GLGuang Li
Guang Li
Electronic nose has been proven effective in alternative herbal medicine classification, but due to the nature of supervised learning, previous research heavily relies on the labelled training data, which are time-costly and labor-intensive to collect. To alleviate the critical dependency on the training data in real-world applications, this study aims to improve classification accuracy via data augmentation strategies. The effectiveness of five data augmentation strategies under different training data inadequacy are investigated in two scenarios: the noise-free scenario where different availabilities of unlabelled data were considered, and the noisy scenario where different levels of Gaussian noises and translational shift were added to represent sensor drift. The five augmentation strategies, namely noise-adding data augmentation, semi-supervised learning, classifier-based online learning, Inductive Conformal Prediction (ICP) online learning and our novel ensemble ICP online learning (EICP) proposed in this study, are compared against supervised learning baselines, with Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) as the classifiers. This study provides a systematic analysis of different augmentation strategies. Our novel strategy, EICP, outperforms the others by showing non-decreasing classification accuracy on all tasks and a significant improvement on most simulated tasks (25 out of 36 tasks, ${p} \leq 0.05$ ), which demonstrated both effectiveness and robustness in boosting the classification model generalizability. This strategy can be employed in other machine learning applications.