Yifan Shi

Yifan Shi

Auto-generated profile, based on publicly available information

Yifan Shi

Department of Mechanics and Material Engineering, Queens University, Kingston, ON, Canada

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
11 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Ling-Feng ShiLing-Feng Shi
Ling-Feng Shi
ZLZhong-Ye Liu
Zhong-Ye Liu
KZKe-Jun Zhou
Ke-Jun Zhou
YSYifan Shi
Yifan Shi
XJXiao Jing
Xiao Jing
Some recent studies use a convolutional neural network (CNN) or long short-term memory (LSTM) to extract gait features, but the methods based on the CNN and LSTM have a high loss rate of time-series and spatial information, respectively. Since gait has obvious time-series characteristics, while CNN only collects waveform characteristics, and only uses CNN for gait recognition, this leads to a certain lack of time-series characteristics. LSTM can collect time-series characteristics, but LSTM results in performance degradation when processing long sequences. However, using CNN can compress the length of feature vectors. In this paper, a sequential convolution LSTM network for gait recognition using multimodal wearable inertial sensors is proposed, which is called SConvLSTM. Based on 1D-CNN and a bidirectional LSTM network, the method can automatically extract features from the raw acceleration and gyroscope signals without a manual feature design. 1D-CNN is first used to extract the high-dimensional features of the inertial sensor signals. While retaining the time-series features of the data, the dimension of the features is expanded, and the length of the feature vectors is compressed. Then, the bidirectional LSTM network is used to extract the time-series features of the data. The proposed method uses fixed-length data frames as the input and does not require gait cycle detection, which avoids the impact of cycle detection errors on the recognition accuracy. We performed experiments on three public benchmark datasets: UCI-HAR, HuGaDB, and WISDM. The results show that SConvLSTM performs better than most of those reporting the best performance methods, at present, on the three datasets.

9 January 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Ling-Feng ShiLing-Feng Shi
Ling-Feng Shi
BFBao-Lin Feng
Bao-Lin Feng
YDYi-Fan Dai
Yi-Fan Dai
GLGong-Xu Liu
Gong-Xu Liu
YSYifan Shi
Yifan Shi
To solve the problem of time-consuming, laborious and low accuracy in magnetic map construction, a trajectory guided two-dimensional magnetic map construction method is proposed in this paper. The absolute displacement calculated by the inertial navigation system is mapped to the real trajectory to construct the magnetic map. The precision of the constructed magnetic map can reach 0.1141 m, and the mapping efficiency is greater than 1800 m2/h. Moreover, the cost of sensor is only $15.4. To deal with the instability problem that the traditional particle filter in PDR suffers from, this paper proposes an integrated particle filter algorithm. The algorithm uses two assumptions: 1. All noises obey Gaussian distribution; 2. The initial position and the results obtained from integrated particle filter are reliable enough. The particle distribution in the case of infinite particles is simulated, and similar particles are integrated. The algorithm breaks through the limit of particle number of particle filter and greatly reduces the randomness of particle filter algorithm. The real-world experiments show that the proposed positioning method can achieve an average positioning error of 0.32m.

13 October 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Ling-Feng ShiLing-Feng Shi
Ling-Feng Shi
WYWei Yin
Wei Yin
YLYun-Feng Lv
Yun-Feng Lv
YSYifan Shi
Yifan Shi
In this paper, based on the study of Linear Frequency Modulated Continuous Wave (LFMCW) radar, a ranging algorithm for the high-precision liquid level measurement in industry is proposed. A new algorithm is developed based on the MacLeod algorithm. The frequency offset δ 0 is estimated, and then (δ 0 -q, δ 0 +q) is used as the iterative estimation initial iteration interval to determine the frequency offset δ 0 more precisely. The improved algorithm is the Golden-MacLeod algorithm, referred to as the GM algorithm. Simulation results show that the GM can effectively reduce the estimation error and maintain the high frequency estimation accuracy at signal-to-noise ratio (SNR) up to -10 dB, which is better than the MacLeod algorithm. In addition, the estimation accuracy, stability and noise immunity are better than other algorithms in the variation interval of SNR greater than -5 dB. Liquid level measurement experiment is tested by TI’s IWR 6843ISK and DCA1000EVM. The measurement results also show that the measurement accuracy of the GM can meet the requirements of industrial applications. This also proves the reliability of the GM in practical applications.

9 August 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Ling-Feng ShiLing-Feng Shi
Ling-Feng Shi
YLYun-Feng Lv
Yun-Feng Lv
WYWei Yin
Wei Yin
YSYifan Shi
Yifan Shi
This paper proposed an autonomous multi-frame fusion method of millimeter wave (mmWave) radar point cloud suitable for low crowd density indoor scenes to overcome the problem of sparse target points in the application of frequency modulated continuous wave (FMCW) radar in indoor 4D point cloud imaging. Without other sensors, in the static or translational state of the radar, the static and dynamic target points in the radar field of vision are distinguished through multiple velocity iterations, and then the static target points are used to estimate the velocity of the radar itself. By calculating the displacement of the radar within a frame time, we carry out velocity filtering on the point cloud to remove the target points with large differences. Finally, the radar point cloud data of each frame is converted to the same geographic coordinate system to achieve 4D point cloud multi-frame fusion. The experimental results show that the presented method can accurately estimate the velocity of the radar and correct the coordinates of each frame point cloud. According to the imaging results, the proposed algorithm can greatly increase the imaging density of point cloud without defocusing, which improves the accuracy and readability of point cloud image with the imaging ability of static and moving targets.

3 October 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Ling-Feng ShiLing-Feng Shi
Ling-Feng Shi
WZWen Zhou
Wen Zhou
XYXu Yan
Xu Yan
YSYifan Shi
Yifan Shi
Current smartphone-based step detection algorithms do not comprehensively consider the randomness of user movements in daily life, such as carrying smartphone in various postures, false walking, and walking in various gaits. To overcome the problem, this paper proposes a novel step detection algorithm based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Hilbert Transform (CEEMDAN-HT). Firstly, the CEEMDAN Partial Reconstruction (CEEMDAN-PR) algorithm is presented to reduce noise for inertial data. In order to compensate the step count misdetection due to the mix-postures. Secondly, we combine Support Vector Machine (SVM) with CEEMDAN energy entropy for accurate identification of user movement state and smartphone carrying posture. This approach addresses the issue of false walking and selects appropriate step detection strategies for different scenarios. Finally, HT is used to obtain instantaneous phase information from inertial data for step detection. This approach is capable of adapting to mixed-gaits and mixed-postures without complex threshold settings. Experiment results show that its superior performance, achieving 98.10% average accuracy in free walking and 93.85% in false walking scenarios.

16 August 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
Ling-Feng ShiLing-Feng Shi
Ling-Feng Shi
RZRui Zeng
Rui Zeng
FJFeng Jing
Feng Jing
YSYifan Shi
Yifan Shi
People’s need for positioning and navigational data has grown over time as communication technology has advanced, becoming an essential and significant aspect of daily life. As a result of the Global Navigation Satellite Systems (GNSS) increasing maturity, satellite positioning technology can now achieve the highest centimeter-level positioning accuracy, effectively meeting the majority of outdoor positioning requirements. However, indoor positioning technology emerged as a solution for locations where satellite signals are obstructed and cannot normally provide positioning information. Researchers have focused on the Bluetooth positioning algorithm among them because it is a wireless positioning method. There are two types of traditional Bluetooth Received Signal Strength Indicator (RSSI) positioning methods based on the Internet of Things (IoT): trilateral and multilateral. However, because environmental interference causes the Bluetooth signal’s RSSI value to fluctuate greatly, using either of the above methods will result in significant errors and a decline in positioning accuracy when buildings, objects, or people are in the way. To address this issue, this paper proposes preprocessing the data prior to applying the least squares method. At the same time, based on processing outcomes, the weighted least squares method is utilized to determine Bluetooth RSSI positioning, resulting in a notable improvement over the accuracy of the traditional RSSI Bluetooth positioning.