Shuai Cao

Dr. Shuai Cao

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
25 September 2018 in Sensors
Verified
Journal Article
Open access
PDF file
LXLingfeng Xu
Lingfeng Xu
XCXiang Chen
Xiang Chen
SCShuai Cao
Shuai Cao
XZXu Zhang
Xu Zhang
XCXun Chen
Xun Chen
To find out the feasibility of different neural networks in sEMG-based force estimation, in this paper, three types of networks, namely convolutional neural network (CNN), long short-term memory (LSTM) network and their combination (C-LSTM) were applied to predict muscle force generated in static isometric elbow flexion across three different circumstances (multi-subject, subject-dependent and subject-independent). Eight healthy men were recruited for the experiments, and the results demonstrated that all the three models were applicable for force estimation, and LSTM and C-LSTM achieved better performances. Even under subject-independent situation, they maintained mean RMSE% of as low as 9.07 ± 1.29 and 8.67 ± 1.14. CNN turned out to be a worse choice, yielding a mean RMSE% of 12.13 ± 1.98. To our knowledge, this work was the first to employ CNN, LSTM and C-LSTM in sEMG-based force estimation, and the results not only prove the strength of the proposed networks, but also pointed out a potential way of achieving high accuracy in real-time, subject-independent force estimation.

16 September 2019 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
YYYi Yu
Yi Yu
XCXiang Chen
Xiang Chen
SCShuai Cao
Shuai Cao
XZXu Zhang
Xu Zhang
XCXun Chen
Xun Chen
In this paper, deep belief net (DBN) was applied into the field of wearable-sensor based Chinese Sign Language (CSL) recognition. Eight subjects were involved in the study, and all of the subjects finished a five-day experiment performing CSL on a target word set consisting of 150 CSL subwords. During the experiment, surface electromyography (sEMG), accelerometer (ACC), and gyroscope (GYRO) signals were collected from the participants. In order to obtain the optimal structure of the network, three different sensor fusion strategies, including data-level fusion, feature-level fusion, and decision-level fusion, were explored. In addition, for the feature-level fusion strategy, two different feature sources, which are hand-crafted features and network generated features, and two different network structures, which are fully-connected net and DBN, were also compared. The result showed that feature level fusion could achieve the best recognition accuracy among the three fusion strategies, and feature-level fusion with network generated features and DBN could achieve the best recognition accuracy. The best recognition accuracy realized in this study was 95.1% for the user-dependent test and 88.2% for the user-independent test. The significance of the study is that it applied the deep learning method into the field of wearable sensors-based CSL recognition, and according to our knowledge it's the first study comparing human engineered features with the network generated features in the correspondent field. The results from the study shed lights on the method of using network-generated features during sensor fusion and CSL recognition.

19 March 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SCShuai Cao
Shuai Cao
XCXiang Chen
Xiang Chen
XZXu Zhang
Xu Zhang
XCXun Chen
Xun Chen
To achieve high precision and robust positioning on mobile devices, we propose a novel audio signal arrival time detection algorithm consisting of both coarse and fine searches. A coarse search uses the cosine theorem to extract the audio data segment (ADS) from the received signal of a mobile device, and a fine search then uses the waveform characteristics of the autocorrelation function of the source signal to estimate the audio arrival time (AAT) from the ADS. An indoor threshold determination experiment, a static positioning experiment, and a moving target positioning experiment were carried out on the developed acoustic indoor positioning system (AIPS) in a hall. The performance of the proposed audio detection algorithm was compared to two other typical detection algorithms. The results of the static positioning experiment show that, in a nonline of sight (NLOS) environment, 90% of the positioning results estimated by the proposed algorithm have an error of less than 0.50 m, whereas only 56% and 6% of the positioning results estimated by the other two classical algorithms have errors of less than 0.50 m. In the target-moving positioning experiment, the positions estimated by the proposed algorithm are closer to the true trajectories and have fewer (less than 0.5%) abnormal positioning errors than the other two classical algorithms. The experimental results also show that the reliability judgment of the positioning results can further improve the robustness of the system. The proposed method has an important application value for the implementation of a highly precise and reliable AIPS.

22 May 2019 in Sensors
Verified
Journal Article
Open access
PDF file
XCXiang Chen
Xiang Chen
YCYuheng Chen
Yuheng Chen
SCShuai Cao
Shuai Cao
LZLei Zhang
Lei Zhang
XZXu Zhang
Xu Zhang
XCXun Chen
Xun Chen
This paper presents a novel audio indoor localization system. In the proposed system, four speakers placed at known positions transmit chirp signals according to the time-division multiple access (TDMA) plus frequency-division multiple access (FDMA) transmission scheme. A smartphone receives the signal via a built-in microphone and calculates the time differences of arrival (TDOAs). Using TDOA measurements, the position is estimated by the shrinking-circle method. In particular, to reduce the positioning error in moving conditions, a TDOA correction method based on Doppler shifts is proposed. The performance of the proposed system was evaluated in real-world experiments using a 10.971 m × 5.684 m positioning area. The results of the static-target positioning experiment showed that the TDMA+FDMA transmission scheme has more advantages in improving the update rate of the positioning system than the TDMA-only transmission scheme. The results of the moving-target positioning experiment under three different speeds demonstrated that the positioning errors were reduced by about 10 cm when the Doppler-shift-based TDOA correction method was adopted. This research provides a possible framework for the realization of a TDOA-chirp-based acoustic indoor positioning system with high positioning accuracy and update rate.

28 December 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
SPShengbing Pei
Shengbing Pei
CWChaoqun Wang
Chaoqun Wang
SCShuai Cao
Shuai Cao
ZLZhao Lv
Zhao Lv
Functional magnetic resonance imaging (fMRI) is an emerging neuroimaging modality that is widely used to study brain function and disorders due to its advantages of non-invasiveness, no radiation damage, and high spatial resolution. Existing studies have focused on fMRI-based recognition models to help diagnose brain disorders. However, due to the high cost of fMRI data acquisition and labeling, the amount of fMRI data is usually small, which largely limits the performance of recognition models. In addition, cross-site classification is always a challenge in fMRI study, because the heterogeneity of data collection at different sites increases the complexity and diversity of the data distribution, making the cross-site classification less robust than site-specific classification. In this paper, we propose three data augmentation methods based on functional connectivity networks (FCNs) of fMRI data, aided by a deep feature fusion method, for automatic disease identification. Firstly, Gaussian noise method, Mixup method, and sliding window method are proposed to effectively augment FCN data, respectively, this can balance the variability of sample distribution. Secondly, convolution neural network and graph attention network are separately employed to extract local and global features from FCN. Finally, the two kinds of features are integrated to classify subjects. The experimental results on the ADHD-200 dataset indicate that: (1) the data augmentation methods can effectively improve identification performance, in particular, the sliding window method performs best; (2) the cross-site attention deficit and hyperactivity disorder (ADHD) classification is improved by combining the data augmentation method of sliding window and deep feature fusion method; (3) the rationality of data augmentation for FCNs is explained by visualizing the hidden fused features with t-stochastic neighborhood embedding algorithm.

20 July 2020 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
TLTao Liu
Tao Liu
XNXiaoji Niu
Xiaoji Niu
Jian KuangJian Kuang
Jian Kuang
SCShuai Cao
Shuai Cao
LZLei Zhang
Lei Zhang
XCXiang Chen
Xiang Chen
Acoustic localization is a viable solution for high-precision indoor positioning with current built-in smartphone sensors. However, the Doppler shift produces an additional error in the time difference of arrival (TDOA) estimation when the smartphone is in motion, resulting in degradation in the acoustic localization performance. In this article, we present an indoor localization system for smartphones that overcomes the effects of the Doppler shift by combining inertial and acoustic sensors data. First, we establish an error correction model related to the current position and velocity of the smartphone, which can estimate and mitigate the errors caused by the Doppler shift in the TDOA measurements. Second, a uniform acceleration dynamic model and an improved pedestrian dead reckoning (PDR) algorithm are designed to obtain the model parameter. Experiments show that the two proposed algorithms reduce the positioning error by 49.1% and 71.9% under continuous acoustic signal conditions and by 33.3% and 69.8% under occasional abnormal signal conditions. The presented system can achieve a positioning accuracy of about 0.2 m (RMS).