Yang Gao

Yang Gao

Auto-generated profile, based on publicly available information

Yang Gao

Research Base of Beijing Modern Manufacturing Development, College of Economics and Management, Beijing University of Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
24 April 2021 in Journal of Healthcare Engineering
Verified
Journal Article
Open access
PDF file
PLPeng Lu
Peng Lu
YGYang Gao
Yang Gao
HXHao Xi
Hao Xi
YZYabin Zhang
Yabin Zhang
CGChao Gao
Chao Gao
XMXiaobo Mao
Xiaobo Mao
Acquiring electrocardiographic (ECG) signals and performing arrhythmia classification in mobile device scenarios have the advantages of short response time, almost no network bandwidth consumption, and human resource savings. In recent years, deep neural networks have become a popular method to efficiently and accurately simulate nonlinear patterns of ECG data in a data-driven manner but require more resources. Therefore, it is crucial to design deep learning (DL) algorithms that are more suitable for resource-constrained mobile devices. In this paper, KecNet, a lightweight neural network construction scheme based on domain knowledge, is proposed to model ECG data by effectively leveraging signal analysis and medical knowledge. To evaluate the performance of KecNet, we use the Association for the Advancement of Medical Instrumentation (AAMI) protocol and the MIT-BIH arrhythmia database to classify five arrhythmia categories. The result shows that the ACC, SEN, and PRE achieve 99.31%, 99.45%, and 98.78%, respectively. In addition, it also possesses high robustness to noisy environments, low memory usage, and physical interpretability advantages. Benefiting from these advantages, KecNet can be applied in practice, especially wearable and lightweight mobile devices for arrhythmia classification.

22 August 2022 in Sustainable Production and Consumption
Verified
Journal Article
Open access
CWChao Wang
Chao Wang
WSWenju Sun
Wenju Sun
MLMing K. Lim
Ming K. Lim
XHXiaoqian Hu
Xiaoqian Hu
YGYang Gao
Yang Gao
PGPezhman Ghadimi
Pezhman Ghadimi

29 May 2021 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
PLPeng Lu
Peng Lu
YZYabin Zhang
Yabin Zhang
BZBing Zhou
Bing Zhou
HZHongpo ZHANG
Hongpo ZHANG
LCliwei chen
liwei chen
HXHao Xi
Hao Xi
In recent years, deep learning (DNN) based methods have made leapfrogging level breakthroughs in detecting cardiac arrhythmias as the cost effectiveness of arithmetic power, and data size has broken through the tipping point. However, the inability of these methods to provide a basis for modeling decisions limits clinicians confidence on such methods. In this paper, a Gate Recurrent Unit (GRU) and decision tree fusion model, referred to as (T-GRU), was designed to explore the problem of arrhythmia recognition and to improve the credibility of deep learning methods. The fusion model multipathway processing time-frequency domain featured the introduction of decision tree probability analysis of frequency domain features, the regularization of GRU model parameters and weight control to improve the decision tree model output weights. The MIT-BIH arrhythmia database was used for validation. Results showed that the low-frequency band features dominated the model prediction. The fusion model had an accuracy of 98.31, sensitivity of 96.85, specificity of 98.81, and precision of 96.73, indicating its high reliability and clinical significance.

4 September 2019 in NeuroReport
Verified
Journal Article
Closed access
SZShibo Zhou
Shibo Zhou
XZXiuming Zhang
Xiuming Zhang
YGYang Gao
Yang Gao
BYBo Yang
Bo Yang
WSWen-Rong Shen
Wen-Rong Shen
Purpose This study assessed the association between diffusion-weighted imaging (DWI) volume and fluid-attenuated inversion recovery vascular hyperintensity (FVH)-DWI mismatch, functional outcome in patients with acute stroke patients receiving endovascular therapy, as well as the value of DWI volume in predicting functional outcome with stroke patients. Methods In 38 stroke patients who received endovascular therapy, FVH-DWI mismatch, DWI volume on admission, DWI volume on follow-up, DWI volume growth, the functional outcome at 3 months [modified Rankin scale (mRS)], and other clinical data were collected. Statistical analysis was performed to compare the associations with the above variables and predict functional outcome after stroke. Results Compared with no FVH-DWI mismatch group (n = 15), FVH-DWI mismatch group (n = 23) had a smaller DWI volume on admission (t = −2.980; P = 0.008), smaller DWI volume on follow-up (t = −2.911; P = 0.009), lower DWI volume growth (t = −2.328; P = 0.031). The 3-month outcome (1.87 ± 0.92) in patients with FVH-DWI mismatch was better than that (2.93 ± 1.62) of patients with no FVH-DWI mismatch (t = −2.307; P = 0.032). Spearman’s rank correlation analysis revealed that FVH-DWI mismatch (r = 0.327; P = 0.045), DWI volume on admission (r = 0.414; P = 0.010), DWI volume on follow-up (r = 0.486; P = 0.002), and DWI volume growth (r = 0.467; P = 0.003) were positively correlated with mRS at 3 months. ROC analysis showed when the optimal cutoff value of DWI volume on admission was 33.50, the sensitivity and specificity for predicting functional outcome was 60 and 95.65%, respectively. Conclusions Evaluating DWI volume on admission, DWI volume on follow-up as well as DWI volume growth comprehensively may be useful in predicting the functional outcome of acute stroke patients after thrombectomy.

15 May 2020
Verified
Report
Open access
WWWenjing Wei
Wenjing Wei
YZYanli Zhang
Yanli Zhang
RCRumeng Chen
Rumeng Chen
YGYang Gao
Yang Gao
QCQiu Chen
Qiu Chen
INPLASY202050065 The efficacy of vitamin D supplementation on Painful diabetic neuropathy,protocol for a systematic review and meta-analysis Keywords: vitamin D; painful diabetic neuropathy; system…

26 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
ASAnkit Shah
Ankit Shah
HDHira Dhamyal
Hira Dhamyal
YGYang Gao
Yang Gao
DADaniel Arancibia
Daniel Arancibia
MAMario Arancibia
Mario Arancibia
RSRita Singh
Rita Singh
Lately, there has been a global effort by multiple research groups to detect COVID-19 from voice. Different researchers use different kinds of information from the voice signal to achieve this. Various types of phonated sounds and the sound of cough and breath have all been used with varying degree of success in automated voice-based COVID-19 detection apps. In this paper, we show that detecting COVID-19 from voice does not require custom-made non-standard features or complicated neural network classifiers rather it can be successfully done with just standard features and simple binary classifiers. In fact, we show that the latter is not only more accurate and interpretable but also more computationally efficient in that they can be run locally on small devices. We demonstrate this on a human-curated dataset of over 1000 subjects, collected and calibrated in clinical settings.