Jingyi Zheng

Dr. Jingyi Zheng

Mathematics and Statistics, Auburn University, Auburn, Alabama, USA
orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
13 September 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
Jingyi ZhengJingyi Zheng
Jingyi Zheng
MLMingli Liang
Mingli Liang
SSSujata Sinha
Sujata Sinha
LGLinqiang Ge
Linqiang Ge
Wei YuWei Yu
Wei Yu
FHFushing Hsieh
Fushing Hsieh
Electroencephalography (EEG) is a brain imaging approach that has been widely used in neuroscience and clinical settings. The conventional EEG analyses usually require pre-defined frequency bands when characterizing neural oscillations and extracting features for classifying EEG signals. However, neural responses are naturally heterogeneous by showing variations in frequency bands of brainwaves and peak frequencies of oscillatory modes across individuals. Fail to account for such variations might result in information loss and classifiers with low accuracy but high variation across individuals. To address these issues, we present a systematic time-frequency analysis approach for analyzing scalp EEG signals. In particular, we propose a data-driven method to compute the subject-specific frequency bands for brain oscillations via Hilbert-Huang Transform, lifting the restriction of using fixed frequency bands for all subjects. Then, we propose two novel metrics to quantify the power and frequency aspects of brainwaves represented by sub-signals decomposed from the EEG signals. The effectiveness of the proposed metrics are tested on two scalp EEG datasets and compared with four commonly used features sets extracted from wavelet and Hilbert-Huang Transform. The validation results show that the proposed metrics are more discriminatory than other features leading to accuracies in the range of 94.93% to 99.84%. Besides classification, the proposed metrics show great potential in quantification of neural oscillations and serving as biomarkers in the neuroscience research.

26 April 2022 in Journal of Neuroscience Methods
Verified
Journal Article
Closed access
YYYuyan Yi
Yuyan Yi
NBNedret Billor
Nedret Billor
MLMingli Liang
Mingli Liang
XCXuan Cao
Xuan Cao
AEArne Ekstrom
Arne Ekstrom
Jingyi ZhengJingyi Zheng
Jingyi Zheng

22 October 2021 in ACM Transactions on Knowledge Discovery From Data
Verified
Journal Article
Open access
YZYang Zhou
Yang Zhou
JRJiaxiang Ren
Jiaxiang Ren
RJRuoming Jin
Ruoming Jin
ZZZijie Zhang
Zijie Zhang
Jingyi ZhengJingyi Zheng
Jingyi Zheng
DDDejing Dou
Dejing Dou
Network alignment, which aims at learning a matching between the same entities across multiple information networks, often suffers challenges from feature inconsistency, high-dimensional features, to unstable alignment results. This article presents a novel network alignment framework, Unsupervised Adversarial learning based Network Alignment(UANA), that combines generative adversarial network (GAN) and reinforcement learning (RL) techniques to tackle the above critical challenges. First, we propose a bidirectional adversarial network distribution matching model to perform the bidirectional cross-network alignment translations between two networks, such that the distributions of real and translated networks completely overlap together. In addition, two cross-network alignment translation cycles are constructed for training the unsupervised alignment without the need of prior alignment knowledge. Second, in order to address the feature inconsistency issue, we integrate a dual adversarial autoencoder module with an adversarial binary classification model together to project two copies of the same vertices with high-dimensional inconsistent features into the same low-dimensional embedding space. This facilitates the translations of the distributions of two networks in the adversarial network distribution matching model. Finally, we develop an RL based optimization approach to solve the vertex matching problem in the discrete space of the GAN model, i.e., directly select the vertices in target networks most relevant to the vertices in source networks, without unstable similarity computation that is sensitive to discriminative features and similarity metrics. Extensive evaluation on real-world graph datasets demonstrates the outstanding capability of UANA to address the unsupervised network alignment problem, in terms of both effectiveness and scalability.

18 March 2021 in Frontiers in Artificial Intelligence
Verified
Journal Article
Open access
PDF file
YLYuexin Li
Yuexin Li
LGLinqiang Ge
Linqiang Ge
YZYang Zhou
Yang Zhou
XCXuan Cao
Xuan Cao
Jingyi ZhengJingyi Zheng
Jingyi Zheng
The outbreak of COVID-19, caused by the SARS-CoV-2 coronavirus, has been declared a pandemic by the World Health Organization (WHO) in March, 2020 and rapidly spread to over 210 countries and territories around the world. By December 24, there are over 77M cumulative confirmed cases with more than 1.72M deaths worldwide. To mathematically describe the dynamic of the COVID-19 pandemic, we propose a time-dependent SEIR model considering the incubation period. Furthermore, we take immunity, reinfection, and vaccination into account and propose the SEVIS model. Unlike the classic SIR based models with constant parameters, our dynamic models not only predicts the number of cases, but also monitors the trajectories of changing parameters, such as transmission rate, recovery rate, and the basic reproduction number. Tracking these parameters, we observe the significant decrease in the transmission rate in the U.S. after the authority announced a series of orders aiming to prevent the spread of the virus, such as closing non-essential businesses and lockdown restrictions. Months later, as restrictions being gradually lifted, we notice a new surge of infection emerges as the transmission rates show increasing trends in some states. Using our epidemiology models, people can track, timely monitor, and predict the COVID-19 pandemic with precision. To illustrate and validate our model, we use the national level data (the U.S.) and the state level data (New York and North Dakota), and the resulting relative prediction errors for the infected group and recovered group are mostly lower than 0.5%. We also simulate the long-term development of the pandemic based on our proposed models to explore when the crisis will end under certain conditions.

18 March 2024 in Cardiovascular Toxicology
Verified
Journal Article
Open access
PDF file
BTBang Truong
Bang Truong
Jingyi ZhengJingyi Zheng
Jingyi Zheng
LHLori Hornsby
Lori Hornsby
BFBrent Fox
Brent Fox
CCChiahung Chou
Chiahung Chou
JQJingjing Qian
Jingjing Qian
In this study, we leveraged machine learning (ML) approach to develop and validate new assessment tools for predicting stroke and bleeding among patients with atrial fibrillation (AFib) and cancer. We conducted a retrospective cohort study including patients who were newly diagnosed with AFib with a record of cancer from the 2012–2018 Surveillance, Epidemiology, and End Results (SEER)-Medicare database. The ML algorithms were developed and validated separately for each outcome by fitting elastic net, random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and neural network models with tenfold cross-validation (train:test = 7:3). We obtained area under the curve (AUC), sensitivity, specificity, and F2 score as performance metrics. Model calibration was assessed using Brier score. In sensitivity analysis, we resampled data using Synthetic Minority Oversampling Technique (SMOTE). Among 18,388 patients with AFib and cancer, 523 (2.84%) had ischemic stroke and 221 (1.20%) had major bleeding within one year after AFib diagnosis. In prediction of ischemic stroke, RF significantly outperformed other ML models [AUC (0.916, 95% CI 0.887–0.945), sensitivity 0.868, specificity 0.801, F2 score 0.375, Brier score = 0.035]. However, the performance of ML algorithms in prediction of major bleeding was low with highest AUC achieved by RF (0.623, 95% CI 0.554–0.692). RF models performed better than CHA2DS2-VASc and HAS-BLED scores. SMOTE did not improve the performance of the ML algorithms. Our study demonstrated a promising application of ML in stroke prediction among patients with AFib and cancer. This tool may be leveraged in assisting clinicians to identify patients at high risk of stroke and optimize treatment decisions.

2 January 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
YYYuyan Yi
Yuyan Yi
NBNedret Billor
Nedret Billor
AEArne Ekstrom
Arne Ekstrom
Jingyi ZhengJingyi Zheng
Jingyi Zheng
Independent component analysis (ICA) is a widely used blind source separation method for signal pre-processing. The determination of the number of independent components (ICs) is crucial for achieving optimal performance, as an incorrect choice can result in either under-decomposition or over-decomposition. In this study, we propose a robust method to automatically determine the optimal number of ICs, named the column-wise independent component analysis (CW_ICA). CW_ICA divides the mixed signals into two blocks and applies ICA separately to each block. A quantitative measure, derived from the rank-based correlation matrix computed from the ICs of the two blocks, is utilized to determine the optimal number of ICs. The proposed method is validated and compared with the existing determination methods using simulation and scalp EEG data. The results demonstrate that CW_ICA is a reliable and robust approach for determining the optimal number of ICs. It offers computational efficiency and can be seamlessly integrated with different ICA methods.