Lei Zhang

Lei Zhang

Auto-generated profile, based on publicly available information

Lei Zhang

Northern Illinois University, DeKalb, IL, USA

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
15 October 2019 in BMC Psychiatry
Verified
Journal Article
Open access
PDF file
JWJingying Wang
Jingying Wang
LZLei Zhang
Lei Zhang
TLTianli Liu
Tianli Liu
WPWei Pan
Wei Pan
BHBin Hu
Bin Hu
Tingshao ZhuTingshao Zhu
Tingshao Zhu
Background: Abnormalities in vocal expression during a depressed episode have frequently been reported in people with depression, but less is known about if these abnormalities only exist in special situations. In addition, the impacts of irrelevant demographic variables on voice were uncontrolled in previous studies. Therefore, this study compares the vocal differences between depressed and healthy people under various situations with irrelevant variables being regarded as covariates. Methods: To examine whether the vocal abnormalities in people with depression only exist in special situations, this study compared the vocal differences between healthy people and patients with unipolar depression in 12 situations (speech scenarios). Positive, negative and neutral voice expressions between depressed and healthy people were compared in four tasks. Multiple analysis of covariance (MANCOVA) was used for evaluating the main effects of variable group (depressed vs. healthy) on acoustic features. The significances of acoustic features were evaluated by both statistical significance and magnitude of effect size. Results: The results of multivariate analysis of covariance showed that significant differences between the two groups were observed in all 12 speech scenarios. Although significant acoustic features were not the same in different scenarios, we found that three acoustic features (loudness, MFCC5 and MFCC7) were consistently different between people with and without depression with large effect magnitude. Conclusions: Vocal differences between depressed and healthy people exist in 12 scenarios. Acoustic features including loudness, MFCC5 and MFCC7 have potentials to be indicators for identifying depression via voice analysis. These findings support that depressed people’s voices include both situation-specific and cross-situational patterns of acoustic features.

8 December 2023 in ACM Computing Surveys
Verified
Journal Article
Open access
Zhiqian ChenZhiqian Chen
Zhiqian Chen
FCFanglan Chen
Fanglan Chen
LZLei Zhang
Lei Zhang
TJTaoran Ji
Taoran Ji
KFKaiqun Fu
Kaiqun Fu
CLChang-Tien Lu
Chang-Tien Lu
Deep learning’s performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theories, direct comparisons are impossible. Prior research has primarily concentrated on categorizing existing models, with little attention paid to their intrinsic connections. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory. The framework incorporates a strong integration between spatial- and spectral-based GNNs while tightly associating approaches that exist within each respective domain.

20 March 2020 in JMIR mHealth and uHealth
Verified
Journal Article
Open access
JWJingying Wang
Jingying Wang
DGDawei Gong
Dawei Gong
HLHuichun Luo
Huichun Luo
WZWenbin Zhang
Wenbin Zhang
LZLei Zhang
Lei Zhang
SWShouyan Wang
Shouyan Wang
Background: Gait impairments including shuffling gait and hesitation are common in people with Parkinson’s disease (PD), and have been linked to increased fall risk and freezing of gait. Nowadays the gait metrics mostly focus on the spatiotemporal characteristics of gait, but less is known of the angular characteristics of the gait, which may provide helpful information pertaining to the functional status and effects of the treatment in PD. Objective: This study aimed to quantify the angles of steps during walking, and explore if this novel step angle metric is associated with the severity of PD and the effects of the treatment including the acute levodopa challenge test (ALCT) and deep brain stimulation (DBS). Methods: A total of 18 participants with PD completed the walking test before and after the ALCT, and 25 participants with PD completed the test with the DBS on and off. The walking test was implemented under two conditions: walking normally at a preferred speed (single task) and walking while performing a cognitive serial subtraction task (dual task). A total of 17 age-matched participants without PD also completed this walking test. The angular velocity was measured using wearable sensors on each ankle, and three gait angular metrics were obtained, that is mean step angle, initial step angle, and last step angle. The conventional gait metrics (ie, step time and step number) were also calculated. Results: The results showed that compared to the control, the following three step angle metrics were significantly smaller in those with PD: mean step angle (F1,48=69.75, P<.001, partial eta-square=0.59), initial step angle (F1,48=15.56, P<.001, partial eta-square=0.25), and last step angle (F1,48=61.99, P<.001, partial eta-square=0.56). Within the PD cohort, both the ALCT and DBS induced greater mean step angles (ACLT: F1,38=5.77, P=.02, partial eta-square=0.13; DBS: F1,52=8.53, P=.005, partial eta-square=0.14) and last step angles (ACLT: F1,38=10, P=.003, partial eta-square=0.21; DBS: F1,52=4.96, P=.003, partial eta-square=0.09), but no significant changes were observed in step time and number after the treatments. Additionally, these step angles were correlated with the Unified Parkinson's Disease Rating Scale, Part III score: mean step angle (single task: r=–0.60, P<.001; dual task: r=–0.52, P<.001), initial step angle (single task: r=–0.35, P=.006; dual task: r=–0.35, P=.01), and last step angle (single task: r=–0.43, P=.001; dual task: r=–0.41, P=.002). Conclusions: This pilot study demonstrated that the gait angular characteristics, as quantified by the step angles, were sensitive to the disease severity of PD and, more importantly, can capture the effects of treatments on the gait, while the traditional metrics cannot. This indicates that these metrics may serve as novel markers to help the assessment of gait in those with PD as well as the rehabilitation of this vulnerable cohort.

21 July 2021 in arXiv
Verified
Preprint
Open access
PDF file
Zhiqian ChenZhiqian Chen
Zhiqian Chen
FCFanglan Chen
Fanglan Chen
LZLei Zhang
Lei Zhang
TJTaoran Ji
Taoran Ji
KFKaiqun Fu
Kaiqun Fu
CLChang-Tien Lu
Chang-Tien Lu
Deep learning's success has been widely recognized in a variety of machine learning tasks, including image classification, audio recognition, and natural language processing. As an extension of deep learning beyond these domains, graph neural networks (GNNs) are designed to handle the non-Euclidean graph-structure which is intractable to previous deep learning techniques. Existing GNNs are presented using various techniques, making direct comparison and cross-reference more complex. Although existing studies categorize GNNs into spatial-based and spectral-based techniques, there hasn't been a thorough examination of their relationship. To close this gap, this study presents a single framework that systematically incorporates most GNNs. We organize existing GNNs into spatial and spectral domains, as well as expose the connections within each domain. A review of spectral graph theory and approximation theory builds a strong relationship across the spatial and spectral domains in further investigation.

3 August 2025
Verified
Conference Paper
Open access
LZLei Zhang
Lei Zhang
Zhiqian ChenZhiqian Chen
Zhiqian Chen
CLChang-Tien Lu
Chang-Tien Lu
LZLiang Zhao
Liang Zhao