Yi Liu

Dr. Yi Liu


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
20 January 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
RZRen Zhang
Ren Zhang
YLYi Liu
Yi Liu
ZZZhiwei Zhang
Zhiwei Zhang
RLRui Luo
Rui Luo
BLBin Lv
Bin Lv
Background: Postpartum depression (PPD) is a prevalent mental health issue with significant impacts on mothers and families. Exploring reliable predictors is crucial for the early and accurate prediction of PPD, which remains challenging. Objective: This study aimed to comprehensively collect variables from multiple aspects, develop and validate machine learning models to achieve precise prediction of PPD, and interpret the model to reveal clinical implications. Methods: This study recruited pregnant women who delivered at the West China Second University Hospital, Sichuan University. Various variables were collected from electronic medical record data and screened using least absolute shrinkage and selection operator penalty regression. Participants were divided into training (1358/2055, 66.1%) and validation (697/2055, 33.9%) sets by random sampling. Machine learning–based predictive models were developed in the training cohort. Models were validated in the validation cohort with receiver operating curve and decision curve analysis. Multiple model interpretation methods were implemented to explain the optimal model. Results: We recruited 2055 participants in this study. The extreme gradient boosting model was the optimal predictive model with the area under the receiver operating curve of 0.849. Shapley Additive Explanation indicated that the most influential predictors of PPD were antepartum depression, lower fetal weight, elevated thyroid-stimulating hormone, declined thyroid peroxidase antibodies, elevated serum ferritin, and older age. Conclusions: This study developed and validated a machine learning–based predictive model for PPD. Several significant risk factors and how they impact the prediction of PPD were revealed. These findings provide new insights into the early screening of individuals with high risk for PPD, emphasizing the need for comprehensive screening approaches that include both physiological and psychological factors.

3 March 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Xueping XuXueping Xu
Xueping Xu
YLYi Liu
Yi Liu
CHChunbo Han
Chunbo Han
XSXin Sun
Xin Sun
The uniformity of the coils is often compromised by the coupling between ferromagnetic materials and coils. The spindle-shaped magnetic shielding cylinder (sMSC) has additional benefits over the magnetic shielding cylinder (MSC). A single-layer cylindrical self-shielding coil designed by the improved target field method (TFM) that is available inside sMSC is proposed. The method dynamically regulates the internal uniformity and external self-shielding performance by assigning different weights to the internal and external field points. To reduce the dependence of the traditional TFM design on relevant factors, the hunter-prey optimization (HPO) is applied to optimize it. The modelling and experimental findings reveal that the maximum homogeneity deviations of the self-shielding coil are 0.24% and 0.28%, respectively. The self-shielded coil takes up less space in comparison to the normal non-moment Helmholtz coils. This method ensures the uniform performance of the internal magnetic field (MF) while rapidly attenuating the external MF.

15 July 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Xueping XuXueping Xu
Xueping Xu
YLYi Liu
Yi Liu
CHChunbo Han
Chunbo Han
XSXin Sun
Xin Sun
The coupling effect between the active magnetic compensation coil and the ferromagnetic material in the spindle-shaped magnetic shielding cylinder (sMSC) normally leads to distortion of the target magnetic field. The existing methods for designing coils within ferromagnetic boundaries are mainly for regular magnetic shielding cylinder (MSC) and cubic magnetic shielding room (MSR); there is currently no analytical method available for designing coils within ferromagnetic boundaries for sMSC. In this article, a new method based on conformal mapping and target field method (CM-TFM) for designing high uniformity cylindrical coils within a closed sMSC is introduced. It addresses the issue of degradation in magnetic field uniformity due to the coupling of the axial uniform field coil with the magnetic shielding ferromagnetic material inside the sMSC. The simulations indicate that the maximum magnetic field deviation in the target area is reduced from 4.04% to 1.38% in the CM-TFM compared to the coil designed using the conventional target field method (TFM) without considering the coupling effect of the magnetically shielded ferromagnetic material and the coil. The overall percentage of the target area with the magnetic field deviation less than 1% is 92.59% in CM-TFM coils, compared to only 40.74% in TFM coils. The experimental results confirm the effectiveness and practicality of this design method in compensating for the residual magnetic field of sMSC. The proposed approach is essential for the implementation of near-zero magnetic field environments.

5 November 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Xueping XuXueping Xu
Xueping Xu
YLYi Liu
Yi Liu
XSXin Sun
Xin Sun
WZweiyong zhou
weiyong zhou
The target field is often distorted by coupling effects of the active magnetic compensation coil and magnetic shielding material in the magnetic shielding room (MSR). The permeability and thickness of the magnetic shielding layer are assumed infinite in existing image methods (IM) which will generate large errors considering actual ferromagnetic boundaries. A novel method for designing high-uniformity biplane coil within MSR is presented. First, the effects of all image points are considered. A variable permeability and thickness image method (PT-IM) is proposed and an analytical model of the coil inside the ferromagnetic boundary is established. Secondly, a linear decreasing weight particle swarm optimization (LDW-PSO) algorithm is applied to optimize the coil parameters. The simulation results indicate that the proposed PT-IM and target field method (PT-IM &TFM) lowers the maximum field deviations of the Bx , By , and Bz uniform field coils by 30.82%, 37.86%, and 35% in the target region, respectively, compared to IM&TFM. The experimental results indicate that the actual maximum magnetic field deviation decreases by 40.01% and 32.48% for the Bx and dBx / dz coils respectively. The results verify the effectiveness and practicality of this method in compensating for the residual magnetic field of MSR.

19 March 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
Xueping XuXueping Xu
Xueping Xu
CHChunbo Han
Chunbo Han
YLYi Liu
Yi Liu
Near-zero magnetic environment serves as a fundamental research condition for multiple scientific fields. To obtain a large-scale and high-performance near-zero magnetic environment, this paper presents a coil design method based on the boundary element method (BEM) for compensating the non-uniform static magnetic field existing in the magnetic shielding room (MSR). To achieve precise compensation of non-uniform magnetic field, BEM-based image method is introduced to eliminate the deviation by coupling between the magnetic field generated by the coil and the magnetic shielding material, and the gray wolf optimization (GWO) algorithm is employed for the optimal design of coils. The experimental results show that the coils designed by the method of this paper can effectively compensate the non-uniform magnetic field distribution within a 100 mm × 100 mm × 100 mm central area of the MSR. The range of the residual magnetic field has been reduced by 87.8%, thereby establishing an environment below 1 nT in the central area of the MSR. The proposed method will lay the foundation for the research of high-performance non-uniform magnetic compensation coils within the MSR.

7 November 2024 in International Journal of Sociologies and Anthropologies Science Reviews
Verified
Journal Article
Open access
PDF file
YLYi Liu
Yi Liu
LOLerlak Othakanon
Lerlak Othakanon
DSDanucha Saleewong
Danucha Saleewong
Background and Aim: The emotional intelligence of preschoolers has a significant impact on their social interactions, scholastic achievement, and general well-being, making it vital for their overall development. Developing emotional intelligence in young children can be challenging, especially in traditional school environments. The objective of this study was to (1) develop a psychological course based on social stories and the 4MAT method to enhance preschool students’ emotional intelligence, (2) compare preschool students’ emotional intelligence before and after implementing through psychological course based on social stories and 4MAT method, and (3) study the learning progression of preschool students’ emotional intelligence who learned through psychological course based on social stories and 4MAT method each time. Materials and Methods: This study used a cluster sampling method with 30 kindergarten students of Hancheng Jiaoda School, People’s Republic of China. The experimental design adopted in this study was a group pretest-posttest design and the equivalent time-sample design. The research instruments were 1) 8 lesson plans, 2) a Test for assessing preschool students’ emotional intelligence (Knowledge), and 3) an Observation form for assessing preschool students’ emotional intelligence (Behavior). The data were analyzed by using mean, standard deviation the t-test for a dependent sample, and one-way Repeated Measures ANOVA. Results: The results of the study were as follows: 1) The psychological course to enhance preschool students’ emotional intelligence consisted of the principle, objective, content, instructional strategy, materials, and evaluation. 2) After implementing social stories and 4MAT learning, the student’s emotional intelligence was higher than before (t=8.317 p = .001). 3) The students’ emotional intelligence increased in the four tests after the psychological course with the F-test statistic (F=6255.071, p=.001), which was less than .05, indicating that there were statistically significant differences in the mean values of the four times emotional intelligence tests. Conclusion: The innovation of this research was: 1) The course components consisted of six components. 2) The instructional strategy to enhance preschool students’ emotional intelligence had 7 steps: Step 1: personalization, step 2: engagement, step 3: application, step 4: creativity, step 5: visual Support, step 6: progress monitoring, and step 7: Inclusivity.