Shiyi Yin

Dr. Shiyi Yin


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
6 May 2023 in Results in Engineering
Verified
Journal Article
Open access
CLChuanjiang Li
Chuanjiang Li
HDHuiyin Deng
Huiyin Deng
SYShiyi Yin
Shiyi Yin
CWChenming Wang
Chenming Wang
YZYanfei Zhu
Yanfei Zhu

24 December 2022 in Buildings
Verified
Journal Article
Open access
PDF file
SYShiyi Yin
Shiyi Yin
YWYaoping Wu
Yaoping Wu
YSYuzhong Shen
Yuzhong Shen
SRSteve Rowlinson
Steve Rowlinson
Different sets of drivers underlie different safety behaviors, and uncovering such complex patterns helps formulate targeted measures to cultivate safety behaviors. Machine learning can explore such complex patterns among safety behavioral data. This paper aims to develop a classification framework for construction personnel’s safety behaviors with machine learning algorithms, including logistics regression (LR), support vector machine (SVM), random forest (RF), and categorical boosting (CatBoost). The classification framework has three steps, i.e., data collection and preprocessing, modeling and algorithm implementation, and optimal model acquisition. For illustrative purposes, five common safety behaviors of a random sample of Hong Kong-based construction personnel are used to validate the classification framework. To achieve high classification performance, this paper employed a combinative strategy, consisting of feature selection, synthetic minority over-sampling technique (SMOTE), one-hot encoding, standard scaler and classifiers to classify safety behaviors, and multi-objective slime mould algorithm (MOSMA) to optimize parameters in the classifiers. Results suggest that the combinative strategy of CatBoost–MOSMA achieves the highest classification performance with the maximum average scores, including area under the curve of receiver characteristic operator (AUC) ranging from 0.84 to 0.92, accuracy ranging from 0.80 to 0.86, and F1-score ranging from 0.79 to 0.86. From the optimal model, a unique set of important features was identified for each safety behavior, and ten out of the 46 input indicators were found important for all five safety behaviors. Based on the findings, this study advocates using the machine learning strategy of CatBoost–MOSMA in future construction safety behavior research and makes concrete and targeted suggestions to cultivate different construction safety behaviors.

31 July 2024 in Journal of the Franklin Institute
Verified
Journal Article
Closed access
YGYa Gu
Ya Gu
LCLin Chen
Lin Chen
CLChuanjiang Li
Chuanjiang Li
SYShiyi Yin
Shiyi Yin

31 August 2012 in International Journal of Digital Content Technology and its Applications
Verified
Journal Article
Closed access
XLXuejing Li
Xuejing Li
BLBin Li
Bin Li
SYShiyi Yin
Shiyi Yin
YJYulin Jiang
Yulin Jiang
SGSong Gao
Song Gao

1 January 2013 in Journal of Applied Mathematics
Verified
Journal Article
Open access
PDF file
SYShiyi Yin
Shiyi Yin
BLBin Li
Bin Li
The contribution of the flow signal is generally addressed by the weight function in the researches of the electromagnetic flowmeters, and various mathematical technologies were concentrated on the methodologies for solving the value of the weight function. However, it is still difficult to avoid the abstruse mathematical theories and the complex calculation when the solution domain is irregular in shape. This paper treats the problem within the intuitive physical perspective, and the approach, in which the proportion of the current is considered as the substitute for the weight function with the hypothetic current excitation source, is presented. A simple mathematical modeling of the current is built by means of the resistive network without the redundant assumption, and the strict mathematical derivation for the conventional asymmetric flow in the circular flowmeter is made to verify the feasibility and the correctness of the approach. The distributions of the weight function in various situations are obtained with the simulation employed, using the resistive network modeling, and the advantages of the approach are discussed.

9 December 2022 in PLOS ONE
Verified
Journal Article
Open access
PDF file
JWJie Wu
Jie Wu
SYShiyi Yin
Shiyi Yin
CLChuanjiang Li
Chuanjiang Li
QZQiaozhen Zhang
Qiaozhen Zhang
A new virtual synchronous generator (VSG) control strategy was researched and proposed for a VSC-HVDC (High Voltage Direct Current Based on Voltage Source Converter) transmission system. It can be applied to half-bridge or full-half-bridge hybrid topology modular multi-level converter (MMC) to improve the stability and reliability of the system. First, it is proposed that the energy stored in the equivalent capacitor of MMC power module was used to imitate the rotor inertial of synchronous generator. It can buffer transient power fluctuations and synchronize autonomously with the grid. Then the impedance characteristics of the proposed control method have been deduced and analyzed. The results show that the VSG control loop mainly improves the low frequency characteristics of the converter. Secondly, the ability to suppress transient fault current is weak. So, a method, that the given values of inner current loop are calculated by grid impedance matrix, was used. A double closed loop control structure composed by a power outer loop based on VSG control and a current inner loop is obtained. The simulation results show that it can effectively improve the current control capability during the transient process for systems with a 1:2 ratio of converter capacity to grid capacity (The grid short-circuit capacity is 60MW and the MMC is 30 MW). Finally, a hybrid MMC simulation model was built based on PSCAD and the steady-state and transient fault ride-through simulations were performed. The power adjustment time of MMC under the proposed VSG control is about 1s, while the adjustment time under the conventional control strategy is greater than 4s.