Lina Yu

Prof. Dr. Lina Yu


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
1 May 2018 in Computers & Industrial Engineering
Verified
Journal Article
Closed access
LYLina Yu
Lina Yu
CZCanrong Zhang
Canrong Zhang
HYHuasheng Yang
Huasheng Yang
LMLixin Miao
Lixin Miao

7 March 2018 in IISE Transactions
Verified
Journal Article
Closed access
LYLina Yu
Lina Yu
HYHuasheng Yang
Huasheng Yang
LMLixin Miao
Lixin Miao
CZCanrong Zhang
Canrong Zhang
Large-scale disasters and catastrophic events typically result in a significant shortage of critical resources, posing a great challenge to allocating limited resources among different affected areas to improve the quality of emergency logistics operations. This article pays attention to the performance of resource allocation, which includes three metrics: efficiency, effectiveness, and equity, respectively corresponding to economic cost, service quality, and fairness. In particular, the effectiveness metric considers human suffering by depicting it as deprivation cost, an economic valuation measurement that has been recently proposed and the equity metric concerns about the service equality at the end of planning horizon. A nonlinear integer model is first proposed and then an equivalent dynamic programming model is developed to avoid the nonlinear terms created by the introduction of the deprivation cost. The dynamic programming method can solve small-scale problems to optimality but meets difficulty when solving medium- and large-scale problems, due to the curse of dimensionality. Therefore, an approximate dynamic programming algorithm, called the rollout algorithm, is proposed to overcome this computational difficulty. The computational complexity of the proposed algorithm is theoretically analyzed. Furthermore, a modified version of the rollout algorithm is presented, with its computational complexity analyzed. Extensive numerical experiments are conducted to test the performance of the proposed algorithms, and the experimental results demonstrate that the initially proposed rollout algorithm yields optimal or near-optimal solutions within a reasonable amount of time. In addition, the impacts of some important parameters are investigated and managerial insights are drawn.

20 January 2025 in Mechatronics and Intelligent Transportation Systems
Verified
Journal Article
Open access
PDF file
JGJing Gao
Jing Gao
YZYin Zhang
Yin Zhang
ZWZhuang Wu
Zhuang Wu
LYLina Yu
Lina Yu
The effective allocation of emergency supplies is crucial in the aftermath of flood disasters, as it directly impacts response times and mitigates casualties and property losses. Traditional methods of material distribution predominantly rely on ground-based transportation, which often proves inefficient and inflexible under the dynamic conditions of a disaster. This study explores the potential of unmanned aerial vehicles (UAVs) as a transformative solution to the challenges associated with emergency material dispatch. Factors influencing UAV scheduling, including environmental constraints, payload capacity, and flight dynamics, are analyzed in depth. Optimization measures for improving UAV collaborative operations are proposed, with a focus on enhancing the efficiency and adaptability of disaster response systems. The integration of reinforcement learning (RL) is examined as a theoretical framework for optimizing UAV collaborative scheduling, facilitating autonomous decision-making in real-time scenarios. An empirical analysis is presented based on the “7-20” rainstorm and flooding disaster in Zhengzhou, illustrating the practical application of collaborative UAVs in disaster relief. The results demonstrate the significant optimization potential of UAV technology, with a notable reduction in response times and improved logistical coordination. Furthermore, the role of UAVs in future disaster relief operations is discussed, with emphasis on the integration of blockchain and smart dispatch systems to enable decentralized, autonomous coordination. These advancements are expected to enhance the overall efficiency of emergency material distribution and better address the complex challenges posed by post-disaster environments. The findings underscore the potential for UAV systems to revolutionize disaster management and contribute to more resilient, responsive strategies in future flood events.

10 December 2024 in Journal of Engineering Management and Systems Engineering
Verified
Journal Article
Open access
PDF file
HLHaiyong Liu
Haiyong Liu
ZWZhuang Wu
Zhuang Wu
LYLina Yu
Lina Yu
The strategic location of emergency supply depots is critical for enhancing pre-disaster preparedness and post-disaster relief efforts. Given the inherent uncertainties and risks associated with natural and man-made disasters, ensuring the swift and effective delivery of relief materials to affected areas is pivotal for minimizing disaster impacts and safeguarding lives and property. This review synthesizes the current body of research on the siting of emergency stockpiles, providing a comprehensive analysis of the factors influencing site selection. Key factors such as the geographic scope of disaster response, hydrographic conditions, transportation infrastructure, and accessibility to affected populations are examined. Various siting models are evaluated to optimize resource allocation, minimize logistics costs, and improve supply chain responsiveness during emergencies. This review also identifies key challenges within the existing literature, including limitations in model algorithms, disaster stage considerations, optimization criteria, and the degree of stakeholder involvement in decision-making. Notably, while previous research has often focused on isolated factors, this study emphasizes the need for an integrated approach that accounts for dynamic, diversified, intelligent, and human-centered considerations. Dynamic models are essential to adapt to the unpredictable nature of disasters, while diversified approaches are necessary to address the varying needs of different disaster types and affected populations. Intelligent decision-making tools, incorporating data analytics and real-time information, can enhance the efficiency and accuracy of site selection processes. Human-centric models, focusing on the actual needs of disaster-affected communities, are critical for ensuring the effectiveness of relief operations. The review concludes by outlining future research directions, emphasizing the importance of developing adaptable, sustainable, and context-specific siting models. Future investigations should focus on the practical application of emerging technologies, such as big data analytics, artificial intelligence, and remote sensing, to refine siting models and improve their responsiveness in a rapidly changing global landscape. These advancements are expected to contribute to more efficient and cost-effective emergency supply systems, better equipped to address the evolving challenges of global disaster risks.

23 July 2025 in Neural Networks
Verified
Journal Article
Closed access
YLYifan Li
Yifan Li
XDXu Dong
Xu Dong
ZWZhuang Wu
Zhuang Wu
JGJing Gao
Jing Gao
TZTianqi Zhang
Tianqi Zhang
LYLina Yu
Lina Yu

30 September 2024 in Acadlore Transactions on AI and Machine Learning
Verified
Journal Article
Open access
PDF file
ZYZeyi Yang
Zeyi Yang
YZYi Zhang
Yi Zhang
LYLina Yu
Lina Yu
Accurately predicting whether bank users will opt for time deposit products is critical for optimizing marketing strategies and enhancing user engagement, ultimately improving a bank’s profitability. Traditional predictive models, such as linear regression and Logistic Regression (LR), are often limited in their ability to capture the complex, time-dependent patterns in user behavior. In this study, a hybrid approach that combines Long Short-Term Memory (LSTM) neural networks and a stacked ensemble learning framework is proposed to address these limitations. Initially, LSTM models were employed to extract temporal features from two distinct bank marketing datasets, thereby capturing the sequential nature of user interactions. These extracted features were subsequently input into several base classifiers, including Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbour (KNN), to conduct initial classifications. The outputs of these classifiers were then integrated using a LR model for final decision-making through a stacking ensemble method. The experimental evaluation demonstrates that the proposed LSTM-stacked model outperforms traditional models in predicting user time deposits on both datasets, providing robust predictive performance. The results suggest that leveraging temporal feature extraction with LSTM and combining it with ensemble techniques yields superior prediction accuracy, thereby offering a more sophisticated solution for banks aiming to enhance their marketing efficiency.