Yuan Xu

This study examines change in operational efficiency and productivity across a balanced panel of 15 container ports for the years 2019 and 2020. Berth length, gantry cranes, and other cranes are inputs; high container throughput is desirable, and extended anchorage waiting time is undesirable. Waiting time is calculated as the unweighted mean of weekly port estimates published by the Asian Development Bank. A pooled convex variable-returns-to-scale directional distance function with weak disposability provides a common reference technology, and the VRS global Malmquist–Luenberger (GML) index compares the two years. The mean transformed efficiency score was 0.855 across 30 port-year observations, declining from 0.878 in 2019 to 0.833 in 2020. The arithmetic mean GML score was 0.951: one port improved, ten declined, and four remained unchanged. A throughput-only model and leave-one-port-out re-estimation show that waiting time treatment and influential reference ports affect individual comparisons. In particular, the omission of Shanghai or Tanjung Pelepas substantially changed some rankings and scores.

Although multimodal transport has been widely developed, the multimodal transport operation system is still not as mature as other single modes of transport. Currently, the optimization of multimodal transport solutions and the allocation of capacity are planned as two separate parts, and the research on customer classification of multimodal transport is insufficient. The current bottleneck in multimodal transportation systems is optimizing multimodal customer classification and transportation solutions. Additionally, such an optimization can significantly improve the system’s overall revenue. Based on the customer classification theory of revenue management, we classified and managed multimodal transport customers and allocated and priced the transportation capacity according to the demand characteristics and price sensitivities of different customers. Furthermore, we considered the impact of transportation scheme planning on the profit of multimodal transport. Accordingly, we developed a joint optimization model for multimodal transport schemes, capacity allocation, and pricing by considering the customer classification. We solved the model using a hybrid particle swarm algorithm and validated it using arithmetic examples. The results indicate that a customer classification strategy can significantly improve the profit of multimodal transport operators when customer demand is unstable, and the total profit of the transportation system is increased by 7%. Moreover, these results suggest combining transportation solution optimization with customer classification can lead to more profitable multimodal revenue management solutions. Thus, our results can guide multimodal operators for systematically dealing with the customer classification problem and optimizing transportation schemes while improving their profits. Moreover, this study offers a reference for decision-making in multimodal operation management.

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses dataset and predict nurse turnover using machine learning algorithms. Four machine learning algorithms, namely logistic regression, random forests, decision tree, and extreme gradient boosting, were applied to the SMOTE-enhanced dataset. The data were split into 80% training and 20% validation sets. Eighteen carefully selected variables from the database served as predictive features, and the machine learning model identified age, working hours, electric health record/electronic medical record, individual income, and job type as important features concerning nurse turnover. The study includes a performance comparison based on accuracy, precision, recall (sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests exhibit the most robust predictive power in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). Extreme gradient boosting, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, electric health record/electronic medical record usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable machine learning algorithms for nurse turnover prediction.

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses (NSSRN) dataset and predict nurse turnover using machine learning (ML) algorithms. Four ML algorithms, namely logistic regression (LR), random forests (RF), decision tree (DT), and extreme gradient boosting (XGBoost), are applied to the SMOTE-enhanced dataset. The data is randomly split into an 80% training set and a 20% validation set. Eighteen carefully selected variables from the NSSRN database serve as predictive features, and the machine learning model identifies feature importance concerning nurse turnover. The study includes a performance comparison based on metrics such as Accuracy, Precision, Recall (Sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests (SMOTE_RT) exhibit the most robust predictive power, both in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). XGBoost, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, EHR/EMR usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable ML algorithms for nurse turnover prediction.

This paper presents a multi-product multi-period stochastic program for an integrated blood supply chain that considers red blood cells and platelets while accounting for multi-product interactions, demand uncertainty, blood age information, blood type substitution, and three types of patients. The aim is to minimize the total cost incurred during the collection, production, inventory, and distribution echelons under centralized control. The supply chains for red blood cells and platelets intertwine at the collection and production echelons as collected whole blood can be separated into red blood cells and platelets at the same time. By adapting to a real-world blood supply chain with one blood center, three collection facilities, and five hospitals, we found a cost advantage of the multi-product model over an uncoordinated model where the red blood cell and platelet supply chains are considered separately. Further sensitivity analyses indicated that the cost savings of the multi-product model mainly come from variations in the number of whole blood donors. These findings suggest that healthcare managers are able to see tremendous improvement in cost efficiency by considering red blood cell and platelet supply chains as a whole, especially with more whole blood donations and a higher percentage of whole blood derived platelets pooled for transfusion.

Measuring the U.S.’s COVID-19 response performance is an extremely important challenge for health care policymakers. This study integrates Data Envelopment Analysis (DEA) with four different machine learning (ML) techniques to assess the efficiency and evaluate the U.S.’s COVID-19 response performance. First, DEA is applied to measure the efficiency of fifty U.S. states considering four inputs: number of tested, public funding, number of health care employees, number of hospital beds. Then, number of recovered from COVID-19 as a desirable output and number of confirmed COVID-19 cases as a undesirable output are considered. In the second stage, Classification and Regression Tree (CART), Boosted Tree (BT), Random Forest (RF), and Logistic Regression (LR) were applied to predict the COVID-19 response performance based on fifteen environmental factors, which were classified into social distancing, health policy, and socioeconomic measures. The results showed that 23 states were efficient with an average efficiency score of 0.97. Furthermore, BT and RF models produced the best prediction results and CART performed better than LR. Lastly, urban, physical inactivity, number of tested per population, population density, and total hospital beds per population were the most influential factors on efficiency.

Partial discharge diagnosis methods, such as ultrasonic method, ultra high frequency method and decomposition product method, have their respective advantages and disadvantages in the application. Therefore, in order to combine the characteristics of various detection methods, it is recommended to carry out joint detection of various methods in the field. In the end, a case of GIS PD is introduced.