Search

Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning, especially graph neural networks (GNNs), as a key building block for combinatorial tasks, either directly as solvers or by enhancing exact solvers. The inductive bias of GNNs effectively encodes combinatorial and relational input due to their invariance to permutations and awareness of input sparsity. This paper presents a conceptual review of recent key advancements in this emerging field, aiming at optimization and machine learning researchers. [ABSTRACT FROM AUTHOR]

With 36 ventures testing autonomous vehicles (AVs) in the State of California, commercial deployment of this disruptive technology is almost around the corner (California Department of Transportation, 2016). Different business models of AVs, including Shared AVs (SAVs) and Private AVs (PAVs), will lead to significantly different changes in regional vehicle inventory and Vehicle Miles Travelled (VMT). Most prior studies have already explored the impact of SAVs on vehicle ownership and VMT generation. Limited understanding has been gained regarding vehicle ownership reduction and unoccupied VMT generation potentials in the era of PAVs. Motivated by such research gap, this study develops models to examine how much vehicle ownership reduction can be achieved once private conventional vehicles are replaced by AVs and the spatial distribution of unoccupied VMT accompanied with the vehicle reduction. The models are implemented using travel survey and synthesized trip profile from Atlanta Metropolitan Area. The results show that more than 18% of the households can reduce vehicles, while maintaining the current travel patterns. This can be translated into a 9.5% reduction in private vehicles in the study region. Meanwhile, 29.8 unoccupied VMT will be induced per day per reduced vehicles. A majority of the unoccupied VMT will be loaded on interstate highways and expressways and the largest percentage inflation in VMT will occur on minor local roads. The results can provide implications for evolving trends in household vehicles uses and the location of dedicated AV lanes in the PAV dominated future. [ABSTRACT FROM AUTHOR]

Background: Total knee arthroplasty (TKA) is one of the most resource-intensive, high-volume surgical procedures. Two drivers of the cost of TKAs are duration of surgery (DOS) and postoperative inpatient length of stay (LOS). The ability to predict TKA DOS and LOS has substantial implications for hospital finances, scheduling, and resource allocation. The goal of this study was to predict DOS and LOS for elective unilateral TKAs using machine learning models (MLMs) based on preoperative factors.Methods: The American College of Surgeons (ACS) National Surgical and Quality Improvement (NSQIP) database was queried for unilateral TKAs from 2014 to 2019. The dataset was split into training, validation, and testing based on year. Models (linear, tree-based, and multilayer perceptron (MLP)) were fitted to the training set in scikit-learn and PyTorch, with hyperparameters tuned on the validation set. The models were trained to minimize the mean squared error (MSE). Models with the best performance on the validation set were evaluated on the testing set according to 1) MSE, 2) buffer accuracy, and 3) classification accuracy, with results compared to a mean regressor.Results: A total of 302,300 patients were included in this study. During validation, the PyTorch MLPs had the best MSEs for DOS (0.918) and LOS (0.715). During testing, the PyTorch MLPs similarly performed best based on MSEs for DOS (0.896) and LOS (0.690). While the scikit-learn MLP yielded the best 30-minute buffer accuracy for DOS (78.8%), the PyTorch MLP provided the best 1-day buffer accuracy for LOS (75.2%). Nearly all the ML models were more accurate than the mean regressors for both DOS and LOS.Conclusion: Conventional and deep learning models performed better than mean regressors for predicting DOS and LOS of unilateral elective TKA patients based on preoperative factors. Future work should include operational factors to improve overall predictions. [ABSTRACT FROM AUTHOR]