arXiv subjects

Liyun Yu

Publications and source records attributed to Liyun Yu.

2 recordsLinked to original sources

arXiv2025

Late Train-Crew Rescheduling: A Tabu-Search-Based Approach Using Restricted DFS

In this paper, we reschedule the duties of train drivers one day before the operation. Because several drivers are absent (for example, because of sick leave), some trains have no driver. Thus, duties need to be rescheduled for the day of operation. We start with a feasible crew schedule for each of the remaining operating drivers, a set of unassigned tasks originally assigned to the absent drivers, and a set of standby drivers with fixed start time, end time, start depot, and end depot. Our aim is to generate a crew schedule with as few canceled tasks as possible. We present a tabu-search-based approach with restricted graph search for crew rescheduling. We also adopt a column-generation approach as a benchmark to reflect the same restrictions and objective function as our tabu-search-based approach. We use it to compare the quality of the results, computational time, and other performance indicators. Our tabu-search-based approach needs less computational time than the column-generation approach to compute an acceptable result. We further test the performance of our approach under different settings. One of the datasets used in the experiments originated from a regional passenger-train system around Stockholm, Sweden, and was provided by M\"alart{\aa}g. The other dataset is generated from the open-source crew scheduling data from the ROMSOC project.

math.OC↗

arXiv2020

ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification

Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the sample size is small. To ensure good generalizability of deep networks under small sample sizes, learning discriminative features is crucial. To this end, several loss functions have been proposed to encourage large intra-class compactness and inter-class separability. In this paper, we propose to enhance the discriminative power of features from a new perspective by introducing a novel neural network termed Relation-and-Margin learning Network (ReMarNet). Our method assembles two networks of different backbones so as to learn the features that can perform excellently in both of the aforementioned two classification mechanisms. Specifically, a relation network is used to learn the features that can support classification based on the similarity between a sample and a class prototype; at the meantime, a fully connected network with the cross entropy loss is used for classification via the decision boundary. Experiments on four image datasets demonstrate that our approach is effective in learning discriminative features from a small set of labeled samples and achieves competitive performance against state-of-the-art methods. Codes are available at https://github.com/liyunyu08/ReMarNet.

cs.CV↗