RESUMEN
The Covering Location Problem (CLP) is widely used for the efficient facility distribution. However, existing algorithms for this problem suffer from long computation times or suboptimal solutions. To address this, we propose two methods based on graph convolutional networks (GCN) to solve two types of covering location problems: the location set covering problem and the maximum covering location problem. The first method, GCN-Greedy, is a supervised algorithm that synergized with the Greedy algorithm as decoder. It designs a specialized loss function to train the model, tailored to the characteristics of the two covering location problems. The second method, reinforcement learning based on GCN with auto-regressive decoder (GCN-AR-RL), represents a reinforcement learning framework that integrates a GCN encoder with an auto-regressive decoder. The experimental results of these models demonstrate the remarkable accuracy and performance advantages. Additionally, we apply these two models to the realistic dataset and achieve good performance.
RESUMEN
Most organisms on Earth possess circadian rhythms in their physiology and behaviors that allow them to resonate with the cycling environment over a 24-h period. However, in human society, a substantial quantity of jobs requires non-24-h working and rest or shift schedules, which causes more or less misalignment in circadian rhythms and disorders as a consequence. In this work, we conducted a sleep deprivation (SD) and non-24-h working and rest schedule (8 h on and 4 h off) experiment over 10 d in total and measured the changes in a series of physiologic and cognitive parameters. The results show that although the subjects could sleep during the schedule, their sleepiness increased significantly. Actigraphy data suggest that a 12-h schedule might result in chronic SD. Along with the increased sleepiness revealed by the Karolinska Sleepiness Scale questionnaire, the neurobehavioral psychomotor vigilance test data reveal that, compared with the control period, the reaction time of the subjects was significantly delayed. The saliva insulin levels were significantly changed in the morning in SD and non-24-h cycles. Salivary biochemical parameters were also altered, including aspartate aminotransferase and K+. 16S rRNA-based analysis of the salivary microbiota showed differentially changed patterns in bacteria composition and concentration. Together, these data demonstrate that an abnormal working and rest schedule might produce comprehensive interference with circadian rhythms, metabolism, and cognition.-Ma, H., Li, Y., Liang, H., Chen, S., Pan, S., Chang, L., Li, S., Zhang, Y., Liu, X., Xu, Y., Shao, Y., Yang, Y., Guo, J. Sleep deprivation and a non-24-h working schedule lead to extensive alterations in physiology and behavior.