Deep Reinforcement Learning Based Resource Allocation for D2D Communications Underlay Cellular Networks.

In this paper, a resource allocation (RA) scheme based on deep reinforcement learning (DRL) is designed for device-to-device (D2D) communications underlay cellular networks. The goal of RA is to determine the transmission power and spectrum channel of D2D links to maximize the sum of the average effective throughput of all cellular and D2D links in a cell accumulated over multiple time steps, where a cellular channel can be allocated to multiple D2D links. Allowing a cellular channel to be shared by multiple D2D links and considering performance over multiple time steps require a high level of system overhead and computational complexity so that optimal RA is practically infeasible in this scenario, especially when a large number of D2D links are involved. To mitigate the complexity, we propose a sub-optimal RA scheme based on a multi-agent DRL, which operates with shared information in participating devices, such as locations and allocated resources. Each agent corresponds to each D2D link and multiple agents perform learning in a staggered and cyclic manner. The proposed DRL-based RA scheme allocates resources to D2D devices promptly according to dynamically varying network set-ups, including device locations. The proposed sub-optimal RA scheme outperforms other schemes, where the performance gain becomes significant when the densities of devices in a cell are high.

Quality of Life in Food Allergy: Validation of the Korean Version of the Food Allergy Quality of Life Questionnaire Parent Form (K-FAQLQ-PF) and Risk Factor Analysis.

PURPOSE: This study aimed to evaluate the reliability and validity of the Korean version of the Food Allergy Quality of Life Questionnaire-Parent Form (K-FAQLQ-PF) and to identify clinical characteristics related to low quality of life (QoL) in Korean children with food allergy (FA). METHODS: Parents of 0-12-year-old patients with FA were enrolled. The English version of FAQLQ-PF was translated into Korean. Construct validation was confirmed by the Food Allergy Independent Measure-Parent Form (FAIM-PF) and the Child Health Questionnaire Parent Form 28 (CHQ-PF28). Logistic regression analyses were used to evaluate associations between potential risk factors and QoL outcomes. RESULTS: A total of 182 patients with a median age of 5.0 years were enrolled in the study. Cronbach's α coefficient values indicating internal consistency were higher than 0.8. Intraclass correlation coefficient values for test-retest reliability were good for all age groups (r > 0.6). Total K-FAQLQ-PF scores were positively correlated with the FAIM-PF (r = 0.56, P < 0.05) and were negatively correlated with the parental impact-emotional domain in the CHQ-PF28 (r = -0.44, P < 0.05). In multivariable logistic regression analysis, low QoL was significantly associated with female sex (adjusted odds ratio [aOR], 2.07; 95% confidence interval [CI], 1.03-4.18), age ≥ 5 years (aOR, 2.84; 95% CI, 1.31-6.16), FA diagnosis before the age of 3 years (aOR, 3.96; 95% CI, 1.13-13.93), the presence of atopic dermatitis (aOR, 2.21; 95% CI, 1.07-4.57), and residence in non-metropolitan areas (aOR, 3.44; 95% CI, 1.73-6.85). CONCLUSIONS: According to parental perceptions, the K-FAQLQ-PF is a valid and reliable tool to assess psychosocial QoL in Korean children with FAs. Age, sex, residential area, and comorbid AD can affect the QoL of pediatric patients with FA.