PURPOSE The purpose of this study was to clarify differences between highly myopic and non-myopic primary open-angle glaucoma (POAG) patients, including normal-tension glaucoma patients. PATIENTS AND METHODS A total of 269 POAG patients were divided into two groups: patients with ≥26.5 mm of axial length (highly myopic group) and patients with <24.0 mm of axial length (non-myopic group). RE...

In this paper, we propose a framework for using reinforcement learning (RL) algorithms to learn good policies for personalized ad recommendation (PAR) systems. The RL algorithms take into account the long-term effect of an action, and thus, could be more suitable than myopic techniques like supervised learning and contextual bandit, for modern PAR systems in which the number of returning visito...

We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain strategic position. Conventional policy learning approaches, such as those based on Markov decision processes, generally fail at learning cohesive long-term behavi...

This paper studies dynamic inventory and pricing decisions for a set of substitutable products over a finite planning horizon. We present a general stochastic, price-dependent demand model that unifies many commonly used demand models in the literature. Unsatisfied demands are backlogged. There are linear purchasing, inventory-holding, and backordering costs. The objective is to maximize the to...

We consider two active binary-classification problems with atypical objectives. In the first, active search, our goal is to actively uncover as many members of a given class as possible. In the second, active surveying, our goal is to actively query points to ultimately predict the proportion of a given class. Numerous real-world problems can be framed in these terms, and in either case typical...

BACKGROUND/PURPOSE To evaluate and compare the diagnostic discriminative ability for detecting glaucoma in highly myopic eyes from a normative database of macular ganglion cell complex (mGCC) thickness based on nonhighly myopic and highly myopic normal eyes. METHODS Forty-nine eyes of 49 participants with high myopia (axial length ≥ 26.0 mm) were enrolled. Spectral-domain optical coherence to...

This paper considers a single-hop wireless sensor network where a fusion center collects data from M energy harvesting wireless sensors. The harvested energy is stored losslessly in an infinite-capacity battery at each sensor. In each time slot, the fusion center schedules K sensors for data transmission over K orthogonal channels. The fusion center does not have direct knowledge on the battery...

In managing an inventory network, two approaches to the pooling of stock have been proposed. Reactive transshipments respond to shortages at a location by moving inventory from elsewhere within the network, while proactive stock redistribution seeks to minimize the chance of future stockouts. This paper is the first to propose an enhanced reactive approach in which individual transshipments are...

Expected inventory order crossovers occur if at the moment of ordering it is expected that orders will not arrive in the sequence they are ordered. Recent research has shown that (a) expected inventory order crossovers will be encountered more frequently in future, and that (b) use of a myopic order-up-to policy based on a stochastic dynamic programming approach leads to improved performance co...

As recently pointed out by the Institute of Medicine, the existing pandemic mitigation models lack the dynamic decision support capability. We develop a large-scale simulation-driven optimization model for generating dynamic predictive distribution of vaccines and antivirals over a network of regional pandemic outbreaks. The model incorporates measures of morbidity, mortality, and social distan...