No abstract

Optimal transport is a framework that facilitates the most efficient allocation of a limited amount of resources. However, the most efficient allocation scheme does not necessarily preserve the most fairness. In this paper, we establish a framework which explicitly considers the fairness of dynamic resource allocation over a network with heterogeneous participants. As computing the transport strategy in a centralized fashion requires significant computational resources, it is imperative to develop computationally light algorithm that can be applied to large scale problems. To this end, we develop a fully distributed algorithm for fair and dynamic optimal transport with provable convergence using alternating method of multipliers. In the designed algorithm, each corresponding pair of resource supplier and receiver compute their own solutions and update the transport schemes through negotiation iteratively which do not require a central planner. The distributed algorithm can yield a fair and efficient resource allocation mechanism over a network. We corroborate the obtained results through case studies.

No abstract

With the continuous rise of the COVID-19 cases worldwide, it is imperative to ensure that all those vulnerable countries lacking vaccine resources can receive sufficient support to contain the risks. COVAX is such an initiative operated by the WHO to supply vaccines to the most needed countries. One critical problem faced by the COVAX is how to distribute the limited amount of vaccines to these countries in the most efficient and equitable manner. This paper aims to address this challenge by first proposing a data-driven risk assessment and prediction model and then developing a decision-making framework to support the strategic vaccine distribution. The machine learning-based risk prediction model characterizes how the risk is influenced by the underlying essential factors, e.g., the vaccination level among the population in each COVAX country. This predictive model is then leveraged to design the optimal vaccine distribution strategy that simultaneously minimizes the resulting risks while maximizing the vaccination coverage in these countries targeted by COVAX. Finally, we corroborate the proposed framework using case studies with real-world data.

An autonomous drone flying near obstacles needs to be able to detect and avoid the obstacles or it will collide with them. In prior work, drones can detect and avoid walls using data from camera, ultrasonic or laser sensors mounted either on the drone or in the environment. It is not always possible to instrument the environment, and sensors added to the drone consume payload and power -both of which are constrained for drones.This paper studies how data mining classification techniques can be used to predict where an obstacle is in relation to the drone based only on monitoring air-disturbance. We modeled the airflow of the rotors physically to deduce higher level features for classification. Data was collected from the drone's IMU while it was flying with a wall to its direct left, front and right, as well as with no walls present. In total 18 higher level features were produced from the raw data. We used an 80%, 20% traintest scheme with the RandomForest (RF), K-Nearest Neighbor (KNN) and GradientBoosting (GB) classifiers. Our results show that with the RF classifier and with 90% accuracy it can predict which direction a wall is in relation to the drone.