Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Computer science & Service (business). The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

Factors Influencing Perceived Fairness in Algorithmic Decision-Making: Algorithm Outcomes, Development Procedures, and Individual Differences

Abstract: Algorithmic decision-making systems are increasingly used throughout the public and private sectors to make important decisions or assist humans in making these decisions with real social consequences. While there has been substantial research in recent years to build fair decision-making algorithms, there has been less research seeking to understand the factors that affect people's perceptions of fairness in these systems, which we argue is also important for their broader acceptance. In this research, we conduct an online experiment to better understand perceptions of fairness, focusing on three sets of factors: algorithm outcomes, algorithm development and deployment procedures, and individual differences. We find that people rate the algorithm as more fair when the algorithm predicts in their favor, even surpassing the negative effects of describing algorithms that are very biased against particular demographic groups. We find that this effect is moderated by several variables, including participants' education level, gender, and several aspects of the development procedure. Our findings suggest that systems that evaluate algorithmic fairness through users' feedback must consider the possibility of "outcome favorability" bias.

Statistical Blockage Modeling and Robustness of Beamforming in Millimeter-Wave Systems

Abstract: There has been a growing interest in the commercialization of millimeter-wave (mmW) technology as a part of the fifth-generation new radio wireless standardization efforts. In this direction, many sets of independent measurements show that the biggest determinants of viability of mmW systems are penetration and blockage of mmW signals through different materials in the scattering environment. With this background, the focus of this paper is on understanding the impact of blockage of mmW signals and reduced spatial coverage due to penetration through the human hand, body, vehicles, and so on. Leveraging measurements with a 28-GHz mmW experimental prototype and electromagnetic simulation studies, we first propose statistical models to capture the impact of the hand, human body, and vehicles. We then study the time scales at which mmW signals are disrupted by blockage (hand and human body). Our results show that these events can be attributed to physical movements, and the time scales corresponding to blockage are, hence, on the order of a few 100 ms or more. Network densification, subarray switching in a user equipment designed with multiple subarrays, fall back mechanisms, etc., can address blockage before it leads to a deleterious impact on the mmW link margin.

Inter-facility transport in inventory management and fulfillment systems

Abstract: In an infrastructure that uses a mobile order fulfillment system, robotic drive units may be dispatched and instructed to bring inventory holders to a workstation where at least one of the inventory holders is packed and prepared for shipment. The robotic drive units are then instructed to move the prepared inventory holder to a transport vehicle such as a truck. Fiducial marks may be removably placed within the transport vehicle to aid navigation of the robotic drive units. At a destination facility, additional robotic drive units may be instructed to move the inventory holders from the truck and place the inventory holders at appropriate storage locations.

Bayesian Graph Convolution LSTM for Skeleton Based Action Recognition

Abstract: We propose a framework for recognizing human actions from skeleton data by modeling the underlying dynamic process that generates the motion pattern. We capture three major factors that contribute to the complexity of the motion pattern including spatial dependencies among body joints, temporal dependencies of body poses, and variation among subjects in action execution. We utilize graph convolution to extract structure-aware feature representation from pose data by exploiting the skeleton anatomy. Long short-term memory (LSTM) network is then used to capture the temporal dynamics of the data. Finally, the whole model is extended under the Bayesian framework to a probabilistic model in order to better capture the stochasticity and variation in the data. An adversarial prior is developed to regularize the model parameters to improve the generalization of the model. A Bayesian inference problem is formulated to solve the classification task. We demonstrate the benefit of this framework in several benchmark datasets with recognition under various generalization conditions.

Implicit social graph edge strengths

Abstract: Techniques for calculating edge strengths for edges of a social graph are described herein. These techniques may determine an affinity between a first user of a social graph and a second user of the social graph. Based at least in part on this affinity, a strength of an edge connecting the first user and the second user on the social graph may be calculated and assigned to the corresponding edge.