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.

System and method for decentralized performance monitoring of host systems

Abstract: Various embodiments of a system and method for decentralized performance monitoring of host systems are described. Embodiments may include one or more client systems, each of which may monitor the performance of one or more host systems. In some embodiments, at least some of the host systems may be members of a cloud computing environment. A given client system may collect metrics from multiple different host systems and aggregate such metrics on the client system. In various embodiments, metrics may be collected by the client system directly from the multiple different host systems without utilizing a centralized repository of metrics. In various embodiments, the given client's receipt of the metrics from the multiple different hosts systems may be an initial aggregation of those metrics together on the same computer system. The client system may generate a graphical representation of the metrics collected from multiple hosts systems.

Techniques for protecting against denial of service attacks near the source

Abstract: Systems and methods protect against denial of service attacks. Remotely originated network traffic addressed to one or more network destinations is routed through one or more locations. One or more of the locations may be geographically proximate to a source of a denial of service attack. One or more denial of service attack mitigation strategies is applied to portions of the network traffic received at the one or more locations. Network traffic not blocked pursuant to the one or more denial of service attack mitigation strategies is dispatched to its intended recipient. Dispatching the unblocked network traffic to its intended recipient may include the use of one or more private channels and/or one or more additional denial of service attack mitigation strategies.

Transferability and Hardness of Supervised Classification Tasks

Abstract: We propose a novel approach for estimating the difficulty and transferability of supervised classification tasks. Unlike previous work, our approach is solution agnostic and does not require or assume trained models. Instead, we estimate these values using an information theoretic approach: treating training labels as random variables and exploring their statistics. When transferring from a source to a target task, we consider the conditional entropy between two such variables (i.e., label assignments of the two tasks). We show analytically and empirically that this value is related to the loss of the transferred model. We further show how to use this value to estimate task hardness. We test our claims extensively on three large scale data sets---CelebA (40 tasks), Animals with Attributes~2 (85 tasks), and Caltech-UCSD Birds~200 (312 tasks)---together representing 437 classification tasks. We provide results showing that our hardness and transferability estimates are strongly correlated with empirical hardness and transferability. As a case study, we transfer a learned face recognition model to CelebA attribute classification tasks, showing state of the art accuracy for highly transferable attributes.

Integration of Sentinel-1 and Sentinel-2 for Classification and LULC Mapping in the Urban Area of Belém, Eastern Brazilian Amazon

Abstract: In tropical regions, such as in the Amazon, the use of optical sensors is limited by high cloud coverage throughout the year. As an alternative, Synthetic Aperture Radar (SAR) products could be used, alone or in combination with optical images, to monitor tropical areas. In this sense, we aimed to select the best Land Use and Land Cover (LULC) classification approach for tropical regions using Sentinel family products. We choose the city of Belem, Brazil, as the study area. Images of close dates from Sentinel-1 (S-1) and Sentinel-2 (S-2) were selected, preprocessed, segmented, and integrated to develop a machine learning LULC classification through a Random Forest (RF) classifier. We also combined textural image analysis (S-1) and vegetation indexes (S-2). A total of six LULC classifications were made. Results showed that the best overall accuracy (OA) was found for the integration of S-1 and S-2 (91.07%) data, followed by S-2 only (89.53%), and S-2 with radiometric indexes (89.45%). The worse result was for S-1 data only (56.01). For our analysis the integration of optical products in the stacking increased de OA in all classifications. However, we suggest the development of more investigations with S-1 products due to its importance for tropical regions.