Deep autoencoders, and other deep neural networks, have demonstrated their effectiveness in discovering non-linear features across many problem domains. However, real-world problems, large outliers pervasive noise are commonplace, one may not access to clean training data as required by standard denoising autoencoders. Herein, we demonstrate novel extensions autoencoders which only maintain a autoencoders' ability discover high quality, but can also eliminate without any data. Our model is...

Future spacecraft communication subsystems will potentially benefit from software-defined radios controlled by artificial intelligence algorithms. In this paper, we propose a novel radio resource allocation algorithm leveraging multiobjective reinforcement learning and neural network ensembles able to manage available resources conflicting mission-based goals. The uncertainty in the performance of thousands possible parameter combinations dynamic behavior channel over time producing...

We present an overview of detailed computational results for families periodic orbits that emanate from the five libration points in Circular Restricted 3-Body Problem, as well various secondary bifurcating families. Our extensive covers all values mass-ratio parameter, and includes many known have been studied past. The numerical continuation bifurcation algorithms employed our study are based on boundary value techniques, implemented software AUTO.

The National Aeronautics and Space Administration (NASA) is in the midst of defining developing future space ground architecture for coming decades to return science exploration discovery data back investigators on Earth. Optimizing from these missions requires planning, design, standards, operations coordinated formulation development throughout mission. use automation enhanced by cognition machine learning are potential methods optimizing return, reducing costs operations, helping manage...

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement and deep artificial neural networks. The objective is to efficiently manage communications system resources monitoring performance functions with common dependent variables result in...

MF-LOGP, a new method for determining single component octanol-water partition coefficients ([Formula: see text]) is presented which uses molecular formula as the only input. Octanol-water are useful in many applications, ranging from environmental fate and drug delivery. Currently, either experimentally measured or predicted function of structural fragments, topological descriptors, thermodynamic properties known calculated precise structures. The MF-LOGP here differs classical methods it...

We show how to compute families of periodic solutions conservative systems with two-point boundary value problem continuation software. The computations include detection bifurcations and corresponding branch switching. A simple example is used illustrate the main idea. Thereafter we circular restricted 3-body problem. also continue figure-8 orbit recently discovered by Chenciner Montgomery, numerically computed Simó, as mass one bodies allowed vary. In particular, invariances (phase-shift,...

A cross-reactive array of semiselective chemiresistive sensors made polymer-graphene nanoplatelet (GNP) composite coated electrodes was examined for detection and discrimination chemical warfare agents (CWA). The arrays employ a set chemically diverse polymers to generate unique response signature multiple CWA simulants background interferents. developed sensors' signal remains consistent after repeated exposures analytes up 5 days with similar magnitude across different replicate the same...

A theory and algorithm for detecting classifying weak, distributed patterns in network data is presented. The we consider are anomalous temporal correlations between signals recorded at sensor nodes a network. We use robust matrix completion second order analysis to detect that not discernible the level of individual sensors. When viewed independently, each node cannot provide definitive determination underlying pattern, but when fused with from across relevant emerge. specifically...

This paper uses network packet capture data to demonstrate how Robust Principal Component Analysis (RPCA) can be used in a new way detect anomalies which serve as cyber-network attack indicators. The approach requires only few parameters learned using partitioned training and shows promise of ameliorating the need for an exhaustive set examples different types attacks. For Lincoln Lab's DARPA intrusion detection set, method achieves low false-positive rates while maintaining reasonable...

Chemical sensors play an important role in a variety of civilian and military domains. In these contexts, the ability to accurately quickly identify chemical agents is utmost importance. practice, constraints on physical footprint, power consumption, ease use, time required for accurate detection often restrict utility sensors, particularly remote isolated regions. One solution address this problem engineering advanced signal processing techniques, which decrease detection. This allows...

Chemical recycling via thermal processes such as pyrolysis is a potentially viable way to convert mixed streams of waste plastics into usable fuels and chemicals. Unfortunately, experimentally measuring product yields for real can be time- cost-prohibitive, the are very sensitive feed composition, especially certain types like poly(ethylene terephthalate) (PET) polyvinyl chloride (PVC). Models capable predicting conversion from composition reaction conditions have potential tools prioritize...

Single-particle tracking (SPT) has been extensively used to obtain information about diffusion and directed motion in a wide range of biological applications. Recently, new methods have appeared for obtaining precise (10s nm) spatial three dimensions (3D) with high temporal resolution (measurements obtained every 4 ms), which promise more accurately sense the true dynamical behavior natural 3D cellular environment. Despite quantitative information, mathematical extracting underlying system...

For many important network types, physical coordinate systems and distances are either difficult to discern or inapplicable. Accordingly, characterizations based on hop-distance measurements, such as Topology Preserving Maps (TPMs) Virtual-Coordinate (VC) attractive alternatives geographic coordinates for algorithms. We present an approach recover geometric topological properties of a with small set distance measurements. The is combination shortest path (often called geodesic) recovery...

While physical coordinates are useful for IoT and sensor network operations, localization is not a viable option large-scale networks of simple devices in complex or harsh environments. Topology Preserving Maps (TPM) extracted from anchor-based Virtual Coordinates (VCs) an attractive free alternative maps. We present approach, based on the theory low-rank matrix completion, to extract TPMs with only partial information about VCs. Evaluation using 2D 3D random anchors shows that accurate can...

Previous research on cognitive radios has addressed the performance of various machine-learning and optimization techniques for decision making terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future installed onboard satellite communications systems specifically tasked radio resource management. This work analyzes learning, reasoning, while considering multiple objectives time-varying...

This paper considers the problem of tracking and predicting state a dynamic system with stochastic dynamics multiple modes operation. A well-known approach to this is "interacting model" (IMM) estimator, which uses knowledge different operation update bank Kalman Filters (each optimal for given mode operation). The IMM combines estimates according posterior probability modes. Despite their popularity, IMMs are known sometimes be slow detect switching, however, can result in large estimation...