Search NASA⌕ Search

SEARCH · Search NASA

Results for “multimode”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 757 records · Page 42

Toward a Deep Learning System for Making Sense of Unlabeled Multimodal Data

Analysts and decision makers are constantly charged with making sense of large amounts of disparate data. With the proliferation of smartphones and the ever-growing array of new sensor technologies, the old adage of swimming in sensors but drowning in data remains especially relevant. As collections of images, video, audio, and text continue to grow, the need for computer-assisted analysis likewise increases. The “data deluge” presents both daunting challenges as well as remarkable opportunities. In this article, we describe Deep Learning approaches for learning representations of data from vast amounts of unlabeled or weakly labeled training sets. These feature representations enable the computer-assisted retrieval and tagging that can help our analysts find patterns in the vast ocean of collected data.

97 MATHEMATICS AND COMPUTING↗

Explaining Multimodal Deceptive News Prediction Models

Social media plays a valuable role in rapid news dissemination, but it also serves as a vehicle to propagate unverified information. For example, news shared on Facebook or Twitter may actually contain disinformation, propaganda, hoaxes, conspiracies, clickbait or satire. This paper presents an in-depth analysis of the behavior of suspicious news classification models including error analysis and prediction confidence. We consider five deep learning architectures that leverage combinations of text, linguistic and image input signals from tweets. The behavior of these models is analyzed across four suspicious news prediction tasks. Our findings include that models leveraging only the text of tweets outperform those leveraging only the image (by 3-13% absolute in F-measure), and that models that combine image and text signals with linguistic cues e.g., biased and subjective language markers can, but do not always, perform even better. Finally, our main contribution is a series of analyses, in which we characterize text and image traits of our classes of suspicious news and analyze patterns of errors made by the various models to inform the design of future deceptive news prediction models.

deep learning, social media, deception↗

Detection and monitoring of changes in metallic structures using multimode acoustic signals

Methods for detecting and monitoring changes in mechanical structures and in walls of pipes, vessels and storage tanks, using muitimode acoustic signal propagation and detection, are described. Acoustic signals having chosen amplitude-time-frequency characteristics excite multiple modes in the structure under investigation, are generated and received at a small number of accessible locations, such as the ends of pipes and the tops and bottoms of vessels and storage tanks, with the inspection region between transmit and receive transducers. Small mechanical changes lead to acoustic scattering and attenuation among the various modes, which are detectable as changes in received signal intensity. Such changes may include material loss, material conversion and material addition. Once the structure is characterized in a known condition, the present method may be used to monitor the structure at a later time to determine whether changes have taken place. Methods for effective temperature compensation are also described. In addition, various pipe geometries and complex pipe geometries involving elbows, flanges, and the like can be monitored.

42 ENGINEERING↗

Multimodal Communication System

Current communications modules operate as a point-to-point radio. This system operates in a point-to-multipoint utilizing multiple radio frequencies for both high bandwidth data to satellite communication. This communication module further allows for multiple users to interact with the communication system in a true cloud type application so that the modules can be handled in a fleet situation.

Vacaliuc, Bogdan↗

Detection, monitoring, and determination of location of changes in metallic structures using multimode acoustic signals

Methods for detection, monitoring, and determination of location of changes in rigid structures with arbitrarily complex geometries are described. Implementations include locating acoustic transducers that generate and receive acoustic signals at multiple locations along a surface of the rigid structure, wherein longitudinal spacing between the transducer locations define measurement zones. Acoustic signals with chosen amplitude-time-frequency characteristics excite multiple vibration modes in the structure within each zone. Small mechanical changes in the inspection zones lead to scattering and attenuation of broadband acoustic signals, which are detectable as changes in received signal characteristics as part of a through-transmission technique. Additional use of short, narrowband pulse acoustic signals as part of a pulse-echo technique allows determination of the relative location of the mechanical change within each zone based on the differential delay profiles.

42 ENGINEERING↗