Search

Objective: Early identification of individuals who are at risk for suicide is crucial in supporting suicide prevention. Machine learning is emerging as a promising approach to support this objective. Machine learning is broadly defined as a set of mathematical models and computational algorithms designed to automatically learn complex patterns between predictors and outcomes from example data, without being explicitly programmed to do so. The model's performance continuously improves over time by learning from newly available data. Method: This concept paper explores how machine learning approaches applied to healthcare data obtained from electronic health records, including billing and claims data, can advance our ability to accurately predict future suicidal behavior. Results: We provide a general overview of machine learning concepts, summarize exemplar studies, describe continued challenges, and propose innovative research directions. Conclusion: Machine learning has potential for improving estimation of suicide risk, yet important challenges and opportunities remain. Further research can focus on incorporating evolving methods for addressing data imbalances, understanding factors that affect generalizability across samples and healthcare systems, expanding the richness of the data, leveraging newer machine learning approaches, and developing automatic learning systems., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Boudreaux, Rundensteiner, Liu, Wang, Larkin, Agu, Ghosh, Semeter, Simon and Davis-Martin.)

Small-scale dynamic auroras have spatial scales of a few km or less, and temporal scales of a few seconds or less, which visualize the complex interplay among charged particles, Alfvén waves, and plasma instabilities working in the magnetosphere-ionosphere coupled regions. We summarize the observed properties of flickering auroras, vortex motions, and filamentary structures. We also summarize the development of fundamental theories, such as dispersive Alfvén waves (DAWs), plasma instabilities in the auroral acceleration region, ionospheric feedback instabilities (IFI), and the ionospheric Alfvén resonator (IAR)., Supplementary Information: The online version contains supplementary material available at 10.1007/s11214-021-00796-w., (© The Author(s) 2021, corrected publication 2021.)

In this paper, we present a technique for dimensionality reduction in hyperspectral imaging during the data collection process. A four-channel hyperspectral imager using liquid crystal Fabry-Perot etalons has been built and used to verify this method for four applications: auroral imaging, plant study, landscape classification, and anomaly detection. This imager is capable of making measurements simultaneously in four wavelength ranges while being tunable within those ranges, and thus can be used to measure narrow contiguous bands in four spectral domains. In this paper, we describe the design, concept of operation, and deployment of this instrument. The results from preliminary testing of this instrument are discussed and are promising and demonstrate this instrument as a good candidate for hyperspectral imaging.

A four channel hyperspectral imager using Liquid Crystal Fabry-Perot (LCFP) etalons has been built and tested. This imager is capable of making measurements simultaneously in four wavelength ranges in the visible spectrum. The instrument was designed to make measurements of natural airglow and auroral emissions in the upper atmosphere of the Earth and was installed and tested at the Poker Flat Research Range in Fairbanks, Alaska from February to April 2014. The results demonstrate the capabilities and challenges this instrument presents as a sensor for aeronomical studies.