Text-based counseling and support systems have seen an increasing proliferation in the past decade. We present Fathom, a natural language interface to help crisis counselors on Crisis Text Line, a new 911-like crisis hotline that takes calls via text messaging rather than voice. Text messaging opens up the opportunity for software to read the messages as well as people, and to provide assistance for human counselors who give clients emotional and practical support. Crisis counseling is a tough job that requires dealing with emotionally stressed people in possibly life-critical situations, under time constraints. Fathom is a system that provides topic modeling of calls and graphical visualization of topic distributions, updated in real time. We develop a mixed-initiative paradigm to train coherent topic and word distributions and use them to power real-time visualizations aimed at reducing counselor cognitive overload. We believe Fathom to be the first real-time computational framework to assist in crisis counseling.
Current peta-scale data analytics frameworks suffer from a significant performance bottleneck due to an imbalance between their enormous computational power and limited I/O bandwidth. Using data compression schemes to reduce the amount of I/O activity is a promising approach to addressing this problem. In this paper, we propose a hybrid framework for interleaving I/O with data compression to achieve improved I/O throughput side-by-side with reduced dataset size. We evaluate several interleaving strategies, present theoretical models, and evaluate the efficiency and scalability of our approach through comparative analysis. With our theoretical model, considering 19 real-world scientific datasets both from the public domain and peta-scale simulations, we estimate that the hybrid method can result in a 12 to 46% increase in throughput on hard-to-compress scientific datasets. At the reported peak bandwidth of 60 GB/s of uncompressed data for a current, leadership-class parallel I/O system, this translates into an effective gain of 7 to 28 GB/s in aggregate throughput.
In an effort to improve orthopedic clinic utilization, we reviewed the incidence of normal radiographic variants in the foot referred from the emergency room or outpatient clinic. The study was undertaken because normal radiographic variants are often confused with fracture. A retrospective study of all foot radiographs referred to the foot clinic at Madigan Army Medical Center was carried out. Distribution of normal radiographic variants and their confusion with fracture were evaluated. Thirty-six percent of all foot radiographs had identifiable accessory bones. The most common accessory bones in descending order were: os peroneum, accessory navicular, and os trigonum. All of the accessory bones identified in our study were asymptomatic. A thorough knowledge of location of normal accessory bones is mandatory and localization of foot symptoms by history and physical examination are necessary to facilitate correct diagnosis and treatment and to avoid unnecessary referral of these patients.
The size and scope of cutting-edge scientific simulations are growing much faster than the I/O and storage capabilities of their runtime environments. The growing gap gets exacerbated by exploratory data-intensive analytics, such as querying simulation data for regions of interest with multivariate, spatio-temporal constraints. Query-driven data exploration induces heterogeneous access patterns that further stress the performance of the underlying storage system. To partially alleviate the problem, data reduction via compression and multiresolution data extraction are becoming an integral part of I/O systems. While addressing the data size issue, these techniques introduce yet another mix of access patterns to a heterogeneous set of possibilities. Moreover, how extreme-scale datasets are partitioned into multiple files and organized on a parallel file systems augments to an already combinatorial space of possible access patterns.To address this challenge, we present MLOC, a parallel Multilevel Layout Optimization framework for Compressed scientific spatio-temporal data at extreme scale. MLOC proposes multiple fine-grained data layout optimization kernels that form a generic core from which a broader constellation of such kernels can be organically consolidated to enable an effective data exploration with various combinations of access patterns. Specifically, the kernels are optimized for access patterns induced by (a) query-driven multivariate, spatio-temporal constraints, (b) precision-driven data analytics, (c) compression-driven data reduction, (d) multiresolution data sampling, and (e) multi-file data partitioning and organization on a parallel file system. MLOC organizes these optimization kernels within a multi-level architecture, on which all the levels can be flexibly re-ordered by user-defined priorities. When tested on query-driven exploration of compressed data, MLOC demonstrates a superior performance compared to any state-of-the-art scientific database management technologies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.