Search

Convolutional Neural Networks (CNNs) are a popular choice for estimating Direction of Arrival (DoA) without explicitly estimating delays between multiple microphones. The CNN method first optimises unknown filter weights (of a CNN) by using observations and ground-truth directional information. This trained CNN is then used to predict incident directions given test observations. Most existing methods train using spectrally-flat random signals and test using speech. In this paper, which focuses on single source DoA estimation, we find that training with speech or music signals produces a relative improvement in DoA accuracy for a variety of audio classes across 16 acoustic conditions and 9 DoAs, amounting to an average improvement of around 17% and 19% respectively when compared to training with spectrally flat random signals. This improvement is also observed in scenarios in which the speech and music signals are synthesised using, for example, a Generative Adversarial Network (GAN). When the acoustic environments during test and training are similar and reverberant, training a CNN with speech outperforms Generalized Cross Correlation (GCC) methods by about 125%. When the test conditions are different, a CNN performs comparably. This paper takes a step towards answering open questions in the literature regarding the nature of the signals used during training, as well as the amount of data required for estimating DoA using CNNs.

Purpose: To identify rates and sociodemographic correlates of food insecurity among low-income smokers.Design: Cross-sectional analysis of baseline survey data from a randomized controlled trial (N = 403) testing a smoking cessation intervention for low-income smokers.Setting: Two safety-net hospitals in New York City.Sample: Current smokers with annual household income <200% of the federal poverty level.Measures: Food insecurity was measured using the United States Department of Agriculture 6-item food security module. Participant sociodemographics were assessed by self-reported survey responses.Analysis: We used frequencies to calculate the proportion of smokers experiencing food insecurity and multivariable logistic regression to identify factors associated with being food insecure.Results: Fifty-eight percent of participants were food insecure, with 29% reporting very high food insecurity. Compared to married participants, separated, widowed, or divorced participants were more likely to be food insecure (adjusted odds ratio [AOR] = 2.33, 95% confidence interval [CI]: 1.25-4.33), as were never married participants (AOR = 2.81, 95% CI: 1.54-5.14).Conclusions: Health promotion approaches that target multiple health risks (eg, smoking andfood access) may be needed for low-income populations. Interventions which seek to alleviate food insecurity may benefit from targeting socially isolated smokers.

ObjectivesThe current study sought to characterise the tobacco retail environment of supportive housing facilities for persons with mental health (MH) conditions in New York City (NYC) and to estimate the potential impact of a tobacco retail ban near public schools on the retail environment of MH housing in NYC.MethodsTexas A&M Geocoding Services was used to geocode the addresses of housing programmes for patients with MH conditions, non-MH residences, public schools and tobacco retailers in NYC. ESRI ArcMap was used to calculate the number of tobacco retailers within a 500-foot radius around each housing programme and school address point, and the Euclidean distance to the nearest retailer. Generalised linear models were used to compare retail counts and distance between MH and non-MH residences.ResultsThe mean number of tobacco retailers within 500 feet of an MH housing programme was 2.9 (SD=2.3) and the mean distance to nearest tobacco retailer was 370.6 feet (SD=350.7). MH residences had more retailers within 500 feet and a shorter distance to the nearest retailer compared with non-MH residences in Brooklyn, the Bronx and Staten Island (p<0.001). Banning tobacco licences within 350, 500 or 1000 feet of a school would significantly improve the tobacco retail environment of MH housing programmes and reduce disparities between MH and non-MH residences in some boroughs.ConclusionsPeople with MH conditions residing in supportive housing in NYC encounter a heavy tobacco retail environment in close proximity to their home, and in some boroughs, one worse than non-MH residences. Implementing a ban on tobacco retail near public schools would improve the tobacco retail environment of MH housing programmes in NYC.

A personal narrative of author's experience of being alcoholic is presented.

The article shares some personality of a television host Elizabeth Vargas. She says that in social gathering, she is very shy and quiet. Vargas hates having make-up on her neck that gets in her collar. She is also a bargain hunter, and one of her favorite was a brown suede Ralph Lauren skirt at 60 percent off.