We propose a machine learning framework to capture the dynamics of high-frequency limit order books in financial equity markets and automate real-time prediction of metrics such as mid-price movement and price spread crossing. By characterizing each entry in a limit order book with a vector of attributes such as price and volume at different levels, the proposed framework builds a learning model for each metric with the help of multi-class support vector machines. Experiments with real data establish that features selected by the proposed framework are effective for short-term price movement forecasts.

No abstract

To understand speech, the slowly varying outline, or envelope, of the acoustic stimulus is used to distinguish words. A small amount of information about the envelope is sufficient for speech recognition, but the mechanism used by the auditory system to extract the envelope is not known. Several different theories have been proposed, including envelope detection by auditory nerve dendrites as well as various mechanisms involving the sensory hair cells. We used recordings from human and animal inner ears to show that the dominant mechanism for envelope detection is distortion introduced by mechanoelectrical transduction channels. This electrical distortion, which is not apparent in the sound-evoked vibrations of the basilar membrane, tracks the envelope, excites the auditory nerve, and transmits information about the shape of the envelope to the brain.

Background: The ubiquity of cell phones, which allow for short message service (SMS), provides new and innovative opportunities for disease prevention and health education. Objective: To explore the use of cell phone-based health education SMS to improve the health literacy of community residents in China. Methods: A multi-stage random sampling method was used to select representative study communities and participants ≥ 18 years old. Intervention participants were sent health education SMSs once a week for 1 year and controls were sent conventional, basic health education measures. Health literacy levels of the residents before and after the intervention were evaluated between intervention and control groups. Results: Public health literacy scores increased 1.5 points, from 61.8 to 63.3, after SMS intervention for 1 year (P<0.01); the increase was greater for males than females (2.01 vs. 1.03; P<0.01) and for Shenzhen local residents than non-permanent residents (2.56 vs. 1.14; P<0.01). The frequency of high health literacy scores was greater for the intervention than control group (22.03% to 30.93% vs. 22.07% to 20.82%). With health literacy as a cost-effective index, the cost-effectiveness per intervention was 0.54. Conclusion: SMS may be a useful tool for improving health literacy.

No abstract