This study explores the influence of social media on stock volatility and builds a feature model with an intelligence algorithm using social media data from *** in China, Sina Finance and Economics, Sina Microblog, an...
详细信息
This study explores the influence of social media on stock volatility and builds a feature model with an intelligence algorithm using social media data from *** in China, Sina Finance and Economics, Sina Microblog, and Oriental Fortune. We find that the effect of social factors, such as increased attention to a stock's volatility, is more significant than public sentiment. A prediction model is introduced based on social factors and public sentiment to predict stock volatility. Our findings indicate that the influence of social media data on the next day's volatility is more significant but declines over time.
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classifiers ...
详细信息
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classifiers to distinguish faces and non-faces. Moreover, to get more accurate results of the face detection, we present a kernel function and a linear combination to build incrementally the strong classifiers based on the weak classifiers. Through comparing and analyzing results of some experiments on the synthetic data and the natural data, we can get more satisfied results by the strong classifiers than by the weak classifies.
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classifiers ...
详细信息
In this paper, we present a strategy to implement multi-pose face detection in compressed domain. The strategy extracts firstly feature vectors from DCT domain, and then uses a boosting algorithm to build classifiers to distinguish faces and non-faces. Moreover, to get more accurate results of the face detection, we present a kernel function and a linear combination to build incrementally the strong classifiers based on the weak classifiers. Through comparing and analyzing results of some experiments on the synthetic data and the natural data, we can get more satisfied results by the strong classifiers than by the weak classifies.
暂无评论