In this paper, we propose a novel threedimensional combining features method for sign language recognition. Based on the Kinect depth data and the skeleton joints data, we acquire the 3D trajectories of right hand, right wrist and right elbow. To construct feature vector, the paper uses combining location and spherical coordinate feature representation. The proposed approach utilizes the feature representation in spherical coordinate system effectively depicting the kinematic connectivity among hand, wrist and elbow for recognition. Meanwhile, 3D trajectory data acquired from Kinect avoid the interference of the illumination change and cluttered background. In experiments with a dataset of 20 gestures from Chinese sign language, the Extreme Learning Machine(ELM) is tested, compared with Support Vector Machine(SVM), the superior recognition performance is verified.

With the development of mobile network technology, network traffic has not only experienced exponential explosive growth, but also its application scenarios have become more and more extensive. It is a challenging proposition to find an efficient and accurate matching prediction model based on massive idiosyncratic data. This scheme proposes to introduce EMD modal decomposition to decompose the local feature components of data based on the time-scale features of the data itself, to do cluster analysis on the components by K-mean clustering algorithm, and then to model and predict the clustered local feature components by XGBoost model, so as to reduce the data dimensionality and prediction complexity. The results show that the modeling and prediction of the clustered local feature components using XGBoost model effectively improves the model prediction accuracy.

No abstract