Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
The Journal of Machine Learning Research
| Hi-index | 0.00 |
Cities have long been considered as complex entities with nonlinear and dynamic properties. Pervasive urban sensing and crowd sourcing have become prevailing technologies that enhance the interplay between the cyber space and the physical world. In this paper, a spectral graph based manifold learning method is proposed to alleviate the impact of noisy, sparse and high-dimensional dataset. Correlation analysis of two physical processes is enhanced by semi-supervised machine learning. Preliminary evaluations on the correlation of traffic density and air quality reveal great potential of our method in future intelligent evironment study.