Significance: Hydrogels maintain great potential for biomedical applications. However, predicting whether a chemical can form a hydrogel simply based on its chemical structure remains challenging. In this study, we developed a combinational approach to obtain a structurally diverse hydrogel library with over 2,000 peptides as a training dataset for machine learning. We calculated their chemical features, including topological and physicochemical properties, and utilized machine learning methods to predict the self-assembly behavior.
Video surveillance in crowded areas is becoming more and more significant for public security. This paper presents a method for the detection of abnormality in crowded scenes based on the crowd motion characteristics. These characteristics includes the crowd kinetic energy and the motion directions. This approach estimates the crowd kinetic energy and the motion directions based on the optical flow techniques. The motion variation is derived from the crowd kinetic energy of two adjacent frames, and the motion direction variation is estimated using mutual information of the direction histograms of two neighboring motion vector fields. The proposed method combines crowd kinetic energy, motion variation and direction variation for the abnormality detection. The experiments on the video data which captured by ourselves demonstrate that our method can detect the abnormal behaviors effectively.
1 January 2012 in Lecture Notes in Computer Science
We propose a coupled dictionary learning method to predict deformation fields based on image appearance. Rather than estimating deformations by standard image registration methods, we investigate how to obtain a basis of the space of deformations. In particular, we explore how image appearance differences with respect to a common atlas image can be used to predict deformations represented by such a basis. We use a coupled dictionary learning method to jointly learn a basis for image appearance differences and their related deformations. Our proposed method is based on local image patches. We evaluate our method on synthetically generated datasets as well as on a structural magnetic resonance brain imaging (MRI) dataset. Our method results in an improved prediction accuracy while reducing the search space compared to nearest neighbor search and demonstrates that learning a deformation basis is feasible.
We propose a robust multimodal dictionary learning method for multimodal images. Joint dictionary learning for both modalities may be impaired by lack of correspondence between image modalities in training data, for example due to areas of low quality in one of the modalities. Dictionaries learned with such non-corresponding data will induce uncertainty about image representation. In this paper, we propose a probabilistic model that accounts for image areas that are poorly corresponding between the image modalities. We cast the problem of learning a dictionary in presence of problematic image patches as a likelihood maximization problem and solve it with a variant of the EM algorithm. Our algorithm iterates identification of poorly corresponding patches and refinements of the dictionary. We tested our method on synthetic and real data. We show improvements in image prediction quality and alignment accuracy when using the method for multimodal image registration.