A versatile medical image segmentation model applicable to images acquired with diverse equipment and protocols can facilitate model deployment and maintenance. However, building such a model typically demands a large, diverse, and fully annotated dataset, which is challenging to obtain due to the labor-intensive nature of data curation. To address this challenge, we propose a cost-effective alternative that harnesses multi-source data with only partial or sparse segmentation labels for training, substantially reducing the cost of developing a versatile model. We devise strategies for model self-disambiguation, prior knowledge incorporation, and imbalance mitigation to tackle challenges associated with inconsistently labeled multi-source data, including label ambiguity and modality, dataset, and class imbalances. Experimental results on a multi-modal dataset compiled from eight different sources for abdominal structure segmentation have demonstrated the effectiveness and superior performance of our method compared to state-of-the-art alternative approaches. We anticipate that its cost-saving features, which optimize the utilization of existing annotated data and reduce annotation efforts for new data, will have a significant impact in the field.

With the development of intelligent manufacturing and "Industry 4.0", the traditional methods of material mechanical properties evaluation cannot meet the needs of industrial production due to the shortcomings of wasted materials, tedious processes, and poor accuracy. This paper combines artificial intelligence technology to propose a new material performance evaluation method. The laser additive manufacturing is taken as the research background, three kinds of Ti6-Al-4V material microstructure images with different properties are used as data sets, based on DenseNet model, a deep convolution neural network NDenseNet is trained to optimize the network model memory and improve the recognition accuracy. The experimental results show that the accuracy of the model reaches 90.4%, loss value remains at 25%. Params and FLOPs are significantly reduced compared with DenseNet model. It only takes 0.1 seconds to process a microstructural image on a GPU processor. This method can greatly reduce the work of researchers, improve product development efficiency in industrial environment, reduce human errors, save production materials, and has guiding significance for the development of high-performance materials.

Recommendation is essential to many online services; however current systems often provide limited interaction and visualization mechanisms, affecting the user satisfaction of recommendation. This paper presents an interactive recommendation approach for the general public without any knowledge of recommendation or visualization algorithms. Our approach emphasizes interactivity, explicit user input, and semantic information convey with the following two components. First, we propose a Latent Semantic Model that captures the statistical features of semantic concepts on 2D domains and abstracts user preferences for personal recommendation, so that high-dimensional spectral space from the rating records can be understood and interacted with directly. Second, we propose an interactive recommendation approach through a storytelling mechanism for promoting the communication between the user and the recommendation system. We demonstrate and evaluate our approach with a real dataset. Our approach can also be extended to other applications including various online recommendation systems.

It has been shown that the adjacency eigenspace of a network contains key information of its underlying structure. However, there has been no study on spectral analysis of the adjacency matrices of directed signed graphs. In this paper, we derive theoretical approximations of spectral projections from such directed signed networks using matrix perturbation theory. We use the derived theoretical results to study the influences of negative intra cluster and inter cluster directed edges on node spectral projections. We then develop a spectral clustering based graph partition algorithm, SC-DSG, and conduct evaluations on both synthetic and real datasets. Both theoretical analysis and empirical evaluation demonstrate the effectiveness of the proposed algorithm.

This paper presents a spectral analysis of signed networks from both theoretical and practical aspects. On the theoretical aspect, we conduct theoretical studies based on results from matrix perturbation for analyzing community structures of complex signed networks and show how the negative edges affect distributions and patterns of node spectral coordinates in the spectral space. We prove and demonstrate that node spectral coordinates form orthogonal clusters for two types of signed networks: graphs with dense inter-community mixed sign edges and$k$-dispute graphs where inner-community connections are absent or very sparse but inter-community connections are dense with negative edges. The cluster orthogonality pattern is different from the line orthogonality pattern (i.e., node spectral coordinates form orthogonal lines) observed in the networks with$k$-block structure. We show why the line orthogonality pattern does not hold in the spectral space for these two types of networks. On the practical aspect, we have developed a clustering method to study signed networks and$k$-dispute networks. Empirical evaluations on both synthetic networks (with up to one million nodes) and real networks show our algorithm outperforms existing clustering methods on signed networks in terms of accuracy and efficiency.

We focus on analysis of dominance, power, influence - that by definition asymmetric - between pairs of individuals in social networks. We conduct dominance analysis based on the canonical analysis of asymmetry that decomposes a square asymmetric matrix into two parts, a symmetric one and a skew-symmetric one, and then applies the singular value decomposition (SVD) on the skew-symmetric part. Each individual node can be projected as one 2-dimensional point based on its row values at each pair of successive singular vectors. The asymmetric relationship between two individuals can then be captured by areas of triangles formed from the two points and the origin in each 2-dimensional space. We quantify node dominance (submissive) score based on the relative position of the node's coordinate from coordinates of all other nodes it dominates (subdues) in the projected singular vector spaces. We conduct dominance/submissiveness analysis for several representative networks including perfect linear orderings, networks with tree structure, and networks with random graphs and examine the departures of a real social network from those representative graphs. Empirical evaluations demonstrate the effectiveness of the proposed approach.

The eigenspace of the adjacency matrix of a graph possesses important information about the network structure. However, analyzing the spectral space properties for directed graphs is challenging due to complex valued decompositions. In this paper, we explore the adjacency eigenspaces of directed graphs. With the aid of the graph perturbation theory, we emphasize on deriving rigorous mathematical results to explain several phenomena related to the eigenspace projection patterns that are unique for directed graphs. Furthermore, we relax the community structure assumption and generalize the theories to the perturbed Perron-Frobenius simple invariant subspace so that the theories can adapt to a much broader range of network structural types. We also develop a graph partitioning algorithm and conduct evaluations to demonstrate its potential.

This paper presents a study of signed networks from both theoretical and practical aspects. On the theoretical aspect, we conduct theoretical study based on matrix perturbation theorem for analyzing community structures of complex signed networks and show how the negative edges affect distributions and patterns of node spectral coordinates in the spectral space. We prove and demonstrate cluster orthogonality for two types of signed networks: graph with dense inter-community mixed sign edges and k-dispute graph. We show why the line orthogonality pattern does not hold in the spectral space for these two types of networks. On the practical aspect, we have developed a clustering method to study signed networks and k-dispute networks. Empirical evaluations on both synthetic and real networks show our algorithm outperforms existing clustering methods on signed networks in terms of accuracy.