Total: 11
ICU mortality risk prediction may help clinicians take effective interventions to improve patient outcome. Existing machine learning approaches often face challenges in integrating a comprehensive panel of physiologic variables and presenting to clinicians interpretable models. We aim to improve both accuracy and interpretability of prediction models by introducing Subgraph Augmented Non-negative Matrix Factorization (SANMF) on ICU physiologic time series. SANMF converts time series into a graph representation and applies frequent subgraph mining to automatically extract temporal trends. We then apply non-negative matrix factorization to group trends in a way that approximates patient pathophysiologic states. Trend groups are then used as features in training a logistic regression model for mortality risk prediction, and are also ranked according to their contribution to mortality risk. We evaluated SANMF against four empirical models on the task of predicting mortality or survival 30 days after discharge from ICU using the observed physiologic measurements between 12 and 24 hours after admission. SANMF outperforms all comparison models, and in particular, demonstrates an improvement in AUC (0.848 vs. 0.827, p<0.002) compared to a state-of-the-art machine learning method that uses manual feature engineering. Feature analysis was performed to illuminate insights and benefits of subgraph groups in mortality risk prediction.
Survival prediction is crucial to healthcare research, but is confined primarily to specific types of data involving only the present measurements. This paper considers the more general class of healthcare data found in practice, which includes a wealth of intermittently varying historical measurements in addition to the present measurements. Making survival predictions on such data bristles with challenges to the existing prediction models. For this reason, we propose a new semi-proportional hazards model using locally time-varying coefficients, and a novel complete-data model learning criterion for coefficient optimization. Experiments on the healthcare data demonstrate the effectiveness and generalizability of our model and its promise in practical applications.
Researchers often summarize their work in the form of posters. Posters provide a coherent and efficient way to convey core ideas from scientific papers. Generating a good scientific poster, however, is a complex and time consuming cognitive task, since such posters need to be readable, informative, and visually aesthetic. In this paper, for the first time, we study the challenging problem of learning to generate posters from scientific papers. To this end, a data-driven framework, that utilizes graphical models, is proposed. Specifically, given content to display, the key elements of a good poster, including panel layout and attributes of each panel, are learned and inferred from data. Then, given inferred layout and attributes, composition of graphical elements within each panel is synthesized. To learn and validate our model, we collect and make public a Poster-Paper dataset, which consists of scientific papers and corresponding posters with exhaustively labelled panels and attributes. Qualitative and quantitative results indicate the effectiveness of our approach.
People often use multiple platforms to fulfill their different information needs. With the ultimate goal of serving people intelligently, a fundamental way is to get comprehensive understanding about user needs. How to organically integrate and bridge cross-platform information in a human-centric way is important. Existing transfer learning assumes either fully-overlapped or non-overlapped among the users. However, the real case is the users of different platforms are partially overlapped. The number of overlapped users is often small and the explicitly known overlapped users is even less due to the lacking of unified ID for a user across different platforms. In this paper, we propose a novel semi-supervised transfer learning method to address the problem of cross-platform behavior prediction, called XPTrans. To alleviate the sparsity issue, it fully exploits the small number of overlapped crowds to optimally bridge a user's behaviors in different platforms. Extensive experiments across two real social networks show that XPTrans significantly outperforms the state-of-the-art. We demonstrate that by fully exploiting 26% overlapped users, XPTrans can predict the behaviors of non-overlapped users with the same accuracy as overlapped users, which means the small overlapped crowds can successfully bridge the information across different platforms.
In this work, we propose a novel automatic makeup detector and remover framework. For makeup detector, a locality-constrained low-rank dictionary learning algorithm is used to determine and locate the usage of cosmetics. For the challenging task of makeup removal, a locality-constrained coupled dictionary learning (LC-CDL) framework is proposed to synthesize non-makeup face, so that the makeup could be erased according to the style. Moreover, we build a stepwise makeup dataset (SMU) which to the best of our knowledge is the first dataset with procedures of makeup. This novel technology itself carries many practical applications, e.g. products recommendation for consumers; user-specified makeup tutorial; security applications on makeup face verification. Finally, our system is evaluated on three existing (VMU, MIW, YMU) and one own-collected makeup datasets. Experimental results have demonstrated the effectiveness of DL-based method on makeup detection. The proposed LC-CDL shows very promising performance on makeup removal regarding on the structure similarity. In addition, the comparison of face verification accuracy with presence or absence of makeup is presented, which illustrates an application of our automatic makeup remover system in the context of face verification with facial makeup.
Psychological theories suggest that emotion represents the state of mind and instinctive responses of one’s cognitive system (Cannon 1927). Emotions are a complex state of feeling that results in physical and psychological changes that influence our behavior. In this paper, we study an interesting problem of emotion contagion in social networks. In particular, by employing an image social network (Flickr) as the basis of our study, we try to unveil how users’ emotional statuses influence each other and how users’ positions in the social network affect their influential strength on emotion. We develop a probabilistic framework to formalize the problem into a role-aware contagion model. The model is able to predict users’ emotional statuses based on their historical emotional statuses and social structures. Experiments on a large Flickr dataset show that the proposed model significantly outperforms (+31% in terms of F1-score) several alternative methods in predicting users’ emotional status. We also discover several intriguing phenomena. For example, the probability that a user feels happy is roughly linear to the number of friends who are also happy; but taking a closer look, the happiness probability is superlinear to the number of happy friends who act as opinion leaders (Page et al. 1999) in the network and sublinear in the number of happy friends who span structural holes (Burt 2001). This offers a new opportunity to understand the underlying mechanism of emotional contagion in online social networks.
Ranking is an important way of retrieving authoritative papers from a large scientific literature database. Current state-of-the-art exploits the flat structure of the heterogeneous academic network to achieve a better ranking of scientific articles, however, ignores the multinomial nature of the multidimensional relationships between different types of academic entities. This paper proposes a novel mutual ranking algorithm based on the multinomial heterogeneous academic hypernetwork, which serves as a generalized model of a scientific literature database. The proposed algorithm is demonstrated effective through extensive evaluation against well-known IR metrics on a well-established benchmarking environment based on the ACL Anthology Network.
In this paper we theoretically study the minimum Differentially Resolving Set (DRS) problem derived from the classical sensor placement optimization problem in network source locating. A DRS of a graph G = (V, E) is defined as a subset S ⊆ V where any two elements in V can be distinguished by their different differential characteristic sets defined on S. The minimum DRS problem aims to find a DRS S in the graph G with minimum total weight Σv∈Sw(v). In this paper we establish a group of Integer Linear Programming (ILP) models as the solution. By the weighted set cover theory, we propose an approximation algorithm with the Θ(ln n) approximability for the minimum DRS problem on general graphs, where n is the graph size.
In Supreme Court parlance and the political science literature, an ideal point positions a justice in a continuous space and can be interpreted as a quantification of the justice's policy preferences. We present an automated approach to infer such ideal points for justices of the US Supreme Court. This approach combines topic modeling over case opinions with the voting (and endorsing) behavior of justices. Furthermore, given a topic of interest, say the Fourth Amendment, the topic model can be optionally seeded with supervised information to steer the inference of ideal points. Application of this methodology over five years of cases provides interesting perspectives into the leaning of justices on crucial issues, coalitions underlying specific topics, and the role of swing justices in deciding the outcomes of cases.
Predicting protein properties such as solvent accessibility and secondary structure from its primary amino acid sequence is an important task in bioinformatics. Recently, a few deep learning models have surpassed the traditional window based multilayer perceptron. Taking inspiration from the image classification domain we propose a deep convolutional neural network architecture, MUST-CNN, to predict protein properties. This architecture uses a novel multilayer shift-and-stitch (MUST) technique to generate fully dense per-position predictions on protein sequences. Our model is significantly simpler than the state-of-the-art, yet achieves better results. By combining MUST and the efficient convolution operation, we can consider far more parameters while retaining very fast prediction speeds. We beat the state-of-the-art performance on two large protein property prediction datasets.
Hospitals are typically optimized to operate near capacity, and there are serious concerns that our healthcare system is not prepared for the next pandemic. Stockpiles of different supplies, e.g., personal protective equipments (PPE) and medical equipment, need to be maintained in order to be able to respond to any future pandemics. Large outbreaks occur with a low probability, and such stockpiles require big investments. Further, hospitals often have mutual sharing agreements, which makes the problem of stockpiling decisions a natural game-theoretical problem. In this paper, we formalize hospital stockpiling as a game-theoretical problem. We use the notion of pairwise Nash stability as a solution concept for this problem, and characterize its structure. We show that stable strategies can lead to high unsatisfied demands in some scenarios, and stockpiles might not be maintained at all nodes. We also show that stable strategies and the social optimum can be computed efficiently.