Motion-adaptive radiotherapy techniques are promising to deliver truly ablative radiation doses to tumors with minimal normal tissue exposure by accounting for real-time tumor movement. However, a major challenge of successful applications of these techniques is the real-time prediction of breathing-induced tumor motion to accommodate system delivery latencies. Predicting respiratory motion in real-time is challenging. The current respiratory motion prediction approaches are still not satisfactory in terms of accuracy and interpretability due to the complexity of breathing patterns and the high inter-individual variability across patients. In this paper, we propose a novel respiratory motion prediction framework which integrates four key components: a personalized monitoring window generator, an orthogonal polynomial approximation-based pattern library builder, a variant best neighbor pattern searcher, and a statistical prediction decision maker. The four functional components work together into a real-time prediction system and is capable of performing personalized tumor position prediction during radiotherapy. Based on a study of respiratory motion of 27 patients with lung cancer, the proposed prediction approach generated consistently better prediction performances than the current respiratory motion prediction approaches, particularly for long prediction horizons.

Identifying important components or factors in large amounts of noisy data is a key problem in machine learning and data mining. Motivated by a pattern decomposition problem in materials discovery, aimed at discovering new materials for renewable energy, e.g. for fuel and solar cells, we introduce CombiFD, a framework for factor based pattern decomposition that allows the incorporation of a-priori knowledge as constraints, including complex combinatorial constraints. In addition, we propose a new pattern decomposition algorithm, called AMIQO, based on solving a sequence of (mixed-integer) quadratic programs. Our approach considerably outperforms the state of the art on the materials discovery problem, scaling to larger datasets and recovering more precise and physically meaningful decompositions. We also show the effectiveness of our approach for enforcing background knowledge on other application domains.

Emotion affects our understanding of the opinions and sentiments of others. Research has demonstrated that humans are able to recognize emotions in various domains, including speech and music, and that there are potential shared features that shape the emotion in both domains. In this paper, we investigate acoustic and visual features that are relevant to emotion perception in the domains of singing and speaking. We train regression models using two paradigms: (1) within-domain, in which models are trained and tested on the same domain and (2) cross-domain, in which models are trained on one domain and tested on the other domain. This strategy allows us to analyze the similarities and differences underlying the relationship between audio-visual feature expression and emotion perception and how this relationship is affected by domain of expression. We use kernel density estimation to model emotion as a probability distribution over the perception associated with multiple evaluators on the valence-activation space. This allows us to model the variation inherent in the reported perception. Results suggest that activation can be modeled more accurately across domains, compared to valence. Furthermore, visual features capture cross-domain emotion more accurately than acoustic features. The results provide additional evidence for a shared mechanism underlying spoken and sung emotion perception.

This paper proposes mining query subtopics from questions in community question answering (CQA). The subtopics are represented as a number of clusters of questions with keywords summarizing the clusters. The task is unique in that the subtopics from questions can not only facilitate user browsing in CQA search, but also describe aspects of queries from a question-answering perspective. The challenges of the task include how to group semantically similar questions and how to find keywords capable of summarizing the clusters. We formulate the subtopic mining task as a non-negative matrix factorization (NMF) problem and further extend the model of NMF to incorporate question similarity estimated from metadata of CQA into learning. Compared with existing methods, our method can jointly optimize question clustering and keyword extraction and encourage the former task to enhance the latter. Experimental results on large scale real world CQA datasets show that the proposed method significantly outperforms the existing methods in terms of keyword extraction, while achieving a comparable performance to the state-of-the-art methods for question clustering.

This paper addresses a new problem concerning the evolution of influence relationships between communities in dynamic social networks. A weighted temporal multigraph is employed to represent the dynamics of the social networks and analyze the influence relationships between communities over time. To ensure the interpretability of the knowledge discovered, evolution of the influence relationships is assessed by introducing the Granger causality. Through extensive experiments, we empirically demonstrate the suitability of our model for studying the evolution of influence between communities. Moreover, we empirically show how our model is able to accurately predict the influence of communities over time using random forest regression.

We present a fully autonomous robotic system for grasping objects in dense clutter. The objects are unknown and have arbitrary shapes. Therefore, we cannot rely on prior models. Instead, the robot learns online, from scratch, to manipulate the objects by trial and error. Grasping objects in clutter is significantly harder than grasping isolated objects, because the robot needs to push and move objects around in order to create sufficient space for the fingers. These pre-grasping actions do not have an immediate utility, and may result in unnecessary delays. The utility of a pre-grasping action can be measured only by looking at the complete chain of consecutive actions and effects. This is a sequential decision-making problem that can be cast in the reinforcement learning framework. We solve this problem by learning the stochastic transitions between the observed states, using nonparametric density estimation. The learned transition function is used only for re-calculating the values of the executed actions in the observed states, with different policies. Values of new state-actions are obtained by regressing the values of the executed actions. The state of the system at a given time is a depth (3D) image of the scene. We use spectral clustering for detecting the different objects in the image. The performance of our system is assessed on a robot with real-world objects.

Sentiment analysis predicts a one-dimensional quantity describing the positive or negative emotion of an author. Mood analysis extends the one-dimensional sentiment response to a multi-dimensional quantity, describing a diverse set of human emotions. In this paper, we extend sentiment and mood analysis temporally and model emotions as a function of time based on temporal streams of blog posts authored by a specific author. The model is useful for constructing predictive models and discovering scientific models of human emotions.

Name of an identity is strongly influenced by his/her cultural background such as gender and ethnicity, both vital attributes for user profiling, attribute-based retrieval, etc. Typically, the associations between names and attributes (e.g., people named "Amy" are mostly females) are annotated manually or provided by the census data of governments. We propose to associate a name and its likely demographic attributes by exploiting click-throughs between name queries and images with automatically detected facial attributes. This is the first work attempting to translate an abstract name to demographic attributes in visual-data-driven manner, and it is adaptive to incremental data, more countries and even unseen names (the names out of click-through data) without additional manual labels. In the experiments, the automatic name-attribute associations can help gender inference with competitive accuracy by using manual labeling. It also benefits profiling social media users and keyword-based face image retrieval, especially for contributing 12% relative improvement of accuracy in adapting to unseen names.

Stochastic blockmodel (SBM) enables us to decompose and analyze an exploratory network without a priori knowledge about its intrinsic structure. However, the task of effectively and efficiently learning a SBM from a large-scale network is still challenging due to the high computational cost of its model selection and parameter estimation. To address this issue, we present a novel SBM learning algorithm referred to as BLOS (BLOckwise Sbm learning). Distinct from the literature, the model selection and parameter estimation of SBM are concurrently, rather than alternately, executed in BLOS by embedding the minimum message length criterion into a block-wise EM algorithm, which greatly reduces the time complexity of SBM learning without losing learning accuracy and modeling flexibility. Its effectiveness and efficiency have been tested through rigorous comparisons with the state-of-the-art methods on both synthetic and real-world networks.

With rapid growth of information on the internet, recommender systems become fundamental for helping users alleviate the problem of information overload. Since contextual information can be used as a significant factor in modeling user behavior, various context-aware recommendation methods are proposed. However, the state-of-the-art context modeling methods treat contexts as other dimensions similar to the dimensions of users and items, and cannot capture the special semantic operation of contexts. On the other hand, some works on multi-domain relation prediction can be used for the context-aware recommendation, but they have problems in generating recommendation under a large amount of contextual information. In this work, we propose Contextual Operating Tensor (COT) model, which represents the common semantic effects of contexts as a contextual operating tensor and represents a context as a latent vector. Then, to model the semantic operation of a context combination, we generate contextual operating matrix from the contextual operating tensor and latent vectors of contexts. Thus latent vectors of users and items can be operated by the contextual operating matrices. Experimental results show that the proposed COT model yields significant improvements over the competitive compared methods on three typical datasets, i.e., Food, Adom and Movielens-1M datasets.