This paper reports on our analysis of the 2011 CAMRa Challenge dataset (Track 2) for context-aware movie recommendation systems. The train dataset comprises 4,536,891 ratings provided by 171,670 users on 23,974$ movies, as well as the household groupings of a subset of the users. The test dataset comprises 5,450 ratings for which the user label is missing, but the household label is provided. The challenge required to identify the user labels for the ratings in the test set. Our main finding is that temporal information (time labels of the ratings) is significantly more useful for achieving this objective than the user preferences (the actual ratings). Using a model that leverages on this fact, we are able to identify users within a known household with an accuracy of approximately 96% (i.e. misclassification rate around 4%).

Electronic health records (EHRs) are an emerging relational domain with large potential to improve clinical outcomes. We apply two statistical relational learning (SRL) algorithms to the task of predicting primary myocardial infarction. We show that one SRL algorithm, relational functional gradient boosting, outperforms propositional learners particularly in the medically-relevant high recall region. We observe that both SRL algorithms predict outcomes better than their propositional analogs and suggest how our methods can augment current epidemiological practices.

We investigate machine learning methods for diagnostic screening of heart disease. Coronary heart disease is the leading cause of death in the US, causing more deaths than all types of cancers combined. Early diagnosis of heart disease in women is harder than it is in men and typically requires the administration of several clinical tests on the patient. Most risk stratification methods aggregate the results of such tests, including the risky, invasive procedures that cannot be administered on all patients. In this paper, our goal is to identify patients who are under high-risk of having heart disease and related adverse events, using a minimal number of diagnostic tests, especially less invasive ones. The low frequency of patients with severe heart disease in the dataset is challenging for most conventional machine learning methods. To overcome this problem, we develop and apply a cost-sensitive k nearest neighbor algorithm. Our contributions are two fold: First, we compare the predictive value of several diagnostic procedures for heart disease, including electrocardiography, angiography, radionuclide perfusion and conclude that in womens heart disease, certain combinations of non-invasive techniques are more predictive than some of the widely used invasive procedures. Then, we evaluate held out data and achieve an AUROC over 0.70, signifying valuable clinical utility, using only the least costly and least invasive tests.

Reading groups domain is a new domain for group recommenders. In this paper we propose a web based group recommender system which is called BoRGo: Book Recommender for Reading Groups, for reading groups domain. BoRGo uses a new information filtering technique which uses the difference between positive and negative feedbacks about a feature of a user profile and also presents an interface for after recommendation processes like achieving a consensus on the reading list.

A cognitive robot should construct a plan to attain its goals. While it executes the actions in its plan, it may face several failures due to both internal and external issues. We present a taxonomy to classify these failures that may be encountered during the execution of cognitive tasks. The taxonomy presents a wide range of failure types. To recover from most of these failures presented in this taxonomy, we propose a Robust Planning Framework for cognitive robots. Our framework combines planning, reasoning and learning procedures into each other for robust execution of cognitive tasks. Failures can be detected and handled by reasoning and replanning, respectively. The framework also facilitates learning new hypotheses incrementally based on experience. It can successfully detect and recover from temporary failures on a selected set of actions executed by a Pioneer3DX robot. It has been shown that our preliminary results for hypothesis learning in failure scenarios are promising.

Smartphones incorporate many diverse and powerful sensors, which creates exciting new opportunities for data mining and human-computer interaction. In this paper we show how standard classification algorithms can use labeled smartphone-based accelerometer data to identify the physical activity a user is performing. Our main focus is on evaluating the relative performance of impersonal and personal activity recognition models. Our impersonal (i.e., universal) models are built using training data from a panel of users and are then applied to new users, while our personal models are built with data from each user and then applied only to new data from that user. Our results indicate that the personal models perform dramatically better than the impersonal models—even when trained from only a few minutes worth of data. These personal models typically even outperform hybrid models that utilize both personal and impersonal data. These results strongly argue for the construction of personal models whenever possible. Our research means that we can unobtrusively gain useful knowledge about the habits of potentially millions of users. It also means that we can facilitate human computer interaction by enabling the smartphone to consider context and this can lead to new and more effective applications.

In this study, we propose a method for learning interactions among different types of objects to devise new plans using these objects. Learning is accomplished by observing a given sequence of events with their timestamps and using spatial information on the initial state of the objects in the environment. We assume that no intermediate state information is available about the states of objects. We have used the Incredible Machine game as a suitable domain for analyzing and learning object interactions. When a knowledge base about relations among objects is provided, interactions to devise new plans are learned to a desired extent. Moreover, using spatial information of objects or temporal information of events makes it feasible to learn the conditional effects of objects on each other. Our analyses show that, integrating spatial and temporal data in a spatio-temporal learning approach gives closer results to that of the knowledge-based approach by providing applicable event models for planning. This is promising because gathering spatio-temporal information does not require great amount of knowledge.

We present a model of unsupervised learning in the hybrid SAL (Synthesis of ACT-R and Leabra) architecture. This model follows the hypothesis that higher evaluative cognitive mechanisms can serve to provide training signals for perceptual learning. This addresses the problem that supervised learning seems necessary for strong perceptual performance, but explicit feedback is rare in the real world and difficult to provide for artificial learning systems. The hybrid model couples the perceptual strengths of Leabra with ACT-R's cognitive mechanisms, specifically its declarative memory, to evolve its own symbolic representations of objects encountered in the world. This is accomplished by presenting the objects to the Leabra visual system and committing the resulting representation to ACT-R's declarative memory. Subsequent presentations are either recalled as instances of a previous object category, in which case the positive association with the representation is rehearsed by Leabra, or they cause ACT-R to generate new category labels, which are also subject to the same rehearsal. The rehearsals drive the network's representations to convergence for a given category; at the same time, rehearsals on the ACT-R side reinforce the chunks that encode the associations between representation and label. In this way, the hybrid model bootstraps itself into learning new categories and their associated features; this framework provides a potential approach to solving the symbol grounding problem. We outline the operations of the hybrid model, evaluate its performance on the CU3D-100 (cu3d.colorado.edu) image set, and discuss further potential improvements to the model, including the integration of motor functions as a way of providing an internal feedback signal to augment and guide a purely bottom-up unsupervised system.

In crowdsourced relevance judging, each crowd workertypically judges only a small number of examples,yielding a sparse and imbalanced set of judgments inwhich relatively few workers influence output consensuslabels, particularly with simple consensus methodslike majority voting. We show how probabilistic matrixfactorization, a standard approach in collaborative filtering,can be used to infer missing worker judgments suchthat all workers influence output labels. Given completeworker judgments inferred by PMF, we evaluate impactin unsupervised and supervised scenarios. In thesupervised case, we consider both weighted voting andworker selection strategies based on worker accuracy.Experiments on a synthetic data set and a real turk dataset with crowd judgments from the 2010 TREC RelevanceFeedback Track show promise of the PMF approachmerits further investigation and analysis.

In digital libraries, a table, as a specific document component as well as a condensed way to present structured and relational data, contains rich information and often the only source of .that information. In order to explore, retrieve, and reuse that data, tables should be identified and the data extracted. Table recognition is an old field of research. However, due to the diversity of table styles, the results are still far from satisfactory, and not a single algorithm performs well on all different types of tables. In this paper, we randomly take samples from the CiteSeerX to investigate diverse table styles for automatic table extraction. We find that table headers are one of the main characteristics of complex table styles. We identify a set of features that can be used to segregate headers from tabular data and build a classifier to detect table headers. Our empirical evaluation on PDF documents shows that using a Random Forest classifier achieves an accuracy of 92%.