Detecting abnormal activities from sensor readings is an important research problem in activity recognition. A number of different algorithms have been proposed in the past to tackle this problem. Many of the previous state-based approaches suffer from the problem of failing to decide the appropriate number of states, which are difficult to find through a trial and-error approach, in real-world applications. In this paper, we propose an accurate and flexible framework for abnormal activity recognition from sensor readings that involves less human tuning of model parameters. Our approach first applies a Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM), which supports an infinite number of states, to automatically find an appropriate number of states. We incorporate a Fisher Kernel into the One-Class Support Vector Machine (OCSVM) model to filter out the activities that are likely to be normal. Finally, we derive an abnormal activity model from the normal activity models to reduce false positive rate in an unsupervised manner. Our main contribution is that our proposed HDP-HMM models can decide the appropriate number of states automatically, and that by incorporating a Fisher Kernel into the OCSVM model, we can combine the advantages from generative model and discriminative model. We demonstrate the effectiveness of our approach by using several real-world datasets to test our algorithm’s performance.

In this paper, we present a method that uses web photos for measuring frame interestingness of a travel video. Web photo collections, such as those on Flickr, tend to contain interesting images because their images are more carefully taken, composed, and selected. Because these photos have already been chosen as subjectively interesting, they serve as evidence that similar images are also interesting. Our idea is to leverage these web photos to measure the interestingness of video frames. Specifically, we measure the interestingness of each video frame according to its similarity to web photos. The similarity is defined based on the scene content and composition. We characterize the scene content using scale invariant local features, specifically SIFT keypoints. We characterize composition by feature distribution. Accordingly, we measure the similarity between a web photo and a video frame based on the co-occurrence of the SIFT features, and the similarity between their spatial distribution. Interestingness of a video frame is measured by considering how many photos it is similar to, and how similar it is to them. Our experiments on measuring frame interestingness of videos from YouTube using photos from Flickr show the initial success of our method.

Deciding consistency of constraint networks is a fundamental problem in qualitative spatial and temporal reasoning. In this paper we introduce a divide-and-conquer method that recursively partitions a given problem into smaller sub-problems in deciding consistency. We identify a key theoretical property of a qualitative calculus that ensures the soundness and completeness of this method, and show that it is satisfied by the Interval Algebra (IA) and the Point Algebra (PA). We develop a new encoding scheme for IA networks based on a combination of our divide-and-conquer method with an existing encoding of IA networks into SAT. We empirically show that our new encoding scheme scales to much larger problems and exhibits a consistent and significant improvement in efficiency over state-of-the-art solvers on the most difficult instances.

Event detection is a critical task in sensor networks for a variety of real-world applications. Many real-world events often exhibit complex spatio-temporal patterns whereby they manifest themselves via observations over time and space proximities. These spatio-temporal events cannot be handled well by many of the previous approaches. In this paper, we propose a new Spatio-Temporal Event Detection (STED) algorithm in sensor networks based on a dynamic conditional random field (DCRF) model. Our STED method handles the uncertainty of sensor data explicitly and permits neighborhood interactions in both observations and event labels. Experiments on both real data and synthetic data demonstrate that our STED method can provide accurate event detection in near real time even for large-scale sensor networks.

Understanding the computational complexity of manipulation in elections is arguably the most central agenda in Computational Social Choice. One of the influential variations of the the problem involves a coalition of manipulators trying to make a favorite candidate win the election. Although the complexity of the problem is well-studied under the assumption that the voters are weighted, there were very few successful attempts to abandon this strong assumption. In this paper, we study the complexity of the unweighted coalitional manipulation problem (UCM) under several prominent voting rules. Our main result is that UCM is NP-complete under the maximin rule; this resolves an enigmatic open question. We then show that UCM is NP-complete under the ranked pairs rule, even with respect to a single manipulator. Furthermore, we provide an extreme hardness-of-approximation result for an optimization version of UCM under ranked pairs. Finally, we show that UCM under the Bucklin rule is in P.

Past approaches for solving MDPs have several weaknesses: 1) Decision-theoretic computation over the state space can yield optimal results but scales poorly. 2) Value-function approximation typically requires human-specified basis functions and has not been shown successful on nominal ("discrete") domains such as those in the ICAPS planning competitions. 3) Replanning by applying a classical planner to a determinized domain model can generate approximate policies for very large problems but has trouble handling probabilistic subtlety.  This paper presents ReTrASE, a novel MDP solver, which combines decision theory, function approximation and classical planning in a new way. ReTrASE uses classical planning to create basis functions for value-function approximation and applies expected-utility analysis to this compact space. Our algorithm is memory-efficient and fast (due to its compact, approximate representation), returns high-quality solutions (due to the decision-theoretic framework) and does not require additional knowledge from domain engineers (since we apply classical planning to automatically construct the basis functions). Experiments demonstrate that ReTrASE outperforms winners from the past three probabilistic-planning competitions on many hard problems.

Real-time dynamic programming (RTDP) solves Markov decision processes (MDPs) when the initial state is restricted, by focusing dynamic programming on the envelope of states reachable from an initial state set. RTDP often provides performance guarantees without visiting the entire state space.  Building on RTDP, recent work has sought to improve its efficiency through various optimizations, including maintaining upper and lower bounds to both govern trial termination and prioritize state exploration. In this work, we take a Bayesian perspective on these upper and lower bounds and use a value of perfect information (VPI) analysis to govern trial termination and exploration in a novel algorithm we call VPI-RTDP.  VPI-RTDP leads to an improvement over state-of-the-art RTDP methods, empirically yielding up to a three-fold reduction in the amount of time and number of visited states required to achieve comparable policy performance.

In many real-world planning scenarios, the users are interested in optimizing multiple objectives (such as makespan and execution cost), but are unable to express their exact tradeoff between those objectives. When a planner encounters such partial preference models, rather than look for a single optimal plan, it needs to present the pareto set of plans and let the user choose from them. This idea of presenting the full pareto set is fraught with both computational and user-interface challenges. To make it practical, we propose the approach of finding a representative subset of the pareto set. We measure the quality of this representative set using the Integrated Convex Preference (ICP) model, originally developed in the OR community. We implement several heuristic approaches based on the Metric-LPG planner to find a good solution set according to this measure. We present empirical results demonstrating the promise of our approach.

Decomposition is an effective technique for solving discrete Constraint Optimization Problems (COPs) with low tree-width. On problems with high treewidth, however, existing decomposition algorithms offer little advantage over branch and bound search (B&B). In this paper we propose a method for exploiting decomposition on problems with high treewidth. Our technique involves modifying B&B to detect and exploit decomposition on a selected subset of the problem’s objectives. Decompositions over this subset, generated during search, are exploited to compute tighter bounds allowing B&B to prune more of its search space. We present a heuristic for selecting an appropriate subset of objectives—one that readily decomposes during search and yet can still provide good bounds. We demonstrate empirically that our approach can significantly improve B&B’s performance and outperform standard decomposition algorithms on a variety of high tree-width problems.

Knowledge-based recommenders support users in the identification of interesting items from large and potentially complex assortments. In cases where no recommendation could be found for a given set of requirements, such systems propose explanations that indicate minimal sets of faulty requirements. Unfortunately, such explanations are not personalized and do not include repair proposals which triggers a low degree of satisfaction and frequent cancellations of recommendation sessions. In this paper we present a personalized repair approach that integrates the calculation of explanations with collaborative problem solving techniques. In order to demonstrate the applicability of our approach, we present the results of an empirical study that show significant improvements in the accuracy of predictions for interesting repairs.