Within multiagent teams research, existing approaches commonly assume agents have perfect knowledge regarding the decision process guiding their teammates' actions. More recently, ad hoc teamwork was introduced to address situations where an agent must coordinate with a variety of potential teammates, including teammates with unknown behavior. This paper examines the communication of intentions for enhanced coordination between such agents. The proposed decision-theoretic approach examines the uncertainty within a model of an unfamiliar teammate, identifying policy information valuable to the collaborative effort. We characterize this capability through theoretical analysis of the computational requirements as well as empirical evaluation of a communicative agent coordinating with an unknown teammate in a variation of the multiagent pursuit domain.

The hospital readmission rate of patients within 30 days after discharge is broadly accepted as a healthcare quality measure and cost driver in the United States. The ability to estimate hospitalization costs alongside 30 day risk-stratification for such readmissions provides additional benefit for accountable care, now a global issue and foundation for the U.S.~government mandate under the Affordable Care Act. Recent data mining efforts either predict healthcare costs or risk of hospital readmission, but not both. In this paper we present a dual predictive modeling effort that utilizes healthcare data to predict the risk and cost of any hospital readmission (``all-cause''). For this purpose, we explore machine learning algorithms to do accurate predictions of healthcare costs and risk of 30-day readmission.Results on risk prediction for ``all-cause'' readmission compared to the standardized readmission tool (LACE) are promising, and the proposed techniques for cost prediction consistently outperform baseline models and demonstrate substantially lower mean absolute error (MAE).

Multiple concurrent physiological streams generated by various medical devices play important roles in patient condition assessment. However, these physiological streams needto be analyzed together and output in real-time for preciseand timely controlling and management, which poses a non-trivial challenge to existing methods. This paper presents ourresearch on real-time assessing based on this kind of data.To address this problem, we first extract sketches from original data with the help of adaptive sampling and wave splittingalgorithm, then define scalable operators on sketches and propose MUNCA (MUlti-dimensional Nearest Center Analysis)to combine these multiple concurrent data together for anal-ysis. Experiments on real data demonstrate the effectiveness and efficiency of the proposed method.

Constrained sampling and counting are two fundamental problems in artificial intelligence with a diverse range of applications, spanning probabilistic reasoning and planning to constrained-random verification. While the theory of these problems was thoroughly investigated in the 1980s, prior work either did not scale to industrial size instances or gave up correctness guarantees to achieve scalability. Recently, we proposed a novel approach that combines universal hashing and SAT solving and scales to formulas with hundreds of thousands of variables without giving up correctness guarantees. This paper provides an overview of the key ingredients of the approach and discusses challenges that need to be overcome to handle larger real-world instances.

2QBF is a special case of general quantified Boolean formulae (QBF). It is limited to just two quantification levels, i.e., to a form forall-exists. Despite this limitation it applies to a wide range of applications, e.g., to artificial intelligence, graph theory, synthesis, etc.. Recent research showed that CEGAR-based methods give a performance boost to QBF solving (e.g, compared to QDPLL). Conjunctive normal form (CNF) is a commonly accepted representation for both SAT and QBF problems; however, it does not reflect the circuit structure that might be present in the problem. Existing attempts of extracting this structure from CNF and using it in 2QBF context do not show advantages over CNF based 2QBF solvers. In this work we introduce a new workflow for 2QBF, containing a new semantic circuit extraction algorithm and a CEGAR-based 2QBF solver that uses circuit structure and is improved by a so-called "cofactor sharing'' heuristics. We evaluate the proposed methodology on a range of benchmarks and show the practicality of the new approach.

Emerging smart buildings, such as the NASA Sustainability Base (SB), have a broad range of energy-related systems, including systems for heating and cooling. While the innovative technologies found in SB and similar smart buildings have the potential to increase the usage of renewable energy, they also add substantial technical complexity. Consequently, managing a smart building can be a challenge compared to managing a traditional building, sometimes leading to adverse events including unintended thermal discomfort of occupants (“too hot” or “too cold”). Fortunately, today’s smart buildings are typically equipped with thousands of sensors, controlled by Building Automation Systems (BASs). However, manually monitoring a BAS time series data stream with thousands of values may lead to information overload for the people managing a smart building. We present here a novel technique, Scalable Causal Learning (SCL), that integrates dimensionality reduction and Bayesian network structure learning techniques. SCL solves two problems associated with the naive application of dimensionality reduction and causal machine learning techniques to BAS time series data: (i) using autoregressive methods for causal learning can lead to induction of spurious causes and (ii) inducing a causal graph from BAS sensor data using existing graph structure learning algorithms may not scale to large data sets. Our novel SCL method addresses both of these problems. We test SCL using time series data from the SB BAS, comparing it with a causal graph learning technique, the PC algorithm. The causal variables identified by SCL are effective in predicting adverse events, namely abnormally low room temperatures, in a conference room in SB. Specifically, the SCL method performs better than the PC algorithm in terms of false alarm rate, missed detection rate and detection time.

A major challenge in cyber-threat analysis is combining information from different sources to find the person or the group responsible for the cyber-attack. It is one of the most important technical and policy challenges in cyber-security. The lack of ground truth for an individual responsible for an attack has limited previous studies. In this paper, we overcome this limitation by building a dataset from the capture-the-flag event held at DEFCON, and propose an argumentation model based on a formal reasoning framework called DeLP (Defeasible Logic Programming) designed to aid an analyst in attributing a cyber-attack to an attacker. We build argumentation-based models from latent variables computed from the dataset to reduce the search space of culprits (attackers) that an analyst can use to identify the attacker. We show that reducing the search space in this manner significantly improves the performance of classification-based approaches to cyber-attribution.

Most modern network-based intrusion detection systems (IDSs) passively monitor network traffic to identify possible attacks through known vectors. Though useful, this approach has widely known high false positive rates, often causing administrators to suffer from a "cry wolf effect," where they ignore all warnings because so many have been false. In this paper, we focus on a method to reduce this effect using an idea borrowed from computer vision and neuroscience called active perception. Our approach is informed by theoretical ideas from decision theory and recent research results in neuroscience. The active perception agent allocates computational and sensing resources to (approximately) optimize its Value of Information. To do this, it draws on models to direct sensors towards phenomena of greatest interest to inform decisions about cyber defense actions. By identifying critical network assets, the organization's mission measures self-interest (and value of information). This model enables the system to follow leads from inexpensive, inaccurate alerts with targeted use of expensive, accurate sensors. This allows the deployment of sensors to build structured interpretations of situations. From these, an organization can meet mission-centered decision-making requirements with calibrated responses proportional to the likelihood of true detection and degree of threat.

A key front for ethical questions in artificial intelligence, and computer science more generally, is teaching students how to engage with the questions they will face in their professional careers based on the tools and technologies we teach them.  In past work (and current teaching) we have advocated for the use of science fiction as an appropriate tool which enables AI researchers to engage students and the public on the current state and potential impacts of AI. We present teaching suggestions for E.M. Forster's 1909 story, "The Machine Stops," to teach topics in computer ethics.  In particular, we use the story to examine ethical issues related to being constantly available for remote contact, physically isolated, and dependent on a machine --- all without mentioning computer games or other media to which students have strong emotional associations. We give a high-level view of common ethical theories and indicate how they inform the questions raised by the story and afford a structure for thinking about how to address them.

The focus of this work is to investigate how children's perception of the robot changes with age and gender, and to enable the robot to adapt to these differences for improving human-robot interaction (HRI). We propose a neural network-based learning architecture to estimate children's age and gender based on the body motion performing a set of actions. To evaluate our system, we collected a fully annotated depth dataset of 28 children (aged between 7 and 16 years old) and applied it to a learning-based method for age and gender estimation by modeling children's 3D skeleton motion data. We discuss our results that show an average accuracy of 95.2% and 90.3% for age and gender respectively in the context of a real-world scenario.