As computational agents are increasingly used beyond research labs, their success will depend on their ability to learn new skills and adapt to their dynamic, complex environments. If human users — without programming skills — can transfer their task knowledge to the agents, learning rates can increase dramatically, reducing costly trials. The TAMER framework guides the design of agents whose behavior can be shaped through signals of approval and disapproval, a natural form of human feedback. Whereas early work on TAMER assumed that the agent's only feedback was from the human teacher, this paper considers the scenario of an agent within a Markov decision process (MDP), receiving and simultaneously learning from both MDP reward and human reinforcement signals. Preserving MDP reward as the determinant of optimal behavior, we test two methods of combining human reinforcement and MDP reward and analyze their respective performances. Both methods create a predictive model, H-hat, of human reinforcement and use that model in different ways to augment a reinforcement learning (RL) algorithm. We additionally introduce a technique for appropriately determining the magnitude of the model's influence on the RL algorithm throughout time and the state space.

A major public health challenge is to develop large-scale health communication interventions that are successful with diverse and vulnerable audiences. Participatory design approaches are critical to create communication programs that are relevant to people’s literacy, language, culture, access and functional needs. Further, there are powerful synergies in linking participatory design and artificial intelligence methods. This paper focuses on traditional weaknesses of health communication, and participatory design strategies and models that can be used by developers, researchers and health practitioners.

A recent direction within belief revision theory is to develop a theory of belief change for the Horn knowledge representation framework. We consider questions related to the complexity aspects of previous work, leading to questions about Horn envelopes (or Horn LUB’s), introduced earlier in the context of knowledge compilation. A characterization is obtained of the remainders of a Horn be- lief set with respect to a consequence to be contracted, as the Horn envelopes of the belief set and an elementary conjunction corresponding to a truth assignment satisfying a certain body building formula. This gives an efficient algorithm to generate all remainders, each represented by a truth assignment. On the negative side, examples are given of Horn belief sets and consequences where Horn formulas representing the result of most contraction operators, based either on remainders or on weak remainders, must have exponential size.

After a hospitalization, approximately 1 out of 5 patients will suffer from an adverse event, and one-third of these complications are preventable. Having a pharmacist follow-up with patients a few days after leaving the hospital has been shown to significantly reduce re-hospitalizations and adverse drug events. In this work, we describe our design for an Embodied Conversational Agent system for longitudinal, post-hospitalization follow-up. We discuss how best-practice follow-up interactions between patients and clinical pharmacists inform the design of our system, focusing on the strategies used by the pharmacist to detect and resolve issues that have occurred post-hospitalization.

We present an approach to integrating rules and ontologies on the basis of the first-order stable model semantics proposed by Ferraris, Lee and Lifschitz. We show that some existing integration proposals can be uniformly reformulated in terms of the first-order stable model semantics. The reformulations are simpler than the original proposals in the sense that they do not refer to grounding.

Inspired by the Rapidly Exploring Random Tree data-structure and algorithm for path planning in high-dimensional, continuous spaces, we consider an approach for spanning a space with a group of simple robots. We employ a minimalist approach in which InfraRed and contact sensors form the primary means of communication; the agents physically embody the elements of the tree through their position and other agents can either follow the tree to useful locations or expand the tree by becoming part of it. Although robots are constrained in some of the operations they may perform in space, we argue that our approach remains consistent with the original data-structure. We demonstrate that one may perform a planning query from a point to the tree origin directly via message passing where passing involves direct physical motion or simple IR messages. Based on the work done by Werger and Matarić , our implementation proves that it is possible to form and maintain a RRT using simple position unaware robots. The work is important because it demonstrates that decentralized path planning can be performed by simple agents using purely reactive behaviors and at the same time poses significant challenges to keep the shape of the tree intact.

Processing high-density clinical signal data (data from biomedical sensors deployed in the clinical environment) is resource intensive and time consuming. We propose a novel approach to storing and processing clinical signal data based on the Apache HBase distributed column-store and the MapReduce programming paradigm with an integrated web-based data visualization layer. An integrated solution negates the need to marshal data into and out of the storage system while also easily parallelizing the computation, a problem that is becoming more and more important due to increasing numbers of sensors and resulting data. We estimate upwards of 50TB of clinical signal data for a 200-bed medical center within the next 5 years. Consequently, efficient processing of clinical signal data is a vital step towards multivariate analysis of the signal data in order to develop better ways of describing a patient’s clinical status.

We present an ontology consisting of a theory of spatial dimension and a theory of dimension-independent mereological and topological relations in space. Though both are fairly weak axiomatizations, their interplay suffices to define various mereotopological relations and to make any necessary dimension constraints explicit. We show that models of the INCH Calculus and the Region-Connection Calculus (RCC) can be obtained from extensions of the proposed ontology.

Sustainability requires emphasizing the importance of environmental causes and effects among design knowledge from heterogeneous stakeholders to make a sustainable decision. Recently, such causes and effects have been well developed in ontological representation, which has been challenged to generate and integrate multiple domain knowledge due to its domain specific characteristics. Moreover, it is too challengeable to represent heterogeneous, domain-specific design knowledge in a standardized way. Causal knowledge can meet the necessity of knowledge integration in domains. Therefore, this paper aims to develop a causal knowledge integration system with the authors’ previous mathematical causal knowledge representation.

Sustainable building design is a complex social and technical process in which a broad range of stakeholders must construct and clearly communicate high quality design spaces. This paper summarizes recent assessments of current practice that illustrate how far industry today is from achieving this quality and clarity. Efforts to develop a platform of tools to address these limitations are discussed. PIP helps people communicate, share, and understand collaborative design processes; MACDADI helps project teams identify and manage rationale and consensus on decisions; Design Scenarios helps them generate requirements-driven alternative spaces, BIM, model-based analysis, and PIDO which helps to systematically assess these alternatives for their energy, daylight, structural, and cost impacts; and iRooms and the web, which help to communicate all of this information to engage designers, stakeholders, and decision makers in fast, multidisciplinary design and analysis processes. This new platform considerably improves the quality and clarity of AEC design spaces. However additional work would enable significant additional improvement. The paper concludes with a proposal for how AI might further improve the performance of this platform.