This paper shows how to improve the recommendations of an interaction-based collaborative filtering (IBCF) recommender used in online dating. Previous work has shown that IBCF works well in this domain, although it tends to rank popular candidates highly, which leads to these users receiving a large number of contacts. We address this problem by using a Decision Tree model as a "critic" to re-rank the candidates generated by IBCF, effectively promoting less popular candidates. This method was first evaluated on historical data from a large online dating site and then trialled live on the same site by providing recommendations to a large number of users throughout a 9 week period. The live trial confirmed the consistency of the analysis on historical data and the ability of the method to generate suitable candidates over an extended period. Our recommendations gave higher success rates than those for a control group made with a baseline recommender.

With rapid profusion of video data, automated surveillanceand intrusion detection is becoming closer to reality. In orderto provide timely responses while limiting false alarms, an intrusiondetection system must balance resources (e.g., time)and accuracy. In this paper, we show how such a system canbe modeled with a partially observable Markov decision process(POMDP), representing possible computer vision filtersand their costs in a way that is similar to human vision systems.The POMDP representation can be optimized to producea dynamic sequence of operations and achieve a tradeoffbetween time and detection quality, taking into accountuncertainty in the filter predictions. In a set of experiments onactual video data, we show that our method can both outperformstatic “expert” models and scale to large dynamic domains.These results suggest that our method could be usedin real-world intrusion detection systems.

This paper describes the development and empirical testing of an intelligent tutoring system (ITS) with two emerging methodologies: (1) a partially observable Markov decision process (POMDP) for representing the learner model and (2) inquiry modeling, which informs the learner model with questions learners ask during instruction. POMDPs have been successfully applied to non-ITS domains but, until recently, have seemed intractable for large-scale intelligent tutoring challenges. New, ITS-specific representations leverage common regularities in intelligent tutoring to make a POMDP practical as a learner model. Inquiry modeling is a novel paradigm for informing learner models by observing rich features of learners’ help requests such as categorical content, context, and timing. The experiment described in this paper demonstrates that inquiry modeling and planning with POMDPs can yield significant and substantive learning improvements in a realistic, scenario-based training task.

Spoken dialogue is increasingly central to systems that assist people. As the tasks that people and machines speak about together become more complex, however, users’ dissatisfaction with those systems is an important concern. This paper presents a novel approach to learning for spoken dialogue systems. It describes embedded wizardry, a methodology for learning from skilled people, and applies it to a library whose patrons order books by telephone. To address the challenges inherent in this application, we introduce RFW+, a domain-independent, feature-selection method that considers feature categories. Models learned with RFW+ on embedded-wizard data improve the performance of a traditional spoken dialogue system.

Introductory engineering courses within large universities often have annual enrollments which can reach up to a thousand students. It is very challenging to achieve differentiated instruction in classrooms with class sizes and student diversity of such great magnitude. Professors can only assess whether students have mastered a concept by using multiple choice questions, while detailed homework assignments, such as planar truss diagrams, are rarely assigned because professors and teaching assistants would be too overburdened with grading to return assignments with valuable feedback in a timely manner. In this paper, we introduce Mechanix, a sketch-based deployed tutoring system for engineering students enrolled in statics courses. Our system not only allows students to enter planar truss and free body diagrams into the system just as they would with pencil and paper, but our system checks the student's work against a hand-drawn answer entered by the instructor, and then returns immediate and detailed feedback to the student. Students are allowed to correct any errors in their work and resubmit until the entire content is correct and thus all of the objectives are learned. Since Mechanix facilitates the grading and feedback processes, instructors are now able to assign free response questions, increasing teacher's knowledge of student comprehension. Furthermore, the iterative correction process allows students to learn during a test, rather than simply displaying memorized information.

One of the key issues for transportation companies is to produce an optimal plan for the work of crew members. Crew planning consists of a sequence of phases, the first two corresponding to planning duties (sequences of trips to be done by crew members from their home base to their home base) and planning rosters (sequences of duties and rest days to be followed by crew members during a certain number of weeks). Both duty and roster planning are subject to a large number of constraints. Duty planning is constrained by intra-duty constraints and roster planning by inter-duty constraints. Since inter-duty constraints relate how duties can be combined into a roster, it is desirable that some of these constraints be transposed into the duty planning phase, as additional constraints, to guarantee that the duties produced in the first phase are "rosterable'' in the second phase. Both Artificial Intelligence (AI) and Operations Research (OR) have addressed duty planning, but for very large scale problems, OR has been far more successful due to its global vision of the problem. This paper discusses the use of AI local search to improve an OR-based duty planning optimizer that uses additional constraints.

The aims of this workshop are to (1) Draw the attention of the AI community to the research challenges and opportunities in semantic cities. (2) Draw the attention on the multidisciplinary dimension and its impact on semantic cities such as transportation, energy, water management. (3) Identify unique issues of this domain and what new techniques may be needed. As example, since governments and citizens are involved data security and privacy are first-class concerns (4) Promoting more cities to become semantic cities (5) Elaborating a (semantic data) benchmark for testing AI techniques on semantic cities. (6) Provide a platform for sharing best-practices and discussion.

Goal-driven automated composition of software components is an important problem with applications in Web service composition and stream processing systems. The popular approach to address this problem is to build the composition automatically using Artificial Intelligence planning. However, it is shown that some of these popular planning approaches may neither be feasible nor scalable for many real large-scale flow-based applications. Recent advances have proven that the automated composition problem can take advantage of expert knowledge restricting the ways in which different reusable components can be composed. This knowledge can be represented using an extensible composition template or pattern. In prior work, a flow pattern language called Cascade and its corresponding specialized planner have shown the best performance in these domains. In this paper, we propose to address this problem using Hierarchical Task Network (HTN) planning. To this end, we propose an automated approach of creating an HTN-based problem from the Cascade representation of the flow patterns. The resulting technique not only allows us to use the HTN planning paradigm and its many advantages including added expressivity but also enables optimization and customization of composition with respect to preferences and constraints. Further, we propose and develop a lookahead heuristic and show that it significantly reduces the planning time. We have performed extensive experimentation in the context of the stream processing application and evaluated applicability and performance of our approach.

This paper presents a prototype system called SFplanner which uses an automated planning technique to generate workflows for reconfiguring a computing infrastructure. The system allows an administrator to specify a configuration task which consists of current state, desired state and global constraints. This task is compiled to a grounded finite-domain representation as the input for the standard (unmodified) Fast-Downward planner in order to automatically generate a workflow. The execution of the workflow will bring the system into the desired state, preserving the global constraints at every stage of the workflow.

Recently, there has been a growing interest in multiagent path planning (MAPF). Applications include vehicle fleet coordination, computer games, robotics, and various military scenarios. Some researchers have worked at a theoretical level, while others implemented solvers to specific applications. Consequently, similar concepts were developed in different subcommunities, using varying terminology.