High throughput genetic sequencing arrays with thousands of measurements per sample and a great amount of related censored clinical data have increased demanding need for better measurement specific model selection. In this paper we establish strong oracle properties of nonconcave penalized methods for nonpolynomial (NP) dimensional data with censoring in the framework of Cox's proportional hazards model. A class of folded-concave penalties are employed and both LASSO and SCAD are discussed specifically. We unveil the question under which dimensionality and correlation restrictions can an oracle estimator be constructed and grasped. It is demonstrated that nonconcave penalties lead to significant reduction of the "irrepresentable condition" needed for LASSO model selection consistency. The large deviation result for martingales, bearing interests of its own, is developed for characterizing the strong oracle property. Moreover, the nonconcave regularized estimator, is shown to achieve asymptotically the information bound of the oracle estimator. A coordinate-wise algorithm is developed for finding the grid of solution paths for penalized hazard regression problems, and its performance is evaluated on simulated and gene association study examples.

In the Silver Anniversary year of FLAIRS, in an effort to promote discussion of emerging ideas and work in order to encourage and help guide researchers, especially new researchers, the program committee added the poster abstract submission category. This allows researchers to present a full poster in the conference poster session and receive that critical, work-shaping feedback that helps guide good work into great work.

In recent years there has been a significant decline in the number of college students choosing majors in computer science or technology related fields. Although this trend is beginning to turn around at the undergraduate level, there remains disparity in the number of under-represented minority students who earn graduate degrees as compared to majority students. Additionally, within the United States, there is an achievement gap between under-represented minority students and majority students at a time when underrepresented groups are becoming an increasing proportion of the national labor force. This reluctance to study Science, Technology, Engineering, and Mathematics (STEM) disciplines must be confronted and changed if the United States is to maintain a competitive position within the global market. Effective use of learning technologies is vital to solving many of our current STEM learning challenges. Robotics is a growing research area in computer science education. We use robotics as a technology tool captivate and engage students in research in robotics.

Search algorithms such as Rapidly-exploring Random Trees (RRTs) are common in robot programming. Including graphical representations of the output of these algorithms in a robotics framework can make the algorithms more accessible to students, and can also help programmers analyze and account for unexpected results. For this project, we used the Tekkotsu open source robot programming framework, available at Tekkotsu.org. We extended Tekkotsu’s graphical user interface for displaying vision data and maps to also display the output of an RRT search. We created several demos using two types of searches: one from a navigation path planner, and one from an arm path planner. In some cases the search had no solution, and the graphical output helped to illustrate why. This confirms the utility of the RRT visualization for explaining unexpected search results. We expect that this tool will also contribute to improved student understanding of the search algorithm.

Psychosocial assessments and treatments are effective for a range of psychological problems.One particular area of concern is youth suicide. This paper reports on the SAMHT intelligent tutoring system, which provides youth suicide risk assessment training.SAMHT's interactive avatar interface is based on an intelligent backend, and provides a believable interaction that is effective for training mental health professionals.

Reading tutors can provide an unprecedented opportunity to collect and analyze large amounts of data for understanding how students learn. We trained models of oral reading prosody (pitch, intensity, and duration) on a corpus of narrations of 4558 sentences by 11 fluent adults. We used these models to evaluate the oral reading prosody of 85,209 sentences read by 55 children (mostly) 7-10 years old who used Project LISTEN's Reading Tutor during the 2005-2006 school year. We mined the resulting data to pinpoint the specific common syntactic and lexical features of text that children scored best and worst on. These features predict their fluency and comprehension test scores and gains better than previous models. Focusing on these features may help human or automated tutors improve children’s fluency and comprehension more effectively.

Modeling skills are essential during the process of learning programming. ITS systems for modeling are typically hard to build due to the ill-definedness of most modeling tasks. This paper presents a system that can teach UML skills to novice programmers. The system is “simple and cheap” in the sense that it only requires an expert solution against which the student solutions are compared, but still flexible enough to accommodate certain degrees of solution flexibility and variability that are characteristic of modeling tasks. An empirical evaluation via a controlled lab study showed that the system worked fine and, while not leading to significant learning gains as compared to a control condition, still revealed some promising results.

Grimes and Warschauer (2010) describe two accuracy (Warschauer & Ware, 2006), there have been kinds of systems: automated essay scoring (AES) and relatively few evaluations of student improvement (e.g., automated writing evaluation (AWE). AES systems strive Kellogg, Whiteford, & Quinlan, 2010) or the role of to assign accurate and reliable scores to essays or specific feedback (e.g., Roscoe, Varner, Cai, Weston, Crossley, & writing features (e.g., mechanics). Scores are generated McNamara, 2011). Hence, in this paper, we explore and using various artificial intelligence (AI) methods, including describe a method for developing pedagogically-guided statistical modeling, natural language processing (NLP), algorithms that guide formative feedback in an intelligent and Latent Semantic Analysis (LSA) (Shermis & Burstein, tutor system (ITS) for writing.

In the area of student knowledge assessment, knowledge tracing is a model that has been used for over a decade to predict student knowledge and performance. Many modifications to this model have been proposed and evaluated, however, the modifications are often based on a combination of intuition and experience in the domain. This method of model improvement can be difficult for researchers without high level of domain experience and furthermore, the best improvements to the model could be unintuitive ones. Therefore, we propose a completely data driven approach to model improvement. This alternative allows for researchers to evaluate which aspects of a model are most likely to result in model performance improvement. Our results suggest a variety of different improvements to knowledge tracing many of which have not been explored.

Concept maps are frequently used in K-12 educational settings. The purpose of this study is to determine whether students’ performance on interactive concept map tasks in Guru, an intelligent tutoring system, is related to immediate and delayed learning outcomes. Guru is a dialogue-based system for high-school biology that intersperses concept map tasks within the tutorial dialogue. Results indicated that when students first attempt to complete concept maps, time spent on the maps may be a good indicator of their understanding, whereas the errors they make on their second attempts with the maps may be an indicator of the knowledge they are lacking.  This pattern of results was observed for one cycle of testing, but not replicated in a second cycle. Differences in the findings for the two testing cycles are most likely due to topic variations.