Research on individual differences indicates that students vary in how they interact with and perform while using intelligent tutoring systems (ITSs). However, less research has investigated how individual differences affect students’ interactions with game-based features. This study examines how learning outcomes and interactions with specific game-based features (off-task personalization vs. on-task mini games) within a game-based ITS, iSTART-ME, vary as a function of students’ performance orientation. The current study (n=40) is part of a larger study (n=126) conducted with high school students. The analyses in this study focus on those students assigned to iSTART-ME. Results indicate that students with higher levels of performance orientation perform better during training, progress further within the system, and interact less frequently with off-task game-based features. These results provide further evidence that individual differences play an important role in influencing students’ interactions and achievement within learning environments.

A very promising tool for data mining and bioinformatics is ensemble gene (feature) selection. Ensemble feature selection is the process of performing multiple runs of feature selection and then aggregating the results into a final ranked list. However, a central question of ensemble feature selection is how to aggregate the individual results into a single ranked feature list. There are a number of techniques available, ranging from simple to complex; the question is which one to choose. This paper is a comprehensive study on the use of nine different rank aggregation techniques for building classification models to use gene microarray data for distinguishing between cancerous and non-cancerous cells (or between patients who did or did not respond well to cancer treatment). The techniques are tested using an ensemble with twenty-five feature selection techniques and fifty iterations along with eleven bioinformatics datasets and five learners. Our results show that Lowest Rank is the worst performing aggregation technique by a clear margin. The other techniques perform similarly well and a simple technique (e.g., Mean aggregation) is preferable due to computation time and the limited possible benefit of a more complex technique. To our knowledge there has never been a study this intensive on the classification abilities of rank aggregation techniques in the field of bioinformatics.

We investigate a method for applying CBR to a source of data where there are no negative exemplars. Our problem domain is one of recommending characteristics of multidisciplinary collaborators based on a collection of funded grants. Thus, there are no negative exemplars. Lacking sufficient domain knowledge, we seek to apply a feedback algorithm to learn weights even in the absence of negative exemplars. Our approach is based on the assumption that well aligned cases, cases where similar problems have similar solutions, are better suited for learning feature weights. Our approach clusters the problem and solution spaces separately to identify well aligned cases. We also identify poorly aligned cases that may hinder effective learning of weights, and exclude them. The clusters of well aligned cases provide a means to utilize feedback algorithms. We use two methods, case alignment and case cohesion, to show that our approach succeeds in identifying well aligned cases. We also compare our approach to a method based on single class learning, a machine learning approach for reasoning without negatives. Our results show that our approach is viable to learning weight in the absence of negative exemplars.

One of the major challenges in bioinformatics is selecting the appropriate genes for a given problem, and moreover, choosing the best gene selection technique for this task. Many such techniques have been developed, each with its own characteristics and complexities. Recently, some works have addressed this by introducing ensemble gene selection, which is the process of performing multiple runs of gene selection and aggregating the results into a single final list. The question is, will ensemble gene selection improve the results over those obtained when using single gene selection techniques (e.g., filter-based gene selection techniques on their own without any ensemble approach)? We compare how five filter-based feature (gene) selection techniques work with and without a data diversity ensemble approach (using a single feature selection technique on multiple sampled datasets created from an original one) when used for building models to label cancerous cells (or predict cancer treatment response) based on gene expression levels. Eleven bioinformatics (gene microarray) datasets are employed, along with four feature subset sizes and five learners. Our results show that the techniques Fold Change Ratio and Information Gain will produce better classification results when an ensemble approach is applied, while Probability Ratio and Signal-to-Noise will, in general, perform better without the ensemble approach. For the Area Under the ROC (Receiver Operating Characteristics) Curve ranker, the classification results are similar with or without the ensemble approach. This is, to our knowledge, the first paper to comprehensively examine the difference between the ensemble and single approaches for gene selection in the biomedical and bioinformatics domains.

Goal-driven autonomy is a framework for intelligent agents that automatically formulate and manage goals in dynamic environments, where goal formulation is the task of identifying goals that the agent should attempt to achieve. We argue that goal formulation is central to high-level autonomy, and explain why identifying domain-independent heuristics for this task is an important research topic in high-level control. We describe two novel domain-independent heuristics for goal formulation (motivators) that evaluate the utility of goals based on the projected consequences of achieving them. We then describe their integration in M-ARTUE, an agent that balances the satisfaction of internal needs with the achievement of goals introduced externally. We assess its performance in a series of experiments in the Rovers With Compass domain. Our results show that using domain-independent heuristics yields performance comparable to using domain-specific knowledge for goal formulation. Finally, in ablation studies we demonstrate that each motivator contributes significantly to M-ARTUE’s performance.

We propose and develop a simple and efficient algorithm for generating extractive multi-document summaries and show that this algorithm exhibits state-of-the-art or near state-of-the-art performance on two Document Understanding Conference datasets and two Text Analysis Conference datasets. Our results show that algorithms using simple features and computationally efficient methods are competitive with much more complex methods for multi-document summarization (MDS). Given these findings, we believe that our summarization algorithm can be used as a baseline in future MDS evaluations. Further, evidence shows that our system is near the upper limit of performance for extractive MDS.

Support vector machines (SVMs) are among the most used methods for pattern recognition. Acceptable results have been obtained with such methods in many domains and applications. However, as most learning algorithms, SVMs have hyperparameters that influence the effectiveness of the generated model. Thus, choosing adequate values for such hyperparameters is critical in order to obtain satisfactory results for a given classification task, a problem known as model selection. This paper introduces a novel model selection approach for SVMs based on multi-objective optimization and on the bias and variance definition. We propose an evolutionary algorithm that aims to select the configuration of hyperparameters that optimizes a trade-off between estimates of bias and variance; two factors that are closely related to the model accuracy and complexity. The proposed technique is evaluated using a suite of benchmark data sets for classification. Experimental results show the validity of our approach. We found that the model selection criteria resulted very helpful for selecting highly effective classification models.

The thalamus is a critical brain structure involved in gating and regulating the flow of sensory and cortical information. The reticular nucleus of the thalamus (TRN) sends inhibitory projections to the thalamic relay nuclei instead of projecting to the cortex as the other thalamic nuclei do. These inhibitory projections endow the TRN with the functionality to modulate and control cortical information flowing through the thalamus. Yet, the functional roles of the TRN and thalamus in high-level cognitive processing, such as spatial reasoning and decision-making, remains poorly understood. Neurocognitive models offer a framework to explore the high-level cognitive functions of the thalamus and TRN. Here, we investigate the functional roles of the thalamus and TRN in high-level cognitive tasks using a large-scale neurocognitive model called ICArUS-MINDS. Our results demonstrate distributed and parallel top-down executive control of semantic and spatial cortical information. Specifically, we observed reticular-thalamic inhibitory gating of spatial and semantic information through top-down task switching control during reasoning, decision making and recall. Thalamic-gating was critical for orchestrating processing sequences of task-dependent switches between cortical sources and targets. These results are an important first step in simulating and understanding the functional roles and behaviors of the thalamic brain system in high-level cognitive processing.

Author identification is a subfield of Natural Language Processing (NLP) that uses machine learning techniques to identify the author of a text. Most previous research focused on long texts with the assumption that a minimum text length threshold exists under which author identification would no longer be effective. This paper examines author identification in short texts far below this threshold, focusing on messages retrieved from Twitter (maximum length: 140 characters) to determine the most effective feature set for author identification. Both Bag-of-Words (BOW) and Style Marker feature sets were extracted and evaluated through a series of 15 experiments involving up to 12 authors with large and small dataset sizes. Support Vector Machines (SVM) were used for all experiments. Our results achieve classification accuracies approaching that of longer texts, even for small dataset sizes of 60 training instances per author. Style Marker feature sets were found to be significantly more useful than BOW feature sets as well as orders of magnitude faster, and are therefore suggested for potential applications in future research.

There is an estimated 150 million children worldwide living with a disability. For many of these children in the U.S., physical therapy is provided as an intervention mechanism to support the child’s academic, developmental, and functional goals from birth and beyond. Typically, for a physical therapy intervention to be adopted, there must be sufficient evidence-based practices showing the efficacy of the given method in use with the target demographic. With the recent advances in robotics, therapeutic intervention protocols using robots is ideally positioned to make an impact in this domain. Unfortunately, there has not yet been sufficient evidence-based research focused on the use of robots in child-based therapy to result in a full systematic review of this area. As such, in this paper we provide a review of the emerging role of robotics in pediatric therapy, with the goal of summarizing the research that could possibly transition into providing evidence on the efficacy of robotic therapeutic interventions for children.