John S. Kinnebrew

Integrating computational thinking with K-12 science education using agent-based computation: A theoretical framework

Computational thinking (CT) draws on concepts and practices that are fundamental to computing and computer science. It includes epistemic and representational practices, such as problem representation, abstraction, decomposition, simulation, verification, and prediction. However, these practices are also central to the development of expertise in scientific and mathematical disciplines. Recently, arguments have been made in favour of integrating CT and programming into the K-12 STEM curricula. In this paper, we first present a theoretical investigation of key issues that need to be considered for integrating CT into K-12 science topics by identifying the synergies between CT and scientific expertise using a particular genre of computation: agent-based computation. We then present a critical review of the literature in educational computing, and propose a set of guidelines for designing learning environments on science topics that can jointly foster the development of computational thinking with scientific expertise. This is followed by the description of a learning environment that supports CT through modeling and simulation to help middle school students learn physics and biology. We demonstrate the effectiveness of our system by discussing the results of a small study conducted in a middle school science classroom. Finally, we discuss the implications of our work for future research on developing CT-based science learning environments.

A Decision-Theoretic Planner with Dynamic Component Reconfiguration for Distributed Real-Time Applications

Distributed real-time embedded (DRE) systems perform sequences of coordination and heterogeneous data manipulation tasks in dynamic environments to meet specified goals. Autonomous operation of DRE systems can benefit from the integrated operation of (1) a decision-theoretic spreading activation partial order planner (SA-POP) that combines task planning and scheduling in uncertain environments with (2) a resource allocation and control engine (RACE) middleware framework that integrates multiple resource management algorithms for (re)deploying and (re)configuring task sequence components in these systems. This paper demonstrates the effectiveness of SA-POP and RACE in managing and executing mission goals for a multisatellite application. Our results show that combining planning, scheduling and resource constraints dynamically is the key to implementing autonomy in DRE systems

Modeling and Measuring Self-Regulated Learning in Teachable Agent Environments

Our learning-by-teaching environment has students take on the role and responsibilities of a teacher to a virtual student named Betty. The environment is designed to help students learn and understand science topics for themselves as they teach and monitor their agent. This process is supported by adaptive scaffolding and feedback through interactions with the teachable agent and a mentor agent. This paper discusses the results of a comparative study conducted in an 8th-grade science classroom, where students received two kinds of metacognitive and learning strategy feedback. We analyze student performance and learning gains as a result of the intervention. To gain further insight into student learning behaviors exhibited during the intervention, we employ a data mining methodology incorporating hidden Markov modeling and sequence mining techniques. The results illustrate both the effectiveness of the experimental agent feedback in encouraging metacognitive learning strategies and the utility of the data mining methodology.

Investigating Self-Regulated Learning in Teachable Agent Environments

We have developed a computer-based learning environment that helps students learn science by constructing causal concept map models. The system builds upon research in learning-by-teaching (LBT) and has students take on the role and responsibilities of being the teacher to a virtual student named Betty. The environment is structured so that successfully instructing their teachable agents requires the students to learn and understand the science topic for themselves. This learning process is supported through the use of adaptive scaffolding provided by feedback from the two agents in the system: the teachable agent, Betty, and a mentor agent, Mr. Davis. For example, if Betty performs poorly on a quiz, she may tell the student that she needs to learn more about the topics on which she is performing poorly. In addition, Mr. Davis may suggest that students ask Betty questions and get her to explain her answers to help them trace the causal reasoning chains in their map and find out where she may be making mistakes. Thus the system is designed to help students develop and refine their own knowledge construction and monitoring strategies as they teach their agent.

An Integrated Planning and Adaptive Resource Management Architecture for Distributed Real-Time Embedded Systems

Real-time and embedded systems have traditionally been designed for closed environments where operating conditions, input workloads, and resource availability are known a priori and are subject to little or no change at runtime. There is an increasing demand, however, for autonomous capabilities in open distributed real-time and embedded (DRE) systems that execute in environments where input workload and resource availability cannot be accurately characterized a priori. These systems can benefit from autonomic computing capabilities, such as self-(re)configuration and self-optimization, that enable autonomous adaptation under varying-even unpredictable-operational conditions. A challenging problem faced by researchers and developers in enabling autonomic computing capabilities to open DRE systems involves devising adaptive planning and resource management strategies that can meet mission objectives and end-to-end quality of service (QoS) requirements of applications. To address this challenge, this paper presents the integrated planning, allocation, and control (IPAC) framework, which provides decision-theoretic planning, dynamic resource allocation, and runtime system control to provide coordinated system adaptation and enable the autonomous operation of open DRE systems. This paper presents two contributions to research on autonomic computing for open DRE systems. First, we describe the design of IPAC and show how IPAC resolves the challenges associated with the autonomous operation of a representative open DRE system case study. Second, we empirically evaluate the planning and adaptive resource management capabilities of IPAC in the context of our case study. Our experimental results demonstrate that IPAC enables the autonomous operation of open DRE systems by performing adaptive planning and management of system resources.

Toward Effective Multi-Capacity Resource Allocation in Distributed Real-Time and Embedded Systems

Effective resource management for distributed real-time embedded (DRE) systems is hard due to their unique characteristics, including (1) constraints in multiple resources and (2) highly fluctuating resource availability and input workload. DRE systems can benefit from a middleware framework that enables adaptive resource management algorithms to ensure application QoS requirements are met. This paper identifies key challenges in designing and extending resource allocation algorithms for DRE systems. We present an empirical study of bin-packing algorithms enhanced to meet these challenges. Our analysis identifies input application patterns that help generate appropriate heuristics for using these algorithms effectively in DRE systems.

A Multi-Agent Architecture Provides Smart Sensing for the NASA Sensor Web

Remote sensing missions for Earth Science contribute greatly to the understanding of the dynamics of our planet. Conventional approaches however, impede the scientific communitys ability to (1) generate and refine models of complex phenomena, such as, extended weather forecasting, (2) detect and rapidly respond to critical transient events (e.g., disasters, such as hurricanes and floods). This paper describes a more effective approach based on intelligent, networked sensor webs that incorporate seamless dynamic connectivity between spacecraft, aircraft, and in situ terrestrial sensors, employs reactive and proactive strategies for improved temporal, spectral, and spatial coverage of the earth and its atmosphere, and uses enhanced dynamic decision-making for rapid responses to changing situations. MACRO, an extension of our earlier work on a multi-agent framework for heterogeneous spacecraft constellations, will provide interoperability and autonomy to achieve the needs for smart sensing in NASAs proposed sensor web. The system capability will be demonstrated via a simulated but salient disaster management scenario on an existing hardware testbed at the Lockheed Martin Advanced Technology Center.

Learner modeling for adaptive scaffolding in a Computational Thinking-based science learning environment

Learner modeling has been used in computer-based learning environments to model learners’ domain knowledge, cognitive skills, and interests, and customize their experiences in the environment based on this information. In this paper, we develop a learner modeling and adaptive scaffolding framework for Computational Thinking using Simulation and Modeling (CTSiM)—an open ended learning environment that supports synergistic learning of science and Computational Thinking (CT) for middle school students. In CTSiM, students have the freedom to choose and coordinate use of the different tools provided in the environment, as they build and test their models. However, the open-ended nature of the environment makes it hard to interpret the intent of students’ actions, and to provide useful feedback and hints that improves student understanding and helps them achieve their learning goals. To address this challenge, we define an extended learner modeling scheme that uses (1) a hierarchical task model for the CTSiM environment, (2) a set of strategies that support effective learning and model building, and (3) effectiveness and coherence measures that help us evaluate student’s proficiency in the different tasks and strategies. We use this scheme to dynamically scaffold learners when they are deficient in performing their tasks, or they demonstrate suboptimal use of strategies. We demonstrate the effectiveness of our approach in a classroom study where one group of 6th grade students received scaffolding and the other did not. We found that students who received scaffolding built more accurate models, used modeling strategies effectively, adopted more useful modeling behaviors, showed a better understanding of important science and CT concepts, and transferred their modeling skills better to new scenarios.

Efficient Allocation of Hierarchically-Decomposable Tasks in a Sensor Web Contract Net

In large, distributed systems, such as a sensor web, allocating resources to tasks that span multiple providers presents significant challenges. Individual subtasks associated with a task could potentially be assigned to a number of agents (e.g., when there is overlap in sensor or data processing capability among constituent sensor networks). This problem is further compounded by the dynamic nature of a sensor web, in which both desired tasks and resource availability change with time and environmental conditions. This paper presents a novel variation of the contract net protocol (CNP) for subtask allocation, which employs brokers to limit communication overhead in a two-phase CNP and aggregate domain information from groups of agents. Experimental results using this subtask allocation approach verify its efficiency and scalability. These results also suggest specific refinements and appropriate parameters for a variety of system configurations and operating conditions in sensor webs and other large multi-agent systems.

Identifying middle school students’ challenges in computational thinking-based science learning

Computational thinking (CT) parallels the core practices of science, technology, engineering, and mathematics (STEM) education and is believed to effectively support students’ learning of science and math concepts. However, despite the synergies between CT and STEM education, integrating the two to support synergistic learning remains an important challenge. Relatively, little is known about how a student’s conceptual understanding develops in such learning environments and the difficulties they face when learning with such integrated curricula. In this paper, we present a research study with CTSiM (Computational Thinking in Simulation and Modeling)—computational thinking-based learning environment for K-12 science, where students build and simulate computational models to study and gain an understanding of science processes. We investigate a set of core challenges (both computational and science domain related) that middle school students face when working with CTSiM, how these challenges evolve across different modeling activities, and the kinds of support provided by human observers that help students overcome these challenges. We identify four broad categories and 14 subcategories of challenges and show that the human-provided scaffolds help reduce the number of challenges students face over time. Finally, we discuss our plans to modify the CTSiM interfaces and embed scaffolding tools into CTSiM to help students overcome their various programming, modeling, and science-related challenges and thus gain a deeper understanding of the science concepts.