Complexity-Based Learning and Teaching: A Case Study in Higher Education

ERIC Educational Resources Information Center

Fabricatore, Carlo; López, María Ximena

2014-01-01

This paper presents a learning and teaching strategy based on complexity science and explores its impacts on a higher education game design course. The strategy aimed at generating conditions fostering individual and collective learning in educational complex adaptive systems, and led the design of the course through an iterative and adaptive…

Online Learning Tools for Middle School Science: Lessons Learned from a Design-Based Research Project

ERIC Educational Resources Information Center

Terrazas-Arellanes, Fatima E.; Knox, Carolyn; Strycker, Lisa A.; Walden, Emily D.

2017-01-01

This article reports on how design-based research methodology was used to guide a line of intervention research that developed, implemented, revised, and evaluated online learning science curricula for middle school students, including general education students and English language learners (primarily of Hispanic origin). The iterative,…

Kernel-based least squares policy iteration for reinforcement learning.

PubMed

Xu, Xin; Hu, Dewen; Lu, Xicheng

2007-07-01

In this paper, we present a kernel-based least squares policy iteration (KLSPI) algorithm for reinforcement learning (RL) in large or continuous state spaces, which can be used to realize adaptive feedback control of uncertain dynamic systems. By using KLSPI, near-optimal control policies can be obtained without much a priori knowledge on dynamic models of control plants. In KLSPI, Mercer kernels are used in the policy evaluation of a policy iteration process, where a new kernel-based least squares temporal-difference algorithm called KLSTD-Q is proposed for efficient policy evaluation. To keep the sparsity and improve the generalization ability of KLSTD-Q solutions, a kernel sparsification procedure based on approximate linear dependency (ALD) is performed. Compared to the previous works on approximate RL methods, KLSPI makes two progresses to eliminate the main difficulties of existing results. One is the better convergence and (near) optimality guarantee by using the KLSTD-Q algorithm for policy evaluation with high precision. The other is the automatic feature selection using the ALD-based kernel sparsification. Therefore, the KLSPI algorithm provides a general RL method with generalization performance and convergence guarantee for large-scale Markov decision problems (MDPs). Experimental results on a typical RL task for a stochastic chain problem demonstrate that KLSPI can consistently achieve better learning efficiency and policy quality than the previous least squares policy iteration (LSPI) algorithm. Furthermore, the KLSPI method was also evaluated on two nonlinear feedback control problems, including a ship heading control problem and the swing up control of a double-link underactuated pendulum called acrobot. Simulation results illustrate that the proposed method can optimize controller performance using little a priori information of uncertain dynamic systems. It is also demonstrated that KLSPI can be applied to online learning control by incorporating an initial controller to ensure online performance.

Socio-Technical Dimensions of an Outdoor Mobile Learning Environment: A Three-Phase Design-Based Research Investigation

ERIC Educational Resources Information Center

Land, Susan M.; Zimmerman, Heather Toomey

2015-01-01

This design-based research project examines three iterations of Tree Investigators, a learning environment designed to support science learning outdoors at an arboretum and nature center using mobile devices (iPads). Researchers coded videorecords and artifacts created by children and parents (n = 53) to understand how both social and…

Towards Collaboration as Learning: Evaluation of an Open CPD Opportunity for HE Teachers

ERIC Educational Resources Information Center

Nerantzi, Chrissi; Gossman, Peter

2015-01-01

Flexible, Distance and Online Learning (FDOL) is an open online course offered as an informal cross-institutional collaboration based on a postgraduate module in the context of teacher education in higher education. The second iteration, FDOL132, was offered in 2013 using a problem-based learning (PBL) design (FISh) to foster collaborative…

Defining and Building an Enriched Learning and Information Environment.

ERIC Educational Resources Information Center

Goodrum, David A.; And Others

1993-01-01

Discusses the development of an Enriched Learning and Information Environment (ELIE). Highlights include technology-based and theory-based frameworks for defining ELIEs; a socio-technical definition; a conceptual prototype; a participatory design process, including iterative design through rapid prototyping; and design issues for technology…

Simulation Learning PC Screen-Based vs. High Fidelity

DTIC Science & Technology

2011-08-01

D., Burgess, L., Berg, B . and Connolly, K . (2009). Teaching mass casualty triage skills using iterative multimanikin simulations. Prehospital...SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18. NUMBER OF PAGES 19a. NAME OF RESPONSIBLE PERSON USAMRMC a. REPORT U b . ABSTRACT U...learning PC screen-based vs. high fidelity – progress chart Attachment B . Approved Protocol - Simulation Learning: PC-Screen Based (PCSB) versus High

An iterated Laplacian based semi-supervised dimensionality reduction for classification of breast cancer on ultrasound images.

PubMed

Liu, Xiao; Shi, Jun; Zhou, Shichong; Lu, Minhua

2014-01-01

The dimensionality reduction is an important step in ultrasound image based computer-aided diagnosis (CAD) for breast cancer. A newly proposed l2,1 regularized correntropy algorithm for robust feature selection (CRFS) has achieved good performance for noise corrupted data. Therefore, it has the potential to reduce the dimensions of ultrasound image features. However, in clinical practice, the collection of labeled instances is usually expensive and time costing, while it is relatively easy to acquire the unlabeled or undetermined instances. Therefore, the semi-supervised learning is very suitable for clinical CAD. The iterated Laplacian regularization (Iter-LR) is a new regularization method, which has been proved to outperform the traditional graph Laplacian regularization in semi-supervised classification and ranking. In this study, to augment the classification accuracy of the breast ultrasound CAD based on texture feature, we propose an Iter-LR-based semi-supervised CRFS (Iter-LR-CRFS) algorithm, and then apply it to reduce the feature dimensions of ultrasound images for breast CAD. We compared the Iter-LR-CRFS with LR-CRFS, original supervised CRFS, and principal component analysis. The experimental results indicate that the proposed Iter-LR-CRFS significantly outperforms all other algorithms.

Design of robust iterative learning control schemes for systems with polytopic uncertainties and sector-bounded nonlinearities

NASA Astrophysics Data System (ADS)

Boski, Marcin; Paszke, Wojciech

2017-01-01

This paper deals with designing of iterative learning control schemes for uncertain systems with static nonlinearities. More specifically, the nonlinear part is supposed to be sector bounded and system matrices are assumed to range in the polytope of matrices. For systems with such nonlinearities and uncertainties the repetitive process setting is exploited to develop a linear matrix inequality based conditions for computing the feedback and feedforward (learning) controllers. These controllers guarantee acceptable dynamics along the trials and ensure convergence of the trial-to-trial error dynamics, respectively. Numerical examples illustrate the theoretical results and confirm effectiveness of the designed control scheme.

Model-based iterative learning control of Parkinsonian state in thalamic relay neuron

NASA Astrophysics Data System (ADS)

Liu, Chen; Wang, Jiang; Li, Huiyan; Xue, Zhiqin; Deng, Bin; Wei, Xile

2014-09-01

Although the beneficial effects of chronic deep brain stimulation on Parkinson's disease motor symptoms are now largely confirmed, the underlying mechanisms behind deep brain stimulation remain unclear and under debate. Hence, the selection of stimulation parameters is full of challenges. Additionally, due to the complexity of neural system, together with omnipresent noises, the accurate model of thalamic relay neuron is unknown. Thus, the iterative learning control of the thalamic relay neuron's Parkinsonian state based on various variables is presented. Combining the iterative learning control with typical proportional-integral control algorithm, a novel and efficient control strategy is proposed, which does not require any particular knowledge on the detailed physiological characteristics of cortico-basal ganglia-thalamocortical loop and can automatically adjust the stimulation parameters. Simulation results demonstrate the feasibility of the proposed control strategy to restore the fidelity of thalamic relay in the Parkinsonian condition. Furthermore, through changing the important parameter—the maximum ionic conductance densities of low-threshold calcium current, the dominant characteristic of the proposed method which is independent of the accurate model can be further verified.

Dynamic adaptive learning for decision-making supporting systems

NASA Astrophysics Data System (ADS)

He, Haibo; Cao, Yuan; Chen, Sheng; Desai, Sachi; Hohil, Myron E.

2008-03-01

This paper proposes a novel adaptive learning method for data mining in support of decision-making systems. Due to the inherent characteristics of information ambiguity/uncertainty, high dimensionality and noisy in many homeland security and defense applications, such as surveillances, monitoring, net-centric battlefield, and others, it is critical to develop autonomous learning methods to efficiently learn useful information from raw data to help the decision making process. The proposed method is based on a dynamic learning principle in the feature spaces. Generally speaking, conventional approaches of learning from high dimensional data sets include various feature extraction (principal component analysis, wavelet transform, and others) and feature selection (embedded approach, wrapper approach, filter approach, and others) methods. However, very limited understandings of adaptive learning from different feature spaces have been achieved. We propose an integrative approach that takes advantages of feature selection and hypothesis ensemble techniques to achieve our goal. Based on the training data distributions, a feature score function is used to provide a measurement of the importance of different features for learning purpose. Then multiple hypotheses are iteratively developed in different feature spaces according to their learning capabilities. Unlike the pre-set iteration steps in many of the existing ensemble learning approaches, such as adaptive boosting (AdaBoost) method, the iterative learning process will automatically stop when the intelligent system can not provide a better understanding than a random guess in that particular subset of feature spaces. Finally, a voting algorithm is used to combine all the decisions from different hypotheses to provide the final prediction results. Simulation analyses of the proposed method on classification of different US military aircraft databases show the effectiveness of this method.

Quantized Iterative Learning Consensus Tracking of Digital Networks With Limited Information Communication.

PubMed

Xiong, Wenjun; Yu, Xinghuo; Chen, Yao; Gao, Jie

2017-06-01

This brief investigates the quantized iterative learning problem for digital networks with time-varying topologies. The information is first encoded as symbolic data and then transmitted. After the data are received, a decoder is used by the receiver to get an estimate of the sender's state. Iterative learning quantized communication is considered in the process of encoding and decoding. A sufficient condition is then presented to achieve the consensus tracking problem in a finite interval using the quantized iterative learning controllers. Finally, simulation results are given to illustrate the usefulness of the developed criterion.

Infant/Toddler Environment Rating Scale (ITERS-3). Third Edition

ERIC Educational Resources Information Center

Harms, Thelma; Cryer, Debby; Clifford, Richard M.; Yazejian, Noreen

2017-01-01

Building on extensive feedback from the field as well as vigorous new research on how best to support infant and toddler development and learning, the authors have revised and updated the widely used "Infant/Toddler Environment Rating Scale." ITERS-3 is the next-generation assessment tool for use in center-based child care programs for…

Detangling the Interrelationships between Self- Regulation and Ill-Structured Problem Solving in Problem-Based Learning

ERIC Educational Resources Information Center

Ge, Xun; Law, Victor; Huang, Kun

2016-01-01

One of the goals for problem-based learning (PBL) is to promote self-regulation. Although self-regulation has been studied extensively, its interrelationships with ill-structured problem solving have been unclear. In order to clarify the interrelationships, this article proposes a conceptual framework illustrating the iterative processes among…

Students' Socio-Scientific Reasoning in an Astrobiological Context during Work with a Digital Learning Environment

ERIC Educational Resources Information Center

Hansson, Lena; Redfors, Andreas; Rosberg, Maria

2011-01-01

In a European project--CoReflect--researchers in seven countries are developing, implementing and evaluating teaching sequences using a web-based platform (STOCHASMOS). The interactive web-based inquiry materials support collaborative and reflective work. The learning environments will be iteratively tested and refined, during different phases of…

Realization of Comfortable Massage by Using Iterative Learning Control Based on EEG

NASA Astrophysics Data System (ADS)

Teramae, Tatsuya; Kushida, Daisuke; Takemori, Fumiaki; Kitamura, Akira

Recently the massage chair is used by a lot of people because they are able to use it easily at home. However a present massage chair only realizes the massage motion. Moreover the massage chair can not consider the user’s condition and massage force. On the other hand, the professional masseur is according to presume the mental condition by patient’s reaction. Then this paper proposes the method of applying masseur’s procedure for the massage chair using iterative learning control based on EEG. And massage force is estimated by acceleration sensor. The realizability of the proposed method is verified by the experimental works using the massage chair.

PID-based error signal modeling

NASA Astrophysics Data System (ADS)

Yohannes, Tesfay

1997-10-01

This paper introduces a PID based signal error modeling. The error modeling is based on the betterment process. The resulting iterative learning algorithm is introduced and a detailed proof is provided for both linear and nonlinear systems.

Ask-the-expert: Active Learning Based Knowledge Discovery Using the Expert

NASA Technical Reports Server (NTRS)

Das, Kamalika; Avrekh, Ilya; Matthews, Bryan; Sharma, Manali; Oza, Nikunj

2017-01-01

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the backend. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.

Ask-the-Expert: Active Learning Based Knowledge Discovery Using the Expert

NASA Technical Reports Server (NTRS)

Das, Kamalika

2017-01-01

Often the manual review of large data sets, either for purposes of labeling unlabeled instances or for classifying meaningful results from uninteresting (but statistically significant) ones is extremely resource intensive, especially in terms of subject matter expert (SME) time. Use of active learning has been shown to diminish this review time significantly. However, since active learning is an iterative process of learning a classifier based on a small number of SME-provided labels at each iteration, the lack of an enabling tool can hinder the process of adoption of these technologies in real-life, in spite of their labor-saving potential. In this demo we present ASK-the-Expert, an interactive tool that allows SMEs to review instances from a data set and provide labels within a single framework. ASK-the-Expert is powered by an active learning algorithm for training a classifier in the back end. We demonstrate this system in the context of an aviation safety application, but the tool can be adopted to work as a simple review and labeling tool as well, without the use of active learning.

A clustering-based graph Laplacian framework for value function approximation in reinforcement learning.

PubMed

Xu, Xin; Huang, Zhenhua; Graves, Daniel; Pedrycz, Witold

2014-12-01

In order to deal with the sequential decision problems with large or continuous state spaces, feature representation and function approximation have been a major research topic in reinforcement learning (RL). In this paper, a clustering-based graph Laplacian framework is presented for feature representation and value function approximation (VFA) in RL. By making use of clustering-based techniques, that is, K-means clustering or fuzzy C-means clustering, a graph Laplacian is constructed by subsampling in Markov decision processes (MDPs) with continuous state spaces. The basis functions for VFA can be automatically generated from spectral analysis of the graph Laplacian. The clustering-based graph Laplacian is integrated with a class of approximation policy iteration algorithms called representation policy iteration (RPI) for RL in MDPs with continuous state spaces. Simulation and experimental results show that, compared with previous RPI methods, the proposed approach needs fewer sample points to compute an efficient set of basis functions and the learning control performance can be improved for a variety of parameter settings.

Effects of iterative learning based signal control strategies on macroscopic fundamental diagrams of urban road networks

NASA Astrophysics Data System (ADS)

Yan, Fei; Tian, Fuli; Shi, Zhongke

2016-10-01

Urban traffic flows are inherently repeated on a daily or weekly basis. This repeatability can help improve the traffic conditions if it is used properly by the control system. In this paper, we propose a novel iterative learning control (ILC) strategy for traffic signals of urban road networks using the repeatability feature of traffic flow. To improve the control robustness, the ILC strategy is further integrated with an error feedback control law in a complementary manner. Theoretical analysis indicates that the ILC-based traffic signal control methods can guarantee the asymptotic learning convergence, despite the presence of modeling uncertainties and exogenous disturbances. Finally, the impacts of the ILC-based signal control strategies on the network macroscopic fundamental diagram (MFD) are examined. The results show that the proposed ILC-based control strategies can homogenously distribute the network accumulation by controlling the vehicle numbers in each link to the desired levels under different traffic demands, which can result in the network with high capacity and mobility.

Distance Metric Learning via Iterated Support Vector Machines.

PubMed

Zuo, Wangmeng; Wang, Faqiang; Zhang, David; Lin, Liang; Huang, Yuchi; Meng, Deyu; Zhang, Lei

2017-07-11

Distance metric learning aims to learn from the given training data a valid distance metric, with which the similarity between data samples can be more effectively evaluated for classification. Metric learning is often formulated as a convex or nonconvex optimization problem, while most existing methods are based on customized optimizers and become inefficient for large scale problems. In this paper, we formulate metric learning as a kernel classification problem with the positive semi-definite constraint, and solve it by iterated training of support vector machines (SVMs). The new formulation is easy to implement and efficient in training with the off-the-shelf SVM solvers. Two novel metric learning models, namely Positive-semidefinite Constrained Metric Learning (PCML) and Nonnegative-coefficient Constrained Metric Learning (NCML), are developed. Both PCML and NCML can guarantee the global optimality of their solutions. Experiments are conducted on general classification, face verification and person re-identification to evaluate our methods. Compared with the state-of-the-art approaches, our methods can achieve comparable classification accuracy and are efficient in training.

Using Analytics to Transform a Problem-Based Case Library: An Educational Design Research Approach

ERIC Educational Resources Information Center

Schmidt, Matthew; Tawfik, Andrew A.

2018-01-01

This article describes the iterative design, development, and evaluation of a case-based learning environment focusing on an ill-structured sales management problem. We discuss our processes and situate them within the broader framework of educational design research. The learning environment evolved over the course of three design phases. A…

Design and Facilitation of Problem-Based Learning in Graduate Teacher Education: An MA TESOL Case

ERIC Educational Resources Information Center

Caswell, Cynthia Ann

2016-01-01

This exploratory, evaluative case study introduces a new context for problem-based learning (PBL) involving an iterative, modular approach to curriculum-wide delivery of PBL in an MA TESOL program. The introduction to the curriculum context provides an overview of the design and delivery features particular to the situation. The delivery approach…

Deep learning methods to guide CT image reconstruction and reduce metal artifacts

NASA Astrophysics Data System (ADS)

Gjesteby, Lars; Yang, Qingsong; Xi, Yan; Zhou, Ye; Zhang, Junping; Wang, Ge

2017-03-01

The rapidly-rising field of machine learning, including deep learning, has inspired applications across many disciplines. In medical imaging, deep learning has been primarily used for image processing and analysis. In this paper, we integrate a convolutional neural network (CNN) into the computed tomography (CT) image reconstruction process. Our first task is to monitor the quality of CT images during iterative reconstruction and decide when to stop the process according to an intelligent numerical observer instead of using a traditional stopping rule, such as a fixed error threshold or a maximum number of iterations. After training on ground truth images, the CNN was successful in guiding an iterative reconstruction process to yield high-quality images. Our second task is to improve a sinogram to correct for artifacts caused by metal objects. A large number of interpolation and normalization-based schemes were introduced for metal artifact reduction (MAR) over the past four decades. The NMAR algorithm is considered a state-of-the-art method, although residual errors often remain in the reconstructed images, especially in cases of multiple metal objects. Here we merge NMAR with deep learning in the projection domain to achieve additional correction in critical image regions. Our results indicate that deep learning can be a viable tool to address CT reconstruction challenges.

Implementation of a Curriculum-Integrated Computer Game for Introducing Scientific Argumentation

NASA Astrophysics Data System (ADS)

Wallon, Robert C.; Jasti, Chandana; Lauren, Hillary Z. G.; Hug, Barbara

2017-11-01

Argumentation has been emphasized in recent US science education reform efforts (NGSS Lead States 2013; NRC 2012), and while existing studies have investigated approaches to introducing and supporting argumentation (e.g., McNeill and Krajcik in Journal of Research in Science Teaching, 45(1), 53-78, 2008; Kang et al. in Science Education, 98(4), 674-704, 2014), few studies have investigated how game-based approaches may be used to introduce argumentation to students. In this paper, we report findings from a design-based study of a teacher's use of a computer game intended to introduce the claim, evidence, reasoning (CER) framework (McNeill and Krajcik 2012) for scientific argumentation. We studied the implementation of the game over two iterations of development in a high school biology teacher's classes. The results of this study include aspects of enactment of the activities and student argument scores. We found the teacher used the game in aspects of explicit instruction of argumentation during both iterations, although the ways in which the game was used differed. Also, students' scores in the second iteration were significantly higher than the first iteration. These findings support the notion that students can learn argumentation through a game, especially when used in conjunction with explicit instruction and support in student materials. These findings also highlight the importance of analyzing classroom implementation in studies of game-based learning.

Developing Preservice Elementary Teachers' Knowledge and Practices through Modeling-Centered Scientific Inquiry

ERIC Educational Resources Information Center

Schwarz, Christina

2009-01-01

Preservice elementary teachers face many challenges in learning how to teach science effectively, such as engaging students in science, organizing instruction, and developing a productive learning community. This paper reports on several iterative cycles of design-based research aimed at fostering preservice teachers' principled reasoning around…

Upper limb stroke rehabilitation: the effectiveness of Stimulation Assistance through Iterative Learning (SAIL).

PubMed

Meadmore, Katie L; Cai, Zhonglun; Tong, Daisy; Hughes, Ann-Marie; Freeman, Chris T; Rogers, Eric; Burridge, Jane H

2011-01-01

A novel system has been developed which combines robotic therapy with electrical stimulation (ES) for upper limb stroke rehabilitation. This technology, termed SAIL: Stimulation Assistance through Iterative Learning, employs advanced model-based iterative learning control (ILC) algorithms to precisely assist participant's completion of 3D tracking tasks with their impaired arm. Data is reported from a preliminary study with unimpaired participants, and also from a single hemiparetic stroke participant with reduced upper limb function who has used the system in a clinical trial. All participants completed tasks which involved moving their (impaired) arm to follow an image of a slowing moving sphere along a trajectory. The participants' arm was supported by a robot and ES was applied to the triceps brachii and anterior deltoid muscles. During each task, the same tracking trajectory was repeated 6 times and ILC was used to compute the stimulation signals to be applied on the next iteration. Unimpaired participants took part in a single, one hour training session and the stroke participant undertook 18, 1 hour treatment sessions composed of tracking tasks varying in length, orientation and speed. The results reported describe changes in tracking ability and demonstrate feasibility of the SAIL system for upper limb rehabilitation. © 2011 IEEE

Iterative Design and Testing for the Development of a Game-Based Chlamydia Awareness Intervention: A Pilot Study.

PubMed

Jiang, Rui; McKanna, James; Calabrese, Samantha; Seif El-Nasr, Magy

2017-08-01

Herein we describe a methodology for developing a game-based intervention to raise awareness of Chlamydia and other sexually transmitted infections among youth in Boston's underserved communities. We engaged in three design-based experiments. These utilized mixed methods, including playtesting and assessment methods, to examine the overall effectiveness of the game. In this case, effectiveness is defined as (1) engaging the target group, (2) increasing knowledge about Chlamydia, and (3) changing attitudes toward Chlamydia testing. These three experiments were performed using participants from different communities and with slightly different versions of the game, as we iterated through the design/feedback process. Overall, participants who played the game showed a significant increase in participants' knowledge of Chlamydia compared with those in the control group (P = 0.0002). The version of the game, including elements specifically targeting systemic thinking, showed significant improvement in participants' intent to get tested compared with the version of the game without such elements (Stage 2: P > 0.05; Stage 3: P = 0.0045). Furthermore, during both Stage 2 and Stage 3, participants showed high levels of enjoyment, mood, and participation and moderate levels of game engagement and social engagement. During Stage 3, however, participants' game engagement (P = 0.0003), social engagement (P = 0.0003), and participation (P = 0.0003) were significantly higher compared with those of Stage 2. Thus, we believe that motivation improvements from Stage 2 to 3 were also effective. Finally, participants' overall learning effectiveness was correlated with their prepositive affect (r = 0.52) and their postproblem hierarchy (r = -0.54). The game improved considerably from its initial conception through three stages of iterative design and feedback. Our assessment methods for each stage targeted and integrated learning, health, and engagement outcomes. Lessons learned through this iterative design process are a great contribution to the games for health community, especially in targeting the development of health and learning goals through game design.

Multi-criteria Integrated Resource Assessment (MIRA)

EPA Pesticide Factsheets

MIRA is an approach that facilitates stakeholder engagement for collaborative multi-objective decision making. MIRA is designed to facilitate and support an inclusive, explicit, transparent, iterative learning-based decision process.

Online Bahavior Aquisition of an Agent based on Coaching as Learning Assistance

NASA Astrophysics Data System (ADS)

Hirokawa, Masakazu; Suzuki, Kenji

This paper describes a novel methodology, namely ``Coaching'', which allows humans to give a subjective evaluation to an agent in an iterative manner. This is an interactive learning method to improve the reinforcement learning by modifying a reward function dynamically according to given evaluations by a trainer and the learning situation of the agent. We demonstrate that the agent can learn different reward functions by given instructions such as ``good or bad'' by human's observation, and can also obtain a set of behavior based on the learnt reward functions through several experiments.

Clinical Training at Remote Sites Using Mobile Technology: An India-USA Partnership

ERIC Educational Resources Information Center

Vyas, R.; Albright, S.; Walker, D.; Zachariah, A.; Lee, M. Y.

2010-01-01

Christian Medical College (CMC), India, and Tufts University School of Medicine, USA, have developed an "institutional hub and spokes" model (campus-based e-learning supporting m-learning in the field) to facilitate clinical education and training at remote secondary hospital sites across India. Iterative research, design, development,…

Modeling Peer Assessment as Agent Negotiation in a Computer Supported Collaborative Learning Environment

ERIC Educational Resources Information Center

Lai, K. Robert; Lan, Chung Hsien

2006-01-01

This work presents a novel method for modeling collaborative learning as multi-issue agent negotiation using fuzzy constraints. Agent negotiation is an iterative process, through which, the proposed method aggregates student marks to reduce personal bias. In the framework, students define individual fuzzy membership functions based on their…

Design Principles for "Thriving in Our Digital World": A High School Computer Science Course

ERIC Educational Resources Information Center

Veletsianos, George; Beth, Bradley; Lin, Calvin; Russell, Gregory

2016-01-01

"Thriving in Our Digital World" is a technology-enhanced dual enrollment course introducing high school students to computer science through project- and problem-based learning. This article describes the evolution of the course and five lessons learned during the design, development, implementation, and iteration of the course from its…

Challenges and Opportunities for Teacher Professional Development in Interactive Use of Technology in African Schools

ERIC Educational Resources Information Center

Hennessy, Sara; Haßler, Bjoern; Hofmann, Riikka

2015-01-01

This article examines the supporting and constraining factors influencing professional learning about interactive teaching and mobile digital technology use in low-resourced basic schools in sub-Saharan Africa. It draws on a case study of iterative development and refinement of a school-based, peer-facilitated professional learning programme…

Learning Biological Networks via Bootstrapping with Optimized GO-based Gene Similarity

DOE Office of Scientific and Technical Information (OSTI.GOV)

Taylor, Ronald C.; Sanfilippo, Antonio P.; McDermott, Jason E.

2010-08-02

Microarray gene expression data provide a unique information resource for learning biological networks using "reverse engineering" methods. However, there are a variety of cases in which we know which genes are involved in a given pathology of interest, but we do not have enough experimental evidence to support the use of fully-supervised/reverse-engineering learning methods. In this paper, we explore a novel semi-supervised approach in which biological networks are learned from a reference list of genes and a partial set of links for these genes extracted automatically from PubMed abstracts, using a knowledge-driven bootstrapping algorithm. We show how new relevant linksmore » across genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. We describe an application of this approach to the TGFB pathway as a case study and show how the ensuing results prove the feasibility of the approach as an alternate or complementary technique to fully supervised methods.« less

Designing the Architecture of Hierachical Neural Networks Model Attention, Learning and Goal-Oriented Behavior

DTIC Science & Technology

1993-12-31

19,23,25,26,27,28,32,33,35,41]) - A new cost function is postulated and an algorithm that employs this cost function is proposed for the learning of...updates the controller parameters from time to time [53]. The learning control algorithm consist of updating the parameter estimates as used in the...proposed cost function with the other learning type algorithms , such as based upon learning of iterative tasks [Kawamura-85], variable structure

A Fast Reduced Kernel Extreme Learning Machine.

PubMed

Deng, Wan-Yu; Ong, Yew-Soon; Zheng, Qing-Hua

2016-04-01

In this paper, we present a fast and accurate kernel-based supervised algorithm referred to as the Reduced Kernel Extreme Learning Machine (RKELM). In contrast to the work on Support Vector Machine (SVM) or Least Square SVM (LS-SVM), which identifies the support vectors or weight vectors iteratively, the proposed RKELM randomly selects a subset of the available data samples as support vectors (or mapping samples). By avoiding the iterative steps of SVM, significant cost savings in the training process can be readily attained, especially on Big datasets. RKELM is established based on the rigorous proof of universal learning involving reduced kernel-based SLFN. In particular, we prove that RKELM can approximate any nonlinear functions accurately under the condition of support vectors sufficiency. Experimental results on a wide variety of real world small instance size and large instance size applications in the context of binary classification, multi-class problem and regression are then reported to show that RKELM can perform at competitive level of generalized performance as the SVM/LS-SVM at only a fraction of the computational effort incurred. Copyright © 2015 Elsevier Ltd. All rights reserved.

Iterating between lessons on concepts and procedures can improve mathematics knowledge.

PubMed

Rittle-Johnson, Bethany; Koedinger, Kenneth

2009-09-01

Knowledge of concepts and procedures seems to develop in an iterative fashion, with increases in one type of knowledge leading to increases in the other type of knowledge. This suggests that iterating between lessons on concepts and procedures may improve learning. The purpose of the current study was to evaluate the instructional benefits of an iterative lesson sequence compared to a concepts-before-procedures sequence for students learning decimal place-value concepts and arithmetic procedures. In two classroom experiments, sixth-grade students from two schools participated (N=77 and 26). Students completed six decimal lessons on an intelligent-tutoring systems. In the iterative condition, lessons cycled between concept and procedure lessons. In the concepts-first condition, all concept lessons were presented before introducing the procedure lessons. In both experiments, students in the iterative condition gained more knowledge of arithmetic procedures, including ability to transfer the procedures to problems with novel features. Knowledge of concepts was fairly comparable across conditions. Finally, pre-test knowledge of one type predicted gains in knowledge of the other type across experiments. An iterative sequencing of lessons seems to facilitate learning and transfer, particularly of mathematical procedures. The findings support an iterative perspective for the development of knowledge of concepts and procedures.

Introducing 12 Year-Olds to Elementary Particles

ERIC Educational Resources Information Center

Wiener, Gerfried J.; Schmeling, Sascha M.; Hopf, Martin

2017-01-01

We present a new learning unit, which introduces 12 year-olds to the subatomic structure of matter. The learning unit was iteratively developed as a design-based research project using the technique of probing acceptance. We give a brief overview of the unit's final version, discuss its key ideas and main concepts, and conclude by highlighting the…

The Iterative Design of a Mobile Learning Application to Support Scientific Inquiry

ERIC Educational Resources Information Center

Marty, Paul F.; Mendenhall, Anne; Douglas, Ian; Southerland, Sherry A.; Sampson, Victor; Kazmer, Michelle M.; Alemanne, Nicole; Clark, Amanda; Schellinger, Jennifer

2013-01-01

The ubiquity of mobile devices makes them well suited for field-based learning experiences that require students to gather data as part of the process of developing scientific inquiry practices. The usefulness of these devices, however, is strongly influenced by the nature of the applications students use to collect data in the field. To…

eNOSHA, a Free, Open and Flexible Learning Object Repository--An Iterative Development Process for Global User-Friendliness

ERIC Educational Resources Information Center

Mozelius, Peter; Hettiarachchi, Enosha

2012-01-01

This paper describes the iterative development process of a Learning Object Repository (LOR), named eNOSHA. Discussions on a project for a LOR started at the e-Learning Centre (eLC) at The University of Colombo, School of Computing (UCSC) in 2007. The eLC has during the last decade been developing learning content for a nationwide e-learning…

Design-Based Implementation Research

ERIC Educational Resources Information Center

LeMahieu, Paul G.; Nordstrum, Lee E.; Potvin, Ashley Seidel

2017-01-01

Purpose: This paper is second of seven in this volume elaborating different approaches to quality improvement in education. It delineates a methodology called design-based implementation research (DBIR). The approach used in this paper is aimed at iteratively improving the quality of classroom teaching and learning practices in defined problem…

Sparsity-constrained PET image reconstruction with learned dictionaries

NASA Astrophysics Data System (ADS)

Tang, Jing; Yang, Bao; Wang, Yanhua; Ying, Leslie

2016-09-01

PET imaging plays an important role in scientific and clinical measurement of biochemical and physiological processes. Model-based PET image reconstruction such as the iterative expectation maximization algorithm seeking the maximum likelihood solution leads to increased noise. The maximum a posteriori (MAP) estimate removes divergence at higher iterations. However, a conventional smoothing prior or a total-variation (TV) prior in a MAP reconstruction algorithm causes over smoothing or blocky artifacts in the reconstructed images. We propose to use dictionary learning (DL) based sparse signal representation in the formation of the prior for MAP PET image reconstruction. The dictionary to sparsify the PET images in the reconstruction process is learned from various training images including the corresponding MR structural image and a self-created hollow sphere. Using simulated and patient brain PET data with corresponding MR images, we study the performance of the DL-MAP algorithm and compare it quantitatively with a conventional MAP algorithm, a TV-MAP algorithm, and a patch-based algorithm. The DL-MAP algorithm achieves improved bias and contrast (or regional mean values) at comparable noise to what the other MAP algorithms acquire. The dictionary learned from the hollow sphere leads to similar results as the dictionary learned from the corresponding MR image. Achieving robust performance in various noise-level simulation and patient studies, the DL-MAP algorithm with a general dictionary demonstrates its potential in quantitative PET imaging.

Research and Teaching: Development of Course-Based Undergraduate Research Experiences Using a Design-Based Approach

ERIC Educational Resources Information Center

Mordacq, John C.; Drane, Denise L.; Swarat, Su L.; Lo, Stanley M.

2017-01-01

In recent years, commissions and reports have called for laboratory courses that engage undergraduates in authentic research experiences. We present an iterative approach for developing course-based undergraduate research experiences (CUREs) that help students learn scientific inquiry skills and foster expert-like perceptions about biology. This…

Off-site training of laparoscopic skills, a scoping review using a thematic analysis.

PubMed

Thinggaard, Ebbe; Kleif, Jakob; Bjerrum, Flemming; Strandbygaard, Jeanett; Gögenur, Ismail; Matthew Ritter, E; Konge, Lars

2016-11-01

The focus of research in simulation-based laparoscopic training has changed from examining whether simulation training works to examining how best to implement it. In laparoscopic skills training, portable and affordable box trainers allow for off-site training. Training outside simulation centers and hospitals can increase access to training, but also poses new challenges to implementation. This review aims to guide implementation of off-site training of laparoscopic skills by critically reviewing the existing literature. An iterative systematic search was carried out in MEDLINE, EMBASE, ERIC, Scopus, and PsychINFO, following a scoping review methodology. The included literature was analyzed iteratively using a thematic analysis approach. The study was reported in accordance with the STructured apprOach to the Reporting In healthcare education of Evidence Synthesis statement. From the search, 22 records were identified and included for analysis. A thematic analysis revealed the themes: access to training, protected training time, distribution of training, goal setting and testing, task design, and unsupervised training. The identified themes were based on learning theories including proficiency-based learning, deliberate practice, and self-regulated learning. Methods of instructional design vary widely in off-site training of laparoscopic skills. Implementation can be facilitated by organizing courses and training curricula following sound education theories such as proficiency-based learning and deliberate practice. Directed self-regulated learning has the potential to improve off-site laparoscopic skills training; however, further studies are needed to demonstrate the effect of this type of instructional design.

Design Approaches to Support Preservice Teachers in Scientific Modeling

NASA Astrophysics Data System (ADS)

Kenyon, Lisa; Davis, Elizabeth A.; Hug, Barbara

2011-02-01

Engaging children in scientific practices is hard for beginning teachers. One such scientific practice with which beginning teachers may have limited experience is scientific modeling. We have iteratively designed preservice teacher learning experiences and materials intended to help teachers achieve learning goals associated with scientific modeling. Our work has taken place across multiple years at three university sites, with preservice teachers focused on early childhood, elementary, and middle school teaching. Based on results from our empirical studies supporting these design decisions, we discuss design features of our modeling instruction in each iteration. Our results suggest some successes in supporting preservice teachers in engaging students in modeling practice. We propose design principles that can guide science teacher educators in incorporating modeling in teacher education.

e-Learning Application for Machine Maintenance Process using Iterative Method in XYZ Company

NASA Astrophysics Data System (ADS)

Nurunisa, Suaidah; Kurniawati, Amelia; Pramuditya Soesanto, Rayinda; Yunan Kurnia Septo Hediyanto, Umar

2016-02-01

XYZ Company is a company based on manufacturing part for airplane, one of the machine that is categorized as key facility in the company is Millac 5H6P. As a key facility, the machines should be assured to work well and in peak condition, therefore, maintenance process is needed periodically. From the data gathering, it is known that there are lack of competency from the maintenance staff to maintain different type of machine which is not assigned by the supervisor, this indicate that knowledge which possessed by maintenance staff are uneven. The purpose of this research is to create knowledge-based e-learning application as a realization from externalization process in knowledge transfer process to maintain the machine. The application feature are adjusted for maintenance purpose using e-learning framework for maintenance process, the content of the application support multimedia for learning purpose. QFD is used in this research to understand the needs from user. The application is built using moodle with iterative method for software development cycle and UML Diagram. The result from this research is e-learning application as sharing knowledge media for maintenance staff in the company. From the test, it is known that the application make maintenance staff easy to understand the competencies.

A Mixed Methods Bounded Case Study: Data-Driven Decision Making within Professional Learning Communities for Response to Intervention

ERIC Educational Resources Information Center

Rodriguez, Gabriel R.

2017-01-01

A growing number of schools are implementing PLCs to address school improvement, staff engage with data to identify student needs and determine instructional interventions. This is a starting point for engaging in the iterative process of learning for the teach in order to increase student learning (Hord & Sommers, 2008). The iterative process…

Distant Supervision with Transductive Learning for Adverse Drug Reaction Identification from Electronic Medical Records

PubMed Central

Ikeda, Mitsuru

2017-01-01

Information extraction and knowledge discovery regarding adverse drug reaction (ADR) from large-scale clinical texts are very useful and needy processes. Two major difficulties of this task are the lack of domain experts for labeling examples and intractable processing of unstructured clinical texts. Even though most previous works have been conducted on these issues by applying semisupervised learning for the former and a word-based approach for the latter, they face with complexity in an acquisition of initial labeled data and ignorance of structured sequence of natural language. In this study, we propose automatic data labeling by distant supervision where knowledge bases are exploited to assign an entity-level relation label for each drug-event pair in texts, and then, we use patterns for characterizing ADR relation. The multiple-instance learning with expectation-maximization method is employed to estimate model parameters. The method applies transductive learning to iteratively reassign a probability of unknown drug-event pair at the training time. By investigating experiments with 50,998 discharge summaries, we evaluate our method by varying large number of parameters, that is, pattern types, pattern-weighting models, and initial and iterative weightings of relations for unlabeled data. Based on evaluations, our proposed method outperforms the word-based feature for NB-EM (iEM), MILR, and TSVM with F1 score of 11.3%, 9.3%, and 6.5% improvement, respectively. PMID:29090077

Conceptual design of data acquisition and control system for two Rf driver based negative ion source for fusion R&D

NASA Astrophysics Data System (ADS)

Soni, Jigensh; Yadav, R. K.; Patel, A.; Gahlaut, A.; Mistry, H.; Parmar, K. G.; Mahesh, V.; Parmar, D.; Prajapati, B.; Singh, M. J.; Bandyopadhyay, M.; Bansal, G.; Pandya, K.; Chakraborty, A.

2013-02-01

Twin Source - An Inductively coupled two RF driver based 180 kW, 1 MHz negative ion source experimental setup is initiated at IPR, Gandhinagar, under Indian program, with the objective of understanding the physics and technology of multi-driver coupling. Twin Source [1] (TS) also provides an intermediate platform between operational ROBIN [2] [5] and eight RF drivers based Indian test facility -INTF [3]. A twin source experiment requires a central system to provide control, data acquisition and communication interface, referred as TS-CODAC, for which a software architecture similar to ITER CODAC core system has been decided for implementation. The Core System is a software suite for ITER plant system manufacturers to use as a template for the development of their interface with CODAC. The ITER approach, in terms of technology, has been adopted for the TS-CODAC so as to develop necessary expertise for developing and operating a control system based on the ITER guidelines as similar configuration needs to be implemented for the INTF. This cost effective approach will provide an opportunity to evaluate and learn ITER CODAC technology, documentation, information technology and control system processes, on an operational machine. Conceptual design of the TS-CODAC system has been completed. For complete control of the system, approximately 200 Nos. control signals and 152 acquisition signals are needed. In TS-CODAC, control loop time required is within the range of 5ms - 10 ms, therefore for the control system, PLC (Siemens S-7 400) has been chosen as suggested in the ITER slow controller catalog. For the data acquisition, the maximum sampling interval required is 100 micro second, and therefore National Instruments (NI) PXIe system and NI 6259 digitizer cards have been selected as suggested in the ITER fast controller catalog. This paper will present conceptual design of TS -CODAC system based on ITER CODAC Core software and applicable plant system integration processes.

Enriching regulatory networks by bootstrap learning using optimised GO-based gene similarity and gene links mined from PubMed abstracts

DOE Office of Scientific and Technical Information (OSTI.GOV)

Taylor, Ronald C.; Sanfilippo, Antonio P.; McDermott, Jason E.

2011-02-18

Transcriptional regulatory networks are being determined using “reverse engineering” methods that infer connections based on correlations in gene state. Corroboration of such networks through independent means such as evidence from the biomedical literature is desirable. Here, we explore a novel approach, a bootstrapping version of our previous Cross-Ontological Analytic method (XOA) that can be used for semi-automated annotation and verification of inferred regulatory connections, as well as for discovery of additional functional relationships between the genes. First, we use our annotation and network expansion method on a biological network learned entirely from the literature. We show how new relevant linksmore » between genes can be iteratively derived using a gene similarity measure based on the Gene Ontology that is optimized on the input network at each iteration. Second, we apply our method to annotation, verification, and expansion of a set of regulatory connections found by the Context Likelihood of Relatedness algorithm.« less

Intelligent tuning method of PID parameters based on iterative learning control for atomic force microscopy.

PubMed

Liu, Hui; Li, Yingzi; Zhang, Yingxu; Chen, Yifu; Song, Zihang; Wang, Zhenyu; Zhang, Suoxin; Qian, Jianqiang

2018-01-01

Proportional-integral-derivative (PID) parameters play a vital role in the imaging process of an atomic force microscope (AFM). Traditional parameter tuning methods require a lot of manpower and it is difficult to set PID parameters in unattended working environments. In this manuscript, an intelligent tuning method of PID parameters based on iterative learning control is proposed to self-adjust PID parameters of the AFM according to the sample topography. This method gets enough information about the output signals of PID controller and tracking error, which will be used to calculate the proper PID parameters, by repeated line scanning until convergence before normal scanning to learn the topography. Subsequently, the appropriate PID parameters are obtained by fitting method and then applied to the normal scanning process. The feasibility of the method is demonstrated by the convergence analysis. Simulations and experimental results indicate that the proposed method can intelligently tune PID parameters of the AFM for imaging different topographies and thus achieve good tracking performance. Copyright © 2017 Elsevier Ltd. All rights reserved.

Learning by Restorying

ERIC Educational Resources Information Center

Slabon, Wayne A.; Richards, Randy L.; Dennen, Vanessa P.

2014-01-01

In this paper, we introduce restorying, a pedagogical approach based on social constructivism that employs successive iterations of rewriting and discussing personal, student-generated, domain-relevant stories to promote conceptual application, critical thinking, and ill-structured problem solving skills. Using a naturalistic, qualitative case…

Development of an Online Smartphone-Based eLearning Nutrition Education Program for Low-Income Individuals.

PubMed

Stotz, Sarah; Lee, Jung Sun

2018-01-01

The objective of this report was to describe the development process of an innovative smartphone-based electronic learning (eLearning) nutrition education program targeted to Supplemental Nutrition Assistance Program-Education-eligible individuals, entitled Food eTalk. Lessons learned from the Food eTalk development process suggest that it is critical to include all key team members from the program's inception using effective inter-team communication systems, understand the unique resources needed, budget ample time for development, and employ an iterative development and evaluation model. These lessons have implications for researchers and funding agencies in developing an innovative evidence-based eLearning nutrition education program to an increasingly technology-savvy, low-income audience. Copyright © 2016 Society for Nutrition Education and Behavior. Published by Elsevier Inc. All rights reserved.

The Development of Instruments to Measure Motivational Interviewing Skill Acquisition for School-Based Personnel

ERIC Educational Resources Information Center

Small, Jason W.; Lee, Jon; Frey, Andy J.; Seeley, John R.; Walker, Hill M.

2014-01-01

As specialized instructional support personnel begin learning and using motivational interviewing (MI) techniques in school-based settings, there is growing need for context-specific measures to assess initial MI skill development. In this article, we describe the iterative development and preliminary evaluation of two measures of MI skill adapted…

Panel Finds Few Learning Benefits in High-Stakes Exams

ERIC Educational Resources Information Center

Sparks, Sarah D.

2011-01-01

As Congress debates how to structure the next iteration of federal school accountability, a new national study has raised serious concerns about the effectiveness of test-based incentives to improve education. A blue-ribbon committee of the National Academies' National Research Council undertook a nearly decade-long study of test-based incentive…

Fuzzy adaptive iterative learning coordination control of second-order multi-agent systems with imprecise communication topology structure

NASA Astrophysics Data System (ADS)

Chen, Jiaxi; Li, Junmin

2018-02-01

In this paper, we investigate the perfect consensus problem for second-order linearly parameterised multi-agent systems (MAS) with imprecise communication topology structure. Takagi-Sugeno (T-S) fuzzy models are presented to describe the imprecise communication topology structure of leader-following MAS, and a distributed adaptive iterative learning control protocol is proposed with the dynamic of leader unknown to any of the agent. The proposed protocol guarantees that the follower agents can track the leader perfectly on [0,T] for the consensus problem. Under alignment condition, a sufficient condition of the consensus for closed-loop MAS is given based on Lyapunov stability theory. Finally, a numerical example and a multiple pendulum system are given to illustrate the effectiveness of the proposed algorithm.

A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

PubMed Central

Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O.

2016-01-01

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems. PMID:28025566

Performance improvement of robots using a learning control scheme

NASA Technical Reports Server (NTRS)

Krishna, Ramuhalli; Chiang, Pen-Tai; Yang, Jackson C. S.

1987-01-01

Many applications of robots require that the same task be repeated a number of times. In such applications, the errors associated with one cycle are also repeated every cycle of the operation. An off-line learning control scheme is used here to modify the command function which would result in smaller errors in the next operation. The learning scheme is based on a knowledge of the errors and error rates associated with each cycle. Necessary conditions for the iterative scheme to converge to zero errors are derived analytically considering a second order servosystem model. Computer simulations show that the errors are reduced at a faster rate if the error rate is included in the iteration scheme. The results also indicate that the scheme may increase the magnitude of errors if the rate information is not included in the iteration scheme. Modification of the command input using a phase and gain adjustment is also proposed to reduce the errors with one attempt. The scheme is then applied to a computer model of a robot system similar to PUMA 560. Improved performance of the robot is shown by considering various cases of trajectory tracing. The scheme can be successfully used to improve the performance of actual robots within the limitations of the repeatability and noise characteristics of the robot.

A 2D systems approach to iterative learning control for discrete linear processes with zero Markov parameters

NASA Astrophysics Data System (ADS)

Hladowski, Lukasz; Galkowski, Krzysztof; Cai, Zhonglun; Rogers, Eric; Freeman, Chris T.; Lewin, Paul L.

2011-07-01

In this article a new approach to iterative learning control for the practically relevant case of deterministic discrete linear plants with uniform rank greater than unity is developed. The analysis is undertaken in a 2D systems setting that, by using a strong form of stability for linear repetitive processes, allows simultaneous consideration of both trial-to-trial error convergence and along the trial performance, resulting in design algorithms that can be computed using linear matrix inequalities (LMIs). Finally, the control laws are experimentally verified on a gantry robot that replicates a pick and place operation commonly found in a number of applications to which iterative learning control is applicable.

Increasing High School Student Interest in Science: An Action Research Study

NASA Astrophysics Data System (ADS)

Vartuli, Cindy A.

An action research study was conducted to determine how to increase student interest in learning science and pursuing a STEM career. The study began by exploring 10th-grade student and teacher perceptions of student interest in science in order to design an instructional strategy for stimulating student interest in learning and pursuing science. Data for this study included responses from 270 students to an on-line science survey and interviews with 11 students and eight science teachers. The action research intervention included two iterations of the STEM Career Project. The first iteration introduced four chemistry classes to the intervention. The researcher used student reflections and a post-project survey to determine if the intervention had influence on the students' interest in pursuing science. The second iteration was completed by three science teachers who had implemented the intervention with their chemistry classes, using student reflections and post-project surveys, as a way to make further procedural refinements and improvements to the intervention and measures. Findings from the exploratory phase of the study suggested students generally had interest in learning science but increasing that interest required including personally relevant applications and laboratory experiences. The intervention included a student-directed learning module in which students investigated three STEM careers and presented information on one of their chosen careers. The STEM Career Project enabled students to explore career possibilities in order to increase their awareness of STEM careers. Findings from the first iteration of the intervention suggested a positive influence on student interest in learning and pursuing science. The second iteration included modifications to the intervention resulting in support for the findings of the first iteration. Results of the second iteration provided modifications that would allow the project to be used for different academic levels. Insights from conducting the action research study provided the researcher with effective ways to make positive changes in her own teaching praxis and the tools used to improve student awareness of STEM career options.

Adaptive iterative learning control of a class of nonlinear time-delay systems with unknown backlash-like hysteresis input and control direction.

PubMed

Wei, Jianming; Zhang, Youan; Sun, Meimei; Geng, Baoliang

2017-09-01

This paper presents an adaptive iterative learning control scheme for a class of nonlinear systems with unknown time-varying delays and control direction preceded by unknown nonlinear backlash-like hysteresis. Boundary layer function is introduced to construct an auxiliary error variable, which relaxes the identical initial condition assumption of iterative learning control. For the controller design, integral Lyapunov function candidate is used, which avoids the possible singularity problem by introducing hyperbolic tangent funciton. After compensating for uncertainties with time-varying delays by combining appropriate Lyapunov-Krasovskii function with Young's inequality, an adaptive iterative learning control scheme is designed through neural approximation technique and Nussbaum function method. On the basis of the hyperbolic tangent function's characteristics, the system output is proved to converge to a small neighborhood of the desired trajectory by constructing Lyapunov-like composite energy function (CEF) in two cases, while keeping all the closed-loop signals bounded. Finally, a simulation example is presented to verify the effectiveness of the proposed approach. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Automating Rule Strengths in Expert Systems.

DTIC Science & Technology

1987-05-01

systems were designed in an incremental, iterative way. One of the most easily identifiable phases in this process, sometimes called tuning, consists...attenuators. The designer of the knowledge-based system must determine (synthesize) or adjust (xfine, if estimates of the values are given) these...values. We consider two ways in which the designer can learn the values. We call the first model of learning the complete case and the second model the

Learning to read aloud: A neural network approach using sparse distributed memory

NASA Technical Reports Server (NTRS)

Joglekar, Umesh Dwarkanath

1989-01-01

An attempt to solve a problem of text-to-phoneme mapping is described which does not appear amenable to solution by use of standard algorithmic procedures. Experiments based on a model of distributed processing are also described. This model (sparse distributed memory (SDM)) can be used in an iterative supervised learning mode to solve the problem. Additional improvements aimed at obtaining better performance are suggested.

Proposing a new iterative learning control algorithm based on a non-linear least square formulation - Minimising draw-in errors

NASA Astrophysics Data System (ADS)

Endelt, B.

2017-09-01

Forming operation are subject to external disturbances and changing operating conditions e.g. new material batch, increasing tool temperature due to plastic work, material properties and lubrication is sensitive to tool temperature. It is generally accepted that forming operations are not stable over time and it is not uncommon to adjust the process parameters during the first half hour production, indicating that process instability is gradually developing over time. Thus, in-process feedback control scheme might not-be necessary to stabilize the process and an alternative approach is to apply an iterative learning algorithm, which can learn from previously produced parts i.e. a self learning system which gradually reduces error based on historical process information. What is proposed in the paper is a simple algorithm which can be applied to a wide range of sheet-metal forming processes. The input to the algorithm is the final flange edge geometry and the basic idea is to reduce the least-square error between the current flange geometry and a reference geometry using a non-linear least square algorithm. The ILC scheme is applied to a square deep-drawing and the Numisheet’08 S-rail benchmark problem, the numerical tests shows that the proposed control scheme is able control and stabilise both processes.

Experiments on individual strategy updating in iterated snowdrift game under random rematching.

PubMed

Qi, Hang; Ma, Shoufeng; Jia, Ning; Wang, Guangchao

2015-03-07

How do people actually play the iterated snowdrift games, particularly under random rematching protocol is far from well explored. Two sets of laboratory experiments on snowdrift game were conducted to investigate human strategy updating rules. Four groups of subjects were modeled by experience-weighted attraction learning theory at individual-level. Three out of the four groups (75%) passed model validation. Substantial heterogeneity is observed among the players who update their strategies in four typical types, whereas rare people behave like belief-based learners even under fixed pairing. Most subjects (63.9%) adopt the reinforcement learning (or alike) rules; but, interestingly, the performance of averaged reinforcement learners suffered. It is observed that two factors seem to benefit players in competition, i.e., the sensitivity to their recent experiences and the overall consideration of forgone payoffs. Moreover, subjects with changing opponents tend to learn faster based on their own recent experience, and display more diverse strategy updating rules than they do with fixed opponent. These findings suggest that most of subjects do apply reinforcement learning alike updating rules even under random rematching, although these rules may not improve their performance. The findings help evolutionary biology researchers to understand sophisticated human behavioral strategies in social dilemmas. Copyright © 2015 Elsevier Ltd. All rights reserved.

Exploring emerging learning needs: a UK-wide consultation on environmental sustainability learning objectives for medical education.

PubMed

Walpole, Sarah C; Mortimer, Frances; Inman, Alice; Braithwaite, Isobel; Thompson, Trevor

2015-12-24

This study aimed to engage wide-ranging stakeholders and develop consensus learning objectives for undergraduate and postgraduate medical education. A UK-wide consultation garnered opinions of healthcare students, healthcare educators and other key stakeholders about environmental sustainability in medical education. The policy Delphi approach informed this study. Draft learning objectives were revised iteratively during three rounds of consultation: online questionnaire or telephone interview, face-to-face seminar and email consultation. Twelve draft learning objectives were developed based on review of relevant literature. In round one, 64 participants' median ratings of the learning objectives were 3.5 for relevance and 3.0 for feasibility on a Likert scale of one to four. Revisions were proposed, e.g. to highlight relevance to public health and professionalism. Thirty three participants attended round two. Conflicting opinions were explored. Added content areas included health benefits of sustainable behaviours. To enhance usability, restructuring provided three overarching learning objectives, each with subsidiary points. All participants from rounds one and two were contacted in round three, and no further edits were required. This is the first attempt to define consensus learning objectives for medical students about environmental sustainability. Allowing a wide range of stakeholders to comment on multiple iterations of the document stimulated their engagement with the issues raised and ownership of the resulting learning objectives.

Cognitive Model of Trust Dynamics Predicts Human Behavior within and between Two Games of Strategic Interaction with Computerized Confederate Agents

PubMed Central

Collins, Michael G.; Juvina, Ion; Gluck, Kevin A.

2016-01-01

When playing games of strategic interaction, such as iterated Prisoner's Dilemma and iterated Chicken Game, people exhibit specific within-game learning (e.g., learning a game's optimal outcome) as well as transfer of learning between games (e.g., a game's optimal outcome occurring at a higher proportion when played after another game). The reciprocal trust players develop during the first game is thought to mediate transfer of learning effects. Recently, a computational cognitive model using a novel trust mechanism has been shown to account for human behavior in both games, including the transfer between games. We present the results of a study in which we evaluate the model's a priori predictions of human learning and transfer in 16 different conditions. The model's predictive validity is compared against five model variants that lacked a trust mechanism. The results suggest that a trust mechanism is necessary to explain human behavior across multiple conditions, even when a human plays against a non-human agent. The addition of a trust mechanism to the other learning mechanisms within the cognitive architecture, such as sequence learning, instance-based learning, and utility learning, leads to better prediction of the empirical data. It is argued that computational cognitive modeling is a useful tool for studying trust development, calibration, and repair. PMID:26903892

Fundamental concepts of problem-based learning for the new facilitator.

PubMed Central

Kanter, S L

1998-01-01

Problem-based learning (PBL) is a powerful small group learning tool that should be part of the armamentarium of every serious educator. Classic PBL uses ill-structured problems to simulate the conditions that occur in the real environment. Students play an active role and use an iterative process of seeking new information based on identified learning issues, restructuring the information in light of the new knowledge, gathering additional information, and so forth. Faculty play a facilitatory role, not a traditional instructional role, by posing metacognitive questions to students. These questions serve to assist in organizing, generalizing, and evaluating knowledge; to probe for supporting evidence; to explore faulty reasoning; to stimulate discussion of attitudes; and to develop self-directed learning and self-assessment skills. Professional librarians play significant roles in the PBL environment extending from traditional service provider to resource person to educator. Students and faculty usually find the learning experience productive and enjoyable. PMID:9681175

Composition of web services using Markov decision processes and dynamic programming.

PubMed

Uc-Cetina, Víctor; Moo-Mena, Francisco; Hernandez-Ucan, Rafael

2015-01-01

We propose a Markov decision process model for solving the Web service composition (WSC) problem. Iterative policy evaluation, value iteration, and policy iteration algorithms are used to experimentally validate our approach, with artificial and real data. The experimental results show the reliability of the model and the methods employed, with policy iteration being the best one in terms of the minimum number of iterations needed to estimate an optimal policy, with the highest Quality of Service attributes. Our experimental work shows how the solution of a WSC problem involving a set of 100,000 individual Web services and where a valid composition requiring the selection of 1,000 services from the available set can be computed in the worst case in less than 200 seconds, using an Intel Core i5 computer with 6 GB RAM. Moreover, a real WSC problem involving only 7 individual Web services requires less than 0.08 seconds, using the same computational power. Finally, a comparison with two popular reinforcement learning algorithms, sarsa and Q-learning, shows that these algorithms require one or two orders of magnitude and more time than policy iteration, iterative policy evaluation, and value iteration to handle WSC problems of the same complexity.

Model-Free Primitive-Based Iterative Learning Control Approach to Trajectory Tracking of MIMO Systems With Experimental Validation.

PubMed

Radac, Mircea-Bogdan; Precup, Radu-Emil; Petriu, Emil M

2015-11-01

This paper proposes a novel model-free trajectory tracking of multiple-input multiple-output (MIMO) systems by the combination of iterative learning control (ILC) and primitives. The optimal trajectory tracking solution is obtained in terms of previously learned solutions to simple tasks called primitives. The library of primitives that are stored in memory consists of pairs of reference input/controlled output signals. The reference input primitives are optimized in a model-free ILC framework without using knowledge of the controlled process. The guaranteed convergence of the learning scheme is built upon a model-free virtual reference feedback tuning design of the feedback decoupling controller. Each new complex trajectory to be tracked is decomposed into the output primitives regarded as basis functions. The optimal reference input for the control system to track the desired trajectory is next recomposed from the reference input primitives. This is advantageous because the optimal reference input is computed straightforward without the need to learn from repeated executions of the tracking task. In addition, the optimization problem specific to trajectory tracking of square MIMO systems is decomposed in a set of optimization problems assigned to each separate single-input single-output control channel that ensures a convenient model-free decoupling. The new model-free primitive-based ILC approach is capable of planning, reasoning, and learning. A case study dealing with the model-free control tuning for a nonlinear aerodynamic system is included to validate the new approach. The experimental results are given.

Enhancement Process of Didactic Strategies in a Degree Course for Pre-Service Teachers

ERIC Educational Resources Information Center

Garcias, Adolfina Pérez; Marín, Victoria I.

2017-01-01

This paper presents a study on the enhancement of didactic strategies based on the idea of personal learning environments (PLE). It was conducted through three iterative cycles during three consecutive academic years according to the phases of design-based research applied to teaching in a university course for pre-service teachers in the…

Examining the Characteristics of Student Postings That Are Liked and Linked in a CSCL Environment

ERIC Educational Resources Information Center

Makos, Alexandra; Lee, Kyungmee; Zingaro, Daniel

2015-01-01

This case study is the first iteration of a large-scale design-based research project to improve Pepper, an interactive discussion-based learning environment. In this phase, we designed and implemented two social features to scaffold positive learner interactivity behaviors: a "Like" button and linking tool. A mixed-methods approach was…

Embodied Design: Constructing Means for Constructing Meaning

ERIC Educational Resources Information Center

Abrahamson, Dor

2009-01-01

Design-based research studies are conducted as iterative implementation-analysis-modification cycles, in which emerging theoretical models and pedagogically plausible activities are reciprocally tuned toward each other as a means of investigating conjectures pertaining to mechanisms underlying content teaching and learning. Yet this approach, even…

Active flow separation control by a position-based iterative learning control algorithm with experimental validation

NASA Astrophysics Data System (ADS)

Cai, Zhonglun; Chen, Peng; Angland, David; Zhang, Xin

2014-03-01

A novel iterative learning control (ILC) algorithm was developed and applied to an active flow control problem. The technique uses pulsed air jets to delay flow separation on a two-element high-lift wing. The ILC algorithm uses position-based pressure measurements to update the actuation. The method was experimentally tested on a wing model in a 0.9 m × 0.6 m low-speed wind tunnel at the University of Southampton. Compressed air and fast switching solenoid valves were used as actuators to excite the flow, and the pressure distribution around the chord of the wing was measured as a feedback control signal for the ILC controller. Experimental results showed that the actuation was able to delay the separation and increase the lift by approximately 10%-15%. By using the ILC algorithm, the controller was able to find the optimum control input and maintain the improvement despite sudden changes of the separation position.

Not All Wizards Are from Oz: Iterative Design of Intelligent Learning Environments by Communication Capacity Tapering

ERIC Educational Resources Information Center

Mavrikis, Manolis; Gutierrez-Santos, Sergio

2010-01-01

This paper presents a methodology for the design of intelligent learning environments. We recognise that in the educational technology field, theory development and system-design should be integrated and rely on an iterative process that addresses: (a) the difficulty to elicit precise, concise, and operationalized knowledge from "experts" and (b)…

Foucauldian Iterative Learning Conversations--An Example of Organisational Change: Developing Conjoint-Work between EPS and Social Workers

ERIC Educational Resources Information Center

Apter, Brian

2014-01-01

An organisational change-process in a UK local authority (LA) over two years is examined using transcribed excerpts from three meetings. The change-process is analysed using a Foucauldian analytical tool--Iterative Learning Conversations (ILCS). An Educational Psychology Service was changed from being primarily an education-focussed…

Learning Efficient Sparse and Low Rank Models.

PubMed

Sprechmann, P; Bronstein, A M; Sapiro, G

2015-09-01

Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with parsimony-promoting terms. The inherently sequential structure and data-dependent complexity and latency of iterative optimization constitute a major limitation in many applications requiring real-time performance or involving large-scale data. Another limitation encountered by these modeling techniques is the difficulty of their inclusion in discriminative learning scenarios. In this work, we propose to move the emphasis from the model to the pursuit algorithm, and develop a process-centric view of parsimonious modeling, in which a learned deterministic fixed-complexity pursuit process is used in lieu of iterative optimization. We show a principled way to construct learnable pursuit process architectures for structured sparse and robust low rank models, derived from the iteration of proximal descent algorithms. These architectures learn to approximate the exact parsimonious representation at a fraction of the complexity of the standard optimization methods. We also show that appropriate training regimes allow to naturally extend parsimonious models to discriminative settings. State-of-the-art results are demonstrated on several challenging problems in image and audio processing with several orders of magnitude speed-up compared to the exact optimization algorithms.

Fast and Epsilon-Optimal Discretized Pursuit Learning Automata.

PubMed

Zhang, JunQi; Wang, Cheng; Zhou, MengChu

2015-10-01

Learning automata (LA) are powerful tools for reinforcement learning. A discretized pursuit LA is the most popular one among them. During an iteration its operation consists of three basic phases: 1) selecting the next action; 2) finding the optimal estimated action; and 3) updating the state probability. However, when the number of actions is large, the learning becomes extremely slow because there are too many updates to be made at each iteration. The increased updates are mostly from phases 1 and 3. A new fast discretized pursuit LA with assured ε -optimality is proposed to perform both phases 1 and 3 with the computational complexity independent of the number of actions. Apart from its low computational complexity, it achieves faster convergence speed than the classical one when operating in stationary environments. This paper can promote the applications of LA toward the large-scale-action oriented area that requires efficient reinforcement learning tools with assured ε -optimality, fast convergence speed, and low computational complexity for each iteration.

Introducing 12 year-olds to elementary particles

NASA Astrophysics Data System (ADS)

Wiener, Gerfried J.; Schmeling, Sascha M.; Hopf, Martin

2017-07-01

We present a new learning unit, which introduces 12 year-olds to the subatomic structure of matter. The learning unit was iteratively developed as a design-based research project using the technique of probing acceptance. We give a brief overview of the unit’s final version, discuss its key ideas and main concepts, and conclude by highlighting the main implications of our research, which we consider to be most promising for use in the physics classroom.

Finding the Optimal Guidance for Enhancing Anchored Instruction

ERIC Educational Resources Information Center

Zydney, Janet Mannheimer; Bathke, Arne; Hasselbring, Ted S.

2014-01-01

This study investigated the effect of different methods of guidance with anchored instruction on students' mathematical problem-solving performance. The purpose of this research was to iteratively design a learning environment to find the optimal level of guidance. Two iterations of the software were compared. The first iteration used explicit…

Leveraging Failure in Design Research

ERIC Educational Resources Information Center

Lobato, Joanne; Walters, C. David; Hohensee, Charles; Gruver, John; Diamond, Jaime Marie

2015-01-01

Even in the resource-rich, more ideal conditions of many design-based classroom interventions, unexpected events can lead to disappointing results in student learning. However, if later iterations in a design research study are more successful, the previous failures can provide opportunities for comparisons to reveal subtle differences in…

Composition of Web Services Using Markov Decision Processes and Dynamic Programming

PubMed Central

Uc-Cetina, Víctor; Moo-Mena, Francisco; Hernandez-Ucan, Rafael

2015-01-01

We propose a Markov decision process model for solving the Web service composition (WSC) problem. Iterative policy evaluation, value iteration, and policy iteration algorithms are used to experimentally validate our approach, with artificial and real data. The experimental results show the reliability of the model and the methods employed, with policy iteration being the best one in terms of the minimum number of iterations needed to estimate an optimal policy, with the highest Quality of Service attributes. Our experimental work shows how the solution of a WSC problem involving a set of 100,000 individual Web services and where a valid composition requiring the selection of 1,000 services from the available set can be computed in the worst case in less than 200 seconds, using an Intel Core i5 computer with 6 GB RAM. Moreover, a real WSC problem involving only 7 individual Web services requires less than 0.08 seconds, using the same computational power. Finally, a comparison with two popular reinforcement learning algorithms, sarsa and Q-learning, shows that these algorithms require one or two orders of magnitude and more time than policy iteration, iterative policy evaluation, and value iteration to handle WSC problems of the same complexity. PMID:25874247

Development of a multimedia educational programme for first-time hearing aid users: a participatory design.

PubMed

Ferguson, Melanie; Leighton, Paul; Brandreth, Marian; Wharrad, Heather

2018-05-02

To develop content for a series of interactive video tutorials (or reusable learning objects, RLOs) for first-time adult hearing aid users, to enhance knowledge of hearing aids and communication. RLO content was based on an electronically-delivered Delphi review, workshops, and iterative peer-review and feedback using a mixed-methods participatory approach. An expert panel of 33 hearing healthcare professionals, and workshops involving 32 hearing aid users and 11 audiologists. This ensured that social, emotional and practical experiences of the end-user alongside clinical validity were captured. Content for evidence-based, self-contained RLOs based on pedagogical principles was developed for delivery via DVD for television, PC or internet. Content was developed based on Delphi review statements about essential information that reached consensus (≥90%), visual representations of relevant concepts relating to hearing aids and communication, and iterative peer-review and feedback of content. This participatory approach recognises and involves key stakeholders in the design process to create content for a user-friendly multimedia educational intervention, to supplement the clinical management of first-time hearing aid users. We propose participatory methodologies are used in the development of content for e-learning interventions in hearing-related research and clinical practice.

Teaching Engineering Design Through Paper Rockets

ERIC Educational Resources Information Center

Welling, Jonathan; Wright, Geoffrey A.

2018-01-01

The paper rocket activity described in this article effectively teaches the engineering design process (EDP) by engaging students in a problem-based learning activity that encourages iterative design. For example, the first rockets the students build typically only fly between 30 and 100 feet. As students test and evaluate their rocket designs,…

Is there a need for a specific educational scholarship for using e-learning in medical education?

PubMed

Sandars, John; Goh, Poh Sun

2016-10-01

We propose the need for a specific educational scholarship when using e-learning in medical education. Effective e-learning has additional factors that require specific critical attention, including the design and delivery of e-learning. An important aspect is the recognition that e-learning is a complex intervention, with several interconnecting components that have to be aligned. This alignment requires an essential iterative development process with usability testing. Effectiveness of e-learning in one context may not be fully realized in another context unless there is further consideration of applicability and scalability. We recommend a participatory approach for an educational scholarship for using e-learning in medical education, such as by action research or design-based research.

Developing Conceptual Understanding and Procedural Skill in Mathematics: An Iterative Process.

ERIC Educational Resources Information Center

Rittle-Johnson, Bethany; Siegler, Robert S.; Alibali, Martha Wagner

2001-01-01

Proposes that conceptual and procedural knowledge develop in an iterative fashion and improved problem representation is one mechanism underlying the relations between them. Two experiments were conducted with 5th and 6th grade students learning about decimal fractions. Results indicate conceptual and procedural knowledge do develop, iteratively,…

Rapid tomographic reconstruction based on machine learning for time-resolved combustion diagnostics

NASA Astrophysics Data System (ADS)

Yu, Tao; Cai, Weiwei; Liu, Yingzheng

2018-04-01

Optical tomography has attracted surged research efforts recently due to the progress in both the imaging concepts and the sensor and laser technologies. The high spatial and temporal resolutions achievable by these methods provide unprecedented opportunity for diagnosis of complicated turbulent combustion. However, due to the high data throughput and the inefficiency of the prevailing iterative methods, the tomographic reconstructions which are typically conducted off-line are computationally formidable. In this work, we propose an efficient inversion method based on a machine learning algorithm, which can extract useful information from the previous reconstructions and build efficient neural networks to serve as a surrogate model to rapidly predict the reconstructions. Extreme learning machine is cited here as an example for demonstrative purpose simply due to its ease of implementation, fast learning speed, and good generalization performance. Extensive numerical studies were performed, and the results show that the new method can dramatically reduce the computational time compared with the classical iterative methods. This technique is expected to be an alternative to existing methods when sufficient training data are available. Although this work is discussed under the context of tomographic absorption spectroscopy, we expect it to be useful also to other high speed tomographic modalities such as volumetric laser-induced fluorescence and tomographic laser-induced incandescence which have been demonstrated for combustion diagnostics.

Rapid tomographic reconstruction based on machine learning for time-resolved combustion diagnostics.

PubMed

Yu, Tao; Cai, Weiwei; Liu, Yingzheng

2018-04-01

Optical tomography has attracted surged research efforts recently due to the progress in both the imaging concepts and the sensor and laser technologies. The high spatial and temporal resolutions achievable by these methods provide unprecedented opportunity for diagnosis of complicated turbulent combustion. However, due to the high data throughput and the inefficiency of the prevailing iterative methods, the tomographic reconstructions which are typically conducted off-line are computationally formidable. In this work, we propose an efficient inversion method based on a machine learning algorithm, which can extract useful information from the previous reconstructions and build efficient neural networks to serve as a surrogate model to rapidly predict the reconstructions. Extreme learning machine is cited here as an example for demonstrative purpose simply due to its ease of implementation, fast learning speed, and good generalization performance. Extensive numerical studies were performed, and the results show that the new method can dramatically reduce the computational time compared with the classical iterative methods. This technique is expected to be an alternative to existing methods when sufficient training data are available. Although this work is discussed under the context of tomographic absorption spectroscopy, we expect it to be useful also to other high speed tomographic modalities such as volumetric laser-induced fluorescence and tomographic laser-induced incandescence which have been demonstrated for combustion diagnostics.

Learning-Based Adaptive Optimal Tracking Control of Strict-Feedback Nonlinear Systems.

PubMed

Gao, Weinan; Jiang, Zhong-Ping; Weinan Gao; Zhong-Ping Jiang; Gao, Weinan; Jiang, Zhong-Ping

2018-06-01

This paper proposes a novel data-driven control approach to address the problem of adaptive optimal tracking for a class of nonlinear systems taking the strict-feedback form. Adaptive dynamic programming (ADP) and nonlinear output regulation theories are integrated for the first time to compute an adaptive near-optimal tracker without any a priori knowledge of the system dynamics. Fundamentally different from adaptive optimal stabilization problems, the solution to a Hamilton-Jacobi-Bellman (HJB) equation, not necessarily a positive definite function, cannot be approximated through the existing iterative methods. This paper proposes a novel policy iteration technique for solving positive semidefinite HJB equations with rigorous convergence analysis. A two-phase data-driven learning method is developed and implemented online by ADP. The efficacy of the proposed adaptive optimal tracking control methodology is demonstrated via a Van der Pol oscillator with time-varying exogenous signals.

Machine learning in motion control

NASA Technical Reports Server (NTRS)

Su, Renjeng; Kermiche, Noureddine

1989-01-01

The existing methodologies for robot programming originate primarily from robotic applications to manufacturing, where uncertainties of the robots and their task environment may be minimized by repeated off-line modeling and identification. In space application of robots, however, a higher degree of automation is required for robot programming because of the desire of minimizing the human intervention. We discuss a new paradigm of robotic programming which is based on the concept of machine learning. The goal is to let robots practice tasks by themselves and the operational data are used to automatically improve their motion performance. The underlying mathematical problem is to solve the problem of dynamical inverse by iterative methods. One of the key questions is how to ensure the convergence of the iterative process. There have been a few small steps taken into this important approach to robot programming. We give a representative result on the convergence problem.

A Machine Learning System for Analyzing Human Tactics in a Game

NASA Astrophysics Data System (ADS)

Ito, Hirotaka; Tanaka, Toshimitsu; Sugie, Noboru

In order to realize advanced man-machine interfaces, it is desired to develop a system that can infer the mental state of human users and then return appropriate responses. As the first step toward the above goal, we developed a system capable of inferring human tactics in a simple game played between the system and a human. We present a machine learning system that plays a color expectation game. The system infers the tactics of the opponent, and then decides the action based on the result. We employed a modified version of classifier system like XCS in order to design the system. In addition, three methods are proposed in order to accelerate the learning rate. They are a masking method, an iterative method, and tactics templates. The results of computer experiments confirmed that the proposed methods effectively accelerate the machine learning. The masking method and the iterative method are effective to a simple strategy that considers only a part of past information. However, study speed of these methods is not enough for the tactics that refers to a lot of past information. For the case, the tactics template was able to settle the study rapidly when the tactics is identified.

Low-rank structure learning via nonconvex heuristic recovery.

PubMed

Deng, Yue; Dai, Qionghai; Liu, Risheng; Zhang, Zengke; Hu, Sanqing

2013-03-01

In this paper, we propose a nonconvex framework to learn the essential low-rank structure from corrupted data. Different from traditional approaches, which directly utilizes convex norms to measure the sparseness, our method introduces more reasonable nonconvex measurements to enhance the sparsity in both the intrinsic low-rank structure and the sparse corruptions. We will, respectively, introduce how to combine the widely used ℓp norm (0 < p < 1) and log-sum term into the framework of low-rank structure learning. Although the proposed optimization is no longer convex, it still can be effectively solved by a majorization-minimization (MM)-type algorithm, with which the nonconvex objective function is iteratively replaced by its convex surrogate and the nonconvex problem finally falls into the general framework of reweighed approaches. We prove that the MM-type algorithm can converge to a stationary point after successive iterations. The proposed model is applied to solve two typical problems: robust principal component analysis and low-rank representation. Experimental results on low-rank structure learning demonstrate that our nonconvex heuristic methods, especially the log-sum heuristic recovery algorithm, generally perform much better than the convex-norm-based method (0 < p < 1) for both data with higher rank and with denser corruptions.

Iterating between Lessons on Concepts and Procedures Can Improve Mathematics Knowledge

ERIC Educational Resources Information Center

Rittle-Johnson, Bethany; Koedinger, Kenneth

2009-01-01

Background: Knowledge of concepts and procedures seems to develop in an iterative fashion, with increases in one type of knowledge leading to increases in the other type of knowledge. This suggests that iterating between lessons on concepts and procedures may improve learning. Aims: The purpose of the current study was to evaluate the…

Solving ill-posed inverse problems using iterative deep neural networks

NASA Astrophysics Data System (ADS)

Adler, Jonas; Öktem, Ozan

2017-12-01

We propose a partially learned approach for the solution of ill-posed inverse problems with not necessarily linear forward operators. The method builds on ideas from classical regularisation theory and recent advances in deep learning to perform learning while making use of prior information about the inverse problem encoded in the forward operator, noise model and a regularising functional. The method results in a gradient-like iterative scheme, where the ‘gradient’ component is learned using a convolutional network that includes the gradients of the data discrepancy and regulariser as input in each iteration. We present results of such a partially learned gradient scheme on a non-linear tomographic inversion problem with simulated data from both the Sheep-Logan phantom as well as a head CT. The outcome is compared against filtered backprojection and total variation reconstruction and the proposed method provides a 5.4 dB PSNR improvement over the total variation reconstruction while being significantly faster, giving reconstructions of 512 × 512 pixel images in about 0.4 s using a single graphics processing unit (GPU).

The Iterated Classification Game: A New Model of the Cultural Transmission of Language

PubMed Central

Swarup, Samarth; Gasser, Les

2010-01-01

The Iterated Classification Game (ICG) combines the Classification Game with the Iterated Learning Model (ILM) to create a more realistic model of the cultural transmission of language through generations. It includes both learning from parents and learning from peers. Further, it eliminates some of the chief criticisms of the ILM: that it does not study grounded languages, that it does not include peer learning, and that it builds in a bias for compositional languages. We show that, over the span of a few generations, a stable linguistic system emerges that can be acquired very quickly by each generation, is compositional, and helps the agents to solve the classification problem with which they are faced. The ICG also leads to a different interpretation of the language acquisition process. It suggests that the role of parents is to initialize the linguistic system of the child in such a way that subsequent interaction with peers results in rapid convergence to the correct language. PMID:20190877

Visual recognition and inference using dynamic overcomplete sparse learning.

PubMed

Murray, Joseph F; Kreutz-Delgado, Kenneth

2007-09-01

We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative world model and from it develop a simplified world model (SWM) based on a tractable variational approximation that is designed to enforce sparse coding. Recent developments in computational methods for learning overcomplete representations (Lewicki & Sejnowski, 2000; Teh, Welling, Osindero, & Hinton, 2003) suggest that overcompleteness can be useful for visual tasks, and we use an overcomplete dictionary learning algorithm (Kreutz-Delgado, et al., 2003) as a preprocessing stage to produce accurate, sparse codings of images. Inference is performed by constructing a dynamic multilayer network with feedforward, feedback, and lateral connections, which is trained to approximate the SWM. Learning is done with a variant of the back-propagation-through-time algorithm, which encourages convergence to desired states within a fixed number of iterations. Vision tasks require large networks, and to make learning efficient, we take advantage of the sparsity of each layer to update only a small subset of elements in a large weight matrix at each iteration. Experiments on a set of rotated objects demonstrate various types of visual inference and show that increasing the degree of overcompleteness improves recognition performance in difficult scenes with occluded objects in clutter.

Multi-modal classification of neurodegenerative disease by progressive graph-based transductive learning

PubMed Central

Wang, Zhengxia; Zhu, Xiaofeng; Adeli, Ehsan; Zhu, Yingying; Nie, Feiping; Munsell, Brent

2018-01-01

Graph-based transductive learning (GTL) is a powerful machine learning technique that is used when sufficient training data is not available. In particular, conventional GTL approaches first construct a fixed inter-subject relation graph that is based on similarities in voxel intensity values in the feature domain, which can then be used to propagate the known phenotype data (i.e., clinical scores and labels) from the training data to the testing data in the label domain. However, this type of graph is exclusively learned in the feature domain, and primarily due to outliers in the observed features, may not be optimal for label propagation in the label domain. To address this limitation, a progressive GTL (pGTL) method is proposed that gradually finds an intrinsic data representation that more accurately aligns imaging features with the phenotype data. In general, optimal feature-to-phenotype alignment is achieved using an iterative approach that: (1) refines inter-subject relationships observed in the feature domain by using the learned intrinsic data representation in the label domain, (2) updates the intrinsic data representation from the refined inter-subject relationships, and (3) verifies the intrinsic data representation on the training data to guarantee an optimal classification when applied to testing data. Additionally, the iterative approach is extended to multi-modal imaging data to further improve pGTL classification accuracy. Using Alzheimer’s disease and Parkinson’s disease study data, the classification accuracy of the proposed pGTL method is compared to several state-of-the-art classification methods, and the results show pGTL can more accurately identify subjects, even at different progression stages, in these two study data sets. PMID:28551556

Active Player Modeling in the Iterated Prisoner's Dilemma

PubMed Central

Park, Hyunsoo; Kim, Kyung-Joong

2016-01-01

The iterated prisoner's dilemma (IPD) is well known within the domain of game theory. Although it is relatively simple, it can also elucidate important problems related to cooperation and trust. Generally, players can predict their opponents' actions when they are able to build a precise model of their behavior based on their game playing experience. However, it is difficult to make such predictions based on a limited number of games. The creation of a precise model requires the use of not only an appropriate learning algorithm and framework but also a good dataset. Active learning approaches have recently been introduced to machine learning communities. The approach can usually produce informative datasets with relatively little effort. Therefore, we have proposed an active modeling technique to predict the behavior of IPD players. The proposed method can model the opponent player's behavior while taking advantage of interactive game environments. This experiment used twelve representative types of players as opponents, and an observer used an active modeling algorithm to model these opponents. This observer actively collected data and modeled the opponent's behavior online. Most of our data showed that the observer was able to build, through direct actions, a more accurate model of an opponent's behavior than when the data were collected through random actions. PMID:26989405

Active Player Modeling in the Iterated Prisoner's Dilemma.

PubMed

Park, Hyunsoo; Kim, Kyung-Joong

2016-01-01

The iterated prisoner's dilemma (IPD) is well known within the domain of game theory. Although it is relatively simple, it can also elucidate important problems related to cooperation and trust. Generally, players can predict their opponents' actions when they are able to build a precise model of their behavior based on their game playing experience. However, it is difficult to make such predictions based on a limited number of games. The creation of a precise model requires the use of not only an appropriate learning algorithm and framework but also a good dataset. Active learning approaches have recently been introduced to machine learning communities. The approach can usually produce informative datasets with relatively little effort. Therefore, we have proposed an active modeling technique to predict the behavior of IPD players. The proposed method can model the opponent player's behavior while taking advantage of interactive game environments. This experiment used twelve representative types of players as opponents, and an observer used an active modeling algorithm to model these opponents. This observer actively collected data and modeled the opponent's behavior online. Most of our data showed that the observer was able to build, through direct actions, a more accurate model of an opponent's behavior than when the data were collected through random actions.

Playing Modeling Games in the Science Classroom: The Case for Disciplinary Integration

ERIC Educational Resources Information Center

Sengupta, Pratim; Clark, Doug

2016-01-01

The authors extend the theory of "disciplinary integration" of games for science education beyond the virtual world of games, and identify two key themes of a practice-based theoretical commitment to science learning: (1) materiality in the classroom, and (2) iterative design of multiple, complementary, symbolic inscriptions (e.g.,…

Onwards and Upwards: Space, Placement, and Liminality in Adult ESOL Classes

ERIC Educational Resources Information Center

Baynham, Mike; Simpson, James

2010-01-01

The extensive literature on classroom-based second language learning makes little attempt to situate the classroom itself in social and multilingual sociolinguistic space, in the complex and iterative networks of encounters and interactions that make up daily life. Daily life is routinely evoked and "brought into" the classroom as a…

Scale-Up: Improving Large Enrollment Physics Courses

NASA Astrophysics Data System (ADS)

Beichner, Robert

1999-11-01

The Student-Centered Activities for Large Enrollment University Physics (SCALE-UP) project is working to establish a learning environment that will promote increased conceptual understanding, improved problem-solving performance, and greater student satisfaction, while still maintaining class sizes of approximately 100. We are also addressing the new ABET engineering accreditation requirements for inquiry-based learning along with communication and team-oriented skills development. Results of studies of our latest classroom design, plans for future classroom space, and the current iteration of instructional materials will be discussed.

An Online Dictionary Learning-Based Compressive Data Gathering Algorithm in Wireless Sensor Networks

PubMed Central

Wang, Donghao; Wan, Jiangwen; Chen, Junying; Zhang, Qiang

2016-01-01

To adapt to sense signals of enormous diversities and dynamics, and to decrease the reconstruction errors caused by ambient noise, a novel online dictionary learning method-based compressive data gathering (ODL-CDG) algorithm is proposed. The proposed dictionary is learned from a two-stage iterative procedure, alternately changing between a sparse coding step and a dictionary update step. The self-coherence of the learned dictionary is introduced as a penalty term during the dictionary update procedure. The dictionary is also constrained with sparse structure. It’s theoretically demonstrated that the sensing matrix satisfies the restricted isometry property (RIP) with high probability. In addition, the lower bound of necessary number of measurements for compressive sensing (CS) reconstruction is given. Simulation results show that the proposed ODL-CDG algorithm can enhance the recovery accuracy in the presence of noise, and reduce the energy consumption in comparison with other dictionary based data gathering methods. PMID:27669250

An Online Dictionary Learning-Based Compressive Data Gathering Algorithm in Wireless Sensor Networks.

PubMed

Wang, Donghao; Wan, Jiangwen; Chen, Junying; Zhang, Qiang

2016-09-22

To adapt to sense signals of enormous diversities and dynamics, and to decrease the reconstruction errors caused by ambient noise, a novel online dictionary learning method-based compressive data gathering (ODL-CDG) algorithm is proposed. The proposed dictionary is learned from a two-stage iterative procedure, alternately changing between a sparse coding step and a dictionary update step. The self-coherence of the learned dictionary is introduced as a penalty term during the dictionary update procedure. The dictionary is also constrained with sparse structure. It's theoretically demonstrated that the sensing matrix satisfies the restricted isometry property (RIP) with high probability. In addition, the lower bound of necessary number of measurements for compressive sensing (CS) reconstruction is given. Simulation results show that the proposed ODL-CDG algorithm can enhance the recovery accuracy in the presence of noise, and reduce the energy consumption in comparison with other dictionary based data gathering methods.

Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors.

PubMed

Wei, Qinglai; Li, Benkai; Song, Ruizhuo

2018-04-01

In this paper, a generalized policy iteration (GPI) algorithm with approximation errors is developed for solving infinite horizon optimal control problems for nonlinear systems. The developed stable GPI algorithm provides a general structure of discrete-time iterative adaptive dynamic programming algorithms, by which most of the discrete-time reinforcement learning algorithms can be described using the GPI structure. It is for the first time that approximation errors are explicitly considered in the GPI algorithm. The properties of the stable GPI algorithm with approximation errors are analyzed. The admissibility of the approximate iterative control law can be guaranteed if the approximation errors satisfy the admissibility criteria. The convergence of the developed algorithm is established, which shows that the iterative value function is convergent to a finite neighborhood of the optimal performance index function, if the approximate errors satisfy the convergence criterion. Finally, numerical examples and comparisons are presented.

Progressive sampling-based Bayesian optimization for efficient and automatic machine learning model selection.

PubMed

Zeng, Xueqiang; Luo, Gang

2017-12-01

Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting algorithms and hyper-parameter values requires advanced machine learning knowledge and many labor-intensive manual iterations. To lower the bar to machine learning, miscellaneous automatic selection methods for algorithms and/or hyper-parameter values have been proposed. Existing automatic selection methods are inefficient on large data sets. This poses a challenge for using machine learning in the clinical big data era. To address the challenge, this paper presents progressive sampling-based Bayesian optimization, an efficient and automatic selection method for both algorithms and hyper-parameter values. We report an implementation of the method. We show that compared to a state of the art automatic selection method, our method can significantly reduce search time, classification error rate, and standard deviation of error rate due to randomization. This is major progress towards enabling fast turnaround in identifying high-quality solutions required by many machine learning-based clinical data analysis tasks.

Case-based learning facilitates critical thinking in undergraduate nutrition education: students describe the big picture.

PubMed

Harman, Tara; Bertrand, Brenda; Greer, Annette; Pettus, Arianna; Jennings, Jill; Wall-Bassett, Elizabeth; Babatunde, Oyinlola Toyin

2015-03-01

The vision of dietetics professions is based on interdependent education, credentialing, and practice. Case-based learning is a method of problem-based learning that is designed to heighten higher-order thinking. Case-based learning can assist students to connect education and specialized practice while developing professional skills for entry-level practice in nutrition and dietetics. This study examined student perspectives of their learning after immersion into case-based learning in nutrition courses. The theoretical frameworks of phenomenology and Bloom's Taxonomy of Educational Objectives triangulated the design of this qualitative study. Data were drawn from 426 written responses and three focus group discussions among 85 students from three upper-level undergraduate nutrition courses. Coding served to deconstruct the essence of respondent meaning given to case-based learning as a learning method. The analysis of the coding was the constructive stage that led to configuration of themes and theoretical practice pathways about student learning. Four leading themes emerged. Story or Scenario represents the ways that students described case-based learning, changes in student thought processes to accommodate case-based learning are illustrated in Method of Learning, higher cognitive learning that was achieved from case-based learning is represented in Problem Solving, and Future Practice details how students explained perceived professional competency gains from case-based learning. The skills that students acquired are consistent with those identified as essential to professional practice. In addition, the common concept of Big Picture was iterated throughout the themes and demonstrated that case-based learning prepares students for multifaceted problems that they are likely to encounter in professional practice. Copyright © 2015 Academy of Nutrition and Dietetics. Published by Elsevier Inc. All rights reserved.

The prefrontal cortex and hybrid learning during iterative competitive games.

PubMed

Abe, Hiroshi; Seo, Hyojung; Lee, Daeyeol

2011-12-01

Behavioral changes driven by reinforcement and punishment are referred to as simple or model-free reinforcement learning. Animals can also change their behaviors by observing events that are neither appetitive nor aversive when these events provide new information about payoffs available from alternative actions. This is an example of model-based reinforcement learning and can be accomplished by incorporating hypothetical reward signals into the value functions for specific actions. Recent neuroimaging and single-neuron recording studies showed that the prefrontal cortex and the striatum are involved not only in reinforcement and punishment, but also in model-based reinforcement learning. We found evidence for both types of learning, and hence hybrid learning, in monkeys during simulated competitive games. In addition, in both the dorsolateral prefrontal cortex and orbitofrontal cortex, individual neurons heterogeneously encoded signals related to actual and hypothetical outcomes from specific actions, suggesting that both areas might contribute to hybrid learning. © 2011 New York Academy of Sciences.

WE-G-18A-04: 3D Dictionary Learning Based Statistical Iterative Reconstruction for Low-Dose Cone Beam CT Imaging

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bai, T; UT Southwestern Medical Center, Dallas, TX; Yan, H

2014-06-15

Purpose: To develop a 3D dictionary learning based statistical reconstruction algorithm on graphic processing units (GPU), to improve the quality of low-dose cone beam CT (CBCT) imaging with high efficiency. Methods: A 3D dictionary containing 256 small volumes (atoms) of 3x3x3 voxels was trained from a high quality volume image. During reconstruction, we utilized a Cholesky decomposition based orthogonal matching pursuit algorithm to find a sparse representation on this dictionary basis of each patch in the reconstructed image, in order to regularize the image quality. To accelerate the time-consuming sparse coding in the 3D case, we implemented our algorithm inmore » a parallel fashion by taking advantage of the tremendous computational power of GPU. Evaluations are performed based on a head-neck patient case. FDK reconstruction with full dataset of 364 projections is used as the reference. We compared the proposed 3D dictionary learning based method with a tight frame (TF) based one using a subset data of 121 projections. The image qualities under different resolutions in z-direction, with or without statistical weighting are also studied. Results: Compared to the TF-based CBCT reconstruction, our experiments indicated that 3D dictionary learning based CBCT reconstruction is able to recover finer structures, to remove more streaking artifacts, and is less susceptible to blocky artifacts. It is also observed that statistical reconstruction approach is sensitive to inconsistency between the forward and backward projection operations in parallel computing. Using high a spatial resolution along z direction helps improving the algorithm robustness. Conclusion: 3D dictionary learning based CBCT reconstruction algorithm is able to sense the structural information while suppressing noise, and hence to achieve high quality reconstruction. The GPU realization of the whole algorithm offers a significant efficiency enhancement, making this algorithm more feasible for potential clinical application. A high zresolution is preferred to stabilize statistical iterative reconstruction. This work was supported in part by NIH(1R01CA154747-01), NSFC((No. 61172163), Research Fund for the Doctoral Program of Higher Education of China (No. 20110201110011), China Scholarship Council.« less

Automated Assume-Guarantee Reasoning by Abstraction Refinement

NASA Technical Reports Server (NTRS)

Pasareanu, Corina S.; Giannakopoulous, Dimitra; Glannakopoulou, Dimitra

2008-01-01

Current automated approaches for compositional model checking in the assume-guarantee style are based on learning of assumptions as deterministic automata. We propose an alternative approach based on abstraction refinement. Our new method computes the assumptions for the assume-guarantee rules as conservative and not necessarily deterministic abstractions of some of the components, and refines those abstractions using counter-examples obtained from model checking them together with the other components. Our approach also exploits the alphabets of the interfaces between components and performs iterative refinement of those alphabets as well as of the abstractions. We show experimentally that our preliminary implementation of the proposed alternative achieves similar or better performance than a previous learning-based implementation.

GWASinlps: Nonlocal prior based iterative SNP selection tool for genome-wide association studies.

PubMed

Sanyal, Nilotpal; Lo, Min-Tzu; Kauppi, Karolina; Djurovic, Srdjan; Andreassen, Ole A; Johnson, Valen E; Chen, Chi-Hua

2018-06-19

Multiple marker analysis of the genome-wide association study (GWAS) data has gained ample attention in recent years. However, because of the ultra high-dimensionality of GWAS data, such analysis is challenging. Frequently used penalized regression methods often lead to large number of false positives, whereas Bayesian methods are computationally very expensive. Motivated to ameliorate these issues simultaneously, we consider the novel approach of using nonlocal priors in an iterative variable selection framework. We develop a variable selection method, named, iterative nonlocal prior based selection for GWAS, or GWASinlps, that combines, in an iterative variable selection framework, the computational efficiency of the screen-and-select approach based on some association learning and the parsimonious uncertainty quantification provided by the use of nonlocal priors. The hallmark of our method is the introduction of 'structured screen-and-select' strategy, that considers hierarchical screening, which is not only based on response-predictor associations, but also based on response-response associations, and concatenates variable selection within that hierarchy. Extensive simulation studies with SNPs having realistic linkage disequilibrium structures demonstrate the advantages of our computationally efficient method compared to several frequentist and Bayesian variable selection methods, in terms of true positive rate, false discovery rate, mean squared error, and effect size estimation error. Further, we provide empirical power analysis useful for study design. Finally, a real GWAS data application was considered with human height as phenotype. An R-package for implementing the GWASinlps method is available at https://cran.r-project.org/web/packages/GWASinlps/index.html. Supplementary data are available at Bioinformatics online.

Researchers Apply Lesson Study: A Cycle of Lesson Planning, Implementation, and Revision

ERIC Educational Resources Information Center

Regan, Kelley S.; Evmenova, Anya S.; Kurz, Leigh Ann; Hughes, Melissa D.; Sacco, Donna; Ahn, Soo Y.; MacVittie, Nichole; Good, Kevin; Boykin, Andrea; Schwartzer, Jessica; Chirinos, David S.

2016-01-01

Scripted lesson plans and/or professional development alone may not be sufficient to encourage teachers to reflect on the quality of their teaching and improve their teaching. One learning tool that teachers may use to improve their teaching is Lesson Study (LS). LS is a collaborative process involving educators, based on concepts of iteration and…

Community Indicators: A Framework for Observing and Supporting Community Activity on Cloudworks

ERIC Educational Resources Information Center

Galley, Rebecca; Conole, Gráinne; Alevizou, Panagiota

2014-01-01

Cloudworks (Cloudworks.ac.uk) is a social networking site designed for sharing, finding and discussing learning and teaching ideas and experiences. Design and development of the site has been based on an iterative analysis, development and implementation approach, underpinned by ongoing research and evaluation. To this end, we have been seeking to…

Conditions for the Effectiveness of a Tablet-Based Algebra Program

ERIC Educational Resources Information Center

Jaciw, Andrew P.; Toby, Megan; Ma, Boya

2012-01-01

Tablets such as the iPad represent the next iteration of technologies that hold promise to facilitate learning, particularly in mathematics. In the case of algebra, tablets have the potential to bring the curriculum to life by easily linking to supporting materials and they allow an interactive experience whereby manipulation of one type of…

Reinforcement learning produces dominant strategies for the Iterated Prisoner's Dilemma.

PubMed

Harper, Marc; Knight, Vincent; Jones, Martin; Koutsovoulos, Georgios; Glynatsi, Nikoleta E; Campbell, Owen

2017-01-01

We present tournament results and several powerful strategies for the Iterated Prisoner's Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also.

Using Peer Feedback to Promote Reflection on Open-Ended Problems

NASA Astrophysics Data System (ADS)

Reinholz, Daniel L.; Dounas-Frazer, Dimitri R.

2016-09-01

This paper describes a new approach for learning from homework called Peer-Assisted Reflection (PAR). PAR involves students using peer feedback to improve their work on open-ended homework problems. Collaborating with peers and revising one's work based on the feedback of others are important aspects of doing and learning physics. While notable exceptions exist, homework and exams are generally individual activities that do not support collaboration and refinement, which misses important opportunities to use assessment for learning. In contrast, PAR provides students with a structure to iteratively engage with challenging, open-ended problems and solicit the input of their peers to improve their work.

Adaptive distance metric learning for diffusion tensor image segmentation.

PubMed

Kong, Youyong; Wang, Defeng; Shi, Lin; Hui, Steve C N; Chu, Winnie C W

2014-01-01

High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework.

Adaptive Distance Metric Learning for Diffusion Tensor Image Segmentation

PubMed Central

Kong, Youyong; Wang, Defeng; Shi, Lin; Hui, Steve C. N.; Chu, Winnie C. W.

2014-01-01

High quality segmentation of diffusion tensor images (DTI) is of key interest in biomedical research and clinical application. In previous studies, most efforts have been made to construct predefined metrics for different DTI segmentation tasks. These methods require adequate prior knowledge and tuning parameters. To overcome these disadvantages, we proposed to automatically learn an adaptive distance metric by a graph based semi-supervised learning model for DTI segmentation. An original discriminative distance vector was first formulated by combining both geometry and orientation distances derived from diffusion tensors. The kernel metric over the original distance and labels of all voxels were then simultaneously optimized in a graph based semi-supervised learning approach. Finally, the optimization task was efficiently solved with an iterative gradient descent method to achieve the optimal solution. With our approach, an adaptive distance metric could be available for each specific segmentation task. Experiments on synthetic and real brain DTI datasets were performed to demonstrate the effectiveness and robustness of the proposed distance metric learning approach. The performance of our approach was compared with three classical metrics in the graph based semi-supervised learning framework. PMID:24651858

Evaluating and redesigning teaching learning sequences at the introductory physics level

NASA Astrophysics Data System (ADS)

Guisasola, Jenaro; Zuza, Kristina; Ametller, Jaume; Gutierrez-Berraondo, José

2017-12-01

In this paper we put forward a proposal for the design and evaluation of teaching and learning sequences in upper secondary school and university. We will connect our proposal with relevant contributions on the design of teaching sequences, ground it on the design-based research methodology, and discuss how teaching and learning sequences designed according to our proposal relate to learning progressions. An iterative methodology for evaluating and redesigning the teaching and learning sequence (TLS) is presented. The proposed assessment strategy focuses on three aspects: (a) evaluation of the activities of the TLS, (b) evaluation of learning achieved by students in relation to the intended objectives, and (c) a document for gathering the difficulties found when implementing the TLS to serve as a guide to teachers. Discussion of this guide with external teachers provides feedback used for the TLS redesign. The context of our implementation and evaluation is an innovative calculus-based physics course for first-year engineering and science degree students at the University of the Basque Country.

Using iterative learning to improve understanding during the informed consent process in a South African psychiatric genomics study.

PubMed

Campbell, Megan M; Susser, Ezra; Mall, Sumaya; Mqulwana, Sibonile G; Mndini, Michael M; Ntola, Odwa A; Nagdee, Mohamed; Zingela, Zukiswa; Van Wyk, Stephanus; Stein, Dan J

2017-01-01

Obtaining informed consent is a great challenge in global health research. There is a need for tools that can screen for and improve potential research participants' understanding of the research study at the time of recruitment. Limited empirical research has been conducted in low and middle income countries, evaluating informed consent processes in genomics research. We sought to investigate the quality of informed consent obtained in a South African psychiatric genomics study. A Xhosa language version of the University of California, San Diego Brief Assessment of Capacity to Consent Questionnaire (UBACC) was used to screen for capacity to consent and improve understanding through iterative learning in a sample of 528 Xhosa people with schizophrenia and 528 controls. We address two questions: firstly, whether research participants' understanding of the research study improved through iterative learning; and secondly, what were predictors for better understanding of the research study at the initial screening? During screening 290 (55%) cases and 172 (33%) controls scored below the 14.5 cut-off for acceptable understanding of the research study elements, however after iterative learning only 38 (7%) cases and 13 (2.5%) controls continued to score below this cut-off. Significant variables associated with increased understanding of the consent included the psychiatric nurse recruiter conducting the consent screening, higher participant level of education, and being a control. The UBACC proved an effective tool to improve understanding of research study elements during consent, for both cases and controls. The tool holds utility for complex studies such as those involving genomics, where iterative learning can be used to make significant improvements in understanding of research study elements. The UBACC may be particularly important in groups with severe mental illness and lower education levels. Study recruiters play a significant role in managing the quality of the informed consent process.

Open-closed-loop iterative learning control for a class of nonlinear systems with random data dropouts

NASA Astrophysics Data System (ADS)

Cheng, X. Y.; Wang, H. B.; Jia, Y. L.; Dong, YH

2018-05-01

In this paper, an open-closed-loop iterative learning control (ILC) algorithm is constructed for a class of nonlinear systems subjecting to random data dropouts. The ILC algorithm is implemented by a networked control system (NCS), where only the off-line data is transmitted by network while the real-time data is delivered in the point-to-point way. Thus, there are two controllers rather than one in the control system, which makes better use of the saved and current information and thereby improves the performance achieved by open-loop control alone. During the transfer of off-line data between the nonlinear plant and the remote controller data dropout occurs randomly and the data dropout rate is modeled as a binary Bernoulli random variable. Both measurement and control data dropouts are taken into consideration simultaneously. The convergence criterion is derived based on rigorous analysis. Finally, the simulation results verify the effectiveness of the proposed method.

A novel artificial neural network method for biomedical prediction based on matrix pseudo-inversion.

PubMed

Cai, Binghuang; Jiang, Xia

2014-04-01

Biomedical prediction based on clinical and genome-wide data has become increasingly important in disease diagnosis and classification. To solve the prediction problem in an effective manner for the improvement of clinical care, we develop a novel Artificial Neural Network (ANN) method based on Matrix Pseudo-Inversion (MPI) for use in biomedical applications. The MPI-ANN is constructed as a three-layer (i.e., input, hidden, and output layers) feed-forward neural network, and the weights connecting the hidden and output layers are directly determined based on MPI without a lengthy learning iteration. The LASSO (Least Absolute Shrinkage and Selection Operator) method is also presented for comparative purposes. Single Nucleotide Polymorphism (SNP) simulated data and real breast cancer data are employed to validate the performance of the MPI-ANN method via 5-fold cross validation. Experimental results demonstrate the efficacy of the developed MPI-ANN for disease classification and prediction, in view of the significantly superior accuracy (i.e., the rate of correct predictions), as compared with LASSO. The results based on the real breast cancer data also show that the MPI-ANN has better performance than other machine learning methods (including support vector machine (SVM), logistic regression (LR), and an iterative ANN). In addition, experiments demonstrate that our MPI-ANN could be used for bio-marker selection as well. Copyright © 2013 Elsevier Inc. All rights reserved.

Hard exudates segmentation based on learned initial seeds and iterative graph cut.

PubMed

Kusakunniran, Worapan; Wu, Qiang; Ritthipravat, Panrasee; Zhang, Jian

2018-05-01

(Background and Objective): The occurrence of hard exudates is one of the early signs of diabetic retinopathy which is one of the leading causes of the blindness. Many patients with diabetic retinopathy lose their vision because of the late detection of the disease. Thus, this paper is to propose a novel method of hard exudates segmentation in retinal images in an automatic way. (Methods): The existing methods are based on either supervised or unsupervised learning techniques. In addition, the learned segmentation models may often cause miss-detection and/or fault-detection of hard exudates, due to the lack of rich characteristics, the intra-variations, and the similarity with other components in the retinal image. Thus, in this paper, the supervised learning based on the multilayer perceptron (MLP) is only used to identify initial seeds with high confidences to be hard exudates. Then, the segmentation is finalized by unsupervised learning based on the iterative graph cut (GC) using clusters of initial seeds. Also, in order to reduce color intra-variations of hard exudates in different retinal images, the color transfer (CT) is applied to normalize their color information, in the pre-processing step. (Results): The experiments and comparisons with the other existing methods are based on the two well-known datasets, e_ophtha EX and DIARETDB1. It can be seen that the proposed method outperforms the other existing methods in the literature, with the sensitivity in the pixel-level of 0.891 for the DIARETDB1 dataset and 0.564 for the e_ophtha EX dataset. The cross datasets validation where the training process is performed on one dataset and the testing process is performed on another dataset is also evaluated in this paper, in order to illustrate the robustness of the proposed method. (Conclusions): This newly proposed method integrates the supervised learning and unsupervised learning based techniques. It achieves the improved performance, when compared with the existing methods in the literature. The robustness of the proposed method for the scenario of cross datasets could enhance its practical usage. That is, the trained model could be more practical for unseen data in the real-world situation, especially when the capturing environments of training and testing images are not the same. Copyright © 2018 Elsevier B.V. All rights reserved.

Neural network error correction for solving coupled ordinary differential equations

NASA Technical Reports Server (NTRS)

Shelton, R. O.; Darsey, J. A.; Sumpter, B. G.; Noid, D. W.

1992-01-01

A neural network is presented to learn errors generated by a numerical algorithm for solving coupled nonlinear differential equations. The method is based on using a neural network to correctly learn the error generated by, for example, Runge-Kutta on a model molecular dynamics (MD) problem. The neural network programs used in this study were developed by NASA. Comparisons are made for training the neural network using backpropagation and a new method which was found to converge with fewer iterations. The neural net programs, the MD model and the calculations are discussed.

Adaptive management of watersheds and related resources

USGS Publications Warehouse

Williams, Byron K.

2009-01-01

The concept of learning about natural resources through the practice of management has been around for several decades and by now is associated with the term adaptive management. The objectives of this paper are to offer a framework for adaptive management that includes an operational definition, a description of conditions in which it can be usefully applied, and a systematic approach to its application. Adaptive decisionmaking is described as iterative, learning-based management in two phases, each with its own mechanisms for feedback and adaptation. The linkages between traditional experimental science and adaptive management are discussed.

Reinforcement learning produces dominant strategies for the Iterated Prisoner’s Dilemma

PubMed Central

Jones, Martin; Koutsovoulos, Georgios; Glynatsi, Nikoleta E.; Campbell, Owen

2017-01-01

We present tournament results and several powerful strategies for the Iterated Prisoner’s Dilemma created using reinforcement learning techniques (evolutionary and particle swarm algorithms). These strategies are trained to perform well against a corpus of over 170 distinct opponents, including many well-known and classic strategies. All the trained strategies win standard tournaments against the total collection of other opponents. The trained strategies and one particular human made designed strategy are the top performers in noisy tournaments also. PMID:29228001

Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares.

PubMed

Zhang, Cheng; Zhang, Tao; Li, Ming; Peng, Chengtao; Liu, Zhaobang; Zheng, Jian

2016-06-18

In order to reduce the radiation dose of CT (computed tomography), compressed sensing theory has been a hot topic since it provides the possibility of a high quality recovery from the sparse sampling data. Recently, the algorithm based on DL (dictionary learning) was developed to deal with the sparse CT reconstruction problem. However, the existing DL algorithm focuses on the minimization problem with the L2-norm regularization term, which leads to reconstruction quality deteriorating while the sampling rate declines further. Therefore, it is essential to improve the DL method to meet the demand of more dose reduction. In this paper, we replaced the L2-norm regularization term with the L1-norm one. It is expected that the proposed L1-DL method could alleviate the over-smoothing effect of the L2-minimization and reserve more image details. The proposed algorithm solves the L1-minimization problem by a weighting strategy, solving the new weighted L2-minimization problem based on IRLS (iteratively reweighted least squares). Through the numerical simulation, the proposed algorithm is compared with the existing DL method (adaptive dictionary based statistical iterative reconstruction, ADSIR) and other two typical compressed sensing algorithms. It is revealed that the proposed algorithm is more accurate than the other algorithms especially when further reducing the sampling rate or increasing the noise. The proposed L1-DL algorithm can utilize more prior information of image sparsity than ADSIR. By transforming the L2-norm regularization term of ADSIR with the L1-norm one and solving the L1-minimization problem by IRLS strategy, L1-DL could reconstruct the image more exactly.

Technology Education Using a Novel Approach in e-Learning-Towards Optimizing the Quality of Learning Outcomes

NASA Astrophysics Data System (ADS)

Malkawi, M. I.; Hawarey, M. M.

2012-04-01

Ever since the advent of the new era in presenting taught material in Electronic Form, international bodies, academic institutions, public sectors, as well as specialized entities in the private sector, globally, have all persevered to exploit the power of Distance Learning and e-Learning to disseminate the knowledge in Science and Art using the ubiquitous World Wide Web and its supporting Internet and Internetworking. Many Science & Education-sponsoring bodies, like UNESCO, the European Community, and the World Bank have been keen at funding multinational Distance Learning projects, many of which were directed at an educated audience in certain technical areas. Many countries around the Middle East have found a number of interested European partners to launch funding requests, and were generally successful in their solicitation efforts for the needed funds from these funding bodies. Albeit their intricacies in generating a wealth of knowledge in electronic form, many of the e-Learning schemas developed thus far, have only pursued their goals in the most conventional of ways; In essence, there had been little innovation introduced to gain anything, if any, above traditional classroom lecturing, other than, of course, the gained advantage of the simultaneous online testing and evaluation of the learned material by the examinees. In a sincere effort to change the way in which people look at the merits of e-Learning, and seek the most out of it, we shall propose a novel approach aimed at optimizing the learning outcomes of presented materials. In this paper we propose what shall henceforth be called as Iterative e-Learning. In Iterative e-Learning, as the name implies, a student uses some form of electronic media to access course material in a specific subject. At the end of each phase (Section, Chapter, Session, etc.) on a specific topic, the student is assessed online of how much he/she would have achieved before he/she would move on. If the student fails, due to some delinquency on a particular topic, the online process of e-Learning would take the student at some more detailed and deeper level on the subject matter where he/she had failed; once the student bridges the gap, to this end, then the ongoing e-Learning process would carry him/her further up the next level of the subject matter he/she is pursuing. This process is carried on at all levels of learning: section, chapter, and course level. A student may not progress to the next course level before he/she would pass the entire course at 80% or more. If in the process of repeating some section, chapter, or a whole course, then the student shall be required to score a higher percentage than the mere 80% he was required to attain the first time around; say 5% more per iteration he/she makes. Here, students going through Iterative e-Learning shall be allowed to move on to the next level of learning sooner than others if the time that takes them to learn a particular topic is shorter than would normally require an average student to expend, provided, of course, they make it through all the required assessment phases. Unlike the traditional ways of classroom or online lecturing, a student going through Iterative e-Learning is expected to achieve a quality of learning never before achieved via standard pedagogical methodologies. With Iterative e-Learning, it is expected that poorly accredited academic institutions will be able, for the first time, to produce the quality of graduates who are more capable of competing for highly paying jobs globally, and to be of the quality of contributing in more industry-supported economies.

Investigating and improving introductory physics students’ understanding of the electric field and superposition principle

NASA Astrophysics Data System (ADS)

Li, Jing; Singh, Chandralekha

2017-09-01

We discuss an investigation of the difficulties that students in a university introductory physics course have with the electric field and superposition principle and how that research was used as a guide in the development and evaluation of a research-validated tutorial on these topics to help students learn these concepts better. The tutorial uses a guided enquiry-based approach to learning and involved an iterative process of development and evaluation. During its development, we obtained feedback both from physics instructors who regularly teach introductory physics in which these concepts are taught and from students for whom the tutorial is intended. The iterative process continued and the feedback was incorporated in the later versions of the tutorial until the researchers were satisfied with the performance of a diverse group of introductory physics students on the post-test after they worked on the tutorial in an individual one-on-one interview situation. Then the final version of the tutorial was administered in several sections of the university physics course after traditional instruction in relevant concepts. We discuss the performance of students in individual interviews and on the pre-test administered before the tutorial (but after traditional lecture-based instruction) and on the post-test administered after the tutorial. We also compare student performance in sections of the class in which students worked on the tutorial with other similar sections of the class in which students only learned via traditional instruction. We find that students performed significantly better in the sections of the class in which the tutorial was used compared to when students learned the material via only lecture-based instruction.

Sea ice classification using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Fung, A. K.; Manry, M. T.

1992-01-01

A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.

A Cost-Effectiveness Analysis of Blended Versus Face-to-Face Delivery of Evidence-Based Medicine to Medical Students.

PubMed

Maloney, Stephen; Nicklen, Peter; Rivers, George; Foo, Jonathan; Ooi, Ying Ying; Reeves, Scott; Walsh, Kieran; Ilic, Dragan

2015-07-21

Blended learning describes a combination of teaching methods, often utilizing digital technologies. Research suggests that learner outcomes can be improved through some blended learning formats. However, the cost-effectiveness of delivering blended learning is unclear. This study aimed to determine the cost-effectiveness of a face-to-face learning and blended learning approach for evidence-based medicine training within a medical program. The economic evaluation was conducted as part of a randomized controlled trial (RCT) comparing the evidence-based medicine (EBM) competency of medical students who participated in two different modes of education delivery. In the traditional face-to-face method, students received ten 2-hour classes. In the blended learning approach, students received the same total face-to-face hours but with different activities and additional online and mobile learning. Online activities utilized YouTube and a library guide indexing electronic databases, guides, and books. Mobile learning involved self-directed interactions with patients in their regular clinical placements. The attribution and differentiation of costs between the interventions within the RCT was measured in conjunction with measured outcomes of effectiveness. An incremental cost-effectiveness ratio was calculated comparing the ongoing operation costs of each method with the level of EBM proficiency achieved. Present value analysis was used to calculate the break-even point considering the transition cost and the difference in ongoing operation cost. The incremental cost-effectiveness ratio indicated that it costs 24% less to educate a student to the same level of EBM competency via the blended learning approach used in the study, when excluding transition costs. The sunk cost of approximately AUD $40,000 to transition to the blended model exceeds any savings from using the approach within the first year of its implementation; however, a break-even point is achieved within its third iteration and relative savings in the subsequent years. The sensitivity analysis indicates that approaches with higher transition costs, or staffing requirements over that of a traditional method, are likely to result in negative value propositions. Under the study conditions, a blended learning approach was more cost-effective to operate and resulted in improved value for the institution after the third year iteration, when compared to the traditional face-to-face model. The wider applicability of the findings are dependent on the type of blended learning utilized, staffing expertise, and educational context.

Studying citizen science through adaptive management and learning feedbacks as mechanisms for improving conservation.

PubMed

Jordan, Rebecca; Gray, Steven; Sorensen, Amanda; Newman, Greg; Mellor, David; Newman, Greg; Hmelo-Silver, Cindy; LaDeau, Shannon; Biehler, Dawn; Crall, Alycia

2016-06-01

Citizen science has generated a growing interest among scientists and community groups, and citizen science programs have been created specifically for conservation. We examined collaborative science, a highly interactive form of citizen science, which we developed within a theoretically informed framework. In this essay, we focused on 2 aspects of our framework: social learning and adaptive management. Social learning, in contrast to individual-based learning, stresses collaborative and generative insight making and is well-suited for adaptive management. Adaptive-management integrates feedback loops that are informed by what is learned and is guided by iterative decision making. Participants engaged in citizen science are able to add to what they are learning through primary data collection, which can result in the real-time information that is often necessary for conservation. Our work is particularly timely because research publications consistently report a lack of established frameworks and evaluation plans to address the extent of conservation outcomes in citizen science. To illustrate how our framework supports conservation through citizen science, we examined how 2 programs enacted our collaborative science framework. Further, we inspected preliminary conservation outcomes of our case-study programs. These programs, despite their recent implementation, are demonstrating promise with regard to positive conservation outcomes. To date, they are independently earning funds to support research, earning buy-in from local partners to engage in experimentation, and, in the absence of leading scientists, are collecting data to test ideas. We argue that this success is due to citizen scientists being organized around local issues and engaging in iterative, collaborative, and adaptive learning. © 2016 Society for Conservation Biology.

Remix as Professional Learning: Educators' Iterative Literacy Practice in CLMOOC

ERIC Educational Resources Information Center

Smith, Anna; West-Puckett, Stephanie; Cantrill, Christina; Zamora, Mia

2016-01-01

The Connected Learning Massive Open Online Collaboration (CLMOOC) is an online professional development experience designed as an openly networked, production-centered, participatory learning collaboration for educators. Addressing the paucity of research that investigates learning processes in MOOC experiences, this paper examines the situated…

Cost-sensitive AdaBoost algorithm for ordinal regression based on extreme learning machine.

PubMed

Riccardi, Annalisa; Fernández-Navarro, Francisco; Carloni, Sante

2014-10-01

In this paper, the well known stagewise additive modeling using a multiclass exponential (SAMME) boosting algorithm is extended to address problems where there exists a natural order in the targets using a cost-sensitive approach. The proposed ensemble model uses an extreme learning machine (ELM) model as a base classifier (with the Gaussian kernel and the additional regularization parameter). The closed form of the derived weighted least squares problem is provided, and it is employed to estimate analytically the parameters connecting the hidden layer to the output layer at each iteration of the boosting algorithm. Compared to the state-of-the-art boosting algorithms, in particular those using ELM as base classifier, the suggested technique does not require the generation of a new training dataset at each iteration. The adoption of the weighted least squares formulation of the problem has been presented as an unbiased and alternative approach to the already existing ELM boosting techniques. Moreover, the addition of a cost model for weighting the patterns, according to the order of the targets, enables the classifier to tackle ordinal regression problems further. The proposed method has been validated by an experimental study by comparing it with already existing ensemble methods and ELM techniques for ordinal regression, showing competitive results.

Game-powered machine learning

PubMed Central

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-01-01

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the “wisdom of the crowds.” Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., “funky jazz with saxophone,” “spooky electronica,” etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data. PMID:22460786

Game-powered machine learning.

PubMed

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-04-24

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds." Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., "funky jazz with saxophone," "spooky electronica," etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data.

Single-hidden-layer feed-forward quantum neural network based on Grover learning.

PubMed

Liu, Cheng-Yi; Chen, Chein; Chang, Ching-Ter; Shih, Lun-Min

2013-09-01

In this paper, a novel single-hidden-layer feed-forward quantum neural network model is proposed based on some concepts and principles in the quantum theory. By combining the quantum mechanism with the feed-forward neural network, we defined quantum hidden neurons and connected quantum weights, and used them as the fundamental information processing unit in a single-hidden-layer feed-forward neural network. The quantum neurons make a wide range of nonlinear functions serve as the activation functions in the hidden layer of the network, and the Grover searching algorithm outstands the optimal parameter setting iteratively and thus makes very efficient neural network learning possible. The quantum neuron and weights, along with a Grover searching algorithm based learning, result in a novel and efficient neural network characteristic of reduced network, high efficient training and prospect application in future. Some simulations are taken to investigate the performance of the proposed quantum network and the result show that it can achieve accurate learning. Copyright © 2013 Elsevier Ltd. All rights reserved.

Automated Deep Learning-Based System to Identify Endothelial Cells Derived from Induced Pluripotent Stem Cells.

PubMed

Kusumoto, Dai; Lachmann, Mark; Kunihiro, Takeshi; Yuasa, Shinsuke; Kishino, Yoshikazu; Kimura, Mai; Katsuki, Toshiomi; Itoh, Shogo; Seki, Tomohisa; Fukuda, Keiichi

2018-06-05

Deep learning technology is rapidly advancing and is now used to solve complex problems. Here, we used deep learning in convolutional neural networks to establish an automated method to identify endothelial cells derived from induced pluripotent stem cells (iPSCs), without the need for immunostaining or lineage tracing. Networks were trained to predict whether phase-contrast images contain endothelial cells based on morphology only. Predictions were validated by comparison to immunofluorescence staining for CD31, a marker of endothelial cells. Method parameters were then automatically and iteratively optimized to increase prediction accuracy. We found that prediction accuracy was correlated with network depth and pixel size of images to be analyzed. Finally, K-fold cross-validation confirmed that optimized convolutional neural networks can identify endothelial cells with high performance, based only on morphology. Copyright © 2018 The Author(s). Published by Elsevier Inc. All rights reserved.

A high-capacity model for one shot association learning in the brain

PubMed Central

Einarsson, Hafsteinn; Lengler, Johannes; Steger, Angelika

2014-01-01

We present a high-capacity model for one-shot association learning (hetero-associative memory) in sparse networks. We assume that basic patterns are pre-learned in networks and associations between two patterns are presented only once and have to be learned immediately. The model is a combination of an Amit-Fusi like network sparsely connected to a Willshaw type network. The learning procedure is palimpsest and comes from earlier work on one-shot pattern learning. However, in our setup we can enhance the capacity of the network by iterative retrieval. This yields a model for sparse brain-like networks in which populations of a few thousand neurons are capable of learning hundreds of associations even if they are presented only once. The analysis of the model is based on a novel result by Janson et al. on bootstrap percolation in random graphs. PMID:25426060

A high-capacity model for one shot association learning in the brain.

PubMed

Einarsson, Hafsteinn; Lengler, Johannes; Steger, Angelika

2014-01-01

We present a high-capacity model for one-shot association learning (hetero-associative memory) in sparse networks. We assume that basic patterns are pre-learned in networks and associations between two patterns are presented only once and have to be learned immediately. The model is a combination of an Amit-Fusi like network sparsely connected to a Willshaw type network. The learning procedure is palimpsest and comes from earlier work on one-shot pattern learning. However, in our setup we can enhance the capacity of the network by iterative retrieval. This yields a model for sparse brain-like networks in which populations of a few thousand neurons are capable of learning hundreds of associations even if they are presented only once. The analysis of the model is based on a novel result by Janson et al. on bootstrap percolation in random graphs.

New Standards Put the Spotlight on Professional Learning

ERIC Educational Resources Information Center

Mizell, Hayes; Hord, Shirley; Killion, Joellen; Hirsh, Stephanie

2011-01-01

Learning Forward introduces new Standards for Professional Learning. This is the third iteration of standards outlining the characteristics of professional learning that lead to effective teaching practices, supportive leadership, and improved student results. The standards are not a prescription for how education leaders and public officials…

An Iterative Learning Algorithm to Map Oil Palm Plantations from Synthetic Aperture Radar and Crowdsourcing

NASA Astrophysics Data System (ADS)

Pinto, N.; Zhang, Z.; Perger, C.; Aguilar-Amuchastegui, N.; Almeyda Zambrano, A. M.; Broadbent, E. N.; Simard, M.; Banerjee, S.

2017-12-01

The oil palm Elaeis spp. grows exclusively in the tropics and provides 30% of the world's vegetable oil. While oil palm-derived biodiesel can reduce carbon emissions from fossil fuels, plantation establishment may be associated with peat fires and deforestation. The ability to monitor plantation establishment and their expansion over carbon-rich tropical forests is critical for quantifying the net impact of oil palm commodities on carbon fluxes. Our objective is to develop a robust methodology to map oil palm plantations in tropical biomes, based on Synthetic Aperture Radar (SAR) from Sentinel-1, ALOS/PALSAR2, and UAVSAR. The C- and L-band signal from these instruments are sensitive to vegetation parameters such as canopy volume, trunk shape, and trunk spatial arrangement, that are critical to differentiate crops from forests and native palms. Based on Bayesian statistics, the learning algorithm employed here adapts to growing knowledge as sites and trainning points are added. We will present an iterative approach wherein a model is initially built at the site with the most training points - in our case, Costa Rica. Model posteriors from Costa Rica, depicting polarimetric signatures of oil palm plantations, are then used as priors in a classification exercise taking place in South Kalimantan. Results are evaluated by local researchers using the LACO Wiki interface. All validation points, including missclassified sites, are used in an additional iteration to improve model results to >90% overall accuracy. We report on the impact of plantation age on polarimetric signatures, and we also compare model performance with and without L-band data.

Deformable Image Registration based on Similarity-Steered CNN Regression.

PubMed

Cao, Xiaohuan; Yang, Jianhua; Zhang, Jun; Nie, Dong; Kim, Min-Jeong; Wang, Qian; Shen, Dinggang

2017-09-01

Existing deformable registration methods require exhaustively iterative optimization, along with careful parameter tuning, to estimate the deformation field between images. Although some learning-based methods have been proposed for initiating deformation estimation, they are often template-specific and not flexible in practical use. In this paper, we propose a convolutional neural network (CNN) based regression model to directly learn the complex mapping from the input image pair (i.e., a pair of template and subject) to their corresponding deformation field. Specifically, our CNN architecture is designed in a patch-based manner to learn the complex mapping from the input patch pairs to their respective deformation field. First, the equalized active-points guided sampling strategy is introduced to facilitate accurate CNN model learning upon a limited image dataset. Then, the similarity-steered CNN architecture is designed, where we propose to add the auxiliary contextual cue, i.e., the similarity between input patches, to more directly guide the learning process. Experiments on different brain image datasets demonstrate promising registration performance based on our CNN model. Furthermore, it is found that the trained CNN model from one dataset can be successfully transferred to another dataset, although brain appearances across datasets are quite variable.

Theorising Teaching and Learning: Pre-Service Teachers' Theoretical Awareness of Learning

ERIC Educational Resources Information Center

Brante, Göran; Holmqvist Olander, Mona; Holmquist, Per-Ola; Palla, Marta

2015-01-01

We examine pre-service teachers' theoretical learning during one five-week training module, and their educators' learning about better lecture design to foster student learning. The study is iterative: interventions (one per group) were implemented sequentially in student groups A-C, the results of the previous intervention serving as the baseline…

Learning to Teach Elementary Science Through Iterative Cycles of Enactment in Culturally and Linguistically Diverse Contexts

NASA Astrophysics Data System (ADS)

Bottoms, SueAnn I.; Ciechanowski, Kathryn M.; Hartman, Brian

2015-12-01

Iterative cycles of enactment embedded in culturally and linguistically diverse contexts provide rich opportunities for preservice teachers (PSTs) to enact core practices of science. This study is situated in the larger Families Involved in Sociocultural Teaching and Science, Technology, Engineering and Mathematics (FIESTAS) project, which weaves together cycles of enactment, core practices in science education and culturally relevant pedagogies. The theoretical foundation draws upon situated learning theory and communities of practice. Using video analysis by PSTs and course artifacts, the authors studied how the iterative process of these cycles guided PSTs development as teachers of elementary science. Findings demonstrate how PSTs were drawing on resources to inform practice, purposefully noticing their practice, renegotiating their roles in teaching, and reconsidering "professional blindness" through cultural practice.

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels.

PubMed

Sornapudi, Sudhir; Stanley, Ronald Joe; Stoecker, William V; Almubarak, Haidar; Long, Rodney; Antani, Sameer; Thoma, George; Zuna, Rosemary; Frazier, Shelliane R

2018-01-01

Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades. In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network. The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques. The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.

On equivalent parameter learning in simplified feature space based on Bayesian asymptotic analysis.

PubMed

Yamazaki, Keisuke

2012-07-01

Parametric models for sequential data, such as hidden Markov models, stochastic context-free grammars, and linear dynamical systems, are widely used in time-series analysis and structural data analysis. Computation of the likelihood function is one of primary considerations in many learning methods. Iterative calculation of the likelihood such as the model selection is still time-consuming though there are effective algorithms based on dynamic programming. The present paper studies parameter learning in a simplified feature space to reduce the computational cost. Simplifying data is a common technique seen in feature selection and dimension reduction though an oversimplified space causes adverse learning results. Therefore, we mathematically investigate a condition of the feature map to have an asymptotically equivalent convergence point of estimated parameters, referred to as the vicarious map. As a demonstration to find vicarious maps, we consider the feature space, which limits the length of data, and derive a necessary length for parameter learning in hidden Markov models. Copyright © 2012 Elsevier Ltd. All rights reserved.

Closed-loop control of artificial pancreatic Beta -cell in type 1 diabetes mellitus using model predictive iterative learning control.

PubMed

Wang, Youqing; Dassau, Eyal; Doyle, Francis J

2010-02-01

A novel combination of iterative learning control (ILC) and model predictive control (MPC), referred to here as model predictive iterative learning control (MPILC), is proposed for glycemic control in type 1 diabetes mellitus. MPILC exploits two key factors: frequent glucose readings made possible by continuous glucose monitoring technology; and the repetitive nature of glucose-meal-insulin dynamics with a 24-h cycle. The proposed algorithm can learn from an individual's lifestyle, allowing the control performance to be improved from day to day. After less than 10 days, the blood glucose concentrations can be kept within a range of 90-170 mg/dL. Generally, control performance under MPILC is better than that under MPC. The proposed methodology is robust to random variations in meal timings within +/-60 min or meal amounts within +/-75% of the nominal value, which validates MPILC's superior robustness compared to run-to-run control. Moreover, to further improve the algorithm's robustness, an automatic scheme for setpoint update that ensures safe convergence is proposed. Furthermore, the proposed method does not require user intervention; hence, the algorithm should be of particular interest for glycemic control in children and adolescents.

Using narrative-based design scaffolds within a mobile learning environment to support learning outdoors with young children

NASA Astrophysics Data System (ADS)

Seely, Brian J.

This study aims to advance learning outdoors with mobile devices. As part of the ongoing Tree Investigators design-based research study, this research investigated a mobile application to support observation, identification, and explanation of the tree life cycle within an authentic, outdoor setting. Recognizing the scientific and conceptual complexity of this topic for young children, the design incorporated technological and design scaffolds within a narrative-based learning environment. In an effort to support learning, 14 participants (aged 5-9) were guided through the mobile app on tree life cycles by a comic-strip pedagogical agent, "Nutty the Squirrel", as they looked to explore and understand through guided observational practices and artifact creation tasks. In comparison to previous iterations of this DBR study, the overall patterns of talk found in this study were similar, with perceptual and conceptual talk being the first and second most frequently coded categories, respectively. However, this study coded considerably more instances of affective talk. This finding of the higher frequency of affective talk could possibly be explained by the relatively younger age of this iteration's participants, in conjunction with the introduced pedagogical agent, who elicited playfulness and delight from the children. The results also indicated a significant improvement when comparing the pretest results (mean score of .86) with the posttest results (mean score of 4.07, out of 5). Learners were not only able to recall the phases of a tree life cycle, but list them in the correct order. The comparison reports a significant increase, showing evidence of increased knowledge and appropriation of scientific vocabulary. The finding suggests the narrative was effective in structuring the complex material into a story for sense making. Future research with narratives should consider a design to promote learner agency through more interactions with the pedagogical agent and a conditional branching scenario framework to further evoke interest and engagement.

An iterative learning control method with application for CNC machine tools

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kim, D.I.; Kim, S.

1996-01-01

A proportional, integral, and derivative (PID) type iterative learning controller is proposed for precise tracking control of industrial robots and computer numerical controller (CNC) machine tools performing repetitive tasks. The convergence of the output error by the proposed learning controller is guaranteed under a certain condition even when the system parameters are not known exactly and unknown external disturbances exist. As the proposed learning controller is repeatedly applied to the industrial robot or the CNC machine tool with the path-dependent repetitive task, the distance difference between the desired path and the actual tracked or machined path, which is one ofmore » the most significant factors in the evaluation of control performance, is progressively reduced. The experimental results demonstrate that the proposed learning controller can improve machining accuracy when the CNC machine tool performs repetitive machining tasks.« less

Learning multimodal dictionaries.

PubMed

Monaci, Gianluca; Jost, Philippe; Vandergheynst, Pierre; Mailhé, Boris; Lesage, Sylvain; Gribonval, Rémi

2007-09-01

Real-world phenomena involve complex interactions between multiple signal modalities. As a consequence, humans are used to integrate at each instant perceptions from all their senses in order to enrich their understanding of the surrounding world. This paradigm can be also extremely useful in many signal processing and computer vision problems involving mutually related signals. The simultaneous processing of multimodal data can, in fact, reveal information that is otherwise hidden when considering the signals independently. However, in natural multimodal signals, the statistical dependencies between modalities are in general not obvious. Learning fundamental multimodal patterns could offer deep insight into the structure of such signals. In this paper, we present a novel model of multimodal signals based on their sparse decomposition over a dictionary of multimodal structures. An algorithm for iteratively learning multimodal generating functions that can be shifted at all positions in the signal is proposed, as well. The learning is defined in such a way that it can be accomplished by iteratively solving a generalized eigenvector problem, which makes the algorithm fast, flexible, and free of user-defined parameters. The proposed algorithm is applied to audiovisual sequences and it is able to discover underlying structures in the data. The detection of such audio-video patterns in audiovisual clips allows to effectively localize the sound source on the video in presence of substantial acoustic and visual distractors, outperforming state-of-the-art audiovisual localization algorithms.

Active Engagement with Assessment and Feedback Can Improve Group-Work Outcomes and Boost Student Confidence

ERIC Educational Resources Information Center

Scott, G. W.

2017-01-01

This study involves evaluation of a novel iterative group-based learning task developed to enable students to actively engage with assessment and feedback in order to improve the quality of their written work. The students were all in the final semester of their final year of study and enrolled on either BSc Zoology or BSc Marine and Freshwater…

Integrating Concept Mapping into Information Systems Education for Meaningful Learning and Assessment

ERIC Educational Resources Information Center

Wei, Wei; Yue, Kwok-Bun

2017-01-01

Concept map (CM) is a theoretically sound yet easy to learn tool and can be effectively used to represent knowledge. Even though many disciplines have adopted CM as a teaching and learning tool to improve learning effectiveness, its application in IS curriculum is sparse. Meaningful learning happens when one iteratively integrates new concepts and…

A Parameter Communication Optimization Strategy for Distributed Machine Learning in Sensors.

PubMed

Zhang, Jilin; Tu, Hangdi; Ren, Yongjian; Wan, Jian; Zhou, Li; Li, Mingwei; Wang, Jue; Yu, Lifeng; Zhao, Chang; Zhang, Lei

2017-09-21

In order to utilize the distributed characteristic of sensors, distributed machine learning has become the mainstream approach, but the different computing capability of sensors and network delays greatly influence the accuracy and the convergence rate of the machine learning model. Our paper describes a reasonable parameter communication optimization strategy to balance the training overhead and the communication overhead. We extend the fault tolerance of iterative-convergent machine learning algorithms and propose the Dynamic Finite Fault Tolerance (DFFT). Based on the DFFT, we implement a parameter communication optimization strategy for distributed machine learning, named Dynamic Synchronous Parallel Strategy (DSP), which uses the performance monitoring model to dynamically adjust the parameter synchronization strategy between worker nodes and the Parameter Server (PS). This strategy makes full use of the computing power of each sensor, ensures the accuracy of the machine learning model, and avoids the situation that the model training is disturbed by any tasks unrelated to the sensors.

Proof Rules for Automated Compositional Verification through Learning

NASA Technical Reports Server (NTRS)

Barringer, Howard; Giannakopoulou, Dimitra; Pasareanu, Corina S.

2003-01-01

Compositional proof systems not only enable the stepwise development of concurrent processes but also provide a basis to alleviate the state explosion problem associated with model checking. An assume-guarantee style of specification and reasoning has long been advocated to achieve compositionality. However, this style of reasoning is often non-trivial, typically requiring human input to determine appropriate assumptions. In this paper, we present novel assume- guarantee rules in the setting of finite labelled transition systems with blocking communication. We show how these rules can be applied in an iterative and fully automated fashion within a framework based on learning.

Design & control of a 3D stroke rehabilitation platform.

PubMed

Cai, Z; Tong, D; Meadmore, K L; Freeman, C T; Hughes, A M; Rogers, E; Burridge, J H

2011-01-01

An upper limb stroke rehabilitation system is developed which combines electrical stimulation with mechanical arm support, to assist patients performing 3D reaching tasks in a virtual reality environment. The Stimulation Assistance through Iterative Learning (SAIL) platform applies electrical stimulation to two muscles in the arm using model-based control schemes which learn from previous trials of the task. This results in accurate movement which maximises the therapeutic effect of treatment. The principal components of the system are described and experimental results confirm its efficacy for clinical use in upper limb stroke rehabilitation. © 2011 IEEE

Cross-domain active learning for video concept detection

NASA Astrophysics Data System (ADS)

Li, Huan; Li, Chao; Shi, Yuan; Xiong, Zhang; Hauptmann, Alexander G.

2011-08-01

As video data from a variety of different domains (e.g., news, documentaries, entertainment) have distinctive data distributions, cross-domain video concept detection becomes an important task, in which one can reuse the labeled data of one domain to benefit the learning task in another domain with insufficient labeled data. In this paper, we approach this problem by proposing a cross-domain active learning method which iteratively queries labels of the most informative samples in the target domain. Traditional active learning assumes that the training (source domain) and test data (target domain) are from the same distribution. However, it may fail when the two domains have different distributions because querying informative samples according to a base learner that initially learned from source domain may no longer be helpful for the target domain. In our paper, we use the Gaussian random field model as the base learner which has the advantage of exploring the distributions in both domains, and adopt uncertainty sampling as the query strategy. Additionally, we present an instance weighting trick to accelerate the adaptability of the base learner, and develop an efficient model updating method which can significantly speed up the active learning process. Experimental results on TRECVID collections highlight the effectiveness.

Experiments on Learning by Back Propagation.

ERIC Educational Resources Information Center

Plaut, David C.; And Others

This paper describes further research on a learning procedure for layered networks of deterministic, neuron-like units, described by Rumelhart et al. The units, the way they are connected, the learning procedure, and the extension to iterative networks are presented. In one experiment, a network learns a set of filters, enabling it to discriminate…

Active Learning with a Human in The Loop

DTIC Science & Technology

2012-11-01

handwrit - ten digits (LeCun et al. [1998]). In the red curve the model is built iteratively: at each iteration the twenty examples with the lowest...continuum. The most we can say about MUC annotation is that it’s simple enough that other tasks are likely to impose a heavier load on the user for

Learning to Teach Elementary Science through Iterative Cycles of Enactment in Culturally and Linguistically Diverse Contexts

ERIC Educational Resources Information Center

Bottoms, SueAnn I.; Ciechanowski, Kathryn M.; Hartman, Brian

2015-01-01

Iterative cycles of enactment embedded in culturally and linguistically diverse contexts provide rich opportunities for preservice teachers (PSTs) to enact core practices of science. This study is situated in the larger Families Involved in Sociocultural Teaching and Science, Technology, Engineering and Mathematics (FIESTAS) project, which weaves…

Slaying the Great Green Dragon: Learning and Modelling Iterable Ordered Optional Adjuncts

ERIC Educational Resources Information Center

Fowlie, Meaghan

2017-01-01

Adjuncts and arguments exhibit different syntactic behaviours, but modelling this difference in minimalist syntax is challenging: on the one hand, adjuncts differ from arguments in that they are optional, transparent, and iterable, but on the other hand they are often strictly ordered, reflecting the kind of strict selection seen in argument…

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels

PubMed Central

Sornapudi, Sudhir; Stanley, Ronald Joe; Stoecker, William V.; Almubarak, Haidar; Long, Rodney; Antani, Sameer; Thoma, George; Zuna, Rosemary; Frazier, Shelliane R.

2018-01-01

Background: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades. Methods: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network. Results: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques. Conclusions: The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods. PMID:29619277

Improved Student Learning through a Faculty Learning Community: How Faculty Collaboration Transformed a Large-Enrollment Course from Lecture to Student Centered

PubMed Central

Elliott, Emily R.; Reason, Robert D.; Coffman, Clark R.; Gangloff, Eric J.; Raker, Jeffrey R.; Powell-Coffman, Jo Anne; Ogilvie, Craig A.

2016-01-01

Undergraduate introductory biology courses are changing based on our growing understanding of how students learn and rapid scientific advancement in the biological sciences. At Iowa State University, faculty instructors are transforming a second-semester large-enrollment introductory biology course to include active learning within the lecture setting. To support this change, we set up a faculty learning community (FLC) in which instructors develop new pedagogies, adapt active-learning strategies to large courses, discuss challenges and progress, critique and revise classroom interventions, and share materials. We present data on how the collaborative work of the FLC led to increased implementation of active-learning strategies and a concurrent improvement in student learning. Interestingly, student learning gains correlate with the percentage of classroom time spent in active-learning modes. Furthermore, student attitudes toward learning biology are weakly positively correlated with these learning gains. At our institution, the FLC framework serves as an agent of iterative emergent change, resulting in the creation of a more student-centered course that better supports learning. PMID:27252298

Robust iterative learning control for multi-phase batch processes: an average dwell-time method with 2D convergence indexes

NASA Astrophysics Data System (ADS)

Wang, Limin; Shen, Yiteng; Yu, Jingxian; Li, Ping; Zhang, Ridong; Gao, Furong

2018-01-01

In order to cope with system disturbances in multi-phase batch processes with different dimensions, a hybrid robust control scheme of iterative learning control combined with feedback control is proposed in this paper. First, with a hybrid iterative learning control law designed by introducing the state error, the tracking error and the extended information, the multi-phase batch process is converted into a two-dimensional Fornasini-Marchesini (2D-FM) switched system with different dimensions. Second, a switching signal is designed using the average dwell-time method integrated with the related switching conditions to give sufficient conditions ensuring stable running for the system. Finally, the minimum running time of the subsystems and the control law gains are calculated by solving the linear matrix inequalities. Meanwhile, a compound 2D controller with robust performance is obtained, which includes a robust extended feedback control for ensuring the steady-state tracking error to converge rapidly. The application on an injection molding process displays the effectiveness and superiority of the proposed strategy.

Ultra-low-dose computed tomographic angiography with model-based iterative reconstruction compared with standard-dose imaging after endovascular aneurysm repair: a prospective pilot study.

PubMed

Naidu, Sailen G; Kriegshauser, J Scott; Paden, Robert G; He, Miao; Wu, Qing; Hara, Amy K

2014-12-01

An ultra-low-dose radiation protocol reconstructed with model-based iterative reconstruction was compared with our standard-dose protocol. This prospective study evaluated 20 men undergoing surveillance-enhanced computed tomography after endovascular aneurysm repair. All patients underwent standard-dose and ultra-low-dose venous phase imaging; images were compared after reconstruction with filtered back projection, adaptive statistical iterative reconstruction, and model-based iterative reconstruction. Objective measures of aortic contrast attenuation and image noise were averaged. Images were subjectively assessed (1 = worst, 5 = best) for diagnostic confidence, image noise, and vessel sharpness. Aneurysm sac diameter and endoleak detection were compared. Quantitative image noise was 26% less with ultra-low-dose model-based iterative reconstruction than with standard-dose adaptive statistical iterative reconstruction and 58% less than with ultra-low-dose adaptive statistical iterative reconstruction. Average subjective noise scores were not different between ultra-low-dose model-based iterative reconstruction and standard-dose adaptive statistical iterative reconstruction (3.8 vs. 4.0, P = .25). Subjective scores for diagnostic confidence were better with standard-dose adaptive statistical iterative reconstruction than with ultra-low-dose model-based iterative reconstruction (4.4 vs. 4.0, P = .002). Vessel sharpness was decreased with ultra-low-dose model-based iterative reconstruction compared with standard-dose adaptive statistical iterative reconstruction (3.3 vs. 4.1, P < .0001). Ultra-low-dose model-based iterative reconstruction and standard-dose adaptive statistical iterative reconstruction aneurysm sac diameters were not significantly different (4.9 vs. 4.9 cm); concordance for the presence of endoleak was 100% (P < .001). Compared with a standard-dose technique, an ultra-low-dose model-based iterative reconstruction protocol provides comparable image quality and diagnostic assessment at a 73% lower radiation dose.

Active Learning by Querying Informative and Representative Examples.

PubMed

Huang, Sheng-Jun; Jin, Rong; Zhou, Zhi-Hua

2014-10-01

Active learning reduces the labeling cost by iteratively selecting the most valuable data to query their labels. It has attracted a lot of interests given the abundance of unlabeled data and the high cost of labeling. Most active learning approaches select either informative or representative unlabeled instances to query their labels, which could significantly limit their performance. Although several active learning algorithms were proposed to combine the two query selection criteria, they are usually ad hoc in finding unlabeled instances that are both informative and representative. We address this limitation by developing a principled approach, termed QUIRE, based on the min-max view of active learning. The proposed approach provides a systematic way for measuring and combining the informativeness and representativeness of an unlabeled instance. Further, by incorporating the correlation among labels, we extend the QUIRE approach to multi-label learning by actively querying instance-label pairs. Extensive experimental results show that the proposed QUIRE approach outperforms several state-of-the-art active learning approaches in both single-label and multi-label learning.

Team-based learning for midwifery education.

PubMed

Moore-Davis, Tonia L; Schorn, Mavis N; Collins, Michelle R; Phillippi, Julia; Holley, Sharon

2015-01-01

Many US health care and education stakeholder groups, recognizing the need to prepare learners for collaborative practice in complex care environments, have called for innovative approaches in health care education. Team-based learning is an educational method that relies on in-depth student preparation prior to class, individual and team knowledge assessment, and use of small-group learning to apply knowledge to complex scenarios. Although team-based learning has been studied as an approach to health care education, its application to midwifery education is not well described. A master's-level, nurse-midwifery, didactic antepartum course was revised to a team-based learning format. Student grades, course evaluations, and aggregate American Midwifery Certification Board examination pass rates for 3 student cohorts participating in the team-based course were compared with 3 student cohorts receiving traditional, lecture-based instruction. Students had mixed responses to the team-based learning format. Student evaluations improved when faculty added recorded lectures as part of student preclass preparation. Statistical comparisons were limited by variations across cohorts; however, student grades and certification examination pass rates did not change substantially after the course revision. Although initial course revision was time-consuming for faculty, subsequent iterations of the course required less effort. Team-based learning provides students with more opportunity to interact during on-site classes and may spur application of knowledge into practice. However, it is difficult to assess the effect of the team-based learning approach with current measures. Further research is needed to determine the effects of team-based learning on communication and collaboration skills, as well as long-term performance in clinical practice. This article is part of a special series of articles that address midwifery innovations in clinical practice, education, interprofessional collaboration, health policy, and global health. © 2015 by the American College of Nurse-Midwives.

Intrusion detection using rough set classification.

PubMed

Zhang, Lian-hua; Zhang, Guan-hua; Zhang, Jie; Bai, Ying-cai

2004-09-01

Recently machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, rough set classification (RSC), a modern learning algorithm, is used to rank the features extracted for detecting intrusions and generate intrusion detection models. Feature ranking is a very critical step when building the model. RSC performs feature ranking before generating rules, and converts the feature ranking to minimal hitting set problem addressed by using genetic algorithm (GA). This is done in classical approaches using Support Vector Machine (SVM) by executing many iterations, each of which removes one useless feature. Compared with those methods, our method can avoid many iterations. In addition, a hybrid genetic algorithm is proposed to increase the convergence speed and decrease the training time of RSC. The models generated by RSC take the form of "IF-THEN" rules, which have the advantage of explication. Tests and comparison of RSC with SVM on DARPA benchmark data showed that for Probe and DoS attacks both RSC and SVM yielded highly accurate results (greater than 99% accuracy on testing set).

Towards a Better Distributed Framework for Learning Big Data

DTIC Science & Technology

2017-06-14

UNLIMITED: PB Public Release 13. SUPPLEMENTARY NOTES 14. ABSTRACT This work aimed at solving issues in distributed machine learning. The PI’s team proposed...communication load. Finally, the team proposed the parallel least-squares policy iteration (parallel LSPI) to parallelize a reinforcement policy learning. 15

Wearable Sensor Data Classification for Human Activity Recognition Based on an Iterative Learning Framework.

PubMed

Davila, Juan Carlos; Cretu, Ana-Maria; Zaremba, Marek

2017-06-07

The design of multiple human activity recognition applications in areas such as healthcare, sports and safety relies on wearable sensor technologies. However, when making decisions based on the data acquired by such sensors in practical situations, several factors related to sensor data alignment, data losses, and noise, among other experimental constraints, deteriorate data quality and model accuracy. To tackle these issues, this paper presents a data-driven iterative learning framework to classify human locomotion activities such as walk, stand, lie, and sit, extracted from the Opportunity dataset. Data acquired by twelve 3-axial acceleration sensors and seven inertial measurement units are initially de-noised using a two-stage consecutive filtering approach combining a band-pass Finite Impulse Response (FIR) and a wavelet filter. A series of statistical parameters are extracted from the kinematical features, including the principal components and singular value decomposition of roll, pitch, yaw and the norm of the axial components. The novel interactive learning procedure is then applied in order to minimize the number of samples required to classify human locomotion activities. Only those samples that are most distant from the centroids of data clusters, according to a measure presented in the paper, are selected as candidates for the training dataset. The newly built dataset is then used to train an SVM multi-class classifier. The latter will produce the lowest prediction error. The proposed learning framework ensures a high level of robustness to variations in the quality of input data, while only using a much lower number of training samples and therefore a much shorter training time, which is an important consideration given the large size of the dataset.

Reducing weight precision of convolutional neural networks towards large-scale on-chip image recognition

NASA Astrophysics Data System (ADS)

Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang

2015-05-01

In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.

VINE: A Variational Inference -Based Bayesian Neural Network Engine

DTIC Science & Technology

2018-01-01

networks are trained using the same dataset and hyper parameter settings as discussed. Table 1 Performance evaluation of the proposed transfer learning...multiplication/addition/subtraction. These operations can be implemented using nested loops in which various iterations of a loop are independent of...each other. This introduces an opportunity for optimization where a loop may be unrolled fully or partially to increase parallelism at the cost of

Powerful Design Principles and Processes: Lessons from a Case of Ambitious Civics Education Curriculum Planning. A Response to "Reinventing the High School Government Course: Rigor, Simulations, and Learning from Text"

ERIC Educational Resources Information Center

Dinkelman, Todd

2016-01-01

In "Reinventing the High School Government Course," the authors presented the latest iteration of an ambitious AP government course developed over a seven-year design-based implementation research project. Chiefly addressed to curriculum developers and civics teachers, the article elaborates key design principles, provides a description…

A Cost-Effectiveness Analysis of Blended Versus Face-to-Face Delivery of Evidence-Based Medicine to Medical Students

PubMed Central

Nicklen, Peter; Rivers, George; Foo, Jonathan; Ooi, Ying Ying; Reeves, Scott; Walsh, Kieran; Ilic, Dragan

2015-01-01

Background Blended learning describes a combination of teaching methods, often utilizing digital technologies. Research suggests that learner outcomes can be improved through some blended learning formats. However, the cost-effectiveness of delivering blended learning is unclear. Objective This study aimed to determine the cost-effectiveness of a face-to-face learning and blended learning approach for evidence-based medicine training within a medical program. Methods The economic evaluation was conducted as part of a randomized controlled trial (RCT) comparing the evidence-based medicine (EBM) competency of medical students who participated in two different modes of education delivery. In the traditional face-to-face method, students received ten 2-hour classes. In the blended learning approach, students received the same total face-to-face hours but with different activities and additional online and mobile learning. Online activities utilized YouTube and a library guide indexing electronic databases, guides, and books. Mobile learning involved self-directed interactions with patients in their regular clinical placements. The attribution and differentiation of costs between the interventions within the RCT was measured in conjunction with measured outcomes of effectiveness. An incremental cost-effectiveness ratio was calculated comparing the ongoing operation costs of each method with the level of EBM proficiency achieved. Present value analysis was used to calculate the break-even point considering the transition cost and the difference in ongoing operation cost. Results The incremental cost-effectiveness ratio indicated that it costs 24% less to educate a student to the same level of EBM competency via the blended learning approach used in the study, when excluding transition costs. The sunk cost of approximately AUD $40,000 to transition to the blended model exceeds any savings from using the approach within the first year of its implementation; however, a break-even point is achieved within its third iteration and relative savings in the subsequent years. The sensitivity analysis indicates that approaches with higher transition costs, or staffing requirements over that of a traditional method, are likely to result in negative value propositions. Conclusions Under the study conditions, a blended learning approach was more cost-effective to operate and resulted in improved value for the institution after the third year iteration, when compared to the traditional face-to-face model. The wider applicability of the findings are dependent on the type of blended learning utilized, staffing expertise, and educational context. PMID:26197801

Application of a repetitive process setting to design of monotonically convergent iterative learning control

NASA Astrophysics Data System (ADS)

Boski, Marcin; Paszke, Wojciech

2015-11-01

This paper deals with the problem of designing an iterative learning control algorithm for discrete linear systems using repetitive process stability theory. The resulting design produces a stabilizing output feedback controller in the time domain and a feedforward controller that guarantees monotonic convergence in the trial-to-trial domain. The results are also extended to limited frequency range design specification. New design procedure is introduced in terms of linear matrix inequality (LMI) representations, which guarantee the prescribed performances of ILC scheme. A simulation example is given to illustrate the theoretical developments.

Scalable Iterative Classification for Sanitizing Large-Scale Datasets

PubMed Central

Li, Bo; Vorobeychik, Yevgeniy; Li, Muqun; Malin, Bradley

2017-01-01

Cheap ubiquitous computing enables the collection of massive amounts of personal data in a wide variety of domains. Many organizations aim to share such data while obscuring features that could disclose personally identifiable information. Much of this data exhibits weak structure (e.g., text), such that machine learning approaches have been developed to detect and remove identifiers from it. While learning is never perfect, and relying on such approaches to sanitize data can leak sensitive information, a small risk is often acceptable. Our goal is to balance the value of published data and the risk of an adversary discovering leaked identifiers. We model data sanitization as a game between 1) a publisher who chooses a set of classifiers to apply to data and publishes only instances predicted as non-sensitive and 2) an attacker who combines machine learning and manual inspection to uncover leaked identifying information. We introduce a fast iterative greedy algorithm for the publisher that ensures a low utility for a resource-limited adversary. Moreover, using five text data sets we illustrate that our algorithm leaves virtually no automatically identifiable sensitive instances for a state-of-the-art learning algorithm, while sharing over 93% of the original data, and completes after at most 5 iterations. PMID:28943741

How can students contribute? A qualitative study of active student involvement in development of technological learning material for clinical skills training.

PubMed

Haraldseid, Cecilie; Friberg, Febe; Aase, Karina

2016-01-01

Policy initiatives and an increasing amount of the literature within higher education both call for students to become more involved in creating their own learning. However, there is a lack of studies in undergraduate nursing education that actively involve students in developing such learning material with descriptions of the students' roles in these interactive processes. Explorative qualitative study, using data from focus group interviews, field notes and student notes. The data has been subjected to qualitative content analysis. Active student involvement through an iterative process identified five different learning needs that are especially important to the students: clarification of learning expectations, help to recognize the bigger picture, stimulation of interaction, creation of structure, and receiving context- specific content. The iterative process involvement of students during the development of new technological learning material will enhance the identification of important learning needs for students. The use of student and teacher knowledge through an adapted co-design process is the most optimal level of that involvement.

Generating Knowledge in a Learning Study--From the Perspective of a Teacher Researcher

ERIC Educational Resources Information Center

Thorsten, Anja

2017-01-01

The purpose of this article is to discuss and describe how a clinical research method can be used to generate knowledge about teaching and learning. This will be addressed from a teacher researcher's perspective, taking a conducted Learning Study as the departure. Learning Study is an interventionist, iterative and collaborative research approach,…

Online Learner Self-Regulation: Learning Presence Viewed through Quantitative Content- and Social Network Analysis

ERIC Educational Resources Information Center

Shea, Peter; Hayes, Suzanne; Smith, Sedef Uzuner; Vickers, Jason; Bidjerano, Temi; Gozza-Cohen, Mary; Jian, Shou-Bang; Pickett, Alexandra M.; Wilde, Jane; Tseng, Chi-Hua

2013-01-01

This paper presents an extension of an ongoing study of online learning framed within the community of inquiry (CoI) model (Garrison, Anderson, & Archer, 2001) in which we further examine a new construct labeled as "learning presence." We use learning presence to refer to the iterative processes of forethought and planning,…

Multi Agent Systems with Symbiotic Learning and Evolution using GNP

NASA Astrophysics Data System (ADS)

Eguchi, Toru; Hirasawa, Kotaro; Hu, Jinglu; Murata, Junichi

Recently, various attempts relevant to Multi Agent Systems (MAS) which is one of the most promising systems based on Distributed Artificial Intelligence have been studied to control large and complicated systems efficiently. In these trends of MAS, Multi Agent Systems with Symbiotic Learning and Evolution named Masbiole has been proposed. In Masbiole, symbiotic phenomena among creatures are considered in the process of learning and evolution of MAS. So we can expect more flexible and sophisticated solutions than conventional MAS. In this paper, we apply Masbiole to Iterative Prisoner’s Dilemma Games (IPD Games) using Genetic Network Programming (GNP) which is a newly developed evolutionary computation method for constituting agents. Some characteristics of Masbiole using GNP in IPD Games are clarified.

Intelligent Learning System using cognitive science theory and artificial intelligence methods

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cristensen, D.L.

1986-01-01

This dissertation is a presentation of a theoretical model of an intelligent Learning System (ILS). The approach view intelligent computer-based instruction on a curricular-level and educational-theory base, instead of the conventional instructional-only level. The ILS is divided into two components: (1) macro-level, curricular; and (2) micro-level (MAIS), instructional. The primary purpose of the ILS macro level is to establish the initial conditions of learning by considering individual difference variables within specification of the curriculum content domain. Second, the ILS macro-level will iteratively update the conditions of learning as the individual student progresses through the given curriculum. The term dynamic ismore » used to describe the expert tutor that establishes and monitors the conditions of instruction between the ILS macro level and the micro level. As the student progresses through the instruction, appropriate information is sent back continuously to the macro level to constantly improve decision making for succeeding conditions of instruction.« less

Enhancing Teacher Preparation and Improving Faculty Teaching Skills: Lessons Learned from Implementing ``Science That Matters'' a Standards Based Interdisciplinary Science Course Sequence

NASA Astrophysics Data System (ADS)

Potter, Robert; Meisels, Gerry

2005-06-01

In a highly collaborative process we developed an introductory science course sequence to improve science literacy especially among future elementary and middle school education majors. The materials and course features were designed using the results of research on teaching and learning to provide a rigorous, relevant and engaging, standard based science experience. More than ten years of combined planning, development, implementation and assessment of this college science course sequence for nonmajors/future teachers has provided significant insights and success in achieving our goal. This paper describes the history and iterative nature of our ongoing improvements, changes in faculty instructional practice, strategies used to overcome student resistance, significant student learning outcomes, support structures for faculty, and the essential and informative role of assessment in improving the outcomes. Our experience with diverse institutions, students and faculty provides the basis for the lessons we have learned and should be of help to others involved in advancing science education.

Virtual reality cataract surgery training: learning curves and concurrent validity.

PubMed

Selvander, Madeleine; Åsman, Peter

2012-08-01

To investigate initial learning curves on a virtual reality (VR) eye surgery simulator and whether achieved skills are transferable between tasks. Thirty-five medical students were randomized to complete ten iterations on either the VR Caspulorhexis module (group A) or the Cataract navigation training module (group B) and then two iterations on the other module. Learning curves were compared between groups. The second Capsulorhexis video was saved and evaluated with the performance rating tool Objective Structured Assessment of Cataract Surgical Skill (OSACSS). The students' stereoacuity was examined. Both groups demonstrated significant improvements in performance over the 10 iterations: group A for all parameters analysed including score (p < 0.0001), time (p < 0.0001) and corneal damage (p = 0.0003), group B for time (p < 0.0001), corneal damage (p < 0.0001) but not for score (p = 0.752). Training on one module did not improve performance on the other. Capsulorhexis score correlated significantly with evaluation of the videos using the OSACSS performance rating tool. For stereoacuity < and ≥120 seconds of arc, sum of both modules' second iteration score was 73.5 and 41.0, respectively (p = 0.062). An initial rapid improvement in performance on a simulator with repeated practice was shown. For capsulorhexis, 10 iterations with only simulator feedback are not enough to reach a plateau for overall score. Skills transfer between modules was not found suggesting benefits from training on both modules. Stereoacuity may be of importance in the recruitment and training of new cataract surgeons. Additional studies are needed to investigate this further. Concurrent validity was found for Capsulorhexis module. © 2010 The Authors. Acta Ophthalmologica © 2010 Acta Ophthalmologica Scandinavica Foundation.

How children perceive fractals: Hierarchical self-similarity and cognitive development

PubMed Central

Martins, Maurício Dias; Laaha, Sabine; Freiberger, Eva Maria; Choi, Soonja; Fitch, W. Tecumseh

2014-01-01

The ability to understand and generate hierarchical structures is a crucial component of human cognition, available in language, music, mathematics and problem solving. Recursion is a particularly useful mechanism for generating complex hierarchies by means of self-embedding rules. In the visual domain, fractals are recursive structures in which simple transformation rules generate hierarchies of infinite depth. Research on how children acquire these rules can provide valuable insight into the cognitive requirements and learning constraints of recursion. Here, we used fractals to investigate the acquisition of recursion in the visual domain, and probed for correlations with grammar comprehension and general intelligence. We compared second (n = 26) and fourth graders (n = 26) in their ability to represent two types of rules for generating hierarchical structures: Recursive rules, on the one hand, which generate new hierarchical levels; and iterative rules, on the other hand, which merely insert items within hierarchies without generating new levels. We found that the majority of fourth graders, but not second graders, were able to represent both recursive and iterative rules. This difference was partially accounted by second graders’ impairment in detecting hierarchical mistakes, and correlated with between-grade differences in grammar comprehension tasks. Empirically, recursion and iteration also differed in at least one crucial aspect: While the ability to learn recursive rules seemed to depend on the previous acquisition of simple iterative representations, the opposite was not true, i.e., children were able to acquire iterative rules before they acquired recursive representations. These results suggest that the acquisition of recursion in vision follows learning constraints similar to the acquisition of recursion in language, and that both domains share cognitive resources involved in hierarchical processing. PMID:24955884

E-Learning Quality Assurance: A Process-Oriented Lifecycle Model

ERIC Educational Resources Information Center

Abdous, M'hammed

2009-01-01

Purpose: The purpose of this paper is to propose a process-oriented lifecycle model for ensuring quality in e-learning development and delivery. As a dynamic and iterative process, quality assurance (QA) is intertwined with the e-learning development process. Design/methodology/approach: After reviewing the existing literature, particularly…

A learning-based agent for home neurorehabilitation.

PubMed

Lydakis, Andreas; Meng, Yuanliang; Munroe, Christopher; Wu, Yi-Ning; Begum, Momotaz

2017-07-01

This paper presents the iterative development of an artificially intelligent system to promote home-based neurorehabilitation. Although proper, structured practice of rehabilitation exercises at home is the key to successful recovery of motor functions, there is no home-program out there which can monitor a patient's exercise-related activities and provide corrective feedback in real time. To this end, we designed a Learning from Demonstration (LfD) based home-rehabilitation framework that combines advanced robot learning algorithms with commercially available wearable technologies. The proposed system uses exercise-related motion information and electromyography signals (EMG) of a patient to train a Markov Decision Process (MDP). The trained MDP model can enable an agent to serve as a coach for a patient. On a system level, this is the first initiative, to the best of our knowledge, to employ LfD in an health-care application to enable lay users to program an intelligent system. From a rehabilitation research perspective, this is a completely novel initiative to employ machine learning to provide interactive corrective feedback to a patient in home settings.

Ontology Sparse Vector Learning Algorithm for Ontology Similarity Measuring and Ontology Mapping via ADAL Technology

NASA Astrophysics Data System (ADS)

Gao, Wei; Zhu, Linli; Wang, Kaiyun

2015-12-01

Ontology, a model of knowledge representation and storage, has had extensive applications in pharmaceutics, social science, chemistry and biology. In the age of “big data”, the constructed concepts are often represented as higher-dimensional data by scholars, and thus the sparse learning techniques are introduced into ontology algorithms. In this paper, based on the alternating direction augmented Lagrangian method, we present an ontology optimization algorithm for ontological sparse vector learning, and a fast version of such ontology technologies. The optimal sparse vector is obtained by an iterative procedure, and the ontology function is then obtained from the sparse vector. Four simulation experiments show that our ontological sparse vector learning model has a higher precision ratio on plant ontology, humanoid robotics ontology, biology ontology and physics education ontology data for similarity measuring and ontology mapping applications.

Multi-objective optimization of radiotherapy: distributed Q-learning and agent-based simulation

NASA Astrophysics Data System (ADS)

Jalalimanesh, Ammar; Haghighi, Hamidreza Shahabi; Ahmadi, Abbas; Hejazian, Hossein; Soltani, Madjid

2017-09-01

Radiotherapy (RT) is among the regular techniques for the treatment of cancerous tumours. Many of cancer patients are treated by this manner. Treatment planning is the most important phase in RT and it plays a key role in therapy quality achievement. As the goal of RT is to irradiate the tumour with adequately high levels of radiation while sparing neighbouring healthy tissues as much as possible, it is a multi-objective problem naturally. In this study, we propose an agent-based model of vascular tumour growth and also effects of RT. Next, we use multi-objective distributed Q-learning algorithm to find Pareto-optimal solutions for calculating RT dynamic dose. We consider multiple objectives and each group of optimizer agents attempt to optimise one of them, iteratively. At the end of each iteration, agents compromise the solutions to shape the Pareto-front of multi-objective problem. We propose a new approach by defining three schemes of treatment planning created based on different combinations of our objectives namely invasive, conservative and moderate. In invasive scheme, we enforce killing cancer cells and pay less attention about irradiation effects on normal cells. In conservative scheme, we take more care of normal cells and try to destroy cancer cells in a less stressed manner. The moderate scheme stands in between. For implementation, each of these schemes is handled by one agent in MDQ-learning algorithm and the Pareto optimal solutions are discovered by the collaboration of agents. By applying this methodology, we could reach Pareto treatment plans through building different scenarios of tumour growth and RT. The proposed multi-objective optimisation algorithm generates robust solutions and finds the best treatment plan for different conditions.

Research as a standard of care in PICU

PubMed Central

Zimmerman, Jerry J.; Anand, Kanwaljeet J. S.; Meert, Kathleen L.; Willson, Douglas F.; Newth, Christopher J. L.; Harrison, Rick; Carcillo, Joseph A.; Berger, John; Jenkins, Tammara L.; Nicholson, Carol; Dean, J. Michael

2016-01-01

Background Excellence in clinical care coupled with basic and applied research reflects the maturation of a medical subspecialty, advances that field, and provides objective data for identifying best practices. Pediatric intensive care units (PICU) are uniquely suited for conducting translational and clinical research. Moreover, multiple investigations have reported that a majority of parents are interested in their children’s participation in clinical research, even when the research offers no direct benefit to their child. However, such activity may generate ethical conflict with bedside care providers trying to acutely identify the best approach for an individual critically ill child. Ultimately, this conflict may diminish enthusiasm for the generation of scientific evidence that supports application of evidence-based medicine into PICU clinical standard work. Objective Provide an overview of current state PICU clinical research strengths, liabilities, opportunities, and barriers, and contrast this with an established pediatric hematology-oncology iterative research model that constitutes a learning healthcare system. Design Narrative review of medical literature published in English. Conclusions Currently most PICU therapy is not evidence-based. Developing a learning healthcare system in the PICU integrates clinical research into usual practice and fosters a culture of evidence-based learning and continual care improvement. As PICU mortality has significantly decreased, identification and validation of patient-centered, clinically relevant research outcome measures other than mortality is essential for future clinical trial design. Because most pediatric critical illness may be classified as rare diseases, participation in research networks will facilitate iterative, collaborative, multi-institutional investigations that over time identify best practices to improve PICU outcomes. Despite real ethical challenges, critically ill children and their families should have the opportunity to participate in translational/clinical research whenever feasible. PMID:26513203

Integrated feature extraction and selection for neuroimage classification

NASA Astrophysics Data System (ADS)

Fan, Yong; Shen, Dinggang

2009-02-01

Feature extraction and selection are of great importance in neuroimage classification for identifying informative features and reducing feature dimensionality, which are generally implemented as two separate steps. This paper presents an integrated feature extraction and selection algorithm with two iterative steps: constrained subspace learning based feature extraction and support vector machine (SVM) based feature selection. The subspace learning based feature extraction focuses on the brain regions with higher possibility of being affected by the disease under study, while the possibility of brain regions being affected by disease is estimated by the SVM based feature selection, in conjunction with SVM classification. This algorithm can not only take into account the inter-correlation among different brain regions, but also overcome the limitation of traditional subspace learning based feature extraction methods. To achieve robust performance and optimal selection of parameters involved in feature extraction, selection, and classification, a bootstrapping strategy is used to generate multiple versions of training and testing sets for parameter optimization, according to the classification performance measured by the area under the ROC (receiver operating characteristic) curve. The integrated feature extraction and selection method is applied to a structural MR image based Alzheimer's disease (AD) study with 98 non-demented and 100 demented subjects. Cross-validation results indicate that the proposed algorithm can improve performance of the traditional subspace learning based classification.

Oxytocin attenuates trust as a subset of more general reinforcement learning, with altered reward circuit functional connectivity in males.

PubMed

Ide, Jaime S; Nedic, Sanja; Wong, Kin F; Strey, Shmuel L; Lawson, Elizabeth A; Dickerson, Bradford C; Wald, Lawrence L; La Camera, Giancarlo; Mujica-Parodi, Lilianne R

2018-07-01

Oxytocin (OT) is an endogenous neuropeptide that, while originally thought to promote trust, has more recently been found to be context-dependent. Here we extend experimental paradigms previously restricted to de novo decision-to-trust, to a more realistic environment in which social relationships evolve in response to iterative feedback over twenty interactions. In a randomized, double blind, placebo-controlled within-subject/crossover experiment of human adult males, we investigated the effects of a single dose of intranasal OT (40 IU) on Bayesian expectation updating and reinforcement learning within a social context, with associated brain circuit dynamics. Subjects participated in a neuroeconomic task (Iterative Trust Game) designed to probe iterative social learning while their brains were scanned using ultra-high field (7T) fMRI. We modeled each subject's behavior using Bayesian updating of belief-states ("willingness to trust") as well as canonical measures of reinforcement learning (learning rate, inverse temperature). Behavioral trajectories were then used as regressors within fMRI activation and connectivity analyses to identify corresponding brain network functionality affected by OT. Behaviorally, OT reduced feedback learning, without bias with respect to positive versus negative reward. Neurobiologically, reduced learning under OT was associated with muted communication between three key nodes within the reward circuit: the orbitofrontal cortex, amygdala, and lateral (limbic) habenula. Our data suggest that OT, rather than inspiring feelings of generosity, instead attenuates the brain's encoding of prediction error and therefore its ability to modulate pre-existing beliefs. This effect may underlie OT's putative role in promoting what has typically been reported as 'unjustified trust' in the face of information that suggests likely betrayal, while also resolving apparent contradictions with regard to OT's context-dependent behavioral effects. Copyright © 2018 Elsevier Inc. All rights reserved.

Advancing Personalized Learning through the Iterative Application of Innovation Science

ERIC Educational Resources Information Center

Redding, Sam; Twyman, Janet; Murphy, Marilyn

2016-01-01

The promise of personalized learning excites many educators, and schools are wondering how best to introduce it and how they know when they have achieved it. Rather than thinking of personalized learning as an "it" (i.e., a program that is either present or not), we might think of it as an approach to teaching and learning that has many…

Picking Deep Filter Responses for Fine-Grained Image Recognition (Open Access Author’s Manuscript)

DTIC Science & Technology

2016-12-16

stages. Our method explores a unified framework based on two steps of deep filter response picking. The first picking step is to find distinctive... filters which respond to specific patterns significantly and consistently, and learn a set of part detectors via iteratively alternating between new...positive sample mining and part model retraining. The second picking step is to pool deep filter responses via spatially weighted combination of Fisher

We Are the Game Changers: An Open Gaming Literacy Programme

ERIC Educational Resources Information Center

Arnab, Sylvester; Morini, Luca; Green, Kate; Masters, Alex; Bellamy-Woods, Tyrone

2017-01-01

This paper discusses the first iteration of Game Changers Programme hosted by Coventry University's Disruptive Media Learning Lab (DMLL), an open game design initiative. The Programme had the goal of facilitating new models of teaching and learning, new practices in cross-faculty learning/ collaboration to make game design and development more…

Design and Implementation of a Learning Analytics Toolkit for Teachers

ERIC Educational Resources Information Center

Dyckhoff, Anna Lea; Zielke, Dennis; Bultmann, Mareike; Chatti, Mohamed Amine; Schroeder, Ulrik

2012-01-01

Learning Analytics can provide powerful tools for teachers in order to support them in the iterative process of improving the effectiveness of their courses and to collaterally enhance their students' performance. In this paper, we present the theoretical background, design, implementation, and evaluation details of eLAT, a Learning Analytics…

Rapid Prototyping of Mobile Learning Games

ERIC Educational Resources Information Center

Federley, Maija; Sorsa, Timo; Paavilainen, Janne; Boissonnier, Kimo; Seisto, Anu

2014-01-01

This position paper presents the first results of an on-going project, in which we explore rapid prototyping method to efficiently produce digital learning solutions that are commercially viable. In this first phase, rapid game prototyping and an iterative approach was tested as a quick and efficient way to create learning games and to evaluate…

From Intent to Action: An Iterative Engineering Process

ERIC Educational Resources Information Center

Mouton, Patrice; Rodet, Jacques; Vacaresse, Sylvain

2015-01-01

Quite by chance, and over the course of a few haphazard meetings, a Master's degree in "E-learning Design" gradually developed in a Faculty of Economics. Its original and evolving design was the result of an iterative process carried out, not by a single Instructional Designer (ID), but by a full ID team. Over the last 10 years it has…

A General Iterative Shrinkage and Thresholding Algorithm for Non-convex Regularized Optimization Problems.

PubMed

Gong, Pinghua; Zhang, Changshui; Lu, Zhaosong; Huang, Jianhua Z; Ye, Jieping

2013-01-01

Non-convex sparsity-inducing penalties have recently received considerable attentions in sparse learning. Recent theoretical investigations have demonstrated their superiority over the convex counterparts in several sparse learning settings. However, solving the non-convex optimization problems associated with non-convex penalties remains a big challenge. A commonly used approach is the Multi-Stage (MS) convex relaxation (or DC programming), which relaxes the original non-convex problem to a sequence of convex problems. This approach is usually not very practical for large-scale problems because its computational cost is a multiple of solving a single convex problem. In this paper, we propose a General Iterative Shrinkage and Thresholding (GIST) algorithm to solve the nonconvex optimization problem for a large class of non-convex penalties. The GIST algorithm iteratively solves a proximal operator problem, which in turn has a closed-form solution for many commonly used penalties. At each outer iteration of the algorithm, we use a line search initialized by the Barzilai-Borwein (BB) rule that allows finding an appropriate step size quickly. The paper also presents a detailed convergence analysis of the GIST algorithm. The efficiency of the proposed algorithm is demonstrated by extensive experiments on large-scale data sets.

Iterative learning control with applications in energy generation, lasers and health care.

PubMed

Rogers, E; Tutty, O R

2016-09-01

Many physical systems make repeated executions of the same finite time duration task. One example is a robot in a factory or warehouse whose task is to collect an object in sequence from a location, transfer it over a finite duration, place it at a specified location or on a moving conveyor and then return for the next one and so on. Iterative learning control was especially developed for systems with this mode of operation and this paper gives an overview of this control design method using relatively recent relevant applications in wind turbines, free-electron lasers and health care, as exemplars to demonstrate its applicability.

Manager Perspectives on Communication and Public ...

EPA Pesticide Factsheets

We argue that public engagement is crucial to achieving lasting ecological success in aquatic restoration efforts, and that the most effective public engagement mechanisms are what we term iterative mechanisms. Here we look to a particular social-ecological system – the restoration community in Rhode Island, U.S.A. and the rivers, wetlands, marshes, and estuaries, and their related species, that they work to protect – to better understand land managers’ perspectives on public engagement in restoration processes. Adopting an inductive approach to critical discourse analysis of interviews with 27 local, state, and federal restoration managers and the forms of public interaction they described, we identify three distinct models of public engagement in natural resources management employed by managers: unidirectional; bidirectional; and iterative. While unidirectional and bidirectional mechanisms can help managers achieve short-term ecological successes, we suggest that adopting an iterative approach can improve the quality of stakeholder and learning interactions and, subsequently, foster lasting ecological successes. We argue that managers can design deliberately for public engagement mechanisms that are best suited to projects in particular social-ecological systems in order to create restoration projects that achieve ecological, learning, and stakeholder successes. We attempt to synthesize the lessons learned from efforts at public engagement in restoratio

A Parameter Communication Optimization Strategy for Distributed Machine Learning in Sensors

PubMed Central

Zhang, Jilin; Tu, Hangdi; Ren, Yongjian; Wan, Jian; Zhou, Li; Li, Mingwei; Wang, Jue; Yu, Lifeng; Zhao, Chang; Zhang, Lei

2017-01-01

In order to utilize the distributed characteristic of sensors, distributed machine learning has become the mainstream approach, but the different computing capability of sensors and network delays greatly influence the accuracy and the convergence rate of the machine learning model. Our paper describes a reasonable parameter communication optimization strategy to balance the training overhead and the communication overhead. We extend the fault tolerance of iterative-convergent machine learning algorithms and propose the Dynamic Finite Fault Tolerance (DFFT). Based on the DFFT, we implement a parameter communication optimization strategy for distributed machine learning, named Dynamic Synchronous Parallel Strategy (DSP), which uses the performance monitoring model to dynamically adjust the parameter synchronization strategy between worker nodes and the Parameter Server (PS). This strategy makes full use of the computing power of each sensor, ensures the accuracy of the machine learning model, and avoids the situation that the model training is disturbed by any tasks unrelated to the sensors. PMID:28934163

Designing Serious Computer Games for People With Moderate and Advanced Dementia: Interdisciplinary Theory-Driven Pilot Study.

PubMed

Tziraki, Chariklia; Berenbaum, Rakel; Gross, Daniel; Abikhzer, Judith; Ben-David, Boaz M

2017-07-31

The field of serious games for people with dementia (PwD) is mostly driven by game-design principals typically applied to games created by and for younger individuals. Little has been done developing serious games to help PwD maintain cognition and to support functionality. We aimed to create a theory-based serious game for PwD, with input from a multi-disciplinary team familiar with aging, dementia, and gaming theory, as well as direct input from end users (the iterative process). Targeting enhanced self-efficacy in daily activities, the goal was to generate a game that is acceptable, accessible and engaging for PwD. The theory-driven game development was based on the following learning theories: learning in context, errorless learning, building on capacities, and acknowledging biological changes-all with the aim to boost self-efficacy. The iterative participatory process was used for game screen development with input of 34 PwD and 14 healthy community dwelling older adults, aged over 65 years. Development of game screens was informed by the bio-psychological aging related disabilities (ie, motor, visual, and perception) as well as remaining neuropsychological capacities (ie, implicit memory) of PwD. At the conclusion of the iterative development process, a prototype game with 39 screens was used for a pilot study with 24 PwD and 14 healthy community dwelling older adults. The game was played twice weekly for 10 weeks. Quantitative analysis showed that the average speed of successful screen completion was significantly longer for PwD compared with healthy older adults. Both PwD and controls showed an equivalent linear increase in the speed for task completion with practice by the third session (P<.02). Most important, the rate of improved processing speed with practice was not statistically different between PwD and controls. This may imply that some form of learning occurred for PwD at a nonsignificantly different rate than for controls. Qualitative results indicate that PwD found the game engaging and fun. Healthy older adults found the game too easy. Increase in self-reported self-efficacy was documented with PwD only. Our study demonstrated that PwD's speed improved with practice at the same rate as healthy older adults. This implies that when tasks are designed to match PwD's abilities, learning ensues. In addition, this pilot study of a serious game, designed for PwD, was accessible, acceptable, and enjoyable for end users. Games designed based on learning theories and input of end users and a multi-disciplinary team familiar with dementia and aging may have the potential of maintaining capacity and improving functionality of PwD. A larger longer study is needed to confirm our findings and evaluate the use of these games in assessing cognitive status and functionality. ©Chariklia Tziraki, Rakel Berenbaum, Daniel Gross, Judith Abikhzer, Boaz M Ben-David. Originally published in JMIR Serious Games (http://games.jmir.org), 31.07.2017.

Designing Serious Computer Games for People With Moderate and Advanced Dementia: Interdisciplinary Theory-Driven Pilot Study

PubMed Central

Gross, Daniel; Abikhzer, Judith

2017-01-01

Background The field of serious games for people with dementia (PwD) is mostly driven by game-design principals typically applied to games created by and for younger individuals. Little has been done developing serious games to help PwD maintain cognition and to support functionality. Objectives We aimed to create a theory-based serious game for PwD, with input from a multi-disciplinary team familiar with aging, dementia, and gaming theory, as well as direct input from end users (the iterative process). Targeting enhanced self-efficacy in daily activities, the goal was to generate a game that is acceptable, accessible and engaging for PwD. Methods The theory-driven game development was based on the following learning theories: learning in context, errorless learning, building on capacities, and acknowledging biological changes—all with the aim to boost self-efficacy. The iterative participatory process was used for game screen development with input of 34 PwD and 14 healthy community dwelling older adults, aged over 65 years. Development of game screens was informed by the bio-psychological aging related disabilities (ie, motor, visual, and perception) as well as remaining neuropsychological capacities (ie, implicit memory) of PwD. At the conclusion of the iterative development process, a prototype game with 39 screens was used for a pilot study with 24 PwD and 14 healthy community dwelling older adults. The game was played twice weekly for 10 weeks. Results Quantitative analysis showed that the average speed of successful screen completion was significantly longer for PwD compared with healthy older adults. Both PwD and controls showed an equivalent linear increase in the speed for task completion with practice by the third session (P<.02). Most important, the rate of improved processing speed with practice was not statistically different between PwD and controls. This may imply that some form of learning occurred for PwD at a nonsignificantly different rate than for controls. Qualitative results indicate that PwD found the game engaging and fun. Healthy older adults found the game too easy. Increase in self-reported self-efficacy was documented with PwD only. Conclusions Our study demonstrated that PwD’s speed improved with practice at the same rate as healthy older adults. This implies that when tasks are designed to match PwD’s abilities, learning ensues. In addition, this pilot study of a serious game, designed for PwD, was accessible, acceptable, and enjoyable for end users. Games designed based on learning theories and input of end users and a multi-disciplinary team familiar with dementia and aging may have the potential of maintaining capacity and improving functionality of PwD. A larger longer study is needed to confirm our findings and evaluate the use of these games in assessing cognitive status and functionality. PMID:28760730

Knowledge of Social Affiliations Biases Economic Decisions

PubMed Central

Martinez, Joel E.; Mack, Michael L.; Gelman, Bernard D.; Preston, Alison R.

2016-01-01

An individual’s reputation and group membership can produce automatic judgments and behaviors toward that individual. Whether an individual’s social reputation impacts interactions with affiliates has yet to be demonstrated. We tested the hypothesis that during initial encounters with others, existing knowledge of their social network guides behavior toward them. Participants learned reputations (cooperate, defect, or equal mix) for virtual players through an iterated economic game (EG). Then, participants learned one novel friend for each player. The critical question was how participants treated the friends in a single-shot EG after the friend-learning phase. Participants tended to cooperate with friends of cooperators and defect on friends of defectors, indicative of a decision making bias based on memory for social affiliations. Interestingly, participants’ explicit predictions of the friends’ future behavior showed no such bias. Moreover, the bias to defect on friends of defectors was enhanced when affiliations were learned in a social context; participants who learned to associate novel faces with player faces during reinforcement learning did not show reputation-based bias for associates of defectors during single-shot EG. These data indicate that when faced with risky social decisions, memories of social connections influence behavior implicitly. PMID:27441563

Using concept maps and goal-setting to support the development of self-regulated learning in a problem-based learning curriculum.

PubMed

Thomas, Lisa; Bennett, Sue; Lockyer, Lori

2016-09-01

Problem-based learning (PBL) in medical education focuses on preparing independent learners for continuing, self-directed, professional development beyond the classroom. Skills in self-regulated learning (SRL) are important for success in PBL and ongoing professional practice. However, the development of SRL skills is often left to chance. This study presents the investigated outcomes for students when support for the development of SRL was embedded in a PBL medical curriculum. This investigation involved design, delivery and testing of SRL support, embedded into the first phase of a four-year, graduate-entry MBBS degree. The intervention included concept mapping and goal-setting activities through iterative processes of planning, monitoring and reflecting on learning. A mixed-methods approach was used to collect data from seven students to develop case studies of engagement with, and outcomes from, the SRL support. The findings indicate that students who actively engaged with support for SRL demonstrated increases in cognitive and metacognitive functioning. Students also reported a greater sense of confidence in and control over their approaches to learning in PBL. This study advances understanding about how the development of SRL can be integrated into PBL.

Incremental Support Vector Machine Framework for Visual Sensor Networks

NASA Astrophysics Data System (ADS)

Awad, Mariette; Jiang, Xianhua; Motai, Yuichi

2006-12-01

Motivated by the emerging requirements of surveillance networks, we present in this paper an incremental multiclassification support vector machine (SVM) technique as a new framework for action classification based on real-time multivideo collected by homogeneous sites. The technique is based on an adaptation of least square SVM (LS-SVM) formulation but extends beyond the static image-based learning of current SVM methodologies. In applying the technique, an initial supervised offline learning phase is followed by a visual behavior data acquisition and an online learning phase during which the cluster head performs an ensemble of model aggregations based on the sensor nodes inputs. The cluster head then selectively switches on designated sensor nodes for future incremental learning. Combining sensor data offers an improvement over single camera sensing especially when the latter has an occluded view of the target object. The optimization involved alleviates the burdens of power consumption and communication bandwidth requirements. The resulting misclassification error rate, the iterative error reduction rate of the proposed incremental learning, and the decision fusion technique prove its validity when applied to visual sensor networks. Furthermore, the enabled online learning allows an adaptive domain knowledge insertion and offers the advantage of reducing both the model training time and the information storage requirements of the overall system which makes it even more attractive for distributed sensor networks communication.

Designing for deeper learning in a blended computer science course for middle school students

NASA Astrophysics Data System (ADS)

Grover, Shuchi; Pea, Roy; Cooper, Stephen

2015-04-01

The focus of this research was to create and test an introductory computer science course for middle school. Titled "Foundations for Advancing Computational Thinking" (FACT), the course aims to prepare and motivate middle school learners for future engagement with algorithmic problem solving. FACT was also piloted as a seven-week course on Stanford's OpenEdX MOOC platform for blended in-class learning. Unique aspects of FACT include balanced pedagogical designs that address the cognitive, interpersonal, and intrapersonal aspects of "deeper learning"; a focus on pedagogical strategies for mediating and assessing for transfer from block-based to text-based programming; curricular materials for remedying misperceptions of computing; and "systems of assessments" (including formative and summative quizzes and tests, directed as well as open-ended programming assignments, and a transfer test) to get a comprehensive picture of students' deeper computational learning. Empirical investigations, accomplished over two iterations of a design-based research effort with students (aged 11-14 years) in a public school, sought to examine student understanding of algorithmic constructs, and how well students transferred this learning from Scratch to text-based languages. Changes in student perceptions of computing as a discipline were measured. Results and mixed-method analyses revealed that students in both studies (1) achieved substantial learning gains in algorithmic thinking skills, (2) were able to transfer their learning from Scratch to a text-based programming context, and (3) achieved significant growth toward a more mature understanding of computing as a discipline. Factor analyses of prior computing experience, multivariate regression analyses, and qualitative analyses of student projects and artifact-based interviews were conducted to better understand the factors affecting learning outcomes. Prior computing experiences (as measured by a pretest) and math ability were found to be strong predictors of learning outcomes.

Data-Driven Learning of Total and Local Energies in Elemental Boron

NASA Astrophysics Data System (ADS)

Deringer, Volker L.; Pickard, Chris J.; Csányi, Gábor

2018-04-01

The allotropes of boron continue to challenge structural elucidation and solid-state theory. Here we use machine learning combined with random structure searching (RSS) algorithms to systematically construct an interatomic potential for boron. Starting from ensembles of randomized atomic configurations, we use alternating single-point quantum-mechanical energy and force computations, Gaussian approximation potential (GAP) fitting, and GAP-driven RSS to iteratively generate a representation of the element's potential-energy surface. Beyond the total energies of the very different boron allotropes, our model readily provides atom-resolved, local energies and thus deepened insight into the frustrated β -rhombohedral boron structure. Our results open the door for the efficient and automated generation of GAPs, and other machine-learning-based interatomic potentials, and suggest their usefulness as a tool for materials discovery.

Data-Driven Learning of Total and Local Energies in Elemental Boron.

PubMed

Deringer, Volker L; Pickard, Chris J; Csányi, Gábor

2018-04-13

The allotropes of boron continue to challenge structural elucidation and solid-state theory. Here we use machine learning combined with random structure searching (RSS) algorithms to systematically construct an interatomic potential for boron. Starting from ensembles of randomized atomic configurations, we use alternating single-point quantum-mechanical energy and force computations, Gaussian approximation potential (GAP) fitting, and GAP-driven RSS to iteratively generate a representation of the element's potential-energy surface. Beyond the total energies of the very different boron allotropes, our model readily provides atom-resolved, local energies and thus deepened insight into the frustrated β-rhombohedral boron structure. Our results open the door for the efficient and automated generation of GAPs, and other machine-learning-based interatomic potentials, and suggest their usefulness as a tool for materials discovery.

Low-dose CT image reconstruction using gain intervention-based dictionary learning

NASA Astrophysics Data System (ADS)

Pathak, Yadunath; Arya, K. V.; Tiwari, Shailendra

2018-05-01

Computed tomography (CT) approach is extensively utilized in clinical diagnoses. However, X-ray residue in human body may introduce somatic damage such as cancer. Owing to radiation risk, research has focused on the radiation exposure distributed to patients through CT investigations. Therefore, low-dose CT has become a significant research area. Many researchers have proposed different low-dose CT reconstruction techniques. But, these techniques suffer from various issues such as over smoothing, artifacts, noise, etc. Therefore, in this paper, we have proposed a novel integrated low-dose CT reconstruction technique. The proposed technique utilizes global dictionary-based statistical iterative reconstruction (GDSIR) and adaptive dictionary-based statistical iterative reconstruction (ADSIR)-based reconstruction techniques. In case the dictionary (D) is predetermined, then GDSIR can be used and if D is adaptively defined then ADSIR is appropriate choice. The gain intervention-based filter is also used as a post-processing technique for removing the artifacts from low-dose CT reconstructed images. Experiments have been done by considering the proposed and other low-dose CT reconstruction techniques on well-known benchmark CT images. Extensive experiments have shown that the proposed technique outperforms the available approaches.

Standard and reduced radiation dose liver CT images: adaptive statistical iterative reconstruction versus model-based iterative reconstruction-comparison of findings and image quality.

PubMed

Shuman, William P; Chan, Keith T; Busey, Janet M; Mitsumori, Lee M; Choi, Eunice; Koprowicz, Kent M; Kanal, Kalpana M

2014-12-01

To investigate whether reduced radiation dose liver computed tomography (CT) images reconstructed with model-based iterative reconstruction ( MBIR model-based iterative reconstruction ) might compromise depiction of clinically relevant findings or might have decreased image quality when compared with clinical standard radiation dose CT images reconstructed with adaptive statistical iterative reconstruction ( ASIR adaptive statistical iterative reconstruction ). With institutional review board approval, informed consent, and HIPAA compliance, 50 patients (39 men, 11 women) were prospectively included who underwent liver CT. After a portal venous pass with ASIR adaptive statistical iterative reconstruction images, a 60% reduced radiation dose pass was added with MBIR model-based iterative reconstruction images. One reviewer scored ASIR adaptive statistical iterative reconstruction image quality and marked findings. Two additional independent reviewers noted whether marked findings were present on MBIR model-based iterative reconstruction images and assigned scores for relative conspicuity, spatial resolution, image noise, and image quality. Liver and aorta Hounsfield units and image noise were measured. Volume CT dose index and size-specific dose estimate ( SSDE size-specific dose estimate ) were recorded. Qualitative reviewer scores were summarized. Formal statistical inference for signal-to-noise ratio ( SNR signal-to-noise ratio ), contrast-to-noise ratio ( CNR contrast-to-noise ratio ), volume CT dose index, and SSDE size-specific dose estimate was made (paired t tests), with Bonferroni adjustment. Two independent reviewers identified all 136 ASIR adaptive statistical iterative reconstruction image findings (n = 272) on MBIR model-based iterative reconstruction images, scoring them as equal or better for conspicuity, spatial resolution, and image noise in 94.1% (256 of 272), 96.7% (263 of 272), and 99.3% (270 of 272), respectively. In 50 image sets, two reviewers (n = 100) scored overall image quality as sufficient or good with MBIR model-based iterative reconstruction in 99% (99 of 100). Liver SNR signal-to-noise ratio was significantly greater for MBIR model-based iterative reconstruction (10.8 ± 2.5 [standard deviation] vs 7.7 ± 1.4, P < .001); there was no difference for CNR contrast-to-noise ratio (2.5 ± 1.4 vs 2.4 ± 1.4, P = .45). For ASIR adaptive statistical iterative reconstruction and MBIR model-based iterative reconstruction , respectively, volume CT dose index was 15.2 mGy ± 7.6 versus 6.2 mGy ± 3.6; SSDE size-specific dose estimate was 16.4 mGy ± 6.6 versus 6.7 mGy ± 3.1 (P < .001). Liver CT images reconstructed with MBIR model-based iterative reconstruction may allow up to 59% radiation dose reduction compared with the dose with ASIR adaptive statistical iterative reconstruction , without compromising depiction of findings or image quality. © RSNA, 2014.

Virtual patients: practical advice for clinical authors using Labyrinth.

PubMed

Begg, Michael

2010-09-01

Labyrinth is a tool originally developed in the University of Edinburgh's Learning Technology Section for authoring and delivering branching case scenarios. The scenarios can incorporate game-informed elements such as scoring, randomising, avatars and counters. Labyrinth has grown more popular internationally since a version of the build was made available on the open source network Source Forge. This paper offers help and advice for clinical educators interested in creating cases. Labyrinth is increasingly recognised as a tool offering great potential for delivering cases that promote rich, situated learning opportunities for learners. There are, however, significant challenges to generating such cases, not least of which is the challenge for potential authors in approaching the process of constructing narrative-rich, context-sensitive cases in an unfamiliar authoring environment. This paper offers a brief overview of the principles informing Labyrinth cases (game-informed learning), and offers some practical advice to better prepare educators with little or no prior experience. Labyrinth has continued to grow and develop, from its roots as a research and development environment to one that is optimised for use by non-technical clinical educators. The process becomes increasingly iterative and better informed as the teaching community push the software further. The positive implications of providing practical advice and concept insight to new case authors is that it ideally leads to a broader base of users who will inform future iterations of the software. © Blackwell Publishing Ltd 2010.

Teaching hydrogeology: a review of current practice

NASA Astrophysics Data System (ADS)

Gleeson, T.; Allen, D. M.; Ferguson, G.

2012-07-01

Hydrogeology is now taught in a broad spectrum of departments and institutions to students with diverse backgrounds. Successful instruction in hydrogeology thus requires a variety of pedagogical approaches depending on desired learning outcomes and the background of students. We review the pedagogical literature in hydrogeology to highlight recent advances and analyze a 2005 survey among 68 hydrogeology instructors. The literature and survey results suggest there are only ~ 15 topics that are considered crucial by most hydrogeologists and > 100 other topics that are considered crucial by some hydrogeologists. The crucial topics focus on properties of aquifers and fundamentals of groundwater flow, and should likely be part of all undergraduate hydrogeology courses. Other topics can supplement and support these crucial topics, depending on desired learning outcomes. Classroom settings continue to provide a venue for emphasizing fundamental knowledge. However, recent pedagogical advances are biased towards field and laboratory instruction with a goal of bolstering experiential learning. Field methods build on the fundamentals taught in the classroom and emphasize the collection of data, data uncertainty, and the development of vocational skills. Laboratory and computer-based exercises similarly build on theory, and offer an opportunity for data analysis and integration. The literature suggests curricula at all levels should ideally balance field, laboratory, and classroom pedagogy into an iterative and integrative whole. An integrated, iterative and balanced approach leads to greater student motivation and advancement of theoretical and vocational knowledge.

Online Distributed Learning Over Networks in RKH Spaces Using Random Fourier Features

NASA Astrophysics Data System (ADS)

Bouboulis, Pantelis; Chouvardas, Symeon; Theodoridis, Sergios

2018-04-01

We present a novel diffusion scheme for online kernel-based learning over networks. So far, a major drawback of any online learning algorithm, operating in a reproducing kernel Hilbert space (RKHS), is the need for updating a growing number of parameters as time iterations evolve. Besides complexity, this leads to an increased need of communication resources, in a distributed setting. In contrast, the proposed method approximates the solution as a fixed-size vector (of larger dimension than the input space) using Random Fourier Features. This paves the way to use standard linear combine-then-adapt techniques. To the best of our knowledge, this is the first time that a complete protocol for distributed online learning in RKHS is presented. Conditions for asymptotic convergence and boundness of the networkwise regret are also provided. The simulated tests illustrate the performance of the proposed scheme.

Drawing Analogies to Deepen Learning

ERIC Educational Resources Information Center

Fava, Michelle

2017-01-01

This article offers examples of how drawing can facilitate thinking skills that promote analogical reasoning to enable deeper learning. The instructional design applies cognitive principles, briefly described here. The workshops were developed iteratively, through feedback from student and teacher participants. Elements of the UK National…

Contextual EFL Learning in a 3D Virtual Environment

ERIC Educational Resources Information Center

Lan, Yu-Ju

2015-01-01

The purposes of the current study are to develop virtually immersive EFL learning contexts for EFL learners in Taiwan to pre- and review English materials beyond the regular English class schedule. A 2-iteration action research lasting for one semester was conducted to evaluate the effects of virtual contexts on learners' EFL learning. 132…

Reflections on the Use of Iterative, Agile and Collaborative Approaches for Blended Flipped Learning Development

ERIC Educational Resources Information Center

Owen, Hazel; Dunham, Nicola

2015-01-01

E-learning experiences are widely becoming common practice in many schools, tertiary institutions and other organisations. However despite this increased use of technology to enhance learning and the associated investment involved the result does not always equate to more engaged, knowledgeable and skilled learners. We have observed two key…

Factors Contributing to Cognitive Absorption and Grounded Learning Effectiveness in a Competitive Business Marketing Simulation

ERIC Educational Resources Information Center

Baker, David Scott; Underwood, James, III; Thakur, Ramendra

2017-01-01

This study aimed to establish a pedagogical positioning of a business marketing simulation as a grounded learning teaching tool and empirically assess the dimensions of cognitive absorption related to grounded learning effectiveness in an iterative business simulation environment. The method/design and sample consisted of a field study survey…

Exploiting Multi-Step Sample Trajectories for Approximate Value Iteration

DTIC Science & Technology

2013-09-01

WORK UNIT NUMBER IH 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) AFRL/ RISC 525 Brooks Road, Rome NY 13441-4505 Binghamton University...S) AND ADDRESS(ES) Air Force Research Laboratory/Information Directorate Rome Research Site/ RISC 525 Brooks Road Rome NY 13441-4505 10. SPONSOR...iteration methods for reinforcement learning (RL) generalize experience from limited samples across large state-action spaces. The function approximators

A fresh look at electron cyclotron current drive power requirements for stabilization of tearing modes in ITER

DOE Office of Scientific and Technical Information (OSTI.GOV)

La Haye, R. J., E-mail: lahaye@fusion.gat.com

2015-12-10

ITER is an international project to design and build an experimental fusion reactor based on the “tokamak” concept. ITER relies upon localized electron cyclotron current drive (ECCD) at the rational safety factor q=2 to suppress or stabilize the expected poloidal mode m=2, toroidal mode n=1 neoclassical tearing mode (NTM) islands. Such islands if unmitigated degrade energy confinement, lock to the resistive wall (stop rotating), cause loss of “H-mode” and induce disruption. The International Tokamak Physics Activity (ITPA) on MHD, Disruptions and Magnetic Control joint experiment group MDC-8 on Current Drive Prevention/Stabilization of Neoclassical Tearing Modes started in 2005, after whichmore » assessments were made for the requirements for ECCD needed in ITER, particularly that of rf power and alignment on q=2 [1]. Narrow well-aligned rf current parallel to and of order of one percent of the total plasma current is needed to replace the “missing” current in the island O-points and heal or preempt (avoid destabilization by applying ECCD on q=2 in absence of the mode) the island [2-4]. This paper updates the advances in ECCD stabilization on NTMs learned in DIII-D experiments and modeling during the last 5 to 10 years as applies to stabilization by localized ECCD of tearing modes in ITER. This includes the ECCD (inside the q=1 radius) stabilization of the NTM “seeding” instability known as sawteeth (m/n=1/1) [5]. Recent measurements in DIII-D show that the ITER-similar current profile is classically unstable, curvature stabilization must not be neglected, and the small island width stabilization effect from helical ion polarization currents is stronger than was previously thought [6]. The consequences of updated assumptions in ITER modeling of the minimum well-aligned ECCD power needed are all-in-all favorable (and well-within the ITER 24 gyrotron capability) when all effects are included. However, a “wild card” may be broadening of the localized ECCD by the presence of the island; various theories predict broadening could occur and there is experimental evidence for broadening in DIII-D. Wider than now expected ECCD in ITER would make alignment easier to do but weaken the stabilization and thus require more rf power. In addition to updated modeling for ITER, advances in the ITER-relevant DIII-D ECCD gyrotron launch mirror control system hardware and real-time plasma control system have been made [7] and there are plans for application in DIII-D ITER demonstration discharges.« less

A fresh look at electron cyclotron current drive power requirements for stabilization of tearing modes in ITER

NASA Astrophysics Data System (ADS)

La Haye, R. J.

2015-12-01

ITER is an international project to design and build an experimental fusion reactor based on the "tokamak" concept. ITER relies upon localized electron cyclotron current drive (ECCD) at the rational safety factor q=2 to suppress or stabilize the expected poloidal mode m=2, toroidal mode n=1 neoclassical tearing mode (NTM) islands. Such islands if unmitigated degrade energy confinement, lock to the resistive wall (stop rotating), cause loss of "H-mode" and induce disruption. The International Tokamak Physics Activity (ITPA) on MHD, Disruptions and Magnetic Control joint experiment group MDC-8 on Current Drive Prevention/Stabilization of Neoclassical Tearing Modes started in 2005, after which assessments were made for the requirements for ECCD needed in ITER, particularly that of rf power and alignment on q=2 [1]. Narrow well-aligned rf current parallel to and of order of one percent of the total plasma current is needed to replace the "missing" current in the island O-points and heal or preempt (avoid destabilization by applying ECCD on q=2 in absence of the mode) the island [2-4]. This paper updates the advances in ECCD stabilization on NTMs learned in DIII-D experiments and modeling during the last 5 to 10 years as applies to stabilization by localized ECCD of tearing modes in ITER. This includes the ECCD (inside the q=1 radius) stabilization of the NTM "seeding" instability known as sawteeth (m/n=1/1) [5]. Recent measurements in DIII-D show that the ITER-similar current profile is classically unstable, curvature stabilization must not be neglected, and the small island width stabilization effect from helical ion polarization currents is stronger than was previously thought [6]. The consequences of updated assumptions in ITER modeling of the minimum well-aligned ECCD power needed are all-in-all favorable (and well-within the ITER 24 gyrotron capability) when all effects are included. However, a "wild card" may be broadening of the localized ECCD by the presence of the island; various theories predict broadening could occur and there is experimental evidence for broadening in DIII-D. Wider than now expected ECCD in ITER would make alignment easier to do but weaken the stabilization and thus require more rf power. In addition to updated modeling for ITER, advances in the ITER-relevant DIII-D ECCD gyrotron launch mirror control system hardware and real-time plasma control system have been made [7] and there are plans for application in DIII-D ITER demonstration discharges.

Optimization Control of the Color-Coating Production Process for Model Uncertainty

PubMed Central

He, Dakuo; Wang, Zhengsong; Yang, Le; Mao, Zhizhong

2016-01-01

Optimized control of the color-coating production process (CCPP) aims at reducing production costs and improving economic efficiency while meeting quality requirements. However, because optimization control of the CCPP is hampered by model uncertainty, a strategy that considers model uncertainty is proposed. Previous work has introduced a mechanistic model of CCPP based on process analysis to simulate the actual production process and generate process data. The partial least squares method is then applied to develop predictive models of film thickness and economic efficiency. To manage the model uncertainty, the robust optimization approach is introduced to improve the feasibility of the optimized solution. Iterative learning control is then utilized to further refine the model uncertainty. The constrained film thickness is transformed into one of the tracked targets to overcome the drawback that traditional iterative learning control cannot address constraints. The goal setting of economic efficiency is updated continuously according to the film thickness setting until this reaches its desired value. Finally, fuzzy parameter adjustment is adopted to ensure that the economic efficiency and film thickness converge rapidly to their optimized values under the constraint conditions. The effectiveness of the proposed optimization control strategy is validated by simulation results. PMID:27247563

Optimization Control of the Color-Coating Production Process for Model Uncertainty.

PubMed

He, Dakuo; Wang, Zhengsong; Yang, Le; Mao, Zhizhong

2016-01-01

Optimized control of the color-coating production process (CCPP) aims at reducing production costs and improving economic efficiency while meeting quality requirements. However, because optimization control of the CCPP is hampered by model uncertainty, a strategy that considers model uncertainty is proposed. Previous work has introduced a mechanistic model of CCPP based on process analysis to simulate the actual production process and generate process data. The partial least squares method is then applied to develop predictive models of film thickness and economic efficiency. To manage the model uncertainty, the robust optimization approach is introduced to improve the feasibility of the optimized solution. Iterative learning control is then utilized to further refine the model uncertainty. The constrained film thickness is transformed into one of the tracked targets to overcome the drawback that traditional iterative learning control cannot address constraints. The goal setting of economic efficiency is updated continuously according to the film thickness setting until this reaches its desired value. Finally, fuzzy parameter adjustment is adopted to ensure that the economic efficiency and film thickness converge rapidly to their optimized values under the constraint conditions. The effectiveness of the proposed optimization control strategy is validated by simulation results.

Electronic patient-reported data capture as a foundation of rapid learning cancer care.

PubMed

Abernethy, Amy P; Ahmad, Asif; Zafar, S Yousuf; Wheeler, Jane L; Reese, Jennifer Barsky; Lyerly, H Kim

2010-06-01

"Rapid learning healthcare" presents a new infrastructure to support comparative effectiveness research. By leveraging heterogeneous datasets (eg, clinical, administrative, genomic, registry, and research), health information technology, and sophisticated iterative analyses, rapid learning healthcare provides a real-time framework in which clinical studies can evaluate the relative impact of therapeutic approaches on a diverse array of measures. This article describes an effort, at 1 academic medical center, to demonstrate what rapid learning healthcare might look like in operation. The article describes the process of developing and testing the components of this new model of integrated clinical/research function, with the pilot site being an academic oncology clinic and with electronic patient-reported outcomes (ePROs) being the foundational dataset. Steps included: feasibility study of the ePRO system; validation study of ePRO collection across 3 cancers; linking ePRO and other datasets; implementation; stakeholder alignment and buy in, and; demonstration through use cases. Two use cases are presented; participants were metastatic breast cancer (n = 65) and gastrointestinal cancer (n = 113) patients at 2 academic medical centers. (1) Patient-reported symptom data were collected with tablet computers; patients with breast and gastrointestinal cancer indicated high levels of sexual distress, which prompted multidisciplinary response, design of an intervention, and successful application for funding to study the intervention's impact. (2) The system evaluated the longitudinal impact of a psychosocial care program provided to patients with breast cancer. Participants used tablet computers to complete PRO surveys; data indicated significant impact on psychosocial outcomes, notably distress and despair, despite advanced disease. Results return to the clinic, allowing iterative update and evaluation. An ePRO-based rapid learning cancer clinic is feasible, providing real-time research-quality data to support comparative effectiveness research.

Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization.

PubMed

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

fMRI data decomposition techniques have advanced significantly from shallow models such as Independent Component Analysis (ICA) and Sparse Coding and Dictionary Learning (SCDL) to deep learning models such Deep Belief Networks (DBN) and Convolutional Autoencoder (DCAE). However, interpretations of those decomposed networks are still open questions due to the lack of functional brain atlases, no correspondence across decomposed or reconstructed networks across different subjects, and significant individual variabilities. Recent studies showed that deep learning, especially deep convolutional neural networks (CNN), has extraordinary ability of accommodating spatial object patterns, e.g., our recent works using 3D CNN for fMRI-derived network classifications achieved high accuracy with a remarkable tolerance for mistakenly labelled training brain networks. However, the training data preparation is one of the biggest obstacles in these supervised deep learning models for functional brain network map recognitions, since manual labelling requires tedious and time-consuming labours which will sometimes even introduce label mistakes. Especially for mapping functional networks in large scale datasets such as hundreds of thousands of brain networks used in this paper, the manual labelling method will become almost infeasible. In response, in this work, we tackled both the network recognition and training data labelling tasks by proposing a new iteratively optimized deep learning CNN (IO-CNN) framework with an automatic weak label initialization, which enables the functional brain networks recognition task to a fully automatic large-scale classification procedure. Our extensive experiments based on ABIDE-II 1099 brains' fMRI data showed the great promise of our IO-CNN framework. Copyright © 2018 Elsevier B.V. All rights reserved.

Imaging complex objects using learning tomography

NASA Astrophysics Data System (ADS)

Lim, JooWon; Goy, Alexandre; Shoreh, Morteza Hasani; Unser, Michael; Psaltis, Demetri

2018-02-01

Optical diffraction tomography (ODT) can be described using the scattering process through an inhomogeneous media. An inherent nonlinearity exists relating the scattering medium and the scattered field due to multiple scattering. Multiple scattering is often assumed to be negligible in weakly scattering media. This assumption becomes invalid as the sample gets more complex resulting in distorted image reconstructions. This issue becomes very critical when we image a complex sample. Multiple scattering can be simulated using the beam propagation method (BPM) as the forward model of ODT combined with an iterative reconstruction scheme. The iterative error reduction scheme and the multi-layer structure of BPM are similar to neural networks. Therefore we refer to our imaging method as learning tomography (LT). To fairly assess the performance of LT in imaging complex samples, we compared LT with the conventional iterative linear scheme using Mie theory which provides the ground truth. We also demonstrate the capacity of LT to image complex samples using experimental data of a biological cell.

Rank-Optimized Logistic Matrix Regression toward Improved Matrix Data Classification.

PubMed

Zhang, Jianguang; Jiang, Jianmin

2018-02-01

While existing logistic regression suffers from overfitting and often fails in considering structural information, we propose a novel matrix-based logistic regression to overcome the weakness. In the proposed method, 2D matrices are directly used to learn two groups of parameter vectors along each dimension without vectorization, which allows the proposed method to fully exploit the underlying structural information embedded inside the 2D matrices. Further, we add a joint [Formula: see text]-norm on two parameter matrices, which are organized by aligning each group of parameter vectors in columns. This added co-regularization term has two roles-enhancing the effect of regularization and optimizing the rank during the learning process. With our proposed fast iterative solution, we carried out extensive experiments. The results show that in comparison to both the traditional tensor-based methods and the vector-based regression methods, our proposed solution achieves better performance for matrix data classifications.

Keeping the Bootcamp Fun Alive!

EPA Science Inventory

This product is a blog post that outlines a course conducted to build on skills learned in a Software Carpentry Bootcamp co-hosted by AED researcher, Jeff Hollister. The post provides details on the course and some lessons learned that will be implemented in future iterations of...

"There Was a Lot of Learning Going on" Using a Digital Medium to Support Learning in a Professional Course for New HE Lecturers

ERIC Educational Resources Information Center

Chesney, Sarah; Marcangelo, Caroline

2010-01-01

This small scale action research study investigated the experiences of learners over two iterations as they completed a patchwork text assignment within the digital medium of a personal learning system (PLS). The aim was to investigate the extent to which using a PLS can facilitate formative and collaborative feedback to assist student learning. A…

A Faculty Professional Development Model That Improves Student Learning, Encourages Active-Learning Instructional Practices, and Works for Faculty at Multiple Institutions.

PubMed

Pelletreau, Karen N; Knight, Jennifer K; Lemons, Paula P; McCourt, Jill S; Merrill, John E; Nehm, Ross H; Prevost, Luanna B; Urban-Lurain, Mark; Smith, Michelle K

2018-06-01

Helping faculty develop high-quality instruction that positively affects student learning can be complicated by time limitations, a lack of resources, and inexperience using student data to make iterative improvements. We describe a community of 16 faculty from five institutions who overcame these challenges and collaboratively designed, taught, iteratively revised, and published an instructional unit about the potential effect of mutations on DNA replication, transcription, and translation. The unit was taught to more than 2000 students in 18 courses, and student performance improved from preassessment to postassessment in every classroom. This increase occurred even though faculty varied in their instructional practices when they were teaching identical materials. We present information on how this faculty group was organized and facilitated, how members used student data to positively affect learning, and how they increased their use of active-learning instructional practices in the classroom as a result of participation. We also interviewed faculty to learn more about the most useful components of the process. We suggest that this professional development model can be used for geographically separated faculty who are interested in working together on a known conceptual difficulty to improve student learning and explore active-learning instructional practices.

Online Pairwise Learning Algorithms.

PubMed

Ying, Yiming; Zhou, Ding-Xuan

2016-04-01

Pairwise learning usually refers to a learning task that involves a loss function depending on pairs of examples, among which the most notable ones are bipartite ranking, metric learning, and AUC maximization. In this letter we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained setting of a reproducing kernel Hilbert space (RKHS) that we refer to as the Online Pairwise lEaRning Algorithm (OPERA). In contrast to existing works (Kar, Sriperumbudur, Jain, & Karnick, 2013 ; Wang, Khardon, Pechyony, & Jones, 2012 ), which require that the iterates are restricted to a bounded domain or the loss function is strongly convex, OPERA is associated with a non-strongly convex objective function and learns the target function in an unconstrained RKHS. Specifically, we establish a general theorem that guarantees the almost sure convergence for the last iterate of OPERA without any assumptions on the underlying distribution. Explicit convergence rates are derived under the condition of polynomially decaying step sizes. We also establish an interesting property for a family of widely used kernels in the setting of pairwise learning and illustrate the convergence results using such kernels. Our methodology mainly depends on the characterization of RKHSs using its associated integral operators and probability inequalities for random variables with values in a Hilbert space.

Osteoarthritis Severity Determination using Self Organizing Map Based Gabor Kernel

NASA Astrophysics Data System (ADS)

Anifah, L.; Purnomo, M. H.; Mengko, T. L. R.; Purnama, I. K. E.

2018-02-01

The number of osteoarthritis patients in Indonesia is enormous, so early action is needed in order for this disease to be handled. The aim of this paper to determine osteoarthritis severity based on x-ray image template based on gabor kernel. This research is divided into 3 stages, the first step is image processing that is using gabor kernel. The second stage is the learning stage, and the third stage is the testing phase. The image processing stage is by normalizing the image dimension to be template to 50 □ 200 image. Learning stage is done with parameters initial learning rate of 0.5 and the total number of iterations of 1000. The testing stage is performed using the weights generated at the learning stage. The testing phase has been done and the results were obtained. The result shows KL-Grade 0 has an accuracy of 36.21%, accuracy for KL-Grade 2 is 40,52%, while accuracy for KL-Grade 2 and KL-Grade 3 are 15,52%, and 25,86%. The implication of this research is expected that this research as decision support system for medical practitioners in determining KL-Grade on X-ray images of knee osteoarthritis.

"They Have to Adapt to Learn": Surgeons' Perspectives on the Role of Procedural Variation in Surgical Education.

PubMed

Apramian, Tavis; Cristancho, Sayra; Watling, Chris; Ott, Michael; Lingard, Lorelei

2016-01-01

Clinical research increasingly acknowledges the existence of significant procedural variation in surgical practice. This study explored surgeons' perspectives regarding the influence of intersurgeon procedural variation on the teaching and learning of surgical residents. This qualitative study used a grounded theory-based analysis of observational and interview data. Observational data were collected in 3 tertiary care teaching hospitals in Ontario, Canada. Semistructured interviews explored potential procedural variations arising during the observations and prompts from an iteratively refined guide. Ongoing data analysis refined the theoretical framework and informed data collection strategies, as prescribed by the iterative nature of grounded theory research. Our sample included 99 hours of observation across 45 cases with 14 surgeons. Semistructured, audio-recorded interviews (n = 14) occurred immediately following observational periods. Surgeons endorsed the use of intersurgeon procedural variations to teach residents about adapting to the complexity of surgical practice and the norms of surgical culture. Surgeons suggested that residents' efforts to identify thresholds of principle and preference are crucial to professional development. Principles that emerged from the study included the following: (1) knowing what comes next, (2) choosing the right plane, (3) handling tissue appropriately, (4) recognizing the abnormal, and (5) making safe progress. Surgeons suggested that learning to follow these principles while maintaining key aspects of surgical culture, like autonomy and individuality, are important social processes in surgical education. Acknowledging intersurgeon variation has important implications for curriculum development and workplace-based assessment in surgical education. Adapting to intersurgeon procedural variations may foster versatility in surgical residents. However, the existence of procedural variations and their active use in surgeons' teaching raises questions about the lack of attention to this form of complexity in current workplace-based assessment strategies. Failure to recognize the role of such variations may threaten the implementation of competency-based medical education in surgery. Copyright © 2015 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

A Fast, Minimalist Search Tool for Remote Sensing Data

NASA Astrophysics Data System (ADS)

Lynnes, C. S.; Macharrie, P. G.; Elkins, M.; Joshi, T.; Fenichel, L. H.

2005-12-01

We present a tool that emphasizes speed and simplicity in searching remotely sensed Earth Science data. The tool, nicknamed "Mirador" (Spanish for a scenic overlook), provides only four freetext search form fields, for Keywords, Location, Data Start and Data Stop. This contrasts with many current Earth Science search tools that offer highly structured interfaces in order to ensure precise, non-zero results. The disadvantages of the structured approach lie in its complexity and resultant learning curve, as well as the time it takes to formulate and execute the search, thus discouraging iterative discovery. On the other hand, the success of the basic Google search interface shows that many users are willing to forgo high search precision if the search process is fast enough to enable rapid iteration. Therefore, we employ several methods to increase the speed of search formulation and execution. Search formulation is expedited by the minimalist search form, with only one required field. Also, a gazetteer enables the use of geographic terms as shorthand for latitude/longitude coordinates. The search execution is accelerated by initially presenting dataset results (returned from a Google Mini appliance) with an estimated number of "hits" for each dataset based on the user's space-time constraints. The more costly file-level search is executed against a PostGres database only when the user "drills down", and then covering only the fraction of the time period needed to return the next page of results. The simplicity of the search form makes the tool easy to learn and use, and the speed of the searches enables an iterative form of data discovery.

An automated construction of error models for uncertainty quantification and model calibration

NASA Astrophysics Data System (ADS)

Josset, L.; Lunati, I.

2015-12-01

To reduce the computational cost of stochastic predictions, it is common practice to rely on approximate flow solvers (or «proxy»), which provide an inexact, but computationally inexpensive response [1,2]. Error models can be constructed to correct the proxy response: based on a learning set of realizations for which both exact and proxy simulations are performed, a transformation is sought to map proxy into exact responses. Once the error model is constructed a prediction of the exact response is obtained at the cost of a proxy simulation for any new realization. Despite its effectiveness [2,3], the methodology relies on several user-defined parameters, which impact the accuracy of the predictions. To achieve a fully automated construction, we propose a novel methodology based on an iterative scheme: we first initialize the error model with a small training set of realizations; then, at each iteration, we add a new realization both to improve the model and to evaluate its performance. More specifically, at each iteration we use the responses predicted by the updated model to identify the realizations that need to be considered to compute the quantity of interest. Another user-defined parameter is the number of dimensions of the response spaces between which the mapping is sought. To identify the space dimensions that optimally balance mapping accuracy and risk of overfitting, we follow a Leave-One-Out Cross Validation. Also, the definition of a stopping criterion is central to an automated construction. We use a stability measure based on bootstrap techniques to stop the iterative procedure when the iterative model has converged. The methodology is illustrated with two test cases in which an inverse problem has to be solved and assess the performance of the method. We show that an iterative scheme is crucial to increase the applicability of the approach. [1] Josset, L., and I. Lunati, Local and global error models for improving uncertainty quantification, Math.ematical Geosciences, 2013 [2] Josset, L., D. Ginsbourger, and I. Lunati, Functional Error Modeling for uncertainty quantification in hydrogeology, Water Resources Research, 2015 [3] Josset, L., V. Demyanov, A.H. Elsheikhb, and I. Lunati, Accelerating Monte Carlo Markov chains with proxy and error models, Computer & Geosciences, 2015 (In press)

Iterative learning control with applications in energy generation, lasers and health care

PubMed Central

Tutty, O. R.

2016-01-01

Many physical systems make repeated executions of the same finite time duration task. One example is a robot in a factory or warehouse whose task is to collect an object in sequence from a location, transfer it over a finite duration, place it at a specified location or on a moving conveyor and then return for the next one and so on. Iterative learning control was especially developed for systems with this mode of operation and this paper gives an overview of this control design method using relatively recent relevant applications in wind turbines, free-electron lasers and health care, as exemplars to demonstrate its applicability. PMID:27713654

An open-closed-loop iterative learning control approach for nonlinear switched systems with application to freeway traffic control

NASA Astrophysics Data System (ADS)

Sun, Shu-Ting; Li, Xiao-Dong; Zhong, Ren-Xin

2017-10-01

For nonlinear switched discrete-time systems with input constraints, this paper presents an open-closed-loop iterative learning control (ILC) approach, which includes a feedforward ILC part and a feedback control part. Under a given switching rule, the mathematical induction is used to prove the convergence of ILC tracking error in each subsystem. It is demonstrated that the convergence of ILC tracking error is dependent on the feedforward control gain, but the feedback control can speed up the convergence process of ILC by a suitable selection of feedback control gain. A switched freeway traffic system is used to illustrate the effectiveness of the proposed ILC law.

Transforming paper-based assessment forms to a digital format: Exemplified by the Housing Enabler prototype app.

PubMed

Svarre, Tanja; Lunn, Tine Bieber Kirkegaard; Helle, Tina

2017-11-01

The aim of this paper is to provide the reader with an overall impression of the stepwise user-centred design approach including the specific methods used and lessons learned when transforming paper-based assessment forms into a prototype app, taking the Housing Enabler as an example. Four design iterations were performed, building on a domain study, workshops, expert evaluation and controlled and realistic usability tests. The user-centred design process involved purposefully selected participants with different Housing Enabler knowledge and housing adaptation experience. The design iterations resulted in the development of a Housing Enabler prototype app. The prototype app has several features and options that are new compared with the original paper-based Housing Enabler assessment form. These new features include a user friendly overview of the assessment form; easy navigation by swiping back and forth between items; onsite data analysis; and ranking of the accessibility score, photo documentation and a data export facility. Based on the presented stepwise approach, a high-fidelity Housing Enabler prototype app was successfully developed. The development process has emphasized the importance of combining design participants' knowledge and experiences, and has shown that methods should seem relevant to participants to increase their engagement.

Learning to See the Infinite: Measuring Visual Literacy Skills in a 1st-Year Seminar Course

ERIC Educational Resources Information Center

Palmer, Michael S.; Matthews, Tatiana

2015-01-01

Visual literacy was a stated learning objective for the fall 2009 iteration of a first-year seminar course. To help students develop visual literacy skills, they received formal instruction throughout the semester and completed a series of carefully designed learning activities. The effects of these interventions were measured using a one-group…

Integrating a MOOC into the Postgraduate ELT Curriculum: Reflecting on Students' Beliefs with a MOOC Blend

ERIC Educational Resources Information Center

Orsini-Jones, Marina; Gafaro, Barbara Conde; Altamimi, Shooq

2017-01-01

This chapter builds on the outcomes of a blended learning action-research project in its third iteration (academic year 2015-16). The FutureLearn Massive Open Online Course (MOOC) "Understanding Language: Learning and Teaching" was integrated into the curriculum of the Master of Arts (MA) in English Language Teaching (ELT) at Coventry…

Situated Cognition and Learning Environments: Implications for Teachers On- and Offline in the New Digital Media Age

ERIC Educational Resources Information Center

Gomez, Kimberley; Lee, Ung-Sang

2015-01-01

John Seely Brown suggested that learning environments should be spaces in which all work is public, is subject to iterative critique by instructors and peers, and in which social interaction is primary. In such spaces, students and teachers engage in a situated cognition approach to teaching and learning where "cognitive accomplishments rely…

Using a web-based, iterative education model to enhance clinical clerkships.

PubMed

Alexander, Erik K; Bloom, Nurit; Falchuk, Kenneth H; Parker, Michael

2006-10-01

Although most clinical clerkship curricula are designed to provide all students consistent exposure to defined course objectives, it is clear that individual students are diverse in their backgrounds and baseline knowledge. Ideally, the learning process should be individualized towards the strengths and weakness of each student, but, until recently, this has proved prohibitively time-consuming. The authors describe a program to develop and evaluate an iterative, Web-based educational model assessing medical students' knowledge deficits and allowing targeted teaching shortly after their identification. Beginning in 2002, a new educational model was created, validated, and applied in a prospective fashion to medical students during an internal medicine clerkship at Harvard Medical School. Using a Web-based platform, five validated questions were delivered weekly and a specific knowledge deficiency identified. Teaching targeted to the deficiency was provided to an intervention cohort of five to seven students in each clerkship, though not to controls (the remaining 7-10 students). Effectiveness of this model was assessed by performance on the following week's posttest question. Specific deficiencies were readily identified weekly using this model. Throughout the year, however, deficiencies varied unpredictably. Teaching targeted to deficiencies resulted in significantly better performance on follow-up questioning compared to the performance of those who did not receive this intervention. This model was easily applied in an additive fashion to the current curriculum, and student acceptance was high. The authors conclude that a Web-based, iterative assessment model can effectively target specific curricular needs unique to each group; focus teaching in a rapid, formative, and highly efficient manner; and may improve the efficiency of traditional clerkship teaching.

Design of a Braille Learning Application for Visually Impaired Students in Bangladesh.

PubMed

Nahar, Lutfun; Jaafar, Azizah; Ahamed, Eistiak; Kaish, A B M A

2015-01-01

Visually impaired students (VIS) are unable to get visual information, which has made their learning process complicated. This paper discusses the overall situation of VIS in Bangladesh and identifies major challenges that they are facing in getting education. The Braille system is followed to educate blind students in Bangladesh. However, lack of Braille based educational resources and technological solutions have made the learning process lengthy and complicated for VIS. As a developing country, Bangladesh cannot afford for the costly Braille related technological tools for VIS. Therefore, a mobile phone based Braille application, "mBRAILLE", for Android platform is designed to provide an easy Braille learning technology for VIS in Bangladesh. The proposed design is evaluated by experts in assistive technology for students with disabilities, and advanced learners of Braille. The application aims to provide a Bangla and English Braille learning platform for VIS. In this paper, we depict iterative (participatory) design of the application along with a preliminary evaluation with 5 blind subjects, and 1 sighted and 2 blind experts. The results show that the design scored an overall satisfaction level of 4.53 out of 5 by all respondents, indicating that our design is ready for the next step of development.

Compressive sensing of electrocardiogram signals by promoting sparsity on the second-order difference and by using dictionary learning.

PubMed

Pant, Jeevan K; Krishnan, Sridhar

2014-04-01

A new algorithm for the reconstruction of electrocardiogram (ECG) signals and a dictionary learning algorithm for the enhancement of its reconstruction performance for a class of signals are proposed. The signal reconstruction algorithm is based on minimizing the lp pseudo-norm of the second-order difference, called as the lp(2d) pseudo-norm, of the signal. The optimization involved is carried out using a sequential conjugate-gradient algorithm. The dictionary learning algorithm uses an iterative procedure wherein a signal reconstruction and a dictionary update steps are repeated until a convergence criterion is satisfied. The signal reconstruction step is implemented by using the proposed signal reconstruction algorithm and the dictionary update step is implemented by using the linear least-squares method. Extensive simulation results demonstrate that the proposed algorithm yields improved reconstruction performance for temporally correlated ECG signals relative to the state-of-the-art lp(1d)-regularized least-squares and Bayesian learning based algorithms. Also for a known class of signals, the reconstruction performance of the proposed algorithm can be improved by applying it in conjunction with a dictionary obtained using the proposed dictionary learning algorithm.

Quantitative Reasoning in Environmental Science: A Learning Progression

ERIC Educational Resources Information Center

Mayes, Robert Lee; Forrester, Jennifer Harris; Christus, Jennifer Schuttlefield; Peterson, Franziska Isabel; Bonilla, Rachel; Yestness, Nissa

2014-01-01

The ability of middle and high school students to reason quantitatively within the context of environmental science was investigated. A quantitative reasoning (QR) learning progression was created with three progress variables: quantification act, quantitative interpretation, and quantitative modeling. An iterative research design was used as it…

Eliminating Unpredictable Variation through Iterated Learning

ERIC Educational Resources Information Center

Smith, Kenny; Wonnacott, Elizabeth

2010-01-01

Human languages may be shaped not only by the (individual psychological) processes of language acquisition, but also by population-level processes arising from repeated language learning and use. One prevalent feature of natural languages is that they avoid unpredictable variation. The current work explores whether linguistic predictability might…

Perceptron Genetic to Recognize Openning Strategy Ruy Lopez

NASA Astrophysics Data System (ADS)

Azmi, Zulfian; Mawengkang, Herman

2018-01-01

The application of Perceptron method is not effective for coding on hardware based systems because it is not real time learning. With Genetic algorithm approach in calculating and searching the best weight (fitness value) system will do learning only one iteration. And the results of this analysis were tested in the case of the introduction of the opening pattern of chess Ruy Lopez. The Analysis with Perceptron Model with Algorithm Approach Genetics from group Artificial Neural Network for open Ruy Lopez. The data is processed with base open chess, with step eight a position white Pion from end open chess. Using perceptron method have many input and one output process many weight and refraction until output equal goal. Data trained and test with software Matlab and system can recognize the chess opening Ruy Lopez or Not open Ruy Lopez with Real time.

Implementation of Competency-Based Pharmacy Education (CBPE)

PubMed Central

Koster, Andries; Schalekamp, Tom; Meijerman, Irma

2017-01-01

Implementation of competency-based pharmacy education (CBPE) is a time-consuming, complicated process, which requires agreement on the tasks of a pharmacist, commitment, institutional stability, and a goal-directed developmental perspective of all stakeholders involved. In this article the main steps in the development of a fully-developed competency-based pharmacy curriculum (bachelor, master) are described and tips are given for a successful implementation. After the choice for entering into CBPE is made and a competency framework is adopted (step 1), intended learning outcomes are defined (step 2), followed by analyzing the required developmental trajectory (step 3) and the selection of appropriate assessment methods (step 4). Designing the teaching-learning environment involves the selection of learning activities, student experiences, and instructional methods (step 5). Finally, an iterative process of evaluation and adjustment of individual courses, and the curriculum as a whole, is entered (step 6). Successful implementation of CBPE requires a system of effective quality management and continuous professional development as a teacher. In this article suggestions for the organization of CBPE and references to more detailed literature are given, hoping to facilitate the implementation of CBPE. PMID:28970422

Multi-Innovation Gradient Iterative Locally Weighted Learning Identification for A Nonlinear Ship Maneuvering System

NASA Astrophysics Data System (ADS)

Bai, Wei-wei; Ren, Jun-sheng; Li, Tie-shan

2018-06-01

This paper explores a highly accurate identification modeling approach for the ship maneuvering motion with fullscale trial. A multi-innovation gradient iterative (MIGI) approach is proposed to optimize the distance metric of locally weighted learning (LWL), and a novel non-parametric modeling technique is developed for a nonlinear ship maneuvering system. This proposed method's advantages are as follows: first, it can avoid the unmodeled dynamics and multicollinearity inherent to the conventional parametric model; second, it eliminates the over-learning or underlearning and obtains the optimal distance metric; and third, the MIGI is not sensitive to the initial parameter value and requires less time during the training phase. These advantages result in a highly accurate mathematical modeling technique that can be conveniently implemented in applications. To verify the characteristics of this mathematical model, two examples are used as the model platforms to study the ship maneuvering.

Intelligent cooperation: A framework of pedagogic practice in the operating room.

PubMed

Sutkin, Gary; Littleton, Eliza B; Kanter, Steven L

2018-04-01

Surgeons who work with trainees must address their learning needs without compromising patient safety. We used a constructivist grounded theory approach to examine videos of five teaching surgeries. Attending surgeons were interviewed afterward while watching cued videos of their cases. Codes were iteratively refined into major themes, and then constructed into a larger framework. We present a novel framework, Intelligent Cooperation, which accounts for the highly adaptive, iterative features of surgical teaching in the operating room. Specifically, we define Intelligent Cooperation as a sequence of coordinated exchanges between attending and trainee that accomplishes small surgical steps while simultaneously uncovering the trainee's learning needs. Intelligent Cooperation requires the attending to accurately determine learning needs, perform real-time needs assessment, provide critical scaffolding, and work with the learner to accomplish the next step in the surgery. This is achieved through intense, coordinated verbal and physical cooperation. Copyright © 2017 Elsevier Inc. All rights reserved.

Off-Policy Integral Reinforcement Learning Method to Solve Nonlinear Continuous-Time Multiplayer Nonzero-Sum Games.

PubMed

Song, Ruizhuo; Lewis, Frank L; Wei, Qinglai

2017-03-01

This paper establishes an off-policy integral reinforcement learning (IRL) method to solve nonlinear continuous-time (CT) nonzero-sum (NZS) games with unknown system dynamics. The IRL algorithm is presented to obtain the iterative control and off-policy learning is used to allow the dynamics to be completely unknown. Off-policy IRL is designed to do policy evaluation and policy improvement in the policy iteration algorithm. Critic and action networks are used to obtain the performance index and control for each player. The gradient descent algorithm makes the update of critic and action weights simultaneously. The convergence analysis of the weights is given. The asymptotic stability of the closed-loop system and the existence of Nash equilibrium are proved. The simulation study demonstrates the effectiveness of the developed method for nonlinear CT NZS games with unknown system dynamics.

Analog Design for Digital Deployment of a Serious Leadership Game

NASA Technical Reports Server (NTRS)

Maxwell, Nicholas; Lang, Tristan; Herman, Jeffrey L.; Phares, Richard

2012-01-01

This paper presents the design, development, and user testing of a leadership development simulation. The authors share lessons learned from using a design process for a board game to allow for quick and inexpensive revision cycles during the development of a serious leadership development game. The goal of this leadership simulation is to accelerate the development of leadership capacity in high-potential mid-level managers (GS-15 level) in a federal government agency. Simulation design included a mixed-method needs analysis, using both quantitative and qualitative approaches to determine organizational leadership needs. Eight design iterations were conducted, including three user testing phases. Three re-design iterations followed initial development, enabling game testing as part of comprehensive instructional events. Subsequent design, development and testing processes targeted digital application to a computer- and tablet-based environment. Recommendations include pros and cons of development and learner testing of an initial analog simulation prior to full digital simulation development.

Teachers Supporting Teachers in Urban Schools: What Iterative Research Designs Can Teach Us.

PubMed

Shernoff, Elisa S; Maríñez-Lora, Ane M; Frazier, Stacy L; Jakobsons, Lara J; Atkins, Marc S; Bonner, Deborah

2011-12-01

Despite alarming rates and negative consequences associated with urban teacher attrition, mentoring programs often fail to target the strongest predictors of attrition: effectiveness around classroom management and engaging learners; and connectedness to colleagues. Using a mixed-method iterative development framework, we highlight the process of developing and evaluating the feasibility of a multi-component professional development model for urban early career teachers. The model includes linking novices with peer-nominated key opinion leader teachers and an external coach who work together to (1) provide intensive support in evidence-based practices for classroom management and engaging learners, and (2) connect new teachers with their larger network of colleagues. Fidelity measures and focus group data illustrated varying attendance rates throughout the school year and that although seminars and professional learning communities were delivered as intended, adaptations to enhance the relevance, authenticity, level, and type of instrumental support were needed. Implications for science and practice are discussed.

Engineering Design Theory: Applying the Success of the Modern World to Campaign Creation

DTIC Science & Technology

2009-05-21

and school of thought) to the simple methods of design.6 This progression is analogous to Peter Senge’s levels of learning disciplines.7 Senge...iterative learning and adaptive action that develops and employs critical and creative thinking , enabling leaders to apply the necessary logic to...overcome mental rigidity and develop group insight, the Army must learn to utilize group learning and thinking , through a fluid and creative open process

An Iterative Learning Control Approach to Improving Fidelity in Internet-Distributed Hardware-in-the-Loop Simulation

DTIC Science & Technology

2012-06-15

pp. 535-543. [17] Compere , M., Goodell, J., Simon, M., Smith, W., and Brudnak, M., 2006, "Robust Control Techniques Enabling Duty Cycle...Technical Paper, 2006-01-3077. [18] Goodell, J., Compere , M., Simon, M., Smith, W., Wright, R., and Brudnak, M., 2006, "Robust Control Techniques for...Smith, W., Compere , M., Goodell, J., Holtz, D., Mortsfield, T., and Shvartsman, A., 2007, "Soldier/Harware-in-the-Loop Simulation- Based Combat Vehicle

Joint Sparse Recovery With Semisupervised MUSIC

NASA Astrophysics Data System (ADS)

Wen, Zaidao; Hou, Biao; Jiao, Licheng

2017-05-01

Discrete multiple signal classification (MUSIC) with its low computational cost and mild condition requirement becomes a significant noniterative algorithm for joint sparse recovery (JSR). However, it fails in rank defective problem caused by coherent or limited amount of multiple measurement vectors (MMVs). In this letter, we provide a novel sight to address this problem by interpreting JSR as a binary classification problem with respect to atoms. Meanwhile, MUSIC essentially constructs a supervised classifier based on the labeled MMVs so that its performance will heavily depend on the quality and quantity of these training samples. From this viewpoint, we develop a semisupervised MUSIC (SS-MUSIC) in the spirit of machine learning, which declares that the insufficient supervised information in the training samples can be compensated from those unlabeled atoms. Instead of constructing a classifier in a fully supervised manner, we iteratively refine a semisupervised classifier by exploiting the labeled MMVs and some reliable unlabeled atoms simultaneously. Through this way, the required conditions and iterations can be greatly relaxed and reduced. Numerical experimental results demonstrate that SS-MUSIC can achieve much better recovery performances than other MUSIC extended algorithms as well as some typical greedy algorithms for JSR in terms of iterations and recovery probability.

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

Accelerating Learning By Neural Networks

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad; Barhen, Jacob

1992-01-01

Electronic neural networks made to learn faster by use of terminal teacher forcing. Method of supervised learning involves addition of teacher forcing functions to excitations fed as inputs to output neurons. Initially, teacher forcing functions are strong enough to force outputs to desired values; subsequently, these functions decay with time. When learning successfully completed, terminal teacher forcing vanishes, and dynamics or neural network become equivalent to those of conventional neural network. Simulated neural network with terminal teacher forcing learned to produce close approximation of circular trajectory in 400 iterations.

Starting SOLO: A multi-pronged scaffolding approach for developing critical climate literacies

NASA Astrophysics Data System (ADS)

Hartman, K.; Goodkin, N.

2016-12-01

As part of Nanyang Technological University's general education requirement, all science and math students must complete a multidisciplinary environmental sustainability course during the spring term. In addition to foundational earth sciences material, the course of 600 students heavily emphasizes the development of multidisciplinary problem solving and communication strategies. Assessments conducted with previous iterations of the course found students had greater facility recalling facts and summarizing the course materials than they did evaluating climate change arguments, critically reasoning through sustainability issues, or thinking scientifically. To address this shortfall, we introduced the use of a rubric for peer review as one would treat acquiring expertise with any scientific tool—provide learners multiple opportunities for use in different contexts while providing interpretable and actionable feedback. In the most recent version of the course, we introduced a common rubric based on Biggs' (2014) SOLO taxonomy. We used the taxonomy to place the components of student learning along continuums signifying increasing levels of complexity. Our particular rubric highlighted five areas of importance when evaluating any written argument: clarity, argument structure, contextualization, use of evidence, and evidence sourcing. More important than the rubric itself was the iterative cycle of rubric use and expert feedback students received. For eight weeks, students used the rubric to evaluate articles on sustainability and were given feedback about how well their evaluations agreed with an "expert panel." As the semester progressed, the level of agreement between the students and the panel improved. Students used the rubric as a base for evaluating their peers' work at the end of the semester. We coded how constructive the comments students gave each other were and analyzed the weekly reading evaluations. Students whose evaluations aligned with the panel during the second half of the semester also provided more constructive feedback to their peers. The relationship did not hold for the first half of the semester—implying learning occurred. Overall, students from the most recent iteration of the course provided more constructive feedback than the previous semester.

Filtering sensory information with XCSF: improving learning robustness and robot arm control performance.

PubMed

Kneissler, Jan; Stalph, Patrick O; Drugowitsch, Jan; Butz, Martin V

2014-01-01

It has been shown previously that the control of a robot arm can be efficiently learned using the XCSF learning classifier system, which is a nonlinear regression system based on evolutionary computation. So far, however, the predictive knowledge about how actual motor activity changes the state of the arm system has not been exploited. In this paper, we utilize the forward velocity kinematics knowledge of XCSF to alleviate the negative effect of noisy sensors for successful learning and control. We incorporate Kalman filtering for estimating successive arm positions, iteratively combining sensory readings with XCSF-based predictions of hand position changes over time. The filtered arm position is used to improve both trajectory planning and further learning of the forward velocity kinematics. We test the approach on a simulated kinematic robot arm model. The results show that the combination can improve learning and control performance significantly. However, it also shows that variance estimates of XCSF prediction may be underestimated, in which case self-delusional spiraling effects can hinder effective learning. Thus, we introduce a heuristic parameter, which can be motivated by theory, and which limits the influence of XCSF's predictions on its own further learning input. As a result, we obtain drastic improvements in noise tolerance, allowing the system to cope with more than 10 times higher noise levels.

On adaptive learning rate that guarantees convergence in feedforward networks.

PubMed

Behera, Laxmidhar; Kumar, Swagat; Patnaik, Awhan

2006-09-01

This paper investigates new learning algorithms (LF I and LF II) based on Lyapunov function for the training of feedforward neural networks. It is observed that such algorithms have interesting parallel with the popular backpropagation (BP) algorithm where the fixed learning rate is replaced by an adaptive learning rate computed using convergence theorem based on Lyapunov stability theory. LF II, a modified version of LF I, has been introduced with an aim to avoid local minima. This modification also helps in improving the convergence speed in some cases. Conditions for achieving global minimum for these kind of algorithms have been studied in detail. The performances of the proposed algorithms are compared with BP algorithm and extended Kalman filtering (EKF) on three bench-mark function approximation problems: XOR, 3-bit parity, and 8-3 encoder. The comparisons are made in terms of number of learning iterations and computational time required for convergence. It is found that the proposed algorithms (LF I and II) are much faster in convergence than other two algorithms to attain same accuracy. Finally, the comparison is made on a complex two-dimensional (2-D) Gabor function and effect of adaptive learning rate for faster convergence is verified. In a nutshell, the investigations made in this paper help us better understand the learning procedure of feedforward neural networks in terms of adaptive learning rate, convergence speed, and local minima.

A Strategic Planning Process Model for Distance Education

ERIC Educational Resources Information Center

Pisel, Kenneth P.

2008-01-01

As more institutions seek to implement or expand distance learning programs, it becomes critical to integrate distance learning programs into broader strategic visions and plans. Using the informed opinion from a panel of peer-nominated experts via iterative Delphi questionnaires, a 10-phased strategic planning process model for distance education…

Origami: An Active Learning Exercise for Scrum Project Management

ERIC Educational Resources Information Center

Sibona, Christopher; Pourreza, Saba; Hill, Stephen

2018-01-01

Scrum is a popular project management model for iterative delivery of software that subscribes to Agile principles. This paper describes an origami active learning exercise to teach the principles of Scrum in management information systems courses. The exercise shows students how Agile methods respond to changes in requirements during project…

Getting Results: Small Changes, Big Cohorts and Technology

ERIC Educational Resources Information Center

Kenney, Jacqueline L.

2012-01-01

This paper presents an example of constructive alignment in practice. Integrated technology supports were deployed to increase the consistency between learning objectives, activities and assessment and to foster student-centred, higher-order learning processes in the unit. Modifications took place over nine iterations of a second-year Marketing…

LATUX: An Iterative Workflow for Designing, Validating, and Deploying Learning Analytics Visualizations

ERIC Educational Resources Information Center

Martinez-Maldonado, Roberto; Pardo, Abelardo; Mirriahi, Negin; Yacef, Kalina; Kay, Judy; Clayphan, Andrew

2015-01-01

Designing, validating, and deploying learning analytics tools for instructors or students is a challenge that requires techniques and methods from different disciplines, such as software engineering, human-computer interaction, computer graphics, educational design, and psychology. Whilst each has established its own design methodologies, we now…

Comparison of sampling strategies for object-based classification of urban vegetation from Very High Resolution satellite images

NASA Astrophysics Data System (ADS)

Rougier, Simon; Puissant, Anne; Stumpf, André; Lachiche, Nicolas

2016-09-01

Vegetation monitoring is becoming a major issue in the urban environment due to the services they procure and necessitates an accurate and up to date mapping. Very High Resolution satellite images enable a detailed mapping of the urban tree and herbaceous vegetation. Several supervised classifications with statistical learning techniques have provided good results for the detection of urban vegetation but necessitate a large amount of training data. In this context, this study proposes to investigate the performances of different sampling strategies in order to reduce the number of examples needed. Two windows based active learning algorithms from state-of-art are compared to a classical stratified random sampling and a third combining active learning and stratified strategies is proposed. The efficiency of these strategies is evaluated on two medium size French cities, Strasbourg and Rennes, associated to different datasets. Results demonstrate that classical stratified random sampling can in some cases be just as effective as active learning methods and that it should be used more frequently to evaluate new active learning methods. Moreover, the active learning strategies proposed in this work enables to reduce the computational runtime by selecting multiple windows at each iteration without increasing the number of windows needed.

Smoothing of cost function leads to faster convergence of neural network learning

NASA Astrophysics Data System (ADS)

Xu, Li-Qun; Hall, Trevor J.

1994-03-01

One of the major problems in supervised learning of neural networks is the inevitable local minima inherent in the cost function f(W,D). This often makes classic gradient-descent-based learning algorithms that calculate the weight updates for each iteration according to (Delta) W(t) equals -(eta) (DOT)$DELwf(W,D) powerless. In this paper we describe a new strategy to solve this problem, which, adaptively, changes the learning rate and manipulates the gradient estimator simultaneously. The idea is to implicitly convert the local- minima-laden cost function f((DOT)) into a sequence of its smoothed versions {f(beta t)}Ttequals1, which, subject to the parameter (beta) t, bears less details at time t equals 1 and gradually more later on, the learning is actually performed on this sequence of functionals. The corresponding smoothed global minima obtained in this way, {Wt}Ttequals1, thus progressively approximate W-the desired global minimum. Experimental results on a nonconvex function minimization problem and a typical neural network learning task are given, analyses and discussions of some important issues are provided.

Developing a holistic policy and intervention framework for global mental health.

PubMed

Khenti, Akwatu; Fréel, Stéfanie; Trainor, Ruth; Mohamoud, Sirad; Diaz, Pablo; Suh, Erica; Bobbili, Sireesha J; Sapag, Jaime C

2016-02-01

There are significant gaps in the accessibility and quality of mental health services around the globe. A wide range of institutions are addressing the challenges, but there is limited reflection and evaluation on the various approaches, how they compare with each other, and conclusions regarding the most effective approach for particular settings. This article presents a framework for global mental health capacity building that could potentially serve as a promising or best practice in the field. The framework is the outcome of a decade of collaborative global health work at the Centre for Addiction and Mental Health (CAMH) (Ontario, Canada). The framework is grounded in scientific evidence, relevant learning and behavioural theories and the underlying principles of health equity and human rights. Grounded in CAMH's research, programme evaluation and practical experience in developing and implementing mental health capacity building interventions, this article presents the iterative learning process and impetus that formed the basis of the framework. A developmental evaluation (Patton M.2010. Developmental Evaluation: Applying Complexity Concepts to Enhance Innovation and Use. New York: Guilford Press.) approach was used to build the framework, as global mental health collaboration occurs in complex or uncertain environments and evolving learning systems. A multilevel framework consists of five central components: (1) holistic health, (2) cultural and socioeconomic relevance, (3) partnerships, (4) collaborative action-based education and learning and (5) sustainability. The framework's practical application is illustrated through the presentation of three international case studies and four policy implications. Lessons learned, limitations and future opportunities are also discussed. The holistic policy and intervention framework for global mental health reflects an iterative learning process that can be applied and scaled up across different settings through appropriate modifications. © The Author 2015. Published by Oxford University Press in association with The London School of Hygiene and Tropical Medicine.

Performance analysis of model based iterative reconstruction with dictionary learning in transportation security CT

NASA Astrophysics Data System (ADS)

Haneda, Eri; Luo, Jiajia; Can, Ali; Ramani, Sathish; Fu, Lin; De Man, Bruno

2016-05-01

In this study, we implement and compare model based iterative reconstruction (MBIR) with dictionary learning (DL) over MBIR with pairwise pixel-difference regularization, in the context of transportation security. DL is a technique of sparse signal representation using an over complete dictionary which has provided promising results in image processing applications including denoising,1 as well as medical CT reconstruction.2 It has been previously reported that DL produces promising results in terms of noise reduction and preservation of structural details, especially for low dose and few-view CT acquisitions.2 A distinguishing feature of transportation security CT is that scanned baggage may contain items with a wide range of material densities. While medical CT typically scans soft tissues, blood with and without contrast agents, and bones, luggage typically contains more high density materials (i.e. metals and glass), which can produce severe distortions such as metal streaking artifacts. Important factors of security CT are the emphasis on image quality such as resolution, contrast, noise level, and CT number accuracy for target detection. While MBIR has shown exemplary performance in the trade-off of noise reduction and resolution preservation, we demonstrate that DL may further improve this trade-off. In this study, we used the KSVD-based DL3 combined with the MBIR cost-minimization framework and compared results to Filtered Back Projection (FBP) and MBIR with pairwise pixel-difference regularization. We performed a parameter analysis to show the image quality impact of each parameter. We also investigated few-view CT acquisitions where DL can show an additional advantage relative to pairwise pixel difference regularization.

Indirect iterative learning control for a discrete visual servo without a camera-robot model.

PubMed

Jiang, Ping; Bamforth, Leon C A; Feng, Zuren; Baruch, John E F; Chen, YangQuan

2007-08-01

This paper presents a discrete learning controller for vision-guided robot trajectory imitation with no prior knowledge of the camera-robot model. A teacher demonstrates a desired movement in front of a camera, and then, the robot is tasked to replay it by repetitive tracking. The imitation procedure is considered as a discrete tracking control problem in the image plane, with an unknown and time-varying image Jacobian matrix. Instead of updating the control signal directly, as is usually done in iterative learning control (ILC), a series of neural networks are used to approximate the unknown Jacobian matrix around every sample point in the demonstrated trajectory, and the time-varying weights of local neural networks are identified through repetitive tracking, i.e., indirect ILC. This makes repetitive segmented training possible, and a segmented training strategy is presented to retain the training trajectories solely within the effective region for neural network approximation. However, a singularity problem may occur if an unmodified neural-network-based Jacobian estimation is used to calculate the robot end-effector velocity. A new weight modification algorithm is proposed which ensures invertibility of the estimation, thus circumventing the problem. Stability is further discussed, and the relationship between the approximation capability of the neural network and the tracking accuracy is obtained. Simulations and experiments are carried out to illustrate the validity of the proposed controller for trajectory imitation of robot manipulators with unknown time-varying Jacobian matrices.

Using Functional Electrical Stimulation Mediated by Iterative Learning Control and Robotics to Improve Arm Movement for People With Multiple Sclerosis.

PubMed

Sampson, Patrica; Freeman, Chris; Coote, Susan; Demain, Sara; Feys, Peter; Meadmore, Katie; Hughes, Ann-Marie

2016-02-01

Few interventions address multiple sclerosis (MS) arm dysfunction but robotics and functional electrical stimulation (FES) appear promising. This paper investigates the feasibility of combining FES with passive robotic support during virtual reality (VR) training tasks to improve upper limb function in people with multiple sclerosis (pwMS). The system assists patients in following a specified trajectory path, employing an advanced model-based paradigm termed iterative learning control (ILC) to adjust the FES to improve accuracy and maximise voluntary effort. Reaching tasks were repeated six times with ILC learning the optimum control action from previous attempts. A convenience sample of five pwMS was recruited from local MS societies, and the intervention comprised 18 one-hour training sessions over 10 weeks. The accuracy of tracking performance without FES and the amount of FES delivered during training were analyzed using regression analysis. Clinical functioning of the arm was documented before and after treatment with standard tests. Statistically significant results following training included: improved accuracy of tracking performance both when assisted and unassisted by FES; reduction in maximum amount of FES needed to assist tracking; and less impairment in the proximal arm that was trained. The system was well tolerated by all participants with no increase in muscle fatigue reported. This study confirms the feasibility of FES combined with passive robot assistance as a potentially effective intervention to improve arm movement and control in pwMS and provides the basis for a follow-up study.

Fast calculation of the `ILC norm' in iterative learning control

NASA Astrophysics Data System (ADS)

Rice, Justin K.; van Wingerden, Jan-Willem

2013-06-01

In this paper, we discuss and demonstrate a method for the exploitation of matrix structure in computations for iterative learning control (ILC). In Barton, Bristow, and Alleyne [International Journal of Control, 83(2), 1-8 (2010)], a special insight into the structure of the lifted convolution matrices involved in ILC is used along with a modified Lanczos method to achieve very fast computational bounds on the learning convergence, by calculating the 'ILC norm' in ? computational complexity. In this paper, we show how their method is equivalent to a special instance of the sequentially semi-separable (SSS) matrix arithmetic, and thus can be extended to many other computations in ILC, and specialised in some cases to even faster methods. Our SSS-based methodology will be demonstrated on two examples: a linear time-varying example resulting in the same ? complexity as in Barton et al., and a linear time-invariant example where our approach reduces the computational complexity to ?, thus decreasing the computation time, for an example, from the literature by a factor of almost 100. This improvement is achieved by transforming the norm computation via a linear matrix inequality into a check of positive definiteness - which allows us to further exploit the almost-Toeplitz properties of the matrix, and additionally provides explicit upper and lower bounds on the norm of the matrix, instead of the indirect Ritz estimate. These methods are now implemented in a MATLAB toolbox, freely available on the Internet.

Semi-Supervised Tensor-Based Graph Embedding Learning and Its Application to Visual Discriminant Tracking.

PubMed

Hu, Weiming; Gao, Jin; Xing, Junliang; Zhang, Chao; Maybank, Stephen

2017-01-01

An appearance model adaptable to changes in object appearance is critical in visual object tracking. In this paper, we treat an image patch as a two-order tensor which preserves the original image structure. We design two graphs for characterizing the intrinsic local geometrical structure of the tensor samples of the object and the background. Graph embedding is used to reduce the dimensions of the tensors while preserving the structure of the graphs. Then, a discriminant embedding space is constructed. We prove two propositions for finding the transformation matrices which are used to map the original tensor samples to the tensor-based graph embedding space. In order to encode more discriminant information in the embedding space, we propose a transfer-learning- based semi-supervised strategy to iteratively adjust the embedding space into which discriminative information obtained from earlier times is transferred. We apply the proposed semi-supervised tensor-based graph embedding learning algorithm to visual tracking. The new tracking algorithm captures an object's appearance characteristics during tracking and uses a particle filter to estimate the optimal object state. Experimental results on the CVPR 2013 benchmark dataset demonstrate the effectiveness of the proposed tracking algorithm.

Machine learning-based kinetic modeling: a robust and reproducible solution for quantitative analysis of dynamic PET data

NASA Astrophysics Data System (ADS)

Pan, Leyun; Cheng, Caixia; Haberkorn, Uwe; Dimitrakopoulou-Strauss, Antonia

2017-05-01

A variety of compartment models are used for the quantitative analysis of dynamic positron emission tomography (PET) data. Traditionally, these models use an iterative fitting (IF) method to find the least squares between the measured and calculated values over time, which may encounter some problems such as the overfitting of model parameters and a lack of reproducibility, especially when handling noisy data or error data. In this paper, a machine learning (ML) based kinetic modeling method is introduced, which can fully utilize a historical reference database to build a moderate kinetic model directly dealing with noisy data but not trying to smooth the noise in the image. Also, due to the database, the presented method is capable of automatically adjusting the models using a multi-thread grid parameter searching technique. Furthermore, a candidate competition concept is proposed to combine the advantages of the ML and IF modeling methods, which could find a balance between fitting to historical data and to the unseen target curve. The machine learning based method provides a robust and reproducible solution that is user-independent for VOI-based and pixel-wise quantitative analysis of dynamic PET data.

Machine learning-based kinetic modeling: a robust and reproducible solution for quantitative analysis of dynamic PET data.

PubMed

Pan, Leyun; Cheng, Caixia; Haberkorn, Uwe; Dimitrakopoulou-Strauss, Antonia

2017-05-07

A variety of compartment models are used for the quantitative analysis of dynamic positron emission tomography (PET) data. Traditionally, these models use an iterative fitting (IF) method to find the least squares between the measured and calculated values over time, which may encounter some problems such as the overfitting of model parameters and a lack of reproducibility, especially when handling noisy data or error data. In this paper, a machine learning (ML) based kinetic modeling method is introduced, which can fully utilize a historical reference database to build a moderate kinetic model directly dealing with noisy data but not trying to smooth the noise in the image. Also, due to the database, the presented method is capable of automatically adjusting the models using a multi-thread grid parameter searching technique. Furthermore, a candidate competition concept is proposed to combine the advantages of the ML and IF modeling methods, which could find a balance between fitting to historical data and to the unseen target curve. The machine learning based method provides a robust and reproducible solution that is user-independent for VOI-based and pixel-wise quantitative analysis of dynamic PET data.

A Randomized Crossover Design to Assess Learning Impact and Student Preference for Active and Passive Online Learning Modules.

PubMed

Prunuske, Amy J; Henn, Lisa; Brearley, Ann M; Prunuske, Jacob

Medical education increasingly involves online learning experiences to facilitate the standardization of curriculum across time and space. In class, delivering material by lecture is less effective at promoting student learning than engaging students in active learning experience and it is unclear whether this difference also exists online. We sought to evaluate medical student preferences for online lecture or online active learning formats and the impact of format on short- and long-term learning gains. Students participated online in either lecture or constructivist learning activities in a first year neurologic sciences course at a US medical school. In 2012, students selected which format to complete and in 2013, students were randomly assigned in a crossover fashion to the modules. In the first iteration, students strongly preferred the lecture modules and valued being told "what they need to know" rather than figuring it out independently. In the crossover iteration, learning gains and knowledge retention were found to be equivalent regardless of format, and students uniformly demonstrated a strong preference for the lecture format, which also on average took less time to complete. When given a choice for online modules, students prefer passive lecture rather than completing constructivist activities, and in the time-limited environment of medical school, this choice results in similar performance on multiple-choice examinations with less time invested. Instructors need to look more carefully at whether assessments and learning strategies are helping students to obtain self-directed learning skills and to consider strategies to help students learn to value active learning in an online environment.

Efficient full-chip SRAF placement using machine learning for best accuracy and improved consistency

NASA Astrophysics Data System (ADS)

Wang, Shibing; Baron, Stanislas; Kachwala, Nishrin; Kallingal, Chidam; Sun, Dezheng; Shu, Vincent; Fong, Weichun; Li, Zero; Elsaid, Ahmad; Gao, Jin-Wei; Su, Jing; Ser, Jung-Hoon; Zhang, Quan; Chen, Been-Der; Howell, Rafael; Hsu, Stephen; Luo, Larry; Zou, Yi; Zhang, Gary; Lu, Yen-Wen; Cao, Yu

2018-03-01

Various computational approaches from rule-based to model-based methods exist to place Sub-Resolution Assist Features (SRAF) in order to increase process window for lithography. Each method has its advantages and drawbacks, and typically requires the user to make a trade-off between time of development, accuracy, consistency and cycle time. Rule-based methods, used since the 90 nm node, require long development time and struggle to achieve good process window performance for complex patterns. Heuristically driven, their development is often iterative and involves significant engineering time from multiple disciplines (Litho, OPC and DTCO). Model-based approaches have been widely adopted since the 20 nm node. While the development of model-driven placement methods is relatively straightforward, they often become computationally expensive when high accuracy is required. Furthermore these methods tend to yield less consistent SRAFs due to the nature of the approach: they rely on a model which is sensitive to the pattern placement on the native simulation grid, and can be impacted by such related grid dependency effects. Those undesirable effects tend to become stronger when more iterations or complexity are needed in the algorithm to achieve required accuracy. ASML Brion has developed a new SRAF placement technique on the Tachyon platform that is assisted by machine learning and significantly improves the accuracy of full chip SRAF placement while keeping consistency and runtime under control. A Deep Convolutional Neural Network (DCNN) is trained using the target wafer layout and corresponding Continuous Transmission Mask (CTM) images. These CTM images have been fully optimized using the Tachyon inverse mask optimization engine. The neural network generated SRAF guidance map is then used to place SRAF on full-chip. This is different from our existing full-chip MB-SRAF approach which utilizes a SRAF guidance map (SGM) of mask sensitivity to improve the contrast of optical image at the target pattern edges. In this paper, we demonstrate that machine learning assisted SRAF placement can achieve a superior process window compared to the SGM model-based SRAF method, while keeping the full-chip runtime affordable, and maintain consistency of SRAF placement . We describe the current status of this machine learning assisted SRAF technique and demonstrate its application to full chip mask synthesis and discuss how it can extend the computational lithography roadmap.

Data-driven model reference control of MIMO vertical tank systems with model-free VRFT and Q-Learning.

PubMed

Radac, Mircea-Bogdan; Precup, Radu-Emil; Roman, Raul-Cristian

2018-02-01

This paper proposes a combined Virtual Reference Feedback Tuning-Q-learning model-free control approach, which tunes nonlinear static state feedback controllers to achieve output model reference tracking in an optimal control framework. The novel iterative Batch Fitted Q-learning strategy uses two neural networks to represent the value function (critic) and the controller (actor), and it is referred to as a mixed Virtual Reference Feedback Tuning-Batch Fitted Q-learning approach. Learning convergence of the Q-learning schemes generally depends, among other settings, on the efficient exploration of the state-action space. Handcrafting test signals for efficient exploration is difficult even for input-output stable unknown processes. Virtual Reference Feedback Tuning can ensure an initial stabilizing controller to be learned from few input-output data and it can be next used to collect substantially more input-state data in a controlled mode, in a constrained environment, by compensating the process dynamics. This data is used to learn significantly superior nonlinear state feedback neural networks controllers for model reference tracking, using the proposed Batch Fitted Q-learning iterative tuning strategy, motivating the original combination of the two techniques. The mixed Virtual Reference Feedback Tuning-Batch Fitted Q-learning approach is experimentally validated for water level control of a multi input-multi output nonlinear constrained coupled two-tank system. Discussions on the observed control behavior are offered. Copyright © 2018 ISA. Published by Elsevier Ltd. All rights reserved.

Diverse power iteration embeddings: Theory and practice

DOE PAGES

Huang, Hao; Yoo, Shinjae; Yu, Dantong; ...

2015-11-09

Manifold learning, especially spectral embedding, is known as one of the most effective learning approaches on high dimensional data, but for real-world applications it raises a serious computational burden in constructing spectral embeddings for large datasets. To overcome this computational complexity, we propose a novel efficient embedding construction, Diverse Power Iteration Embedding (DPIE). DPIE shows almost the same effectiveness of spectral embeddings and yet is three order of magnitude faster than spectral embeddings computed from eigen-decomposition. Our DPIE is unique in that (1) it finds linearly independent embeddings and thus shows diverse aspects of dataset; (2) the proposed regularized DPIEmore » is effective if we need many embeddings; (3) we show how to efficiently orthogonalize DPIE if one needs; and (4) Diverse Power Iteration Value (DPIV) provides the importance of each DPIE like an eigen value. As a result, such various aspects of DPIE and DPIV ensure that our algorithm is easy to apply to various applications, and we also show the effectiveness and efficiency of DPIE on clustering, anomaly detection, and feature selection as our case studies.« less

Networked iterative learning control design for discrete-time systems with stochastic communication delay in input and output channels

NASA Astrophysics Data System (ADS)

Liu, Jian; Ruan, Xiaoe

2017-07-01

This paper develops two kinds of derivative-type networked iterative learning control (NILC) schemes for repetitive discrete-time systems with stochastic communication delay occurred in input and output channels and modelled as 0-1 Bernoulli-type stochastic variable. In the two schemes, the delayed signal of the current control input is replaced by the synchronous input utilised at the previous iteration, whilst for the delayed signal of the system output the one scheme substitutes it by the synchronous predetermined desired trajectory and the other takes it by the synchronous output at the previous operation, respectively. In virtue of the mathematical expectation, the tracking performance is analysed which exhibits that for both the linear time-invariant and nonlinear affine systems the two kinds of NILCs are convergent under the assumptions that the probabilities of communication delays are adequately constrained and the product of the input-output coupling matrices is full-column rank. Last, two illustrative examples are presented to demonstrate the effectiveness and validity of the proposed NILC schemes.

Passive and active adaptive management: Approaches and an example

USGS Publications Warehouse

Williams, B.K.

2011-01-01

Adaptive management is a framework for resource conservation that promotes iterative learning-based decision making. Yet there remains considerable confusion about what adaptive management entails, and how to actually make resource decisions adaptively. A key but somewhat ambiguous distinction in adaptive management is between active and passive forms of adaptive decision making. The objective of this paper is to illustrate some approaches to active and passive adaptive management with a simple example involving the drawdown of water impoundments on a wildlife refuge. The approaches are illustrated for the drawdown example, and contrasted in terms of objectives, costs, and potential learning rates. Some key challenges to the actual practice of AM are discussed, and tradeoffs between implementation costs and long-term benefits are highlighted. ?? 2010 Elsevier Ltd.

Explaining Cooperation in Groups: Testing Models of Reciprocity and Learning

ERIC Educational Resources Information Center

Biele, Guido; Rieskamp, Jorg; Czienskowski, Uwe

2008-01-01

What are the cognitive processes underlying cooperation in groups? This question is addressed by examining how well a reciprocity model, two learning models, and social value orientation can predict cooperation in two iterated n-person social dilemmas with continuous contributions. In the first of these dilemmas, the public goods game,…

Who Are with Us: MOOC Learners on a FutureLearn Course

ERIC Educational Resources Information Center

Liyanagunawardena, Tharindu Rekha; Lundqvist, Karsten Øster; Williams, Shirley Ann

2015-01-01

Massive open online courses (MOOCs) attract learners with a variety of backgrounds. Engaging them using game development was trialled in a beginner's programming course, "Begin programming: build your first mobile game," on FutureLearn platform. The course has completed two iterations: first in autumn 2013 and second in spring 2014 with…

Rules, Roles and Tools: Activity Theory and the Comparative Study of E-Learning

ERIC Educational Resources Information Center

Benson, Angela; Lawler, Cormac; Whitworth, Andrew

2008-01-01

Activity theory (AT) is a powerful tool for investigating "artefacts in use", ie, the ways technologies interrelate with their local context. AT reveals the interfaces between e-learning at the macro- (strategy, policy, "campus-wide" solutions) and the micro-organisational levels (everyday working practice, iterative change, individual…

Multimodal and Adaptive Learning Management: An Iterative Design

ERIC Educational Resources Information Center

Squires, David R.; Orey, Michael A.

2015-01-01

The purpose of this study is to measure the outcome of a comprehensive learning management system implemented at a Spinal Cord Injury (SCI) hospital in the Southeast United States. Specifically this SCI hospital has been experiencing an evident volume of patients returning seeking more information about the nature of their injuries. Recognizing…

Is This a Meaningful Learning Experience? Interactive Critical Self-Inquiry as Investigation

ERIC Educational Resources Information Center

Allard, Andrea C.; Gallant, Andrea

2012-01-01

What conditions enable educators to engage in meaningful learning experiences with peers and beginning practitioners? This article documents a self-study on our actions-in-practice in a peer mentoring project. The investigation involved an iterative process to improve our knowledge as teacher educators, reflective practitioners, and researchers.…

Developing a Multi-Year Learning Progression for Carbon Cycling in Socio-Ecological Systems

ERIC Educational Resources Information Center

Mohan, Lindsey; Chen, Jing; Anderson, Charles W.

2009-01-01

This study reports on our steps toward achieving a conceptually coherent and empirically validated learning progression for carbon cycling in socio-ecological systems. It describes an iterative process of designing and analyzing assessment and interview data from students in upper elementary through high school. The product of our development…

Learner-Controlled Scaffolding Linked to Open-Ended Problems in a Digital Learning Environment

ERIC Educational Resources Information Center

Edson, Alden Jack

2017-01-01

This exploratory study reports on how students activated learner-controlled scaffolding and navigated through sequences of connected problems in a digital learning environment. A design experiment was completed to (re)design, iteratively develop, test, and evaluate a digital version of an instructional unit focusing on binomial distributions and…

User Acceptance of a Haptic Interface for Learning Anatomy

ERIC Educational Resources Information Center

Yeom, Soonja; Choi-Lundberg, Derek; Fluck, Andrew; Sale, Arthur

2013-01-01

Visualizing the structure and relationships in three dimensions (3D) of organs is a challenge for students of anatomy. To provide an alternative way of learning anatomy engaging multiple senses, we are developing a force-feedback (haptic) interface for manipulation of 3D virtual organs, using design research methodology, with iterations of system…

Online selective kernel-based temporal difference learning.

PubMed

Chen, Xingguo; Gao, Yang; Wang, Ruili

2013-12-01

In this paper, an online selective kernel-based temporal difference (OSKTD) learning algorithm is proposed to deal with large scale and/or continuous reinforcement learning problems. OSKTD includes two online procedures: online sparsification and parameter updating for the selective kernel-based value function. A new sparsification method (i.e., a kernel distance-based online sparsification method) is proposed based on selective ensemble learning, which is computationally less complex compared with other sparsification methods. With the proposed sparsification method, the sparsified dictionary of samples is constructed online by checking if a sample needs to be added to the sparsified dictionary. In addition, based on local validity, a selective kernel-based value function is proposed to select the best samples from the sample dictionary for the selective kernel-based value function approximator. The parameters of the selective kernel-based value function are iteratively updated by using the temporal difference (TD) learning algorithm combined with the gradient descent technique. The complexity of the online sparsification procedure in the OSKTD algorithm is O(n). In addition, two typical experiments (Maze and Mountain Car) are used to compare with both traditional and up-to-date O(n) algorithms (GTD, GTD2, and TDC using the kernel-based value function), and the results demonstrate the effectiveness of our proposed algorithm. In the Maze problem, OSKTD converges to an optimal policy and converges faster than both traditional and up-to-date algorithms. In the Mountain Car problem, OSKTD converges, requires less computation time compared with other sparsification methods, gets a better local optima than the traditional algorithms, and converges much faster than the up-to-date algorithms. In addition, OSKTD can reach a competitive ultimate optima compared with the up-to-date algorithms.

A machine learning heuristic to identify biologically relevant and minimal biomarker panels from omics data

PubMed Central

2015-01-01

Background Investigations into novel biomarkers using omics techniques generate large amounts of data. Due to their size and numbers of attributes, these data are suitable for analysis with machine learning methods. A key component of typical machine learning pipelines for omics data is feature selection, which is used to reduce the raw high-dimensional data into a tractable number of features. Feature selection needs to balance the objective of using as few features as possible, while maintaining high predictive power. This balance is crucial when the goal of data analysis is the identification of highly accurate but small panels of biomarkers with potential clinical utility. In this paper we propose a heuristic for the selection of very small feature subsets, via an iterative feature elimination process that is guided by rule-based machine learning, called RGIFE (Rule-guided Iterative Feature Elimination). We use this heuristic to identify putative biomarkers of osteoarthritis (OA), articular cartilage degradation and synovial inflammation, using both proteomic and transcriptomic datasets. Results and discussion Our RGIFE heuristic increased the classification accuracies achieved for all datasets when no feature selection is used, and performed well in a comparison with other feature selection methods. Using this method the datasets were reduced to a smaller number of genes or proteins, including those known to be relevant to OA, cartilage degradation and joint inflammation. The results have shown the RGIFE feature reduction method to be suitable for analysing both proteomic and transcriptomics data. Methods that generate large ‘omics’ datasets are increasingly being used in the area of rheumatology. Conclusions Feature reduction methods are advantageous for the analysis of omics data in the field of rheumatology, as the applications of such techniques are likely to result in improvements in diagnosis, treatment and drug discovery. PMID:25923811

Active learning strategies for the deduplication of electronic patient data using classification trees.

PubMed

Sariyar, M; Borg, A; Pommerening, K

2012-10-01

Supervised record linkage methods often require a clerical review to gain informative training data. Active learning means to actively prompt the user to label data with special characteristics in order to minimise the review costs. We conducted an empirical evaluation to investigate whether a simple active learning strategy using binary comparison patterns is sufficient or if string metrics together with a more sophisticated algorithm are necessary to achieve high accuracies with a small training set. Based on medical registry data with different numbers of attributes, we used active learning to acquire training sets for classification trees, which were then used to classify the remaining data. Active learning for binary patterns means that every distinct comparison pattern represents a stratum from which one item is sampled. Active learning for patterns consisting of the Levenshtein string metric values uses an iterative process where the most informative and representative examples are added to the training set. In this context, we extended the active learning strategy by Sarawagi and Bhamidipaty (2002). On the original data set, active learning based on binary comparison patterns leads to the best results. When dropping four or six attributes, using string metrics leads to better results. In both cases, not more than 200 manually reviewed training examples are necessary. In record linkage applications where only forename, name and birthday are available as attributes, we suggest the sophisticated active learning strategy based on string metrics in order to achieve highly accurate results. We recommend the simple strategy if more attributes are available, as in our study. In both cases, active learning significantly reduces the amount of manual involvement in training data selection compared to usual record linkage settings. Copyright © 2012 Elsevier Inc. All rights reserved.

3D Reconstruction of human bones based on dictionary learning.

PubMed

Zhang, Binkai; Wang, Xiang; Liang, Xiao; Zheng, Jinjin

2017-11-01

An effective method for reconstructing a 3D model of human bones from computed tomography (CT) image data based on dictionary learning is proposed. In this study, the dictionary comprises the vertices of triangular meshes, and the sparse coefficient matrix indicates the connectivity information. For better reconstruction performance, we proposed a balance coefficient between the approximation and regularisation terms and a method for optimisation. Moreover, we applied a local updating strategy and a mesh-optimisation method to update the dictionary and the sparse matrix, respectively. The two updating steps are iterated alternately until the objective function converges. Thus, a reconstructed mesh could be obtained with high accuracy and regularisation. The experimental results show that the proposed method has the potential to obtain high precision and high-quality triangular meshes for rapid prototyping, medical diagnosis, and tissue engineering. Copyright © 2017 IPEM. Published by Elsevier Ltd. All rights reserved.

Person Re-Identification via Distance Metric Learning With Latent Variables.

PubMed

Sun, Chong; Wang, Dong; Lu, Huchuan

2017-01-01

In this paper, we propose an effective person re-identification method with latent variables, which represents a pedestrian as the mixture of a holistic model and a number of flexible models. Three types of latent variables are introduced to model uncertain factors in the re-identification problem, including vertical misalignments, horizontal misalignments and leg posture variations. The distance between two pedestrians can be determined by minimizing a given distance function with respect to latent variables, and then be used to conduct the re-identification task. In addition, we develop a latent metric learning method for learning the effective metric matrix, which can be solved via an iterative manner: once latent information is specified, the metric matrix can be obtained based on some typical metric learning methods; with the computed metric matrix, the latent variables can be determined by searching the state space exhaustively. Finally, extensive experiments are conducted on seven databases to evaluate the proposed method. The experimental results demonstrate that our method achieves better performance than other competing algorithms.

Structural limitations of learning in a crowd: communication vulnerability and information diffusion in MOOCs.

PubMed

Gillani, Nabeel; Yasseri, Taha; Eynon, Rebecca; Hjorth, Isis

2014-09-23

Massive Open Online Courses (MOOCs) bring together a global crowd of thousands of learners for several weeks or months. In theory, the openness and scale of MOOCs can promote iterative dialogue that facilitates group cognition and knowledge construction. Using data from two successive instances of a popular business strategy MOOC, we filter observed communication patterns to arrive at the "significant" interaction networks between learners and use complex network analysis to explore the vulnerability and information diffusion potential of the discussion forums. We find that different discussion topics and pedagogical practices promote varying levels of 1) "significant" peer-to-peer engagement, 2) participant inclusiveness in dialogue, and ultimately, 3) modularity, which impacts information diffusion to prevent a truly "global" exchange of knowledge and learning. These results indicate the structural limitations of large-scale crowd-based learning and highlight the different ways that learners in MOOCs leverage, and learn within, social contexts. We conclude by exploring how these insights may inspire new developments in online education.

Structural limitations of learning in a crowd: communication vulnerability and information diffusion in MOOCs

PubMed Central

Gillani, Nabeel; Yasseri, Taha; Eynon, Rebecca; Hjorth, Isis

2014-01-01

Massive Open Online Courses (MOOCs) bring together a global crowd of thousands of learners for several weeks or months. In theory, the openness and scale of MOOCs can promote iterative dialogue that facilitates group cognition and knowledge construction. Using data from two successive instances of a popular business strategy MOOC, we filter observed communication patterns to arrive at the “significant” interaction networks between learners and use complex network analysis to explore the vulnerability and information diffusion potential of the discussion forums. We find that different discussion topics and pedagogical practices promote varying levels of 1) “significant” peer-to-peer engagement, 2) participant inclusiveness in dialogue, and ultimately, 3) modularity, which impacts information diffusion to prevent a truly “global” exchange of knowledge and learning. These results indicate the structural limitations of large-scale crowd-based learning and highlight the different ways that learners in MOOCs leverage, and learn within, social contexts. We conclude by exploring how these insights may inspire new developments in online education. PMID:25244925

Structural limitations of learning in a crowd: communication vulnerability and information diffusion in MOOCs

NASA Astrophysics Data System (ADS)

Gillani, Nabeel; Yasseri, Taha; Eynon, Rebecca; Hjorth, Isis

2014-09-01

Massive Open Online Courses (MOOCs) bring together a global crowd of thousands of learners for several weeks or months. In theory, the openness and scale of MOOCs can promote iterative dialogue that facilitates group cognition and knowledge construction. Using data from two successive instances of a popular business strategy MOOC, we filter observed communication patterns to arrive at the ``significant'' interaction networks between learners and use complex network analysis to explore the vulnerability and information diffusion potential of the discussion forums. We find that different discussion topics and pedagogical practices promote varying levels of 1) ``significant'' peer-to-peer engagement, 2) participant inclusiveness in dialogue, and ultimately, 3) modularity, which impacts information diffusion to prevent a truly ``global'' exchange of knowledge and learning. These results indicate the structural limitations of large-scale crowd-based learning and highlight the different ways that learners in MOOCs leverage, and learn within, social contexts. We conclude by exploring how these insights may inspire new developments in online education.

Mastering the game of Go without human knowledge.

PubMed

Silver, David; Schrittwieser, Julian; Simonyan, Karen; Antonoglou, Ioannis; Huang, Aja; Guez, Arthur; Hubert, Thomas; Baker, Lucas; Lai, Matthew; Bolton, Adrian; Chen, Yutian; Lillicrap, Timothy; Hui, Fan; Sifre, Laurent; van den Driessche, George; Graepel, Thore; Hassabis, Demis

2017-10-18

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo's own move selections and also the winner of AlphaGo's games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

Mastering the game of Go without human knowledge

NASA Astrophysics Data System (ADS)

Silver, David; Schrittwieser, Julian; Simonyan, Karen; Antonoglou, Ioannis; Huang, Aja; Guez, Arthur; Hubert, Thomas; Baker, Lucas; Lai, Matthew; Bolton, Adrian; Chen, Yutian; Lillicrap, Timothy; Hui, Fan; Sifre, Laurent; van den Driessche, George; Graepel, Thore; Hassabis, Demis

2017-10-01

A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. Recently, AlphaGo became the first program to defeat a world champion in the game of Go. The tree search in AlphaGo evaluated positions and selected moves using deep neural networks. These neural networks were trained by supervised learning from human expert moves, and by reinforcement learning from self-play. Here we introduce an algorithm based solely on reinforcement learning, without human data, guidance or domain knowledge beyond game rules. AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also the winner of AlphaGo’s games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved superhuman performance, winning 100-0 against the previously published, champion-defeating AlphaGo.

Incrementally learning objects by touch: online discriminative and generative models for tactile-based recognition.

PubMed

Soh, Harold; Demiris, Yiannis

2014-01-01

Human beings not only possess the remarkable ability to distinguish objects through tactile feedback but are further able to improve upon recognition competence through experience. In this work, we explore tactile-based object recognition with learners capable of incremental learning. Using the sparse online infinite Echo-State Gaussian process (OIESGP), we propose and compare two novel discriminative and generative tactile learners that produce probability distributions over objects during object grasping/palpation. To enable iterative improvement, our online methods incorporate training samples as they become available. We also describe incremental unsupervised learning mechanisms, based on novelty scores and extreme value theory, when teacher labels are not available. We present experimental results for both supervised and unsupervised learning tasks using the iCub humanoid, with tactile sensors on its five-fingered anthropomorphic hand, and 10 different object classes. Our classifiers perform comparably to state-of-the-art methods (C4.5 and SVM classifiers) and findings indicate that tactile signals are highly relevant for making accurate object classifications. We also show that accurate "early" classifications are possible using only 20-30 percent of the grasp sequence. For unsupervised learning, our methods generate high quality clusterings relative to the widely-used sequential k-means and self-organising map (SOM), and we present analyses into the differences between the approaches.

Enhancing Schools’ Capacity to Support Children in Poverty: An Ecological Model of School-Based Mental Health Services

PubMed Central

Frazier, Stacy L.; Atkins, Marc S.; Schoenwald, Sonja K.; Glisson, Charles

2013-01-01

School based mental health services for children in poverty can capitalize on schools’ inherent capacity to support development and bridge home and neighborhood ecologies. We propose an ecological model informed by public health and organizational theories to refocus school based services in poor communities on the core function of schools to promote learning. We describe how coalescing mental health resources around school goals includes a focus on universal programming, mobilizing indigenous school and community resources, and supporting core teaching technologies. We suggest an iterative research–practice approach to program adaptation and implementation as a means toward advancing science and developing healthy children. PMID:18581225

An Active Learning Framework for Hyperspectral Image Classification Using Hierarchical Segmentation

NASA Technical Reports Server (NTRS)

Zhang, Zhou; Pasolli, Edoardo; Crawford, Melba M.; Tilton, James C.

2015-01-01

Augmenting spectral data with spatial information for image classification has recently gained significant attention, as classification accuracy can often be improved by extracting spatial information from neighboring pixels. In this paper, we propose a new framework in which active learning (AL) and hierarchical segmentation (HSeg) are combined for spectral-spatial classification of hyperspectral images. The spatial information is extracted from a best segmentation obtained by pruning the HSeg tree using a new supervised strategy. The best segmentation is updated at each iteration of the AL process, thus taking advantage of informative labeled samples provided by the user. The proposed strategy incorporates spatial information in two ways: 1) concatenating the extracted spatial features and the original spectral features into a stacked vector and 2) extending the training set using a self-learning-based semi-supervised learning (SSL) approach. Finally, the two strategies are combined within an AL framework. The proposed framework is validated with two benchmark hyperspectral datasets. Higher classification accuracies are obtained by the proposed framework with respect to five other state-of-the-art spectral-spatial classification approaches. Moreover, the effectiveness of the proposed pruning strategy is also demonstrated relative to the approaches based on a fixed segmentation.

Designing a Web-Based Learning Portal for Geographic Visualization and Analysis in Public Health

PubMed Central

Robinson, Anthony C.; Roth, Robert E.; MacEachren, Alan M.

2011-01-01

Interactive mapping and spatial analysis tools are underutilized by health researchers and decision-makers due to scarce training materials, few examples demonstrating the successful use of geographic visualization, and poor mechanisms for sharing results generated by geovisualization. We report here on the development of the Geovisual EXplication (G-EX) Portal, a web-based application designed to connect researchers in geovisualization and related mapping sciences to users who are working in public health and epidemiology. This paper focuses on the design and development of the G-EX Portal Learn module, a set of tools intended to disseminate learning artifacts. Initial design and development of the G-EX Portal has been guided by our past research on use and usability of geovisualization in public health. As part of the iterative design and development process, we conducted a needs assessment survey with targeted end-users that we report on here. The survey focused on users’ current learning habits, their preferred kind of learning artifacts, and issues they may have with contributing learning artifacts to web portals. Survey results showed that users desire a diverse set of learning artifacts in terms of both formats and topics covered. Results also revealed a willingness of users to contribute both learning artifacts and personal information that would help other users to evaluate the credibility of the learning artifact source. We include a detailed description of the G-EX Portal Learn module and focus on modifications to the design of the Learn module as a result from feedback we received from our survey. PMID:21937462

Development of online instructional resources for Earth system science education: An example of current practice from China

NASA Astrophysics Data System (ADS)

Dong, Shaochun; Xu, Shijin; Lu, Xiancai

2009-06-01

Educators around the world are striving to make science more accessible and relevant to students. Online instructional resources have become an integral component of tertiary science education and will continue to grow in influence and importance over the coming decades. A case study in the iterative improvement of the online instructional resources provided for first-year undergraduates taking " Introductory Earth System Science" at Nanjing University in China is presented in this paper. Online instructional resources are used to conduct a student-centered learning model in the domain of Earth system science, resulting in a sustainable online instructional framework for students and instructors. The purpose of our practice is to make Earth system science education more accessible and exciting to students, changing instruction from a largely textbook-based teacher-centered approach to a more interactive and student-centered approach, and promoting the integration of knowledge and development of deep understanding by students. Evaluation on learning performance and learning satisfaction is conducted to identify helpful components and perception based on students' learning activities. The feedbacks indicate that the use of online instructional resources has positive impacts on mitigating Earth system science education challenges, and has the potential to promote deep learning.

Fragment-based quantitative structure-activity relationship (FB-QSAR) for fragment-based drug design.

PubMed

Du, Qi-Shi; Huang, Ri-Bo; Wei, Yu-Tuo; Pang, Zong-Wen; Du, Li-Qin; Chou, Kuo-Chen

2009-01-30

In cooperation with the fragment-based design a new drug design method, the so-called "fragment-based quantitative structure-activity relationship" (FB-QSAR) is proposed. The essence of the new method is that the molecular framework in a family of drug candidates are divided into several fragments according to their substitutes being investigated. The bioactivities of molecules are correlated with the physicochemical properties of the molecular fragments through two sets of coefficients in the linear free energy equations. One coefficient set is for the physicochemical properties and the other for the weight factors of the molecular fragments. Meanwhile, an iterative double least square (IDLS) technique is developed to solve the two sets of coefficients in a training data set alternately and iteratively. The IDLS technique is a feedback procedure with machine learning ability. The standard Two-dimensional quantitative structure-activity relationship (2D-QSAR) is a special case, in the FB-QSAR, when the whole molecule is treated as one entity. The FB-QSAR approach can remarkably enhance the predictive power and provide more structural insights into rational drug design. As an example, the FB-QSAR is applied to build a predictive model of neuraminidase inhibitors for drug development against H5N1 influenza virus. (c) 2008 Wiley Periodicals, Inc.

Knowledge 'Translation' as social learning: negotiating the uptake of research-based knowledge in practice.

PubMed

Salter, K L; Kothari, A

2016-02-29

Knowledge translation and evidence-based practice have relied on research derived from clinical trials, which are considered to be methodologically rigorous. The result is practice recommendations based on a narrow view of evidence. We discuss how, within a practice environment, in fact individuals adopt and apply new evidence derived from multiple sources through ongoing, iterative learning cycles. The discussion is presented in four sections. After elaborating on the multiple forms of evidence used in practice, in section 2 we argue that the practitioner derives contextualized knowledge through reflective practice. Then, in section 3, the focus shifts from the individual to the team with consideration of social learning and theories of practice. In section 4 we discuss the implications of integrative and negotiated knowledge exchange and generation within the practice environment. Namely, how can we promote the use of research within a team-based, contextualized knowledge environment? We suggest support for: 1) collaborative learning environments for active learning and reflection, 2) engaged scholarship approaches so that practice can inform research in a collaborative manner and 3) leveraging authoritative opinion leaders for their clinical expertise during the shared negotiation of knowledge and research. Our approach also points to implications for studying evidence-informed practice: the identification of practice change (as an outcome) ought to be supplemented with understandings of how and when social negotiation processes occur to achieve integrated knowledge. This article discusses practice knowledge as dependent on the practice context and on social learning processes, and suggests how research knowledge uptake might be supported from this vantage point.

The “Empty Chairs” Approach to Learning: Simulation-Based Train the Trainer Program in Mzuzu, Malawi

PubMed Central

Sigalet, Elaine; Wishart, Ian; Lufesi, Norman; Haji, Faizal

2017-01-01

Together, a group of Canadian colleagues from St. John's, Newfoundland, Calgary, Alberta (some via Doha) and London, Ontario introduced the first Train the Trainer in Simulation-Based Learning (TTT-SBL) program in Mzuzu Central Hospital and Mzuzu University in Malawi. The team led by Elaine Sigalet (Doha) and consisting of Ian Wishart (Calgary), Faizal Haji (London) and Adam Dubrowski (St. John's) was invited to Malawi by Norman Lufesi to conduct a two-day TTT-SBL course for facilitators who teach an Emergency Triage, Assessment and Treatment (ETAT) plus Trauma course. The following technical report describes this course.  All trainees-facilitators who took part in the first iteration of the TTT-SBL course were asked to participate in teaching an ETAT course and modify it to include elements of simulation. The new format of ETAT resulted in a reduction of time necessary to conduct the course from four days (based on historical data) to 2.5 days. PMID:28580202

Nonlinear Motion Tracking by Deep Learning Architecture

NASA Astrophysics Data System (ADS)

Verma, Arnav; Samaiya, Devesh; Gupta, Karunesh K.

2018-03-01

In the world of Artificial Intelligence, object motion tracking is one of the major problems. The extensive research is being carried out to track people in crowd. This paper presents a unique technique for nonlinear motion tracking in the absence of prior knowledge of nature of nonlinear path that the object being tracked may follow. We achieve this by first obtaining the centroid of the object and then using the centroid as the current example for a recurrent neural network trained using real-time recurrent learning. We have tweaked the standard algorithm slightly and have accumulated the gradient for few previous iterations instead of using just the current iteration as is the norm. We show that for a single object, such a recurrent neural network is highly capable of approximating the nonlinearity of its path.

Development of a public health reporting data warehouse: lessons learned.

PubMed

Rizi, Seyed Ali Mussavi; Roudsari, Abdul

2013-01-01

Data warehouse projects are perceived to be risky and prone to failure due to many organizational and technical challenges. However, often iterative and lengthy processes of implementation of data warehouses at an enterprise level provide an opportunity for formative evaluation of these solutions. This paper describes lessons learned from successful development and implementation of the first phase of an enterprise data warehouse to support public health surveillance at British Columbia Centre for Disease Control. Iterative and prototyping approach to development, overcoming technical challenges of extraction and integration of data from large scale clinical and ancillary systems, a novel approach to record linkage, flexible and reusable modeling of clinical data, and securing senior management support at the right time were the main factors that contributed to the success of the data warehousing project.

Machine learning in cardiovascular medicine: are we there yet?

PubMed

Shameer, Khader; Johnson, Kipp W; Glicksberg, Benjamin S; Dudley, Joel T; Sengupta, Partho P

2018-01-19

Artificial intelligence (AI) broadly refers to analytical algorithms that iteratively learn from data, allowing computers to find hidden insights without being explicitly programmed where to look. These include a family of operations encompassing several terms like machine learning, cognitive learning, deep learning and reinforcement learning-based methods that can be used to integrate and interpret complex biomedical and healthcare data in scenarios where traditional statistical methods may not be able to perform. In this review article, we discuss the basics of machine learning algorithms and what potential data sources exist; evaluate the need for machine learning; and examine the potential limitations and challenges of implementing machine in the context of cardiovascular medicine. The most promising avenues for AI in medicine are the development of automated risk prediction algorithms which can be used to guide clinical care; use of unsupervised learning techniques to more precisely phenotype complex disease; and the implementation of reinforcement learning algorithms to intelligently augment healthcare providers. The utility of a machine learning-based predictive model will depend on factors including data heterogeneity, data depth, data breadth, nature of modelling task, choice of machine learning and feature selection algorithms, and orthogonal evidence. A critical understanding of the strength and limitations of various methods and tasks amenable to machine learning is vital. By leveraging the growing corpus of big data in medicine, we detail pathways by which machine learning may facilitate optimal development of patient-specific models for improving diagnoses, intervention and outcome in cardiovascular medicine. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.

Iterative quantization: a Procrustean approach to learning binary codes for large-scale image retrieval.

PubMed

Gong, Yunchao; Lazebnik, Svetlana; Gordo, Albert; Perronnin, Florent

2013-12-01

This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections. We formulate this problem in terms of finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube, and propose a simple and efficient alternating minimization algorithm to accomplish this task. This algorithm, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). The resulting binary codes significantly outperform several other state-of-the-art methods. We also show that further performance improvements can result from transforming the data with a nonlinear kernel mapping prior to PCA or CCA. Finally, we demonstrate an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.

Convergence of Proximal Iteratively Reweighted Nuclear Norm Algorithm for Image Processing.

PubMed

Sun, Tao; Jiang, Hao; Cheng, Lizhi

2017-08-25

The nonsmooth and nonconvex regularization has many applications in imaging science and machine learning research due to its excellent recovery performance. A proximal iteratively reweighted nuclear norm algorithm has been proposed for the nonsmooth and nonconvex matrix minimizations. In this paper, we aim to investigate the convergence of the algorithm. With the Kurdyka-Łojasiewicz property, we prove the algorithm globally converges to a critical point of the objective function. The numerical results presented in this paper coincide with our theoretical findings.

Using Iterative Plan-Do-Study-Act Cycles to Improve Teaching Pedagogy.

PubMed

Murray, Elizabeth J

2018-01-15

Most students entering nursing programs today are members of Generation Y or the Millennial generation, and they learn differently than previous generations. Nurse educators must consider implementing innovative teaching strategies that appeal to the newest generation of learners. The Plan-Do-Study-Act cycle is a framework that can be helpful when planning, assessing, and continually improving teaching pedagogy. This article describes the use of iterative Plan-Do-Study-Act cycles to implement a change in teaching pedagogy.

Implementation of team-based learning in year 1 of a PBL based medical program: a pilot study.

PubMed

Burgess, Annette; Ayton, Tom; Mellis, Craig

2016-02-04

A traditional and effective form of teaching within medical education has been Problem Based Learning (PBL). However, this method of teaching is resource intensive, normally requiring one tutor for every ten students. Team-based learning (TBL) has gained recent popularity in medical education, and can be applied to large groups of up to 100 students. TBL makes use of the advantages of small group teaching and learning, but in contrast to PBL, does not need large numbers of teachers. This study sought to explore the efficacy of using TBL in place of PBL in Year 1 of a medical program. In Year 1 of the medical program, two iterations of TBL, with 20 students, were run following four iterations of PBL within the Cardiology teaching block. Student feedback following PBL and TBL was collected by questionnaire, using closed and open ended questions. Additionally, individual and team tests were held at the beginning of each TBL class, and results of each week were compared. All students (n = 20) participated in the test in week 1, and 18/20 students participated in week 2. In total, 19/20 (95%) of students completed the questionnaires regarding their PBL and TBL experiences. The use of small groups, the readiness assurance tests, immediate feedback from an expert clinician, as well as time efficiency were all aspects of the TBL experience that students found positive. The clinical problem-solving activity, however, was considered to be less effective with TBL. There was a significant improvement (p = 0.004) in students' score from the week 1 assessment (median = 2) to the week 2 (median = 3.5) assessment. Interestingly, all teams but one (Team 1) achieved a lower score on their second week assessment than on their first. However, the lowest performing team in week 1 outperformed all other teams in week 2. Students favoured many aspects of the TBL process, particularly motivation to do the pre-reading, and better engagement in the process. Additionally, the application of TBL principles meant the sessions were not reliant upon a large teacher to student ratio. Students, however, highlighted the need for more time within TBL for clinical problem-solving.

On the solution of evolution equations based on multigrid and explicit iterative methods

NASA Astrophysics Data System (ADS)

Zhukov, V. T.; Novikova, N. D.; Feodoritova, O. B.

2015-08-01

Two schemes for solving initial-boundary value problems for three-dimensional parabolic equations are studied. One is implicit and is solved using the multigrid method, while the other is explicit iterative and is based on optimal properties of the Chebyshev polynomials. In the explicit iterative scheme, the number of iteration steps and the iteration parameters are chosen as based on the approximation and stability conditions, rather than on the optimization of iteration convergence to the solution of the implicit scheme. The features of the multigrid scheme include the implementation of the intergrid transfer operators for the case of discontinuous coefficients in the equation and the adaptation of the smoothing procedure to the spectrum of the difference operators. The results produced by these schemes as applied to model problems with anisotropic discontinuous coefficients are compared.

How do medical educators design a curriculum that facilitates student learning about professionalism?

PubMed

Langendyk, Vicki; Mason, Glenn; Wang, Shaoyu

2016-02-04

This study analyses the ways in which curriculum reform facilitated student learning about professionalism. Design-based research provided the structure for an iterative approach to curriculum change which we undertook over a 3 year period. The learning environment of the Personal and Professional Development Theme (PPD) was analysed through the sociocultural lens of Activity Theory. Lave and Wenger's and Mezirow's learning theories informed curriculum reform to support student development of a patient-centred and critically reflective professional identity. The renewed pedagogical outcomes were aligned with curriculum content, learning and teaching processes and assessment, and intense staff education was undertaken. We analysed qualitative data from tutor interviews and free-response student surveys to evaluate the impact of curriculum reform. Students' and tutors' reflections on learning in PPD converged on two principle themes--'Developing a philosophy of medicine' and 'Becoming an ethical doctor'--which corresponded to the overarching PPD theme aims of communicative learning. Students and tutors emphasised the importance of the unique learning environment of PPD tutorials for nurturing personal development and the positive impact of the renewed assessment programme on learning. A theory-led approach to curriculum reform resulted in student engagement in the PPD curriculum and facilitated a change in student perspective about the epistemological foundation of medicine.

Exploring the Impact of Global Studies Experiences on Undergraduate Student Development: Some Curricular Considerations

ERIC Educational Resources Information Center

Stephens, Christopher J.; Morford, Z. Harrison; Cihon, Traci M.; Forand, Elissa Hamilton; Neri-Hernández, Lucero

2018-01-01

In this manuscript, the authors detail the initial evaluations of the effects of participation in two iterations of an interdisciplinary learning community with a short-term study abroad opportunity on undergraduate student learning and behavior. The results suggest that the CHE (Cultural, Historical, and Environmental) log tool may be useful in…

Using Learning Trajectories for Teacher Learning to Structure Professional Development

ERIC Educational Resources Information Center

Bargagliotti, Anna E.; Anderson, Celia Rousseau

2017-01-01

As a result of the increased focus on data literacy and data science across the world, there has been a large demand for professional development in statistics. However, exactly how these professional development opportunities should be structured remains an open question. The purpose of this paper is to describe the first iteration of a design…

Shaping Aspirations, Awareness, Academics, and Action: Outcomes of Summer Enrichment Programs for English-Learning Secondary Students

ERIC Educational Resources Information Center

Matthews, Paul H.; Mellom, Paula J.

2012-01-01

Mixed-method evaluation of two iterations of month-long summer enrichment programs for English-learning secondary students investigated impacts on participants' beliefs about school and academic achievement, and on actual course choices, test outcomes, and graduation rates. Students (N = 85) from one ethnically diverse, high-poverty high school in…

[MicroRNA Target Prediction Based on Support Vector Machine Ensemble Classification Algorithm of Under-sampling Technique].

PubMed

Chen, Zhiru; Hong, Wenxue

2016-02-01

Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.

Equivalent charge source model based iterative maximum neighbor weight for sparse EEG source localization.

PubMed

Xu, Peng; Tian, Yin; Lei, Xu; Hu, Xiao; Yao, Dezhong

2008-12-01

How to localize the neural electric activities within brain effectively and precisely from the scalp electroencephalogram (EEG) recordings is a critical issue for current study in clinical neurology and cognitive neuroscience. In this paper, based on the charge source model and the iterative re-weighted strategy, proposed is a new maximum neighbor weight based iterative sparse source imaging method, termed as CMOSS (Charge source model based Maximum neighbOr weight Sparse Solution). Different from the weight used in focal underdetermined system solver (FOCUSS) where the weight for each point in the discrete solution space is independently updated in iterations, the new designed weight for each point in each iteration is determined by the source solution of the last iteration at both the point and its neighbors. Using such a new weight, the next iteration may have a bigger chance to rectify the local source location bias existed in the previous iteration solution. The simulation studies with comparison to FOCUSS and LORETA for various source configurations were conducted on a realistic 3-shell head model, and the results confirmed the validation of CMOSS for sparse EEG source localization. Finally, CMOSS was applied to localize sources elicited in a visual stimuli experiment, and the result was consistent with those source areas involved in visual processing reported in previous studies.

Region growing using superpixels with learned shape prior

NASA Astrophysics Data System (ADS)

Borovec, Jiří; Kybic, Jan; Sugimoto, Akihiro

2017-11-01

Region growing is a classical image segmentation method based on hierarchical region aggregation using local similarity rules. Our proposed method differs from classical region growing in three important aspects. First, it works on the level of superpixels instead of pixels, which leads to a substantial speed-up. Second, our method uses learned statistical shape properties that encourage plausible shapes. In particular, we use ray features to describe the object boundary. Third, our method can segment multiple objects and ensure that the segmentations do not overlap. The problem is represented as an energy minimization and is solved either greedily or iteratively using graph cuts. We demonstrate the performance of the proposed method and compare it with alternative approaches on the task of segmenting individual eggs in microscopy images of Drosophila ovaries.

From Innovation to Impact at Scale: Lessons Learned from a Cluster of Research-Community Partnerships

PubMed Central

Schindler, Holly S.; Fisher, Philip A.; Shonkoff, Jack P.

2017-01-01

This paper presents a description of how an interdisciplinary network of academic researchers, community-based programs, parents, and state agencies have joined together to design, test, and scale a suite of innovative intervention strategies rooted in new knowledge about the biology of adversity. Through a process of co-creation, collective pilot-testing, and the support of a measurement and evaluation hub, the Washington State Innovation Cluster is using rapid cycle, iterative learning to elucidate differential impacts of interventions designed to build child and caregiver capacities and address the developmental consequences of socioeconomic disadvantage. Key characteristics of the Innovation Cluster model are described and an example is presented of a video-coaching intervention that has been implemented, adapted, and evaluated through this distinctive, collaborative process. PMID:28777436

Off-Policy Actor-Critic Structure for Optimal Control of Unknown Systems With Disturbances.

PubMed

Song, Ruizhuo; Lewis, Frank L; Wei, Qinglai; Zhang, Huaguang

2016-05-01

An optimal control method is developed for unknown continuous-time systems with unknown disturbances in this paper. The integral reinforcement learning (IRL) algorithm is presented to obtain the iterative control. Off-policy learning is used to allow the dynamics to be completely unknown. Neural networks are used to construct critic and action networks. It is shown that if there are unknown disturbances, off-policy IRL may not converge or may be biased. For reducing the influence of unknown disturbances, a disturbances compensation controller is added. It is proven that the weight errors are uniformly ultimately bounded based on Lyapunov techniques. Convergence of the Hamiltonian function is also proven. The simulation study demonstrates the effectiveness of the proposed optimal control method for unknown systems with disturbances.

Teachers Supporting Teachers in Urban Schools: What Iterative Research Designs Can Teach Us

PubMed Central

Shernoff, Elisa S.; Maríñez-Lora, Ane M.; Frazier, Stacy L.; Jakobsons, Lara J.; Atkins, Marc S.; Bonner, Deborah

2012-01-01

Despite alarming rates and negative consequences associated with urban teacher attrition, mentoring programs often fail to target the strongest predictors of attrition: effectiveness around classroom management and engaging learners; and connectedness to colleagues. Using a mixed-method iterative development framework, we highlight the process of developing and evaluating the feasibility of a multi-component professional development model for urban early career teachers. The model includes linking novices with peer-nominated key opinion leader teachers and an external coach who work together to (1) provide intensive support in evidence-based practices for classroom management and engaging learners, and (2) connect new teachers with their larger network of colleagues. Fidelity measures and focus group data illustrated varying attendance rates throughout the school year and that although seminars and professional learning communities were delivered as intended, adaptations to enhance the relevance, authenticity, level, and type of instrumental support were needed. Implications for science and practice are discussed. PMID:23275682

Sparse time-frequency decomposition based on dictionary adaptation.

PubMed

Hou, Thomas Y; Shi, Zuoqiang

2016-04-13

In this paper, we propose a time-frequency analysis method to obtain instantaneous frequencies and the corresponding decomposition by solving an optimization problem. In this optimization problem, the basis that is used to decompose the signal is not known a priori. Instead, it is adapted to the signal and is determined as part of the optimization problem. In this sense, this optimization problem can be seen as a dictionary adaptation problem, in which the dictionary is adaptive to one signal rather than a training set in dictionary learning. This dictionary adaptation problem is solved by using the augmented Lagrangian multiplier (ALM) method iteratively. We further accelerate the ALM method in each iteration by using the fast wavelet transform. We apply our method to decompose several signals, including signals with poor scale separation, signals with outliers and polluted by noise and a real signal. The results show that this method can give accurate recovery of both the instantaneous frequencies and the intrinsic mode functions. © 2016 The Author(s).

A Distributed Learning Method for ℓ1-Regularized Kernel Machine over Wireless Sensor Networks

PubMed Central

Ji, Xinrong; Hou, Cuiqin; Hou, Yibin; Gao, Fang; Wang, Shulong

2016-01-01

In wireless sensor networks, centralized learning methods have very high communication costs and energy consumption. These are caused by the need to transmit scattered training examples from various sensor nodes to the central fusion center where a classifier or a regression machine is trained. To reduce the communication cost, a distributed learning method for a kernel machine that incorporates ℓ1 norm regularization (ℓ1-regularized) is investigated, and a novel distributed learning algorithm for the ℓ1-regularized kernel minimum mean squared error (KMSE) machine is proposed. The proposed algorithm relies on in-network processing and a collaboration that transmits the sparse model only between single-hop neighboring nodes. This paper evaluates the proposed algorithm with respect to the prediction accuracy, the sparse rate of model, the communication cost and the number of iterations on synthetic and real datasets. The simulation results show that the proposed algorithm can obtain approximately the same prediction accuracy as that obtained by the batch learning method. Moreover, it is significantly superior in terms of the sparse rate of model and communication cost, and it can converge with fewer iterations. Finally, an experiment conducted on a wireless sensor network (WSN) test platform further shows the advantages of the proposed algorithm with respect to communication cost. PMID:27376298

User-Driven Sampling Strategies in Image Exploitation

DOE PAGES

Harvey, Neal R.; Porter, Reid B.

2013-12-23

Visual analytics and interactive machine learning both try to leverage the complementary strengths of humans and machines to solve complex data exploitation tasks. These fields overlap most significantly when training is involved: the visualization or machine learning tool improves over time by exploiting observations of the human-computer interaction. This paper focuses on one aspect of the human-computer interaction that we call user-driven sampling strategies. Unlike relevance feedback and active learning sampling strategies, where the computer selects which data to label at each iteration, we investigate situations where the user selects which data is to be labeled at each iteration. User-drivenmore » sampling strategies can emerge in many visual analytics applications but they have not been fully developed in machine learning. We discovered that in user-driven sampling strategies suggest new theoretical and practical research questions for both visualization science and machine learning. In this paper we identify and quantify the potential benefits of these strategies in a practical image analysis application. We find user-driven sampling strategies can sometimes provide significant performance gains by steering tools towards local minima that have lower error than tools trained with all of the data. Furthermore, in preliminary experiments we find these performance gains are particularly pronounced when the user is experienced with the tool and application domain.« less

User-driven sampling strategies in image exploitation

NASA Astrophysics Data System (ADS)

Harvey, Neal; Porter, Reid

2013-12-01

Visual analytics and interactive machine learning both try to leverage the complementary strengths of humans and machines to solve complex data exploitation tasks. These fields overlap most significantly when training is involved: the visualization or machine learning tool improves over time by exploiting observations of the human-computer interaction. This paper focuses on one aspect of the human-computer interaction that we call user-driven sampling strategies. Unlike relevance feedback and active learning sampling strategies, where the computer selects which data to label at each iteration, we investigate situations where the user selects which data is to be labeled at each iteration. User-driven sampling strategies can emerge in many visual analytics applications but they have not been fully developed in machine learning. User-driven sampling strategies suggest new theoretical and practical research questions for both visualization science and machine learning. In this paper we identify and quantify the potential benefits of these strategies in a practical image analysis application. We find user-driven sampling strategies can sometimes provide significant performance gains by steering tools towards local minima that have lower error than tools trained with all of the data. In preliminary experiments we find these performance gains are particularly pronounced when the user is experienced with the tool and application domain.

Creating a Learning Organization for State, Local, and Tribal Law Enforcement to Combat Violent Extremism

DTIC Science & Technology

2016-09-01

iterations in that time for the student practitioners to work through. When possible, case studies will be selected from actual counter-radicalizations...justify participation in the learning 9 organization. Those cases will be evaluated on a case -by- case basis and the need to expand the CVE mission...interested within the learning organization. The National Fire Academy Executive Fire Officer Program applied research pre -course is an example of

A new model for graduate education and innovation in medical technology.

PubMed

Yazdi, Youseph; Acharya, Soumyadipta

2013-09-01

We describe a new model of graduate education in bioengineering innovation and design- a year long Master's degree program that educates engineers in the process of healthcare technology innovation for both advanced and low-resource global markets. Students are trained in an iterative "Spiral Innovation" approach that ensures early, staged, and repeated examination of all key elements of a successful medical device. This includes clinical immersion based problem identification and assessment (at Johns Hopkins Medicine and abroad), team based concept and business model development, and project planning based on iterative technical and business plan de-risking. The experiential, project based learning process is closely supported by several core courses in business, design, and engineering. Students in the program work on two team based projects, one focused on addressing healthcare needs in advanced markets and a second focused on low-resource settings. The program recently completed its fourth year of existence, and has graduated 61 students, who have continued on to industry or startups (one half), additional graduate education, or medical school (one third), or our own Global Health Innovation Fellowships. Over the 4 years, the program has sponsored 10 global health teams and 14 domestic/advanced market medtech teams, and launched 5 startups, of which 4 are still active. Projects have attracted over US$2.5M in follow-on awards and grants, that are supporting the continued development of over a dozen projects.

Groupwise Image Registration Guided by a Dynamic Digraph of Images.

PubMed

Tang, Zhenyu; Fan, Yong

2016-04-01

For groupwise image registration, graph theoretic methods have been adopted for discovering the manifold of images to be registered so that accurate registration of images to a group center image can be achieved by aligning similar images that are linked by the shortest graph paths. However, the image similarity measures adopted to build a graph of images in the extant methods are essentially pairwise measures, not effective for capturing the groupwise similarity among multiple images. To overcome this problem, we present a groupwise image similarity measure that is built on sparse coding for characterizing image similarity among all input images and build a directed graph (digraph) of images so that similar images are connected by the shortest paths of the digraph. Following the shortest paths determined according to the digraph, images are registered to a group center image in an iterative manner by decomposing a large anatomical deformation field required to register an image to the group center image into a series of small ones between similar images. During the iterative image registration, the digraph of images evolves dynamically at each iteration step to pursue an accurate estimation of the image manifold. Moreover, an adaptive dictionary strategy is adopted in the groupwise image similarity measure to ensure fast convergence of the iterative registration procedure. The proposed method has been validated based on both simulated and real brain images, and experiment results have demonstrated that our method was more effective for learning the manifold of input images and achieved higher registration accuracy than state-of-the-art groupwise image registration methods.

Exploring Alignment among Learning Progressions, Teacher-Designed Formative Assessment Tasks, and Student Growth: Results of a Four-Year Study

ERIC Educational Resources Information Center

Furtak, Erin Marie; Circi, Ruhan; Heredia, Sara C.

2018-01-01

This article describes a 4-year study of experienced high school biology teachers' participation in a five-step professional development experience in which they iteratively studied student ideas with the support of a set of learning progressions, designed formative assessment activities, practiced using those activities with their students,…

Fostering Self-Regulated Learning in a Blended Environment Using Group Awareness and Peer Assistance as External Scaffolds

ERIC Educational Resources Information Center

Lin, J-W.; Lai, Y-C.; Lai, Y-C.; Chang, L-C.

2016-01-01

Most systems for training self-regulated learning (SRL) behaviour focus on the provision of a learner-centred environment. Such systems repeat the training process and place learners alone to experience that process iteratively. According to the relevant literature, external scaffolds are more promising for effective SRL training. In this work,…

Self-Regulated Learning: The Continuous-Change Conceptual Framework and a Vision of New Paradigm, Technology System, and Pedagogical Support

ERIC Educational Resources Information Center

Huh, Yeol; Reigeluth, Charles M.

2017-01-01

A modified conceptual framework called the Continuous-Change Framework for self-regulated learning (SRL) is presented. Common elements and limitations among the past frameworks are discussed in relation to the modified conceptual framework. The iterative nature of the goal setting process and overarching presence of self-efficacy and motivational…

For the Love of Statistics: Appreciating and Learning to Apply Experimental Analysis and Statistics through Computer Programming Activities

ERIC Educational Resources Information Center

Mascaró, Maite; Sacristán, Ana Isabel; Rufino, Marta M.

2016-01-01

For the past 4 years, we have been involved in a project that aims to enhance the teaching and learning of experimental analysis and statistics, of environmental and biological sciences students, through computational programming activities (using R code). In this project, through an iterative design, we have developed sequences of R-code-based…

Playing and Learning: An iPad Game Development & Implementation Case Study

ERIC Educational Resources Information Center

Jenson, Jennifer; de Castell, Suzanne; Muehrer, Rachel; McLaughlin-Jenkins, Erin

2016-01-01

There is a great deal of enthusiasm for the use of games in formal educational contexts; however, there is a notable and problematic lack of studies that make use of replicable study designs to empirically link games to learning (Young, et al., 2012). This paper documents the iterative design and development of an educationally focused game,…

Tensor-based Dictionary Learning for Spectral CT Reconstruction

PubMed Central

Zhang, Yanbo; Wang, Ge

2016-01-01

Spectral computed tomography (CT) produces an energy-discriminative attenuation map of an object, extending a conventional image volume with a spectral dimension. In spectral CT, an image can be sparsely represented in each of multiple energy channels, and are highly correlated among energy channels. According to this characteristics, we propose a tensor-based dictionary learning method for spectral CT reconstruction. In our method, tensor patches are extracted from an image tensor, which is reconstructed using the filtered backprojection (FBP), to form a training dataset. With the Candecomp/Parafac decomposition, a tensor-based dictionary is trained, in which each atom is a rank-one tensor. Then, the trained dictionary is used to sparsely represent image tensor patches during an iterative reconstruction process, and the alternating minimization scheme is adapted for optimization. The effectiveness of our proposed method is validated with both numerically simulated and real preclinical mouse datasets. The results demonstrate that the proposed tensor-based method generally produces superior image quality, and leads to more accurate material decomposition than the currently popular popular methods. PMID:27541628

Acceleration of image-based resolution modelling reconstruction using an expectation maximization nested algorithm.

PubMed

Angelis, G I; Reader, A J; Markiewicz, P J; Kotasidis, F A; Lionheart, W R; Matthews, J C

2013-08-07

Recent studies have demonstrated the benefits of a resolution model within iterative reconstruction algorithms in an attempt to account for effects that degrade the spatial resolution of the reconstructed images. However, these algorithms suffer from slower convergence rates, compared to algorithms where no resolution model is used, due to the additional need to solve an image deconvolution problem. In this paper, a recently proposed algorithm, which decouples the tomographic and image deconvolution problems within an image-based expectation maximization (EM) framework, was evaluated. This separation is convenient, because more computational effort can be placed on the image deconvolution problem and therefore accelerate convergence. Since the computational cost of solving the image deconvolution problem is relatively small, multiple image-based EM iterations do not significantly increase the overall reconstruction time. The proposed algorithm was evaluated using 2D simulations, as well as measured 3D data acquired on the high-resolution research tomograph. Results showed that bias reduction can be accelerated by interleaving multiple iterations of the image-based EM algorithm solving the resolution model problem, with a single EM iteration solving the tomographic problem. Significant improvements were observed particularly for voxels that were located on the boundaries between regions of high contrast within the object being imaged and for small regions of interest, where resolution recovery is usually more challenging. Minor differences were observed using the proposed nested algorithm, compared to the single iteration normally performed, when an optimal number of iterations are performed for each algorithm. However, using the proposed nested approach convergence is significantly accelerated enabling reconstruction using far fewer tomographic iterations (up to 70% fewer iterations for small regions). Nevertheless, the optimal number of nested image-based EM iterations is hard to be defined and it should be selected according to the given application.

2009 Space Shuttle Probabilistic Risk Assessment Overview

NASA Technical Reports Server (NTRS)

Hamlin, Teri L.; Canga, Michael A.; Boyer, Roger L.; Thigpen, Eric B.

2010-01-01

Loss of a Space Shuttle during flight has severe consequences, including loss of a significant national asset; loss of national confidence and pride; and, most importantly, loss of human life. The Shuttle Probabilistic Risk Assessment (SPRA) is used to identify risk contributors and their significance; thus, assisting management in determining how to reduce risk. In 2006, an overview of the SPRA Iteration 2.1 was presented at PSAM 8 [1]. Like all successful PRAs, the SPRA is a living PRA and has undergone revisions since PSAM 8. The latest revision to the SPRA is Iteration 3. 1, and it will not be the last as the Shuttle program progresses and more is learned. This paper discusses the SPRA scope, overall methodology, and results, as well as provides risk insights. The scope, assumptions, uncertainties, and limitations of this assessment provide risk-informed perspective to aid management s decision-making process. In addition, this paper compares the Iteration 3.1 analysis and results to the Iteration 2.1 analysis and results presented at PSAM 8.

Supervised guiding long-short term memory for image caption generation based on object classes

NASA Astrophysics Data System (ADS)

Wang, Jian; Cao, Zhiguo; Xiao, Yang; Qi, Xinyuan

2018-03-01

The present models of image caption generation have the problems of image visual semantic information attenuation and errors in guidance information. In order to solve these problems, we propose a supervised guiding Long Short Term Memory model based on object classes, named S-gLSTM for short. It uses the object detection results from R-FCN as supervisory information with high confidence, and updates the guidance word set by judging whether the last output matches the supervisory information. S-gLSTM learns how to extract the current interested information from the image visual se-mantic information based on guidance word set. The interested information is fed into the S-gLSTM at each iteration as guidance information, to guide the caption generation. To acquire the text-related visual semantic information, the S-gLSTM fine-tunes the weights of the network through the back-propagation of the guiding loss. Complementing guidance information at each iteration solves the problem of visual semantic information attenuation in the traditional LSTM model. Besides, the supervised guidance information in our model can reduce the impact of the mismatched words on the caption generation. We test our model on MSCOCO2014 dataset, and obtain better performance than the state-of-the- art models.

New methods of testing nonlinear hypothesis using iterative NLLS estimator

NASA Astrophysics Data System (ADS)

Mahaboob, B.; Venkateswarlu, B.; Mokeshrayalu, G.; Balasiddamuni, P.

2017-11-01

This research paper discusses the method of testing nonlinear hypothesis using iterative Nonlinear Least Squares (NLLS) estimator. Takeshi Amemiya [1] explained this method. However in the present research paper, a modified Wald test statistic due to Engle, Robert [6] is proposed to test the nonlinear hypothesis using iterative NLLS estimator. An alternative method for testing nonlinear hypothesis using iterative NLLS estimator based on nonlinear hypothesis using iterative NLLS estimator based on nonlinear studentized residuals has been proposed. In this research article an innovative method of testing nonlinear hypothesis using iterative restricted NLLS estimator is derived. Pesaran and Deaton [10] explained the methods of testing nonlinear hypothesis. This paper uses asymptotic properties of nonlinear least squares estimator proposed by Jenrich [8]. The main purpose of this paper is to provide very innovative methods of testing nonlinear hypothesis using iterative NLLS estimator, iterative NLLS estimator based on nonlinear studentized residuals and iterative restricted NLLS estimator. Eakambaram et al. [12] discussed least absolute deviation estimations versus nonlinear regression model with heteroscedastic errors and also they studied the problem of heteroscedasticity with reference to nonlinear regression models with suitable illustration. William Grene [13] examined the interaction effect in nonlinear models disused by Ai and Norton [14] and suggested ways to examine the effects that do not involve statistical testing. Peter [15] provided guidelines for identifying composite hypothesis and addressing the probability of false rejection for multiple hypotheses.

Spine detection in CT and MR using iterated marginal space learning.

PubMed

Michael Kelm, B; Wels, Michael; Kevin Zhou, S; Seifert, Sascha; Suehling, Michael; Zheng, Yefeng; Comaniciu, Dorin

2013-12-01

Examinations of the spinal column with both, Magnetic Resonance (MR) imaging and Computed Tomography (CT), often require a precise three-dimensional positioning, angulation and labeling of the spinal disks and the vertebrae. A fully automatic and robust approach is a prerequisite for an automated scan alignment as well as for the segmentation and analysis of spinal disks and vertebral bodies in Computer Aided Diagnosis (CAD) applications. In this article, we present a novel method that combines Marginal Space Learning (MSL), a recently introduced concept for efficient discriminative object detection, with a generative anatomical network that incorporates relative pose information for the detection of multiple objects. It is used to simultaneously detect and label the spinal disks. While a novel iterative version of MSL is used to quickly generate candidate detections comprising position, orientation, and scale of the disks with high sensitivity, the anatomical network selects the most likely candidates using a learned prior on the individual nine dimensional transformation spaces. Finally, we propose an optional case-adaptive segmentation approach that allows to segment the spinal disks and vertebrae in MR and CT respectively. Since the proposed approaches are learning-based, they can be trained for MR or CT alike. Experimental results based on 42 MR and 30 CT volumes show that our system not only achieves superior accuracy but also is among the fastest systems of its kind in the literature. On the MR data set the spinal disks of a whole spine are detected in 11.5s on average with 98.6% sensitivity and 0.073 false positive detections per volume. On the CT data a comparable sensitivity of 98.0% with 0.267 false positives is achieved. Detected disks are localized with an average position error of 2.4 mm/3.2 mm and angular error of 3.9°/4.5° in MR/CT, which is close to the employed hypothesis resolution of 2.1 mm and 3.3°. Copyright © 2012 Elsevier B.V. All rights reserved.

Implementation of modified team-based learning within a problem based learning medical curriculum: a focus group study.

PubMed

Burgess, Annette; Roberts, Chris; Ayton, Tom; Mellis, Craig

2018-04-10

While Problem Based Learning (PBL) has long been established internationally, Team-based learning (TBL) is a relatively new pedagogy in medical curricula. Both PBL and TBL are designed to facilitate a learner-centred approach, where students, in interactive small groups, use peer-assisted learning to solve authentic, professionally relevant problems. Differences, however, exist between PBL and TBL in terms of preparation requirements, group numbers, learning strategies, and class structure. Although there are many similarities and some differences between PBL and TBL, both rely on constructivist learning theory to engage and motivate students in their learning. The aim of our study was to qualitatively explore students' perceptions of having their usual PBL classes run in TBL format. In 2014, two iterations in a hybrid PBL curriculum were converted to TBL format, with two PBL groups of 10 students each, being combined to form one TBL class of 20, split into four groups of five students. At the completion of two TBL sessions, all students were invited to attend one of two focus groups, with 14 attending. Thematic analysis was used to code and categorise the data into themes, with constructivist theory used as a conceptual framework to identify recurrent themes. Four key themes emerged; guided learning, problem solving, collaborative learning, and critical reflection. Although structured, students were attracted to the active and collaborative approach of TBL. They perceived the key advantages of TBL to include the smaller group size, the preparatory Readiness Assurance Testing process, facilitation by a clinician, an emphasis on basic science concepts, and immediate feedback. The competitiveness of TBL was seen as a spur to learning. These elements motivated students to prepare, promoted peer assisted teaching and learning, and focussed team discussion. An important advantage of PBL over TBL, was the opportunity for adequate clinical reasoning within the problem solving activity. Students found their learning experience in TBL and PBL qualitatively different. There were advantages and disadvantages to both. This suggests a hybrid approach utilising the strengths of both methods should be considered for wide scale implementation.

Prediction, experimental results and analysis of the ITER TF insert coil quench propagation tests, using the 4C code

NASA Astrophysics Data System (ADS)

Zanino, R.; Bonifetto, R.; Brighenti, A.; Isono, T.; Ozeki, H.; Savoldi, L.

2018-07-01

The ITER toroidal field insert (TFI) coil is a single-layer Nb3Sn solenoid tested in 2016-2017 at the National Institutes for Quantum and Radiological Science and Technology (former JAEA) in Naka, Japan. The TFI, the last in a series of ITER insert coils, was tested in operating conditions relevant for the actual ITER TF coils, inserting it in the borehole of the central solenoid model coil, which provided the background magnetic field. In this paper, we consider the five quench propagation tests that were performed using one or two inductive heaters (IHs) as drivers; out of these, three used just one IH but with increasing delay times, up to 7.5 s, between the quench detection and the TFI current dump. The results of the 4C code prediction of the quench propagation up to the current dump are presented first, based on simulations performed before the tests. We then describe the experimental results, showing good reproducibility. Finally, we compare the 4C code predictions with the measurements, confirming the 4C code capability to accurately predict the quench propagation, and the evolution of total and local voltages, as well as of the hot spot temperature. To the best of our knowledge, such a predictive validation exercise is performed here for the first time for the quench of a Nb3Sn coil. Discrepancies between prediction and measurement are found in the evolution of the jacket temperatures, in the He pressurization and quench acceleration in the late phase of the transient before the dump, as well as in the early evolution of the inlet and outlet He mass flow rate. Based on the lessons learned in the predictive exercise, the model is then refined to try and improve a posteriori (i.e. in interpretive, as opposed to predictive mode) the agreement between simulation and experiment.

Intelligent model-based OPC

NASA Astrophysics Data System (ADS)

Huang, W. C.; Lai, C. M.; Luo, B.; Tsai, C. K.; Chih, M. H.; Lai, C. W.; Kuo, C. C.; Liu, R. G.; Lin, H. T.

2006-03-01

Optical proximity correction is the technique of pre-distorting mask layouts so that the printed patterns are as close to the desired shapes as possible. For model-based optical proximity correction, a lithographic model to predict the edge position (contour) of patterns on the wafer after lithographic processing is needed. Generally, segmentation of edges is performed prior to the correction. Pattern edges are dissected into several small segments with corresponding target points. During the correction, the edges are moved back and forth from the initial drawn position, assisted by the lithographic model, to finally settle on the proper positions. When the correction converges, the intensity predicted by the model in every target points hits the model-specific threshold value. Several iterations are required to achieve the convergence and the computation time increases with the increase of the required iterations. An artificial neural network is an information-processing paradigm inspired by biological nervous systems, such as how the brain processes information. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems. A neural network can be a powerful data-modeling tool that is able to capture and represent complex input/output relationships. The network can accurately predict the behavior of a system via the learning procedure. A radial basis function network, a variant of artificial neural network, is an efficient function approximator. In this paper, a radial basis function network was used to build a mapping from the segment characteristics to the edge shift from the drawn position. This network can provide a good initial guess for each segment that OPC has carried out. The good initial guess reduces the required iterations. Consequently, cycle time can be shortened effectively. The optimization of the radial basis function network for this system was practiced by genetic algorithm, which is an artificially intelligent optimization method with a high probability to obtain global optimization. From preliminary results, the required iterations were reduced from 5 to 2 for a simple dumbbell-shape layout.

Maintaining Web-based Bibliographies: A Case Study of Iter, the Bibliography of Renaissance Europe.

ERIC Educational Resources Information Center

Castell, Tracy

1997-01-01

Introduces Iter, a nonprofit research project developed for the World Wide Web and dedicated to increasing access to all published materials pertaining to the Renaissance and, eventually, the Middle Ages. Discusses information management issues related to building and maintaining Iter's first Web-based bibliography, focusing on printed secondary…

Iterative free-energy optimization for recurrent neural networks (INFERNO).

PubMed

Pitti, Alexandre; Gaussier, Philippe; Quoy, Mathias

2017-01-01

The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework based on the free-energy principle, we propose to see the problem of spikes' synchrony as an optimization problem of the neurons sub-threshold activity for the generation of long neuronal chains. Using a stochastic gradient descent, a reinforcement signal (presumably dopaminergic) evaluates the quality of one input vector to move the recurrent neural network to a desired activity; depending on the error made, this input vector is strengthened to hill-climb the gradient or elicited to search for another solution. This vector can be learned then by one associative memory as a model of the basal-ganglia to control the recurrent neural network. Experiments on habit learning and on sequence retrieving demonstrate the capabilities of the dual system to generate very long and precise spatio-temporal sequences, above two hundred iterations. Its features are applied then to the sequential planning of arm movements. In line with neurobiological theories, we discuss its relevance for modeling the cortico-basal working memory to initiate flexible goal-directed neuronal chains of causation and its relation to novel architectures such as Deep Networks, Neural Turing Machines and the Free-Energy Principle.

Development of a Mixed Methods Investigation of Process and Outcomes of Community-Based Participatory Research.

PubMed

Lucero, Julie; Wallerstein, Nina; Duran, Bonnie; Alegria, Margarita; Greene-Moton, Ella; Israel, Barbara; Kastelic, Sarah; Magarati, Maya; Oetzel, John; Pearson, Cynthia; Schulz, Amy; Villegas, Malia; White Hat, Emily R

2018-01-01

This article describes a mixed methods study of community-based participatory research (CBPR) partnership practices and the links between these practices and changes in health status and disparities outcomes. Directed by a CBPR conceptual model and grounded in indigenous-transformative theory, our nation-wide, cross-site study showcases the value of a mixed methods approach for better understanding the complexity of CBPR partnerships across diverse community and research contexts. The article then provides examples of how an iterative, integrated approach to our mixed methods analysis yielded enriched understandings of two key constructs of the model: trust and governance. Implications and lessons learned while using mixed methods to study CBPR are provided.

Development of an ICT in IBSE course for science teachers: A design-based research

NASA Astrophysics Data System (ADS)

Tran, Trinh-Ba

2018-01-01

Integration of ICT tools for measuring with sensors, analyzing video, and modelling into Inquiry-Based Science Education (IBSE) is a need globally recognized. The challenge to teachers is how to turn manipulation of equipment and software into manipulation of ideas. We have developed a short ICT in IBSE course to prepare and support science teachers to teach inquiry-based activities with ICT tools. Within the framework of design-based research, we first defined the pedagogical principles from the literature, developed core materials for teacher learning, explored boundary conditions of the training in different countries, and elaborated set-ups of the course for the Dutch, Slovak, and Vietnamese contexts. Next, we taught and evaluated three iterative cycles of the Dutch course set-ups for pre-service science teachers from four teacher-education institutes nationwide. In each cycle, data on the teacher learning was collected via observations, questionnaires, interviews, and documents. These data were then analyzed for the questions about faithful implementation and effectiveness of the course. Following the same approach, we taught and evaluated two cycles of the Slovak course set-ups for in-service science teachers in the context of the national accreditation programme for teacher professional development. In addition, we investigated applicability of the final Dutch course set-up in the context of the physics-education master program in Vietnam with adaptations geared to educational and cultural difference. Through the iterations of implementation, evaluation, and revision, eventually the course objectives were achieved to certain extent; the pedagogical principles and core materials proved to be effective and applicable in different contexts. We started this research and design project with the pedagogical principles and concluded it with these principles (i.e. complete theory-practice cycle, depth first, distributed learning, and ownership of learning) as the core of the basic design of the ICT in IBSE course. These principles can be considered as independent, validated educational products, which teacher educators can "buy into" and use for broader aims than only "ICT in IBSE" integration. Pedagogical principles establish the theoretical model underlying the course design, provide guidelines and structure to the (re)design, implementation, evaluation, and optimization process, and help to communicate the design-based research to others. The role of pedagogical principles in design-based research is indeed essential. Moreover, we incorporated a robustness test and a generalizability/transferability test as a further step in our design-based research and achieved successful outcomes with this step. Consequently, we strongly recommend the testing of the design product in routine implementation conditions and in considerably different contexts (e.g. different programmes or even countries) as part of design-based research.

Robust Visual Tracking via Online Discriminative and Low-Rank Dictionary Learning.

PubMed

Zhou, Tao; Liu, Fanghui; Bhaskar, Harish; Yang, Jie

2017-09-12

In this paper, we propose a novel and robust tracking framework based on online discriminative and low-rank dictionary learning. The primary aim of this paper is to obtain compact and low-rank dictionaries that can provide good discriminative representations of both target and background. We accomplish this by exploiting the recovery ability of low-rank matrices. That is if we assume that the data from the same class are linearly correlated, then the corresponding basis vectors learned from the training set of each class shall render the dictionary to become approximately low-rank. The proposed dictionary learning technique incorporates a reconstruction error that improves the reliability of classification. Also, a multiconstraint objective function is designed to enable active learning of a discriminative and robust dictionary. Further, an optimal solution is obtained by iteratively computing the dictionary, coefficients, and by simultaneously learning the classifier parameters. Finally, a simple yet effective likelihood function is implemented to estimate the optimal state of the target during tracking. Moreover, to make the dictionary adaptive to the variations of the target and background during tracking, an online update criterion is employed while learning the new dictionary. Experimental results on a publicly available benchmark dataset have demonstrated that the proposed tracking algorithm performs better than other state-of-the-art trackers.

Improved Student Learning through a Faculty Learning Community: How Faculty Collaboration Transformed a Large-Enrollment Course from Lecture to Student Centered.

PubMed

Elliott, Emily R; Reason, Robert D; Coffman, Clark R; Gangloff, Eric J; Raker, Jeffrey R; Powell-Coffman, Jo Anne; Ogilvie, Craig A

2016-01-01

Undergraduate introductory biology courses are changing based on our growing understanding of how students learn and rapid scientific advancement in the biological sciences. At Iowa State University, faculty instructors are transforming a second-semester large-enrollment introductory biology course to include active learning within the lecture setting. To support this change, we set up a faculty learning community (FLC) in which instructors develop new pedagogies, adapt active-learning strategies to large courses, discuss challenges and progress, critique and revise classroom interventions, and share materials. We present data on how the collaborative work of the FLC led to increased implementation of active-learning strategies and a concurrent improvement in student learning. Interestingly, student learning gains correlate with the percentage of classroom time spent in active-learning modes. Furthermore, student attitudes toward learning biology are weakly positively correlated with these learning gains. At our institution, the FLC framework serves as an agent of iterative emergent change, resulting in the creation of a more student-centered course that better supports learning. © 2016 E. R. Elliott et al. CBE—Life Sciences Education © 2016 The American Society for Cell Biology. This article is distributed by The American Society for Cell Biology under license from the author(s). It is available to the public under an Attribution–Noncommercial–Share Alike 3.0 Unported Creative Commons License (http://creativecommons.org/licenses/by-nc-sa/3.0).

Myria: Scalable Analytics as a Service

NASA Astrophysics Data System (ADS)

Howe, B.; Halperin, D.; Whitaker, A.

2014-12-01

At the UW eScience Institute, we're working to empower non-experts, especially in the sciences, to write and use data-parallel algorithms. To this end, we are building Myria, a web-based platform for scalable analytics and data-parallel programming. Myria's internal model of computation is the relational algebra extended with iteration, such that every program is inherently data-parallel, just as every query in a database is inherently data-parallel. But unlike databases, iteration is a first class concept, allowing us to express machine learning tasks, graph traversal tasks, and more. Programs can be expressed in a number of languages and can be executed on a number of execution environments, but we emphasize a particular language called MyriaL that supports both imperative and declarative styles and a particular execution engine called MyriaX that uses an in-memory column-oriented representation and asynchronous iteration. We deliver Myria over the web as a service, providing an editor, performance analysis tools, and catalog browsing features in a single environment. We find that this web-based "delivery vector" is critical in reaching non-experts: they are insulated from irrelevant effort technical work associated with installation, configuration, and resource management. The MyriaX backend, one of several execution runtimes we support, is a main-memory, column-oriented, RDBMS-on-the-worker system that supports cyclic data flows as a first-class citizen and has been shown to outperform competitive systems on 100-machine cluster sizes. I will describe the Myria system, give a demo, and present some new results in large-scale oceanographic microbiology.

Family learning with mobile devices in the outdoors: Designing an e-Trailguide to facilitate families' joint engagement with the natural world

NASA Astrophysics Data System (ADS)

McClain, Lucy R.

This study describes the implementation of a self-guiding mobile learning tool designed to support families' engagements with the natural world as they explored the flora and fauna along one nature trail at an environmental center. Thirty-one family groups (n = 105 individuals) participated in this study during the summer season and used an iPad-based e-Trailguide during their nature walk. Design-based research methods guided this study's design, which focused on the third iteration of the e-Trailguide. Data included evaluation of families' content knowledge gains related to the local biodiversity as revealed through post-hike interviews, while videorecords of each family's nature walk experience were also collected. Qualitative analyses focused on the design features within the e-Trailguide that supported the families' technology-mediated engagements with nature and their interactions with each other at one Discovery Spot along the nature trail. Findings include: (a) open-ended interviews after the e-Trailguide experience provided a descriptive understanding of the families' conceptual knowledge gains; (b) four place-based design features within the e-Trailguide enabled and supported families' observational, pointing, and tactile investigation engagements with the natural world; (c) parents took on teacher-like roles for their children by connecting information from the e-Trailguide to the natural objects nearby as evidenced through their frequency of pointing gestures; and (d) the development of an analytical framework related to joint observation strategies used between family members to support science-related sense making. Design recommendations for the future implementation of e-Trailguides in outdoor settings include the incorporation of place-based observational questions, place-based textual prompts for focusing observations, drawing activities to record observations, and place-based images to support identification of wildlife. Key words: family learning, engagement, mobile-based learning, outdoor learning, observation, environmental education, informal science learning.

Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

NASA Technical Reports Server (NTRS)

Tran, Loc; Cross, Charles; Montague, Gilbert; Motter, Mark; Neilan, James; Qualls, Garry; Rothhaar, Paul; Trujillo, Anna; Allen, B. Danette

2015-01-01

We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

Integral reinforcement learning for continuous-time input-affine nonlinear systems with simultaneous invariant explorations.

PubMed

Lee, Jae Young; Park, Jin Bae; Choi, Yoon Ho

2015-05-01

This paper focuses on a class of reinforcement learning (RL) algorithms, named integral RL (I-RL), that solve continuous-time (CT) nonlinear optimal control problems with input-affine system dynamics. First, we extend the concepts of exploration, integral temporal difference, and invariant admissibility to the target CT nonlinear system that is governed by a control policy plus a probing signal called an exploration. Then, we show input-to-state stability (ISS) and invariant admissibility of the closed-loop systems with the policies generated by integral policy iteration (I-PI) or invariantly admissible PI (IA-PI) method. Based on these, three online I-RL algorithms named explorized I-PI and integral Q -learning I, II are proposed, all of which generate the same convergent sequences as I-PI and IA-PI under the required excitation condition on the exploration. All the proposed methods are partially or completely model free, and can simultaneously explore the state space in a stable manner during the online learning processes. ISS, invariant admissibility, and convergence properties of the proposed methods are also investigated, and related with these, we show the design principles of the exploration for safe learning. Neural-network-based implementation methods for the proposed schemes are also presented in this paper. Finally, several numerical simulations are carried out to verify the effectiveness of the proposed methods.

Active Learning to Understand Infectious Disease Models and Improve Policy Making

PubMed Central

Vladislavleva, Ekaterina; Broeckhove, Jan; Beutels, Philippe; Hens, Niel

2014-01-01

Modeling plays a major role in policy making, especially for infectious disease interventions but such models can be complex and computationally intensive. A more systematic exploration is needed to gain a thorough systems understanding. We present an active learning approach based on machine learning techniques as iterative surrogate modeling and model-guided experimentation to systematically analyze both common and edge manifestations of complex model runs. Symbolic regression is used for nonlinear response surface modeling with automatic feature selection. First, we illustrate our approach using an individual-based model for influenza vaccination. After optimizing the parameter space, we observe an inverse relationship between vaccination coverage and cumulative attack rate reinforced by herd immunity. Second, we demonstrate the use of surrogate modeling techniques on input-response data from a deterministic dynamic model, which was designed to explore the cost-effectiveness of varicella-zoster virus vaccination. We use symbolic regression to handle high dimensionality and correlated inputs and to identify the most influential variables. Provided insight is used to focus research, reduce dimensionality and decrease decision uncertainty. We conclude that active learning is needed to fully understand complex systems behavior. Surrogate models can be readily explored at no computational expense, and can also be used as emulator to improve rapid policy making in various settings. PMID:24743387

Active learning to understand infectious disease models and improve policy making.

PubMed

Willem, Lander; Stijven, Sean; Vladislavleva, Ekaterina; Broeckhove, Jan; Beutels, Philippe; Hens, Niel

2014-04-01

Modeling plays a major role in policy making, especially for infectious disease interventions but such models can be complex and computationally intensive. A more systematic exploration is needed to gain a thorough systems understanding. We present an active learning approach based on machine learning techniques as iterative surrogate modeling and model-guided experimentation to systematically analyze both common and edge manifestations of complex model runs. Symbolic regression is used for nonlinear response surface modeling with automatic feature selection. First, we illustrate our approach using an individual-based model for influenza vaccination. After optimizing the parameter space, we observe an inverse relationship between vaccination coverage and cumulative attack rate reinforced by herd immunity. Second, we demonstrate the use of surrogate modeling techniques on input-response data from a deterministic dynamic model, which was designed to explore the cost-effectiveness of varicella-zoster virus vaccination. We use symbolic regression to handle high dimensionality and correlated inputs and to identify the most influential variables. Provided insight is used to focus research, reduce dimensionality and decrease decision uncertainty. We conclude that active learning is needed to fully understand complex systems behavior. Surrogate models can be readily explored at no computational expense, and can also be used as emulator to improve rapid policy making in various settings.

Learning to manage complexity through simulation: students' challenges and possible strategies.

PubMed

Gormley, Gerard J; Fenwick, Tara

2016-06-01

Many have called for medical students to learn how to manage complexity in healthcare. This study examines the nuances of students' challenges in coping with a complex simulation learning activity, using concepts from complexity theory, and suggests strategies to help them better understand and manage complexity.Wearing video glasses, participants took part in a simulation ward-based exercise that incorporated characteristics of complexity. Video footage was used to elicit interviews, which were transcribed. Using complexity theory as a theoretical lens, an iterative approach was taken to identify the challenges that participants faced and possible coping strategies using both interview transcripts and video footage.Students' challenges in coping with clinical complexity included being: a) unprepared for 'diving in', b) caught in an escalating system, c) captured by the patient, and d) unable to assert boundaries of acceptable practice.Many characteristics of complexity can be recreated in a ward-based simulation learning activity, affording learners an embodied and immersive experience of these complexity challenges. Possible strategies for managing complexity themes include: a) taking time to size up the system, b) attuning to what emerges, c) reducing complexity, d) boundary practices, and e) working with uncertainty. This study signals pedagogical opportunities for recognizing and dealing with complexity.

Data-Driven Property Estimation for Protective Clothing

DTIC Science & Technology

2014-09-01

reliable predictions falls under the rubric “machine learning”. Inspired by the applications of machine learning in pharmaceutical drug design and...using genetic algorithms, for instance— descriptor selection can be automated as well. A well-known structured learning technique—Artificial Neural...descriptors automatically, by iteration, e.g., using a genetic algorithm [49]. 4.2.4 Avoiding Overfitting A peril of all regression—least squares as

Through the Looking Glass: Adult Education through the Lens of the Australian Journal of Adult Learning over Fifty Years

ERIC Educational Resources Information Center

Harris, Roger; Morrison, Anne

2011-01-01

In this paper we review fifty years of articles published in Australian Journal of Adult Learning in its various iterations. We examine the different roles of the journal: to illuminate the history and trends of adult education authors; to be the flagship of the adult education profession in Australia; to reflect on significant national events;…

An Oracle-based co-training framework for writer identification in offline handwriting

NASA Astrophysics Data System (ADS)

Porwal, Utkarsh; Rajan, Sreeranga; Govindaraju, Venu

2012-01-01

State-of-the-art techniques for writer identification have been centered primarily on enhancing the performance of the system for writer identification. Machine learning algorithms have been used extensively to improve the accuracy of such system assuming sufficient amount of data is available for training. Little attention has been paid to the prospect of harnessing the information tapped in a large amount of un-annotated data. This paper focuses on co-training based framework that can be used for iterative labeling of the unlabeled data set exploiting the independence between the multiple views (features) of the data. This paradigm relaxes the assumption of sufficiency of the data available and tries to generate labeled data from unlabeled data set along with improving the accuracy of the system. However, performance of co-training based framework is dependent on the effectiveness of the algorithm used for the selection of data points to be added in the labeled set. We propose an Oracle based approach for data selection that learns the patterns in the score distribution of classes for labeled data points and then predicts the labels (writers) of the unlabeled data point. This method for selection statistically learns the class distribution and predicts the most probable class unlike traditional selection algorithms which were based on heuristic approaches. We conducted experiments on publicly available IAM dataset and illustrate the efficacy of the proposed approach.

How do medical educators design a curriculum that facilitates student learning about professionalism?

PubMed Central

Mason, Glenn; Wang, Shaoyu

2016-01-01

Objectives This study analyses the ways in which curriculum reform facilitated student learning about professionalism. Methods Design-based research provided the structure for an iterative approach to curriculum change which we undertook over a 3 year period. The learning environment of the Personal and Professional Development Theme (PPD) was analysed through the sociocultural lens of Activity Theory. Lave and Wenger’s and Mezirow’s learning theories informed curriculum reform to support student development of a patient-centred and critically reflective professional identity. The renewed pedagogical outcomes were aligned with curriculum content, learning and teaching processes and assessment, and intense staff education was undertaken. We analysed qualitative data from tutor interviews and free-response student surveys to evaluate the impact of curriculum reform. Results Students’ and tutors’ reflections on learning in PPD converged on two principle themes - ‘Developing a philosophy of medicine’ and ‘Becoming an ethical doctor’- which corresponded to the overarching PPD theme aims of communicative learning. Students and tutors emphasised the importance of the unique learning environment of PPD tutorials for nurturing personal development and the positive impact of the renewed assessment programme on learning. Conclusions A theory-led approach to curriculum reform resulted in student engagement in the PPD curriculum and facilitated a change in student perspective about the epistemological foundation of medicine. PMID:26845777

Unsupervised segmentation of H and E breast images

NASA Astrophysics Data System (ADS)

Hope, Tyna A.; Yaffe, Martin J.

2017-03-01

Heterogeneity of ductal carcinoma in situ (DCIS) continues to be an important topic. Combining biomarker and hematoxylin and eosin (HE) morphology information may provide more insights than either alone. We are working towards a computer-based identification and description system for DCIS. As part of the system we are developing a region of interest finder for further processing, such as identifying DCIS and other HE based measures. The segmentation algorithm is designed to be tolerant of variability in staining and require no user interaction. To achieve stain variation tolerance we use unsupervised learning and iteratively interrogate the image for information. Using simple rules (e.g., "hematoxylin stains nuclei") and iteratively assessing the resultant objects (small hematoxylin stained objects are lymphocytes), the system builds up a knowledge base so that it is not dependent upon manual annotations. The system starts with image resolution-based assumptions but these are replaced by knowledge gained. The algorithm pipeline is designed to find the simplest items first (segment stains), then interesting subclasses and objects (stroma, lymphocytes), and builds information until it is possible to segment blobs that are normal, DCIS, and the range of benign glands. Once the blobs are found, features can be obtained and DCIS detected. In this work we present the early segmentation results with stains where hematoxylin ranges from blue dominant to red dominant in RGB space.

An iterative method for the Helmholtz equation

NASA Technical Reports Server (NTRS)

Bayliss, A.; Goldstein, C. I.; Turkel, E.

1983-01-01

An iterative algorithm for the solution of the Helmholtz equation is developed. The algorithm is based on a preconditioned conjugate gradient iteration for the normal equations. The preconditioning is based on an SSOR sweep for the discrete Laplacian. Numerical results are presented for a wide variety of problems of physical interest and demonstrate the effectiveness of the algorithm.

Young children make their gestural communication systems more language-like: segmentation and linearization of semantic elements in motion events.

PubMed

Clay, Zanna; Pople, Sally; Hood, Bruce; Kita, Sotaro

2014-08-01

Research on Nicaraguan Sign Language, created by deaf children, has suggested that young children use gestures to segment the semantic elements of events and linearize them in ways similar to those used in signed and spoken languages. However, it is unclear whether this is due to children's learning processes or to a more general effect of iterative learning. We investigated whether typically developing children, without iterative learning, segment and linearize information. Gestures produced in the absence of speech to express a motion event were examined in 4-year-olds, 12-year-olds, and adults (all native English speakers). We compared the proportions of gestural expressions that segmented semantic elements into linear sequences and that encoded them simultaneously. Compared with adolescents and adults, children reshaped the holistic stimuli by segmenting and recombining their semantic features into linearized sequences. A control task on recognition memory ruled out the possibility that this was due to different event perception or memory. Young children spontaneously bring fundamental properties of language into their communication system. © The Author(s) 2014.

Analysis Resilient Algorithm on Artificial Neural Network Backpropagation

NASA Astrophysics Data System (ADS)

Saputra, Widodo; Tulus; Zarlis, Muhammad; Widia Sembiring, Rahmat; Hartama, Dedy

2017-12-01

Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. This is a reason to improve a method to accelerate the training. One of Artificial Neural Network (ANN) Backpropagation method is a resilient method. Resilient method of changing weights and bias network with direct adaptation process of weighting based on local gradient information from every learning iteration. Predicting data result of Istanbul Stock Exchange training getting better. Mean Square Error (MSE) value is getting smaller and increasing accuracy.

a Radical Collaborative Approach: Developing a Model for Learning Theory, Human-Based Computation and Participant Motivation in a Rock-Art Heritage Application

NASA Astrophysics Data System (ADS)

Haubt, R.

2016-06-01

This paper explores a Radical Collaborative Approach in the global and centralized Rock-Art Database project to find new ways to look at rock-art by making information more accessible and more visible through public contributions. It looks at rock-art through the Key Performance Indicator (KPI), identified with the latest Australian State of the Environment Reports to help develop a better understanding of rock-art within a broader Cultural and Indigenous Heritage context. Using a practice-led approach the project develops a conceptual collaborative model that is deployed within the RADB Management System. Exploring learning theory, human-based computation and participant motivation the paper develops a procedure for deploying collaborative functions within the interface design of the RADB Management System. The paper presents the results of the collaborative model implementation and discusses considerations for the next iteration of the RADB Universe within an Agile Development Approach.

Progressive Learning of Topic Modeling Parameters: A Visual Analytics Framework.

PubMed

El-Assady, Mennatallah; Sevastjanova, Rita; Sperrle, Fabian; Keim, Daniel; Collins, Christopher

2018-01-01

Topic modeling algorithms are widely used to analyze the thematic composition of text corpora but remain difficult to interpret and adjust. Addressing these limitations, we present a modular visual analytics framework, tackling the understandability and adaptability of topic models through a user-driven reinforcement learning process which does not require a deep understanding of the underlying topic modeling algorithms. Given a document corpus, our approach initializes two algorithm configurations based on a parameter space analysis that enhances document separability. We abstract the model complexity in an interactive visual workspace for exploring the automatic matching results of two models, investigating topic summaries, analyzing parameter distributions, and reviewing documents. The main contribution of our work is an iterative decision-making technique in which users provide a document-based relevance feedback that allows the framework to converge to a user-endorsed topic distribution. We also report feedback from a two-stage study which shows that our technique results in topic model quality improvements on two independent measures.

Health Worker Focused Distributed Simulation for Improving Capability of Health Systems in Liberia.

PubMed

Gale, Thomas C E; Chatterjee, Arunangsu; Mellor, Nicholas E; Allan, Richard J

2016-04-01

The main goal of this study was to produce an adaptable learning platform using virtual learning and distributed simulation, which can be used to train health care workers, across a wide geographical area, key safety messages regarding infection prevention control (IPC). A situationally responsive agile methodology, Scrum, was used to develop a distributed simulation module using short 1-week iterations and continuous synchronous plus asynchronous communication including end users and IPC experts. The module contained content related to standard IPC precautions (including handwashing techniques) and was structured into 3 distinct sections related to donning, doffing, and hazard perception training. Using Scrum methodology, we were able to link concepts applied to best practices in simulation-based medical education (deliberate practice, continuous feedback, self-assessment, and exposure to uncommon events), pedagogic principles related to adult learning (clear goals, contextual awareness, motivational features), and key learning outcomes regarding IPC, as a rapid response initiative to the Ebola outbreak in West Africa. Gamification approach has been used to map learning mechanics to enhance user engagement. The developed IPC module demonstrates how high-frequency, low-fidelity simulations can be rapidly designed using scrum-based agile methodology. Analytics incorporated into the tool can help demonstrate improved confidence and competence of health care workers who are treating patients within an Ebola virus disease outbreak region. These concepts could be used in a range of evolving disasters where rapid development and communication of key learning messages are required.

Sparse Representation with Spatio-Temporal Online Dictionary Learning for Efficient Video Coding.

PubMed

Dai, Wenrui; Shen, Yangmei; Tang, Xin; Zou, Junni; Xiong, Hongkai; Chen, Chang Wen

2016-07-27

Classical dictionary learning methods for video coding suer from high computational complexity and interfered coding eciency by disregarding its underlying distribution. This paper proposes a spatio-temporal online dictionary learning (STOL) algorithm to speed up the convergence rate of dictionary learning with a guarantee of approximation error. The proposed algorithm incorporates stochastic gradient descents to form a dictionary of pairs of 3-D low-frequency and highfrequency spatio-temporal volumes. In each iteration of the learning process, it randomly selects one sample volume and updates the atoms of dictionary by minimizing the expected cost, rather than optimizes empirical cost over the complete training data like batch learning methods, e.g. K-SVD. Since the selected volumes are supposed to be i.i.d. samples from the underlying distribution, decomposition coecients attained from the trained dictionary are desirable for sparse representation. Theoretically, it is proved that the proposed STOL could achieve better approximation for sparse representation than K-SVD and maintain both structured sparsity and hierarchical sparsity. It is shown to outperform batch gradient descent methods (K-SVD) in the sense of convergence speed and computational complexity, and its upper bound for prediction error is asymptotically equal to the training error. With lower computational complexity, extensive experiments validate that the STOL based coding scheme achieves performance improvements than H.264/AVC or HEVC as well as existing super-resolution based methods in ratedistortion performance and visual quality.

SACFIR: SDN-Based Application-Aware Centralized Adaptive Flow Iterative Reconfiguring Routing Protocol for WSNs.

PubMed

Aslam, Muhammad; Hu, Xiaopeng; Wang, Fan

2017-12-13

Smart reconfiguration of a dynamic networking environment is offered by the central control of Software-Defined Networking (SDN). Centralized SDN-based management architectures are capable of retrieving global topology intelligence and decoupling the forwarding plane from the control plane. Routing protocols developed for conventional Wireless Sensor Networks (WSNs) utilize limited iterative reconfiguration methods to optimize environmental reporting. However, the challenging networking scenarios of WSNs involve a performance overhead due to constant periodic iterative reconfigurations. In this paper, we propose the SDN-based Application-aware Centralized adaptive Flow Iterative Reconfiguring (SACFIR) routing protocol with the centralized SDN iterative solver controller to maintain the load-balancing between flow reconfigurations and flow allocation cost. The proposed SACFIR's routing protocol offers a unique iterative path-selection algorithm, which initially computes suitable clustering based on residual resources at the control layer and then implements application-aware threshold-based multi-hop report transmissions on the forwarding plane. The operation of the SACFIR algorithm is centrally supervised by the SDN controller residing at the Base Station (BS). This paper extends SACFIR to SDN-based Application-aware Main-value Centralized adaptive Flow Iterative Reconfiguring (SAMCFIR) to establish both proactive and reactive reporting. The SAMCFIR transmission phase enables sensor nodes to trigger direct transmissions for main-value reports, while in the case of SACFIR, all reports follow computed routes. Our SDN-enabled proposed models adjust the reconfiguration period according to the traffic burden on sensor nodes, which results in heterogeneity awareness, load-balancing and application-specific reconfigurations of WSNs. Extensive experimental simulation-based results show that SACFIR and SAMCFIR yield the maximum scalability, network lifetime and stability period when compared to existing routing protocols.

SACFIR: SDN-Based Application-Aware Centralized Adaptive Flow Iterative Reconfiguring Routing Protocol for WSNs

PubMed Central

Hu, Xiaopeng; Wang, Fan

2017-01-01

Smart reconfiguration of a dynamic networking environment is offered by the central control of Software-Defined Networking (SDN). Centralized SDN-based management architectures are capable of retrieving global topology intelligence and decoupling the forwarding plane from the control plane. Routing protocols developed for conventional Wireless Sensor Networks (WSNs) utilize limited iterative reconfiguration methods to optimize environmental reporting. However, the challenging networking scenarios of WSNs involve a performance overhead due to constant periodic iterative reconfigurations. In this paper, we propose the SDN-based Application-aware Centralized adaptive Flow Iterative Reconfiguring (SACFIR) routing protocol with the centralized SDN iterative solver controller to maintain the load-balancing between flow reconfigurations and flow allocation cost. The proposed SACFIR’s routing protocol offers a unique iterative path-selection algorithm, which initially computes suitable clustering based on residual resources at the control layer and then implements application-aware threshold-based multi-hop report transmissions on the forwarding plane. The operation of the SACFIR algorithm is centrally supervised by the SDN controller residing at the Base Station (BS). This paper extends SACFIR to SDN-based Application-aware Main-value Centralized adaptive Flow Iterative Reconfiguring (SAMCFIR) to establish both proactive and reactive reporting. The SAMCFIR transmission phase enables sensor nodes to trigger direct transmissions for main-value reports, while in the case of SACFIR, all reports follow computed routes. Our SDN-enabled proposed models adjust the reconfiguration period according to the traffic burden on sensor nodes, which results in heterogeneity awareness, load-balancing and application-specific reconfigurations of WSNs. Extensive experimental simulation-based results show that SACFIR and SAMCFIR yield the maximum scalability, network lifetime and stability period when compared to existing routing protocols. PMID:29236031

Refining a learning progression of energy

NASA Astrophysics Data System (ADS)

Yao, Jian-Xin; Guo, Yu-Ying; Neumann, Knut

2017-11-01

This paper presents a revised learning progression for the energy concept and initial findings on diverse progressions among subgroups of sample students. The revised learning progression describes how students progress towards an understanding of the energy concept along two progress variables identified from previous studies - key ideas about energy and levels of conceptual development. To assess students understanding with respect to the revised learning progression, we created a specific instrument, the Energy Concept Progression Assessment (ECPA) based on previous work on assessing students' understanding of energy. After iteratively refining the instrument in two pilot studies, the ECPA was administered to a total of 4550 students (Grades 8-12) from schools in two districts in a major city in Mainland China. Rasch analysis was used to examine the validity of the revised learning progression and explore factors explaining different progressions. Our results confirm the validity of the four conceptual development levels. In addition, we found that although following a similar progression pattern, students' progression rate was significantly influenced by environmental factors such as school type. In the discussion of our findings, we address the non-linear and complex nature of students' progression in understanding energy. We conclude with illuminating our research's implication for curriculum design and energy teaching.

Using a Systematic Approach and Theoretical Framework to Design a Curriculum for the Shaping Healthy Choices Program.

PubMed

Linnell, Jessica D; Zidenberg-Cherr, Sheri; Briggs, Marilyn; Scherr, Rachel E; Brian, Kelley M; Hillhouse, Carol; Smith, Martin H

2016-01-01

To examine the use of a systematic approach and theoretical framework to develop an inquiry-based, garden-enhanced nutrition curriculum for the Shaping Healthy Choices Program. Curriculum development occurred in 3 steps: identification of learning objectives, determination of evidence of learning, and activity development. Curriculum activities were further refined through pilot-testing, which was conducted in 2 phases. Formative data collected during pilot-testing resulted in improvements to activities. Using a systematic, iterative process resulted in a curriculum called Discovering Healthy Choices, which has a strong foundation in Social Cognitive Theory and constructivist learning theory. Furthermore, the Backward Design method provided the design team with a systematic approach to ensure activities addressed targeted learning objectives and overall Shaping Healthy Choices Program goals. The process by which a nutrition curriculum is developed may have a direct effect on student outcomes. Processes by which nutrition curricula are designed and learning objectives are selected, and how theory and pedagogy are applied should be further investigated so that effective approaches to developing garden-enhanced nutrition interventions can be determined and replicated. Copyright © 2016 Society for Nutrition Education and Behavior. Published by Elsevier Inc. All rights reserved.

Innovative Graduate Research Education for Advancement of Implementation Science in Adolescent Behavioral Health

PubMed Central

Levin, Bruce Lubotsky; Massey, Tom; Baldwin, Julie; Williamson, Heather

2016-01-01

An innovative approach to research education that integrates the theory and principles of implementation science, participatory research, and service learning in the area of adolescent behavioral health is presented. Qualitative interviews and surveys of program participants have been conducted to assess the program’s curricula, service-learning partnerships, student (scholar) satisfaction, and views of community partnerships and academic mentors. The Institute has experienced the successful completion of its first and second cohorts and enrollment of a third cohort of scholars. Community partners are utilizing results of service-learning projects to influence agency operations. Institute scholars have identified research and service learning experiences as key factors in the decision to apply to the Institute graduate certificate program. The availability of tuition support is identified as valuable but not ranked as the most important reason for scholar interest in the program. Academic mentors report positive relationships with community agencies. Future iterations of the program will expand options for distance learning and alternatives to traditional graduate education for community-based scholars. Community partner agency capacity for participation is expected to change over time. Methods are being identified to both sustain existing partnerships and develop new community partnership relationships. PMID:26746638

Innovative Graduate Research Education for Advancement of Implementation Science in Adolescent Behavioral Health.

PubMed

Burton, Donna L; Levin, Bruce Lubotsky; Massey, Tom; Baldwin, Julie; Williamson, Heather

2016-04-01

An innovative approach to research education that integrates the theory and principles of implementation science, participatory research, and service learning in the area of adolescent behavioral health is presented. Qualitative interviews and surveys of program participants have been conducted to assess the program's curricula, service-learning partnerships, student (scholar) satisfaction, and views of community partnerships and academic mentors. The Institute has experienced the successful completion of its first and second cohorts and enrollment of a third cohort of scholars. Community partners are utilizing results of service-learning projects to influence agency operations. Institute scholars have identified research and service learning experiences as key factors in the decision to apply to the Institute graduate certificate program. The availability of tuition support is identified as valuable but not ranked as the most important reason for scholar interest in the program. Academic mentors report positive relationships with community agencies. Future iterations of the program will expand options for distance learning and alternatives to traditional graduate education for community-based scholars. Community partner agency capacity for participation is expected to change over time. Methods are being identified to both sustain existing partnerships and develop new community partnership relationships.

Nested Conjugate Gradient Algorithm with Nested Preconditioning for Non-linear Image Restoration.

PubMed

Skariah, Deepak G; Arigovindan, Muthuvel

2017-06-19

We develop a novel optimization algorithm, which we call Nested Non-Linear Conjugate Gradient algorithm (NNCG), for image restoration based on quadratic data fitting and smooth non-quadratic regularization. The algorithm is constructed as a nesting of two conjugate gradient (CG) iterations. The outer iteration is constructed as a preconditioned non-linear CG algorithm; the preconditioning is performed by the inner CG iteration that is linear. The inner CG iteration, which performs preconditioning for outer CG iteration, itself is accelerated by an another FFT based non-iterative preconditioner. We prove that the method converges to a stationary point for both convex and non-convex regularization functionals. We demonstrate experimentally that proposed method outperforms the well-known majorization-minimization method used for convex regularization, and a non-convex inertial-proximal method for non-convex regularization functional.

Adaptive Management of Ecosystems

EPA Science Inventory

Adaptive management is an approach to natural resource management that emphasizes learning through management. As such, management may be treated as experiment, with replication, or management may be conducted in an iterative manner. Although the concept has resonated with many...

Introductory Statistics in the Garden

ERIC Educational Resources Information Center

Wagaman, John C.

2017-01-01

This article describes four semesters of introductory statistics courses that incorporate service learning and gardening into the curriculum with applications of the binomial distribution, least squares regression and hypothesis testing. The activities span multiple semesters and are iterative in nature.

Robust iterative learning contouring controller with disturbance observer for machine tool feed drives.

PubMed

Simba, Kenneth Renny; Bui, Ba Dinh; Msukwa, Mathew Renny; Uchiyama, Naoki

2018-04-01

In feed drive systems, particularly machine tools, a contour error is more significant than the individual axial tracking errors from the view point of enhancing precision in manufacturing and production systems. The contour error must be within the permissible tolerance of given products. In machining complex or sharp-corner products, large contour errors occur mainly owing to discontinuous trajectories and the existence of nonlinear uncertainties. Therefore, it is indispensable to design robust controllers that can enhance the tracking ability of feed drive systems. In this study, an iterative learning contouring controller consisting of a classical Proportional-Derivative (PD) controller and disturbance observer is proposed. The proposed controller was evaluated experimentally by using a typical sharp-corner trajectory, and its performance was compared with that of conventional controllers. The results revealed that the maximum contour error can be reduced by about 37% on average. Copyright © 2018 ISA. Published by Elsevier Ltd. All rights reserved.

Ground Truth Creation for Complex Clinical NLP Tasks - an Iterative Vetting Approach and Lessons Learned.

PubMed

Liang, Jennifer J; Tsou, Ching-Huei; Devarakonda, Murthy V

2017-01-01

Natural language processing (NLP) holds the promise of effectively analyzing patient record data to reduce cognitive load on physicians and clinicians in patient care, clinical research, and hospital operations management. A critical need in developing such methods is the "ground truth" dataset needed for training and testing the algorithms. Beyond localizable, relatively simple tasks, ground truth creation is a significant challenge because medical experts, just as physicians in patient care, have to assimilate vast amounts of data in EHR systems. To mitigate potential inaccuracies of the cognitive challenges, we present an iterative vetting approach for creating the ground truth for complex NLP tasks. In this paper, we present the methodology, and report on its use for an automated problem list generation task, its effect on the ground truth quality and system accuracy, and lessons learned from the effort.

An integrated method for atherosclerotic carotid plaque segmentation in ultrasound image.

PubMed

Qian, Chunjun; Yang, Xiaoping

2018-01-01

Carotid artery atherosclerosis is an important cause of stroke. Ultrasound imaging has been widely used in the diagnosis of atherosclerosis. Therefore, segmenting atherosclerotic carotid plaque in ultrasound image is an important task. Accurate plaque segmentation is helpful for the measurement of carotid plaque burden. In this paper, we propose and evaluate a novel learning-based integrated framework for plaque segmentation. In our study, four different classification algorithms, along with the auto-context iterative algorithm, were employed to effectively integrate features from ultrasound images and later also the iteratively estimated and refined probability maps together for pixel-wise classification. The four classification algorithms were support vector machine with linear kernel, support vector machine with radial basis function kernel, AdaBoost and random forest. The plaque segmentation was implemented in the generated probability map. The performance of the four different learning-based plaque segmentation methods was tested on 29 B-mode ultrasound images. The evaluation indices for our proposed methods were consisted of sensitivity, specificity, Dice similarity coefficient, overlap index, error of area, absolute error of area, point-to-point distance, and Hausdorff point-to-point distance, along with the area under the ROC curve. The segmentation method integrated the random forest and an auto-context model obtained the best results (sensitivity 80.4 ± 8.4%, specificity 96.5 ± 2.0%, Dice similarity coefficient 81.0 ± 4.1%, overlap index 68.3 ± 5.8%, error of area -1.02 ± 18.3%, absolute error of area 14.7 ± 10.9%, point-to-point distance 0.34 ± 0.10 mm, Hausdorff point-to-point distance 1.75 ± 1.02 mm, and area under the ROC curve 0.897), which were almost the best, compared with that from the existed methods. Our proposed learning-based integrated framework investigated in this study could be useful for atherosclerotic carotid plaque segmentation, which will be helpful for the measurement of carotid plaque burden. Copyright © 2017 Elsevier B.V. All rights reserved.

Publishing activities improves undergraduate biology education

PubMed Central

Smith, Michelle K

2018-01-01

Abstract To improve undergraduate biology education, there is an urgent need for biology instructors to publish their innovative active-learning instructional materials in peer-reviewed journals. To do this, instructors can measure student knowledge about a variety of biology concepts, iteratively design activities, explore student learning outcomes and publish the results. Creating a set of well-vetted activities, searchable through a journal interface, saves other instructors time and encourages the use of active-learning instructional practices. For authors, these publications offer new opportunities to collaborate and can provide evidence of a commitment to using active-learning instructional techniques in the classroom. PMID:29672697

Publishing activities improves undergraduate biology education.

PubMed

Smith, Michelle K

2018-06-01

To improve undergraduate biology education, there is an urgent need for biology instructors to publish their innovative active-learning instructional materials in peer-reviewed journals. To do this, instructors can measure student knowledge about a variety of biology concepts, iteratively design activities, explore student learning outcomes and publish the results. Creating a set of well-vetted activities, searchable through a journal interface, saves other instructors time and encourages the use of active-learning instructional practices. For authors, these publications offer new opportunities to collaborate and can provide evidence of a commitment to using active-learning instructional techniques in the classroom.

A Fast Optimization Method for General Binary Code Learning.

PubMed

Shen, Fumin; Zhou, Xiang; Yang, Yang; Song, Jingkuan; Shen, Heng; Tao, Dacheng

2016-09-22

Hashing or binary code learning has been recognized to accomplish efficient near neighbor search, and has thus attracted broad interests in recent retrieval, vision and learning studies. One main challenge of learning to hash arises from the involvement of discrete variables in binary code optimization. While the widely-used continuous relaxation may achieve high learning efficiency, the pursued codes are typically less effective due to accumulated quantization error. In this work, we propose a novel binary code optimization method, dubbed Discrete Proximal Linearized Minimization (DPLM), which directly handles the discrete constraints during the learning process. Specifically, the discrete (thus nonsmooth nonconvex) problem is reformulated as minimizing the sum of a smooth loss term with a nonsmooth indicator function. The obtained problem is then efficiently solved by an iterative procedure with each iteration admitting an analytical discrete solution, which is thus shown to converge very fast. In addition, the proposed method supports a large family of empirical loss functions, which is particularly instantiated in this work by both a supervised and an unsupervised hashing losses, together with the bits uncorrelation and balance constraints. In particular, the proposed DPLM with a supervised `2 loss encodes the whole NUS-WIDE database into 64-bit binary codes within 10 seconds on a standard desktop computer. The proposed approach is extensively evaluated on several large-scale datasets and the generated binary codes are shown to achieve very promising results on both retrieval and classification tasks.

Reinforcement learning for partially observable dynamic processes: adaptive dynamic programming using measured output data.

PubMed

Lewis, F L; Vamvoudakis, Kyriakos G

2011-02-01

Approximate dynamic programming (ADP) is a class of reinforcement learning methods that have shown their importance in a variety of applications, including feedback control of dynamical systems. ADP generally requires full information about the system internal states, which is usually not available in practical situations. In this paper, we show how to implement ADP methods using only measured input/output data from the system. Linear dynamical systems with deterministic behavior are considered herein, which are systems of great interest in the control system community. In control system theory, these types of methods are referred to as output feedback (OPFB). The stochastic equivalent of the systems dealt with in this paper is a class of partially observable Markov decision processes. We develop both policy iteration and value iteration algorithms that converge to an optimal controller that requires only OPFB. It is shown that, similar to Q -learning, the new methods have the important advantage that knowledge of the system dynamics is not needed for the implementation of these learning algorithms or for the OPFB control. Only the order of the system, as well as an upper bound on its "observability index," must be known. The learned OPFB controller is in the form of a polynomial autoregressive moving-average controller that has equivalent performance with the optimal state variable feedback gain.

“They Have to Adapt to Learn”: Surgeons’ Perspectives on the Role of Procedural Variation in Surgical Education

PubMed Central

Apramian, Tavis; Cristancho, Sayra; Watling, Chris; Ott, Michael; Lingard, Lorelei

2017-01-01

OBJECTIVE Clinical research increasingly acknowledges the existence of significant procedural variation in surgical practice. This study explored surgeons’ perspectives regarding the influence of intersurgeon procedural variation on the teaching and learning of surgical residents. DESIGN AND SETTING This qualitative study used a grounded theory-based analysis of observational and interview data. Observational data were collected in 3 tertiary care teaching hospitals in Ontario, Canada. Semistructured interviews explored potential procedural variations arising during the observations and prompts from an iteratively refined guide. Ongoing data analysis refined the theoretical framework and informed data collection strategies, as prescribed by the iterative nature of grounded theory research. PARTICIPANTS Our sample included 99 hours of observation across 45 cases with 14 surgeons. Semistructured, audio-recorded interviews (n = 14) occurred immediately following observational periods. RESULTS Surgeons endorsed the use of intersurgeon procedural variations to teach residents about adapting to the complexity of surgical practice and the norms of surgical culture. Surgeons suggested that residents’ efforts to identify thresholds of principle and preference are crucial to professional development. Principles that emerged from the study included the following: (1) knowing what comes next, (2) choosing the right plane, (3) handling tissue appropriately, (4) recognizing the abnormal, and (5) making safe progress. Surgeons suggested that learning to follow these principles while maintaining key aspects of surgical culture, like autonomy and individuality, are important social processes in surgical education. CONCLUSIONS Acknowledging intersurgeon variation has important implications for curriculum development and workplace-based assessment in surgical education. Adapting to intersurgeon procedural variations may foster versatility in surgical residents. However, the existence of procedural variations and their active use in surgeons’ teaching raises questions about the lack of attention to this form of complexity in current workplace-based assessment strategies. Failure to recognize the role of such variations may threaten the implementation of competency-based medical education in surgery. PMID:26705062

Approximately adaptive neural cooperative control for nonlinear multiagent systems with performance guarantee

NASA Astrophysics Data System (ADS)

Wang, Jing; Yang, Tianyu; Staskevich, Gennady; Abbe, Brian

2017-04-01

This paper studies the cooperative control problem for a class of multiagent dynamical systems with partially unknown nonlinear system dynamics. In particular, the control objective is to solve the state consensus problem for multiagent systems based on the minimisation of certain cost functions for individual agents. Under the assumption that there exist admissible cooperative controls for such class of multiagent systems, the formulated problem is solved through finding the optimal cooperative control using the approximate dynamic programming and reinforcement learning approach. With the aid of neural network parameterisation and online adaptive learning, our method renders a practically implementable approximately adaptive neural cooperative control for multiagent systems. Specifically, based on the Bellman's principle of optimality, the Hamilton-Jacobi-Bellman (HJB) equation for multiagent systems is first derived. We then propose an approximately adaptive policy iteration algorithm for multiagent cooperative control based on neural network approximation of the value functions. The convergence of the proposed algorithm is rigorously proved using the contraction mapping method. The simulation results are included to validate the effectiveness of the proposed algorithm.

Transforming a Traditional Inquiry-Based Science Unit into a STEM Unit for Elementary Pre-service Teachers: A View from the Trenches

NASA Astrophysics Data System (ADS)

Schmidt, Matthew; Fulton, Lori

2016-04-01

The need to prepare students with twenty-first-century skills through STEM-related teaching is strong, especially at the elementary level. However, most teacher education preparation programs do not focus on STEM education. In an attempt to provide an exemplary model of a STEM unit, we used a rapid prototyping approach to transform an inquiry-based unit on moon phases into one that integrated technology in a meaningful manner to develop technological literacy and scientific concepts for pre-service teachers (PSTs). Using qualitative case study methodology, we describe lessons learned related to the development and implementation of a STEM unit in an undergraduate elementary methods course, focusing on the impact the inquiry model had on PSTs' perceptions of inquiry-based science instruction and how the integration of technology impacted their learning experience. Using field notes and survey data, we uncovered three overarching themes. First, we found that PSTs held absolutist beliefs and had a need for instruction on inquiry-based learning and teaching. Second, we determined that explicit examples of effective and ineffective technology use are needed to help PSTs develop an understanding of meaningful technology integration. Finally, the rapid prototyping approach resulted in a successful modification of the unit, but caused the usability of our digital instructional materials to suffer. Our findings suggest that while inquiry-based STEM units can be implemented in existing programs, creating and testing these prototypes requires significant effort to meet PSTs' learning needs, and that iterating designs is essential to successful implementation.

Design principles for simulation games for learning clinical reasoning: A design-based research approach.

PubMed

Koivisto, J-M; Haavisto, E; Niemi, H; Haho, P; Nylund, S; Multisilta, J

2018-01-01

Nurses sometimes lack the competence needed for recognising deterioration in patient conditions and this is often due to poor clinical reasoning. There is a need to develop new possibilities for learning this crucial competence area. In addition, educators need to be future oriented; they need to be able to design and adopt new pedagogical innovations. The purpose of the study is to describe the development process and to generate principles for the design of nursing simulation games. A design-based research methodology is applied in this study. Iterative cycles of analysis, design, development, testing and refinement were conducted via collaboration among researchers, educators, students, and game designers. The study facilitated the generation of reusable design principles for simulation games to guide future designers when designing and developing simulation games for learning clinical reasoning. This study makes a major contribution to research on simulation game development in the field of nursing education. The results of this study provide important insights into the significance of involving nurse educators in the design and development process of educational simulation games for the purpose of nursing education. Copyright © 2017 Elsevier Ltd. All rights reserved.

After-School Spaces: Looking for Learning in All the Right Places

NASA Astrophysics Data System (ADS)

Schnittka, Christine G.; Evans, Michael A.; Won, Samantha G. L.; Drape, Tiffany A.

2016-06-01

After-school settings provide youth with homework support, social outlets and fun activities, and help build self-confidence. They are safe places for forming relationships with caring adults. More after-school settings are starting to integrate Science, Technology, Engineering, and Mathematics (STEM) topics. What science skills and concepts might youth learn in engineering design-based after-school settings? Traditional assessments often fail to capture the ways youth learn in informal settings, and deep science understandings are notoriously difficult to measure. In this study, we examined three after-school settings where 65 youth were learning science through engineering design challenges. In this informal setting, we examined storyboards, social networking forum (SNF) chat logs, videos of whole-class interactions, interviews with groups and single participants, and traditional multiple-choice pre- and posttest results. As we looked for evidence of learning, we found that the social networking forum was rich with data. Interviews were even more informative, much more so than traditional pencil and paper multiple-choice tests. We found that different kinds of elicitation strategies adopted by site leaders and facilitators played an important role in the ways youth constructed knowledge. These elicitation strategies also helped us find evidence of learning. Based on findings, future iterations of the curricula will involve tighter integration of social networking forums, continued use of videotaped interviews for data collection, an increased focus on training site leaders and facilitators in elicitation strategies, and more open-ended pencil and paper assessments in order to facilitate the process of looking for learning.

Iterative Methods for the Non-LTE Transfer of Polarized Radiation: Resonance Line Polarization in One-dimensional Atmospheres

NASA Astrophysics Data System (ADS)

Trujillo Bueno, Javier; Manso Sainz, Rafael

1999-05-01

This paper shows how to generalize to non-LTE polarization transfer some operator splitting methods that were originally developed for solving unpolarized transfer problems. These are the Jacobi-based accelerated Λ-iteration (ALI) method of Olson, Auer, & Buchler and the iterative schemes based on Gauss-Seidel and successive overrelaxation (SOR) iteration of Trujillo Bueno and Fabiani Bendicho. The theoretical framework chosen for the formulation of polarization transfer problems is the quantum electrodynamics (QED) theory of Landi Degl'Innocenti, which specifies the excitation state of the atoms in terms of the irreducible tensor components of the atomic density matrix. This first paper establishes the grounds of our numerical approach to non-LTE polarization transfer by concentrating on the standard case of scattering line polarization in a gas of two-level atoms, including the Hanle effect due to a weak microturbulent and isotropic magnetic field. We begin demonstrating that the well-known Λ-iteration method leads to the self-consistent solution of this type of problem if one initializes using the ``exact'' solution corresponding to the unpolarized case. We show then how the above-mentioned splitting methods can be easily derived from this simple Λ-iteration scheme. We show that our SOR method is 10 times faster than the Jacobi-based ALI method, while our implementation of the Gauss-Seidel method is 4 times faster. These iterative schemes lead to the self-consistent solution independently of the chosen initialization. The convergence rate of these iterative methods is very high; they do not require either the construction or the inversion of any matrix, and the computing time per iteration is similar to that of the Λ-iteration method.

Virtual reality and gaming systems to improve walking and mobility for people with musculoskeletal and neuromuscular conditions.

PubMed

Deutsch, Judith E

2009-01-01

Improving walking for individuals with musculoskeletal and neuromuscular conditions is an important aspect of rehabilitation. The capabilities of clinicians who address these rehabilitation issues could be augmented with innovations such as virtual reality gaming based technologies. The chapter provides an overview of virtual reality gaming based technologies currently being developed and tested to improve motor and cognitive elements required for ambulation and mobility in different patient populations. Included as well is a detailed description of a single VR system, consisting of the rationale for development and iterative refinement of the system based on clinical science. These concepts include: neural plasticity, part-task training, whole task training, task specific training, principles of exercise and motor learning, sensorimotor integration, and visual spatial processing.

Advanced Agent Methods in Adversarial Environment

DTIC Science & Technology

2005-11-30

2 Contents Contents 1 Introduction – Technical Statement of Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.1...37 5.4.1 Deriving Trust Observations from Coalition Cooperation Results . . . . . . . . . . . 37 Contents 3 5.4.2 Iterative Learning of...85 4 Contents A.3.5 Class Finder

Improving Group Work Practices in Teaching Life Sciences: Trialogical Learning

NASA Astrophysics Data System (ADS)

Tammeorg, Priit; Mykkänen, Anna; Rantamäki, Tomi; Lakkala, Minna; Muukkonen, Hanni

2017-08-01

Trialogical learning, a collaborative and iterative knowledge creation process using real-life artefacts or problems, familiarizes students with working life environments and aims to teach skills required in the professional world. We target one of the major limitation factors for optimal trialogical learning in university settings, inefficient group work. We propose a course design combining effective group working practices with trialogical learning principles in life sciences. We assess the usability of our design in (a) a case study on crop science education and (b) a questionnaire for university teachers in life science fields. Our approach was considered useful and supportive of the learning process by all the participants in the case study: the students, the stakeholders and the facilitator. Correspondingly, a group of university teachers expressed that the trialogical approach and the involvement of stakeholders could promote efficient learning. In our case in life sciences, we identified the key issues in facilitating effective group work to be the design of meaningful tasks and the allowance of sufficient time to take action based on formative feedback. Even though trialogical courses can be time consuming, the experience of applying knowledge in real-life cases justifies using the approach, particularly for students just about to enter their professional careers.

Convex Formulations of Learning from Crowds

NASA Astrophysics Data System (ADS)

Kajino, Hiroshi; Kashima, Hisashi

It has attracted considerable attention to use crowdsourcing services to collect a large amount of labeled data for machine learning, since crowdsourcing services allow one to ask the general public to label data at very low cost through the Internet. The use of crowdsourcing has introduced a new challenge in machine learning, that is, coping with low quality of crowd-generated data. There have been many recent attempts to address the quality problem of multiple labelers, however, there are two serious drawbacks in the existing approaches, that are, (i) non-convexity and (ii) task homogeneity. Most of the existing methods consider true labels as latent variables, which results in non-convex optimization problems. Also, the existing models assume only single homogeneous tasks, while in realistic situations, clients can offer multiple tasks to crowds and crowd workers can work on different tasks in parallel. In this paper, we propose a convex optimization formulation of learning from crowds by introducing personal models of individual crowds without estimating true labels. We further extend the proposed model to multi-task learning based on the resemblance between the proposed formulation and that for an existing multi-task learning model. We also devise efficient iterative methods for solving the convex optimization problems by exploiting conditional independence structures in multiple classifiers.

Experimental search for high-temperature ferroelectric perovskites guided by two-step machine learning.

PubMed

Balachandran, Prasanna V; Kowalski, Benjamin; Sehirlioglu, Alp; Lookman, Turab

2018-04-26

Experimental search for high-temperature ferroelectric perovskites is a challenging task due to the vast chemical space and lack of predictive guidelines. Here, we demonstrate a two-step machine learning approach to guide experiments in search of xBi[Formula: see text]O 3 -(1 - x)PbTiO 3 -based perovskites with high ferroelectric Curie temperature. These involve classification learning to screen for compositions in the perovskite structures, and regression coupled to active learning to identify promising perovskites for synthesis and feedback. The problem is challenging because the search space is vast, spanning ~61,500 compositions and only 167 are experimentally studied. Furthermore, not every composition can be synthesized in the perovskite phase. In this work, we predict x, y, Me', and Me″ such that the resulting compositions have both high Curie temperature and form in the perovskite structure. Outcomes from both successful and failed experiments then iteratively refine the machine learning models via an active learning loop. Our approach finds six perovskites out of ten compositions synthesized, including three previously unexplored {Me'Me″} pairs, with 0.2Bi(Fe 0.12 Co 0.88 )O 3 -0.8PbTiO 3 showing the highest measured Curie temperature of 898 K among them.

Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses

NASA Astrophysics Data System (ADS)

Huang, Haiping

2017-05-01

Revealing hidden features in unlabeled data is called unsupervised feature learning, which plays an important role in pretraining a deep neural network. Here we provide a statistical mechanics analysis of the unsupervised learning in a restricted Boltzmann machine with binary synapses. A message passing equation to infer the hidden feature is derived, and furthermore, variants of this equation are analyzed. A statistical analysis by replica theory describes the thermodynamic properties of the model. Our analysis confirms an entropy crisis preceding the non-convergence of the message passing equation, suggesting a discontinuous phase transition as a key characteristic of the restricted Boltzmann machine. Continuous phase transition is also confirmed depending on the embedded feature strength in the data. The mean-field result under the replica symmetric assumption agrees with that obtained by running message passing algorithms on single instances of finite sizes. Interestingly, in an approximate Hopfield model, the entropy crisis is absent, and a continuous phase transition is observed instead. We also develop an iterative equation to infer the hyper-parameter (temperature) hidden in the data, which in physics corresponds to iteratively imposing Nishimori condition. Our study provides insights towards understanding the thermodynamic properties of the restricted Boltzmann machine learning, and moreover important theoretical basis to build simplified deep networks.

Preparing pre-service teachers to integrate technology into inquiry-based science education: Three case studies in The Netherlands

NASA Astrophysics Data System (ADS)

Tran, Trinh-Ba; van den Berg, Ed; Ellermeijer, Ton; Beishuizen, Jos

2016-05-01

Integration of technology ( e.g. measuring with sensors, video measurement, and modeling) into secondary-school science teaching is a need globally recognized. A central issue of incorporating these technologies in teaching is how to turn manipulations of equipment and software into manipulations of ideas. Therefore, preparation for pre-service teachers to apply ICT tools should be combined with the issues of minds-on inquiring and meaning-making. From this perspective, we developed a course within the post-graduate teacher-education program in the Netherlands. During the course, pre-service teachers learnt not only to master ICT skills but also to design, teach, and evaluate an inquiry-based lesson in which the ICT tool was integrated. Besides three life sessions, teachers' learning scenario also consisted of individual tasks which teachers could carry out mostly in the school or at home with support materials and online assistance. We taught three iterations of the course within a design-research framework in 2013, 2014 and collected data on the teacher learning processes and outcomes. The analyses of these data from observation, interviews, questionnaires, and documents were to evaluate implementation of the course, then suggest for revisions of the course set-up, which was executed and then assessed again in a subsequent case study. Main outcomes of the three case studies can be summarized as follows: within a limited time (3 life sessions spread over 2-3 months), the heterogeneous groups of pre-service teachers achieved a reasonable level of competence regarding the use of ICT tools in inquiry-based lessons. The blended set-up with support materials, especially the Coach activities and the lesson-plan form for an ICT-integrated inquiry-based lesson, contributed to this result under the condition that the course participants really spent considerable time outside the life sessions. There was a need for more time for hands-on, in-group activities in life sessions and more detailed feedback on individual reports of pre-service teachers. The majority of the pre-service teachers were able to design a lesson plan aimed at a certain inquiry level with integration of ICT, but just a few could implement it faithfully in the classroom. There was still a considerable difference between intended inquiry activities and actual realized inquiry which parallels results from the literature for experienced teachers. The participants had to struggle with science --ICT conceptual issues as well as getting their students to focus on inquiry and concept learning in the classroom. Each evaluation guided iteration of the course resulted in better learning outcomes.

Automated Knowledge Discovery From Simulators

NASA Technical Reports Server (NTRS)

Burl, Michael; DeCoste, Dennis; Mazzoni, Dominic; Scharenbroich, Lucas; Enke, Brian; Merline, William

2007-01-01

A computational method, SimLearn, has been devised to facilitate efficient knowledge discovery from simulators. Simulators are complex computer programs used in science and engineering to model diverse phenomena such as fluid flow, gravitational interactions, coupled mechanical systems, and nuclear, chemical, and biological processes. SimLearn uses active-learning techniques to efficiently address the "landscape characterization problem." In particular, SimLearn tries to determine which regions in "input space" lead to a given output from the simulator, where "input space" refers to an abstraction of all the variables going into the simulator, e.g., initial conditions, parameters, and interaction equations. Landscape characterization can be viewed as an attempt to invert the forward mapping of the simulator and recover the inputs that produce a particular output. Given that a single simulation run can take days or weeks to complete even on a large computing cluster, SimLearn attempts to reduce costs by reducing the number of simulations needed to effect discoveries. Unlike conventional data-mining methods that are applied to static predefined datasets, SimLearn involves an iterative process in which a most informative dataset is constructed dynamically by using the simulator as an oracle. On each iteration, the algorithm models the knowledge it has gained through previous simulation trials and then chooses which simulation trials to run next. Running these trials through the simulator produces new data in the form of input-output pairs. The overall process is embodied in an algorithm that combines support vector machines (SVMs) with active learning. SVMs use learning from examples (the examples are the input-output pairs generated by running the simulator) and a principle called maximum margin to derive predictors that generalize well to new inputs. In SimLearn, the SVM plays the role of modeling the knowledge that has been gained through previous simulation trials. Active learning is used to determine which new input points would be most informative if their output were known. The selected input points are run through the simulator to generate new information that can be used to refine the SVM. The process is then repeated. SimLearn carefully balances exploration (semi-randomly searching around the input space) versus exploitation (using the current state of knowledge to conduct a tightly focused search). During each iteration, SimLearn uses not one, but an ensemble of SVMs. Each SVM in the ensemble is characterized by different hyper-parameters that control various aspects of the learned predictor - for example, whether the predictor is constrained to be very smooth (nearby points in input space lead to similar output predictions) or whether the predictor is allowed to be "bumpy." The various SVMs will have different preferences about which input points they would like to run through the simulator next. SimLearn includes a formal mechanism for balancing the ensemble SVM preferences so that a single choice can be made for the next set of trials.

Confidence-Based Data Association and Discriminative Deep Appearance Learning for Robust Online Multi-Object Tracking.

PubMed

Bae, Seung-Hwan; Yoon, Kuk-Jin

2018-03-01

Online multi-object tracking aims at estimating the tracks of multiple objects instantly with each incoming frame and the information provided up to the moment. It still remains a difficult problem in complex scenes, because of the large ambiguity in associating multiple objects in consecutive frames and the low discriminability between objects appearances. In this paper, we propose a robust online multi-object tracking method that can handle these difficulties effectively. We first define the tracklet confidence using the detectability and continuity of a tracklet, and decompose a multi-object tracking problem into small subproblems based on the tracklet confidence. We then solve the online multi-object tracking problem by associating tracklets and detections in different ways according to their confidence values. Based on this strategy, tracklets sequentially grow with online-provided detections, and fragmented tracklets are linked up with others without any iterative and expensive association steps. For more reliable association between tracklets and detections, we also propose a deep appearance learning method to learn a discriminative appearance model from large training datasets, since the conventional appearance learning methods do not provide rich representation that can distinguish multiple objects with large appearance variations. In addition, we combine online transfer learning for improving appearance discriminability by adapting the pre-trained deep model during online tracking. Experiments with challenging public datasets show distinct performance improvement over other state-of-the-arts batch and online tracking methods, and prove the effect and usefulness of the proposed methods for online multi-object tracking.

Accelerated iterative beam angle selection in IMRT

DOE Office of Scientific and Technical Information (OSTI.GOV)

Bangert, Mark, E-mail: m.bangert@dkfz.de; Unkelbach, Jan

2016-03-15

Purpose: Iterative methods for beam angle selection (BAS) for intensity-modulated radiation therapy (IMRT) planning sequentially construct a beneficial ensemble of beam directions. In a naïve implementation, the nth beam is selected by adding beam orientations one-by-one from a discrete set of candidates to an existing ensemble of (n − 1) beams. The best beam orientation is identified in a time consuming process by solving the fluence map optimization (FMO) problem for every candidate beam and selecting the beam that yields the largest improvement to the objective function value. This paper evaluates two alternative methods to accelerate iterative BAS based onmore » surrogates for the FMO objective function value. Methods: We suggest to select candidate beams not based on the FMO objective function value after convergence but (1) based on the objective function value after five FMO iterations of a gradient based algorithm and (2) based on a projected gradient of the FMO problem in the first iteration. The performance of the objective function surrogates is evaluated based on the resulting objective function values and dose statistics in a treatment planning study comprising three intracranial, three pancreas, and three prostate cases. Furthermore, iterative BAS is evaluated for an application in which a small number of noncoplanar beams complement a set of coplanar beam orientations. This scenario is of practical interest as noncoplanar setups may require additional attention of the treatment personnel for every couch rotation. Results: Iterative BAS relying on objective function surrogates yields similar results compared to naïve BAS with regard to the objective function values and dose statistics. At the same time, early stopping of the FMO and using the projected gradient during the first iteration enable reductions in computation time by approximately one to two orders of magnitude. With regard to the clinical delivery of noncoplanar IMRT treatments, we could show that optimized beam ensembles using only a few noncoplanar beam orientations often approach the plan quality of fully noncoplanar ensembles. Conclusions: We conclude that iterative BAS in combination with objective function surrogates can be a viable option to implement automated BAS at clinically acceptable computation times.« less

Accelerated iterative beam angle selection in IMRT.

PubMed

Bangert, Mark; Unkelbach, Jan

2016-03-01

Iterative methods for beam angle selection (BAS) for intensity-modulated radiation therapy (IMRT) planning sequentially construct a beneficial ensemble of beam directions. In a naïve implementation, the nth beam is selected by adding beam orientations one-by-one from a discrete set of candidates to an existing ensemble of (n - 1) beams. The best beam orientation is identified in a time consuming process by solving the fluence map optimization (FMO) problem for every candidate beam and selecting the beam that yields the largest improvement to the objective function value. This paper evaluates two alternative methods to accelerate iterative BAS based on surrogates for the FMO objective function value. We suggest to select candidate beams not based on the FMO objective function value after convergence but (1) based on the objective function value after five FMO iterations of a gradient based algorithm and (2) based on a projected gradient of the FMO problem in the first iteration. The performance of the objective function surrogates is evaluated based on the resulting objective function values and dose statistics in a treatment planning study comprising three intracranial, three pancreas, and three prostate cases. Furthermore, iterative BAS is evaluated for an application in which a small number of noncoplanar beams complement a set of coplanar beam orientations. This scenario is of practical interest as noncoplanar setups may require additional attention of the treatment personnel for every couch rotation. Iterative BAS relying on objective function surrogates yields similar results compared to naïve BAS with regard to the objective function values and dose statistics. At the same time, early stopping of the FMO and using the projected gradient during the first iteration enable reductions in computation time by approximately one to two orders of magnitude. With regard to the clinical delivery of noncoplanar IMRT treatments, we could show that optimized beam ensembles using only a few noncoplanar beam orientations often approach the plan quality of fully noncoplanar ensembles. We conclude that iterative BAS in combination with objective function surrogates can be a viable option to implement automated BAS at clinically acceptable computation times.

Approximate dynamic programming for optimal stationary control with control-dependent noise.

PubMed

Jiang, Yu; Jiang, Zhong-Ping

2011-12-01

This brief studies the stochastic optimal control problem via reinforcement learning and approximate/adaptive dynamic programming (ADP). A policy iteration algorithm is derived in the presence of both additive and multiplicative noise using Itô calculus. The expectation of the approximated cost matrix is guaranteed to converge to the solution of some algebraic Riccati equation that gives rise to the optimal cost value. Moreover, the covariance of the approximated cost matrix can be reduced by increasing the length of time interval between two consecutive iterations. Finally, a numerical example is given to illustrate the efficiency of the proposed ADP methodology.

An empirical study of ensemble-based semi-supervised learning approaches for imbalanced splice site datasets.

PubMed

Stanescu, Ana; Caragea, Doina

2015-01-01

Recent biochemical advances have led to inexpensive, time-efficient production of massive volumes of raw genomic data. Traditional machine learning approaches to genome annotation typically rely on large amounts of labeled data. The process of labeling data can be expensive, as it requires domain knowledge and expert involvement. Semi-supervised learning approaches that can make use of unlabeled data, in addition to small amounts of labeled data, can help reduce the costs associated with labeling. In this context, we focus on the problem of predicting splice sites in a genome using semi-supervised learning approaches. This is a challenging problem, due to the highly imbalanced distribution of the data, i.e., small number of splice sites as compared to the number of non-splice sites. To address this challenge, we propose to use ensembles of semi-supervised classifiers, specifically self-training and co-training classifiers. Our experiments on five highly imbalanced splice site datasets, with positive to negative ratios of 1-to-99, showed that the ensemble-based semi-supervised approaches represent a good choice, even when the amount of labeled data consists of less than 1% of all training data. In particular, we found that ensembles of co-training and self-training classifiers that dynamically balance the set of labeled instances during the semi-supervised iterations show improvements over the corresponding supervised ensemble baselines. In the presence of limited amounts of labeled data, ensemble-based semi-supervised approaches can successfully leverage the unlabeled data to enhance supervised ensembles learned from highly imbalanced data distributions. Given that such distributions are common for many biological sequence classification problems, our work can be seen as a stepping stone towards more sophisticated ensemble-based approaches to biological sequence annotation in a semi-supervised framework.

An empirical study of ensemble-based semi-supervised learning approaches for imbalanced splice site datasets

PubMed Central

2015-01-01

Background Recent biochemical advances have led to inexpensive, time-efficient production of massive volumes of raw genomic data. Traditional machine learning approaches to genome annotation typically rely on large amounts of labeled data. The process of labeling data can be expensive, as it requires domain knowledge and expert involvement. Semi-supervised learning approaches that can make use of unlabeled data, in addition to small amounts of labeled data, can help reduce the costs associated with labeling. In this context, we focus on the problem of predicting splice sites in a genome using semi-supervised learning approaches. This is a challenging problem, due to the highly imbalanced distribution of the data, i.e., small number of splice sites as compared to the number of non-splice sites. To address this challenge, we propose to use ensembles of semi-supervised classifiers, specifically self-training and co-training classifiers. Results Our experiments on five highly imbalanced splice site datasets, with positive to negative ratios of 1-to-99, showed that the ensemble-based semi-supervised approaches represent a good choice, even when the amount of labeled data consists of less than 1% of all training data. In particular, we found that ensembles of co-training and self-training classifiers that dynamically balance the set of labeled instances during the semi-supervised iterations show improvements over the corresponding supervised ensemble baselines. Conclusions In the presence of limited amounts of labeled data, ensemble-based semi-supervised approaches can successfully leverage the unlabeled data to enhance supervised ensembles learned from highly imbalanced data distributions. Given that such distributions are common for many biological sequence classification problems, our work can be seen as a stepping stone towards more sophisticated ensemble-based approaches to biological sequence annotation in a semi-supervised framework. PMID:26356316

Cyclic Game Dynamics Driven by Iterated Reasoning

PubMed Central

Frey, Seth; Goldstone, Robert L.

2013-01-01

Recent theories from complexity science argue that complex dynamics are ubiquitous in social and economic systems. These claims emerge from the analysis of individually simple agents whose collective behavior is surprisingly complicated. However, economists have argued that iterated reasoning–what you think I think you think–will suppress complex dynamics by stabilizing or accelerating convergence to Nash equilibrium. We report stable and efficient periodic behavior in human groups playing the Mod Game, a multi-player game similar to Rock-Paper-Scissors. The game rewards subjects for thinking exactly one step ahead of others in their group. Groups that play this game exhibit cycles that are inconsistent with any fixed-point solution concept. These cycles are driven by a “hopping” behavior that is consistent with other accounts of iterated reasoning: agents are constrained to about two steps of iterated reasoning and learn an additional one-half step with each session. If higher-order reasoning can be complicit in complex emergent dynamics, then cyclic and chaotic patterns may be endogenous features of real-world social and economic systems. PMID:23441191

Intelligent process mapping through systematic improvement of heuristics

NASA Technical Reports Server (NTRS)

Ieumwananonthachai, Arthur; Aizawa, Akiko N.; Schwartz, Steven R.; Wah, Benjamin W.; Yan, Jerry C.

1992-01-01

The present system for automatic learning/evaluation of novel heuristic methods applicable to the mapping of communication-process sets on a computer network has its basis in the testing of a population of competing heuristic methods within a fixed time-constraint. The TEACHER 4.1 prototype learning system implemented or learning new postgame analysis heuristic methods iteratively generates and refines the mappings of a set of communicating processes on a computer network. A systematic exploration of the space of possible heuristic methods is shown to promise significant improvement.

SU-F-BRCD-09: Total Variation (TV) Based Fast Convergent Iterative CBCT Reconstruction with GPU Acceleration.

PubMed

Xu, Q; Yang, D; Tan, J; Anastasio, M

2012-06-01

To improve image quality and reduce imaging dose in CBCT for radiation therapy applications and to realize near real-time image reconstruction based on use of a fast convergence iterative algorithm and acceleration by multi-GPUs. An iterative image reconstruction that sought to minimize a weighted least squares cost function that employed total variation (TV) regularization was employed to mitigate projection data incompleteness and noise. To achieve rapid 3D image reconstruction (< 1 min), a highly optimized multiple-GPU implementation of the algorithm was developed. The convergence rate and reconstruction accuracy were evaluated using a modified 3D Shepp-Logan digital phantom and a Catphan-600 physical phantom. The reconstructed images were compared with the clinical FDK reconstruction results. Digital phantom studies showed that only 15 iterations and 60 iterations are needed to achieve algorithm convergence for 360-view and 60-view cases, respectively. The RMSE was reduced to 10-4 and 10-2, respectively, by using 15 iterations for each case. Our algorithm required 5.4s to complete one iteration for the 60-view case using one Tesla C2075 GPU. The few-view study indicated that our iterative algorithm has great potential to reduce the imaging dose and preserve good image quality. For the physical Catphan studies, the images obtained from the iterative algorithm possessed better spatial resolution and higher SNRs than those obtained from by use of a clinical FDK reconstruction algorithm. We have developed a fast convergence iterative algorithm for CBCT image reconstruction. The developed algorithm yielded images with better spatial resolution and higher SNR than those produced by a commercial FDK tool. In addition, from the few-view study, the iterative algorithm has shown great potential for significantly reducing imaging dose. We expect that the developed reconstruction approach will facilitate applications including IGART and patient daily CBCT-based treatment localization. © 2012 American Association of Physicists in Medicine.

Bounded-Angle Iterative Decoding of LDPC Codes

NASA Technical Reports Server (NTRS)

Dolinar, Samuel; Andrews, Kenneth; Pollara, Fabrizio; Divsalar, Dariush

2009-01-01

Bounded-angle iterative decoding is a modified version of conventional iterative decoding, conceived as a means of reducing undetected-error rates for short low-density parity-check (LDPC) codes. For a given code, bounded-angle iterative decoding can be implemented by means of a simple modification of the decoder algorithm, without redesigning the code. Bounded-angle iterative decoding is based on a representation of received words and code words as vectors in an n-dimensional Euclidean space (where n is an integer).

Innovations in Undergraduate Chemical Biology Education.

PubMed

Van Dyke, Aaron R; Gatazka, Daniel H; Hanania, Mariah M

2018-01-19

Chemical biology derives intellectual vitality from its scientific interface: applying chemical strategies and perspectives to biological questions. There is a growing need for chemical biologists to synergistically integrate their research programs with their educational activities to become holistic teacher-scholars. This review examines how course-based undergraduate research experiences (CUREs) are an innovative method to achieve this integration. Because CUREs are course-based, the review first offers strategies for creating a student-centered learning environment, which can improve students' outcomes. Exemplars of CUREs in chemical biology are then presented and organized to illustrate the five defining characteristics of CUREs: significance, scientific practices, discovery, collaboration, and iteration. Finally, strategies to overcome common barriers in CUREs are considered as well as future innovations in chemical biology education.

Development of a Mixed Methods Investigation of Process and Outcomes of Community-Based Participatory Research

PubMed Central

Lucero, Julie; Wallerstein, Nina; Duran, Bonnie; Alegria, Margarita; Greene-Moton, Ella; Israel, Barbara; Kastelic, Sarah; Magarati, Maya; Oetzel, John; Pearson, Cynthia; Schulz, Amy; Villegas, Malia; White Hat, Emily R.

2017-01-01

This article describes a mixed methods study of community-based participatory research (CBPR) partnership practices and the links between these practices and changes in health status and disparities outcomes. Directed by a CBPR conceptual model and grounded in indigenous-transformative theory, our nation-wide, cross-site study showcases the value of a mixed methods approach for better understanding the complexity of CBPR partnerships across diverse community and research contexts. The article then provides examples of how an iterative, integrated approach to our mixed methods analysis yielded enriched understandings of two key constructs of the model: trust and governance. Implications and lessons learned while using mixed methods to study CBPR are provided. PMID:29230152

Interdisciplinary Research: Performance and Policy Issues.

ERIC Educational Resources Information Center

Rossini, Frederick A.; Porter, Alan L.

1981-01-01

Successful interdisciplinary research performance, it is suggested, depends on such structural and process factors as leadership, team characteristics, study bounding, iteration, communication patterns, and epistemological factors. Appropriate frameworks for socially organizing the development of knowledge such as common group learning, modeling,…

Lessons learned in the deployment of a HIV counseling and testing management information system on a new project.

PubMed

Makinde, Olusesan A; Ezomike, Chioma F; Lehmann, Harold P; Ibanga, Iko J

2011-11-28

To share our experience on how we used simple but detailed processes and deployed a management information system on a new HIV counseling and testing (HCT) project in Nigeria. The procedures used in this study were adopted for their strength in identifying areas of continuous improvement as the project was implemented. We used an iterative brainstorming technique among 30 participants (volunteer counselors and project management staff) as well as iterative quality audits to identify several limitations to the success of the project and to propose solutions. We then implemented the solutions and reevaluated for performance. Findings from the evaluations were then reintroduced into the brainstorming and planning sessions. Several limitations were identified with the most prominent being the poor documentation of records at the site and the lack of a document transfer trail for audit purposes. Communication, cohesion and team focus are necessary to achieve success on any new project. Institutionalizing routine HIV behavioral surveillance using data collected at HCT will help in streamlining interventions that will be evidence-based. 2011 Wolters Kluwer Health | Lippincott Williams & Wilkins

Optimised Iteration in Coupled Monte Carlo - Thermal-Hydraulics Calculations

NASA Astrophysics Data System (ADS)

Hoogenboom, J. Eduard; Dufek, Jan

2014-06-01

This paper describes an optimised iteration scheme for the number of neutron histories and the relaxation factor in successive iterations of coupled Monte Carlo and thermal-hydraulic reactor calculations based on the stochastic iteration method. The scheme results in an increasing number of neutron histories for the Monte Carlo calculation in successive iteration steps and a decreasing relaxation factor for the spatial power distribution to be used as input to the thermal-hydraulics calculation. The theoretical basis is discussed in detail and practical consequences of the scheme are shown, among which a nearly linear increase per iteration of the number of cycles in the Monte Carlo calculation. The scheme is demonstrated for a full PWR type fuel assembly. Results are shown for the axial power distribution during several iteration steps. A few alternative iteration method are also tested and it is concluded that the presented iteration method is near optimal.

Spectral Reconstruction Based on Svm for Cross Calibration

NASA Astrophysics Data System (ADS)

Gao, H.; Ma, Y.; Liu, W.; He, H.

2017-05-01

Chinese HY-1C/1D satellites will use a 5nm/10nm-resolutional visible-near infrared(VNIR) hyperspectral sensor with the solar calibrator to cross-calibrate with other sensors. The hyperspectral radiance data are composed of average radiance in the sensor's passbands and bear a spectral smoothing effect, a transform from the hyperspectral radiance data to the 1-nm-resolution apparent spectral radiance by spectral reconstruction need to be implemented. In order to solve the problem of noise cumulation and deterioration after several times of iteration by the iterative algorithm, a novel regression method based on SVM is proposed, which can approach arbitrary complex non-linear relationship closely and provide with better generalization capability by learning. In the opinion of system, the relationship between the apparent radiance and equivalent radiance is nonlinear mapping introduced by spectral response function(SRF), SVM transform the low-dimensional non-linear question into high-dimensional linear question though kernel function, obtaining global optimal solution by virtue of quadratic form. The experiment is performed using 6S-simulated spectrums considering the SRF and SNR of the hyperspectral sensor, measured reflectance spectrums of water body and different atmosphere conditions. The contrastive result shows: firstly, the proposed method is with more reconstructed accuracy especially to the high-frequency signal; secondly, while the spectral resolution of the hyperspectral sensor reduces, the proposed method performs better than the iterative method; finally, the root mean square relative error(RMSRE) which is used to evaluate the difference of the reconstructed spectrum and the real spectrum over the whole spectral range is calculated, it decreses by one time at least by proposed method.

State-of-the-art Anonymization of Medical Records Using an Iterative Machine Learning Framework

PubMed Central

Szarvas, György; Farkas, Richárd; Busa-Fekete, Róbert

2007-01-01

Objective The anonymization of medical records is of great importance in the human life sciences because a de-identified text can be made publicly available for non-hospital researchers as well, to facilitate research on human diseases. Here the authors have developed a de-identification model that can successfully remove personal health information (PHI) from discharge records to make them conform to the guidelines of the Health Information Portability and Accountability Act. Design We introduce here a novel, machine learning-based iterative Named Entity Recognition approach intended for use on semi-structured documents like discharge records. Our method identifies PHI in several steps. First, it labels all entities whose tags can be inferred from the structure of the text and it then utilizes this information to find further PHI phrases in the flow text parts of the document. Measurements Following the standard evaluation method of the first Workshop on Challenges in Natural Language Processing for Clinical Data, we used token-level Precision, Recall and Fβ=1 measure metrics for evaluation. Results Our system achieved outstanding accuracy on the standard evaluation dataset of the de-identification challenge, with an F measure of 99.7534% for the best submitted model. Conclusion We can say that our system is competitive with the current state-of-the-art solutions, while we describe here several techniques that can be beneficial in other tasks that need to handle structured documents such as clinical records. PMID:17823086

Usability engineering for augmented reality: employing user-based studies to inform design.

PubMed

Gabbard, Joseph L; Swan, J Edward

2008-01-01

A major challenge, and thus opportunity, in the field of human-computer interaction and specifically usability engineering is designing effective user interfaces for emerging technologies that have no established design guidelines or interaction metaphors or introduce completely new ways for users to perceive and interact with technology and the world around them. Clearly, augmented reality is one such emerging technology. We propose a usability engineering approach that employs user-based studies to inform design, by iteratively inserting a series of user-based studies into a traditional usability engineering lifecycle to better inform initial user interface designs. We present an exemplar user-based study conducted to gain insight into how users perceive text in outdoor augmented reality settings and to derive implications for design in outdoor augmented reality. We also describe lessons learned from our experiences conducting user-based studies as part of the design process.

Research at ITER towards DEMO: Specific reactor diagnostic studies to be carried out on ITER

DOE Office of Scientific and Technical Information (OSTI.GOV)

Krasilnikov, A. V.; Kaschuck, Y. A.; Vershkov, V. A.

2014-08-21

In ITER diagnostics will operate in the very hard radiation environment of fusion reactor. Extensive technology studies are carried out during development of the ITER diagnostics and procedures of their calibration and remote handling. Results of these studies and practical application of the developed diagnostics on ITER will provide the direct input to DEMO diagnostic development. The list of DEMO measurement requirements and diagnostics will be determined during ITER experiments on the bases of ITER plasma physics results and success of particular diagnostic application in reactor-like ITER plasma. Majority of ITER diagnostic already passed the conceptual design phase and representmore » the state of the art in fusion plasma diagnostic development. The number of related to DEMO results of ITER diagnostic studies such as design and prototype manufacture of: neutron and γ–ray diagnostics, neutral particle analyzers, optical spectroscopy including first mirror protection and cleaning technics, reflectometry, refractometry, tritium retention measurements etc. are discussed.« less

Research at ITER towards DEMO: Specific reactor diagnostic studies to be carried out on ITER

NASA Astrophysics Data System (ADS)

Krasilnikov, A. V.; Kaschuck, Y. A.; Vershkov, V. A.; Petrov, A. A.; Petrov, V. G.; Tugarinov, S. N.

2014-08-01

In ITER diagnostics will operate in the very hard radiation environment of fusion reactor. Extensive technology studies are carried out during development of the ITER diagnostics and procedures of their calibration and remote handling. Results of these studies and practical application of the developed diagnostics on ITER will provide the direct input to DEMO diagnostic development. The list of DEMO measurement requirements and diagnostics will be determined during ITER experiments on the bases of ITER plasma physics results and success of particular diagnostic application in reactor-like ITER plasma. Majority of ITER diagnostic already passed the conceptual design phase and represent the state of the art in fusion plasma diagnostic development. The number of related to DEMO results of ITER diagnostic studies such as design and prototype manufacture of: neutron and γ-ray diagnostics, neutral particle analyzers, optical spectroscopy including first mirror protection and cleaning technics, reflectometry, refractometry, tritium retention measurements etc. are discussed.

A strategy with novel evolutionary features for the iterated prisoner's dilemma.

PubMed

Li, Jiawei; Kendall, Graham

2009-01-01

In recent iterated prisoner's dilemma tournaments, the most successful strategies were those that had identification mechanisms. By playing a predetermined sequence of moves and learning from their opponents' responses, these strategies managed to identify their opponents. We believe that these identification mechanisms may be very useful in evolutionary games. In this paper one such strategy, which we call collective strategy, is analyzed. Collective strategies apply a simple but efficient identification mechanism (that just distinguishes themselves from other strategies), and this mechanism allows them to only cooperate with their group members and defect against any others. In this way, collective strategies are able to maintain a stable population in evolutionary iterated prisoner's dilemma. By means of an invasion barrier, this strategy is compared with other strategies in evolutionary dynamics in order to demonstrate its evolutionary features. We also find that this collective behavior assists the evolution of cooperation in specific evolutionary environments.

Accelerated Path-following Iterative Shrinkage Thresholding Algorithm with Application to Semiparametric Graph Estimation

PubMed Central

Zhao, Tuo; Liu, Han

2016-01-01

We propose an accelerated path-following iterative shrinkage thresholding algorithm (APISTA) for solving high dimensional sparse nonconvex learning problems. The main difference between APISTA and the path-following iterative shrinkage thresholding algorithm (PISTA) is that APISTA exploits an additional coordinate descent subroutine to boost the computational performance. Such a modification, though simple, has profound impact: APISTA not only enjoys the same theoretical guarantee as that of PISTA, i.e., APISTA attains a linear rate of convergence to a unique sparse local optimum with good statistical properties, but also significantly outperforms PISTA in empirical benchmarks. As an application, we apply APISTA to solve a family of nonconvex optimization problems motivated by estimating sparse semiparametric graphical models. APISTA allows us to obtain new statistical recovery results which do not exist in the existing literature. Thorough numerical results are provided to back up our theory. PMID:28133430

Heuristic pattern correction scheme using adaptively trained generalized regression neural networks.

PubMed

Hoya, T; Chambers, J A

2001-01-01

In many pattern classification problems, an intelligent neural system is required which can learn the newly encountered but misclassified patterns incrementally, while keeping a good classification performance over the past patterns stored in the network. In the paper, an heuristic pattern correction scheme is proposed using adaptively trained generalized regression neural networks (GRNNs). The scheme is based upon both network growing and dual-stage shrinking mechanisms. In the network growing phase, a subset of the misclassified patterns in each incoming data set is iteratively added into the network until all the patterns in the incoming data set are classified correctly. Then, the redundancy in the growing phase is removed in the dual-stage network shrinking. Both long- and short-term memory models are considered in the network shrinking, which are motivated from biological study of the brain. The learning capability of the proposed scheme is investigated through extensive simulation studies.

Mitigation of time-varying distortions in Nyquist-WDM systems using machine learning

NASA Astrophysics Data System (ADS)

Granada Torres, Jhon J.; Varughese, Siddharth; Thomas, Varghese A.; Chiuchiarelli, Andrea; Ralph, Stephen E.; Cárdenas Soto, Ana M.; Guerrero González, Neil

2017-11-01

We propose a machine learning-based nonsymmetrical demodulation technique relying on clustering to mitigate time-varying distortions derived from several impairments such as IQ imbalance, bias drift, phase noise and interchannel interference. Experimental results show that those impairments cause centroid movements in the received constellations seen in time-windows of 10k symbols in controlled scenarios. In our demodulation technique, the k-means algorithm iteratively identifies the cluster centroids in the constellation of the received symbols in short time windows by means of the optimization of decision thresholds for a minimum BER. We experimentally verified the effectiveness of this computationally efficient technique in multicarrier 16QAM Nyquist-WDM systems over 270 km links. Our nonsymmetrical demodulation technique outperforms the conventional QAM demodulation technique, reducing the OSNR requirement up to ∼0.8 dB at a BER of 1 × 10-2 for signals affected by interchannel interference.

Deep learning for low-dose CT

NASA Astrophysics Data System (ADS)

Chen, Hu; Zhang, Yi; Zhou, Jiliu; Wang, Ge

2017-09-01

Given the potential risk of X-ray radiation to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. Currently, the main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction algorithms, but they need to access raw data whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, deconvolution network, and shortcut connections into the residual encoder-decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods. Especially, our method has been favorably evaluated in terms of noise suppression and structural preservation.

Mutual information, neural networks and the renormalization group

NASA Astrophysics Data System (ADS)

Koch-Janusz, Maciej; Ringel, Zohar

2018-06-01

Physical systems differing in their microscopic details often display strikingly similar behaviour when probed at macroscopic scales. Those universal properties, largely determining their physical characteristics, are revealed by the powerful renormalization group (RG) procedure, which systematically retains `slow' degrees of freedom and integrates out the rest. However, the important degrees of freedom may be difficult to identify. Here we demonstrate a machine-learning algorithm capable of identifying the relevant degrees of freedom and executing RG steps iteratively without any prior knowledge about the system. We introduce an artificial neural network based on a model-independent, information-theoretic characterization of a real-space RG procedure, which performs this task. We apply the algorithm to classical statistical physics problems in one and two dimensions. We demonstrate RG flow and extract the Ising critical exponent. Our results demonstrate that machine-learning techniques can extract abstract physical concepts and consequently become an integral part of theory- and model-building.

Deep Learning Methods for Improved Decoding of Linear Codes

NASA Astrophysics Data System (ADS)

Nachmani, Eliya; Marciano, Elad; Lugosch, Loren; Gross, Warren J.; Burshtein, David; Be'ery, Yair

2018-02-01

The problem of low complexity, close to optimal, channel decoding of linear codes with short to moderate block length is considered. It is shown that deep learning methods can be used to improve a standard belief propagation decoder, despite the large example space. Similar improvements are obtained for the min-sum algorithm. It is also shown that tying the parameters of the decoders across iterations, so as to form a recurrent neural network architecture, can be implemented with comparable results. The advantage is that significantly less parameters are required. We also introduce a recurrent neural decoder architecture based on the method of successive relaxation. Improvements over standard belief propagation are also observed on sparser Tanner graph representations of the codes. Furthermore, we demonstrate that the neural belief propagation decoder can be used to improve the performance, or alternatively reduce the computational complexity, of a close to optimal decoder of short BCH codes.

Hierarchical extreme learning machine based reinforcement learning for goal localization

NASA Astrophysics Data System (ADS)

AlDahoul, Nouar; Zaw Htike, Zaw; Akmeliawati, Rini

2017-03-01

The objective of goal localization is to find the location of goals in noisy environments. Simple actions are performed to move the agent towards the goal. The goal detector should be capable of minimizing the error between the predicted locations and the true ones. Few regions need to be processed by the agent to reduce the computational effort and increase the speed of convergence. In this paper, reinforcement learning (RL) method was utilized to find optimal series of actions to localize the goal region. The visual data, a set of images, is high dimensional unstructured data and needs to be represented efficiently to get a robust detector. Different deep Reinforcement models have already been used to localize a goal but most of them take long time to learn the model. This long learning time results from the weights fine tuning stage that is applied iteratively to find an accurate model. Hierarchical Extreme Learning Machine (H-ELM) was used as a fast deep model that doesn’t fine tune the weights. In other words, hidden weights are generated randomly and output weights are calculated analytically. H-ELM algorithm was used in this work to find good features for effective representation. This paper proposes a combination of Hierarchical Extreme learning machine and Reinforcement learning to find an optimal policy directly from visual input. This combination outperforms other methods in terms of accuracy and learning speed. The simulations and results were analysed by using MATLAB.

High-bandwidth and flexible tracking control for precision motion with application to a piezo nanopositioner.

PubMed

Feng, Zhao; Ling, Jie; Ming, Min; Xiao, Xiao-Hui

2017-08-01

For precision motion, high-bandwidth and flexible tracking are the two important issues for significant performance improvement. Iterative learning control (ILC) is an effective feedforward control method only for systems that operate strictly repetitively. Although projection ILC can track varying references, the performance is still limited by the fixed-bandwidth Q-filter, especially for triangular waves tracking commonly used in a piezo nanopositioner. In this paper, a wavelet transform-based linear time-varying (LTV) Q-filter design for projection ILC is proposed to compensate high-frequency errors and improve the ability to tracking varying references simultaneously. The LVT Q-filter is designed based on the modulus maximum of wavelet detail coefficients calculated by wavelet transform to determine the high-frequency locations of each iteration with the advantages of avoiding cross-terms and segmenting manually. The proposed approach was verified on a piezo nanopositioner. Experimental results indicate that the proposed approach can locate the high-frequency regions accurately and achieve the best performance under varying references compared with traditional frequency-domain and projection ILC with a fixed-bandwidth Q-filter, which validates that through implementing the LTV filter on projection ILC, high-bandwidth and flexible tracking can be achieved simultaneously by the proposed approach.

Automatic face naming by learning discriminative affinity matrices from weakly labeled images.

PubMed

Xiao, Shijie; Xu, Dong; Wu, Jianxin

2015-10-01

Given a collection of images, where each image contains several faces and is associated with a few names in the corresponding caption, the goal of face naming is to infer the correct name for each face. In this paper, we propose two new methods to effectively solve this problem by learning two discriminative affinity matrices from these weakly labeled images. We first propose a new method called regularized low-rank representation by effectively utilizing weakly supervised information to learn a low-rank reconstruction coefficient matrix while exploring multiple subspace structures of the data. Specifically, by introducing a specially designed regularizer to the low-rank representation method, we penalize the corresponding reconstruction coefficients related to the situations where a face is reconstructed by using face images from other subjects or by using itself. With the inferred reconstruction coefficient matrix, a discriminative affinity matrix can be obtained. Moreover, we also develop a new distance metric learning method called ambiguously supervised structural metric learning by using weakly supervised information to seek a discriminative distance metric. Hence, another discriminative affinity matrix can be obtained using the similarity matrix (i.e., the kernel matrix) based on the Mahalanobis distances of the data. Observing that these two affinity matrices contain complementary information, we further combine them to obtain a fused affinity matrix, based on which we develop a new iterative scheme to infer the name of each face. Comprehensive experiments demonstrate the effectiveness of our approach.

Adaptive Constrained Optimal Control Design for Data-Based Nonlinear Discrete-Time Systems With Critic-Only Structure.

PubMed

Luo, Biao; Liu, Derong; Wu, Huai-Ning

2018-06-01

Reinforcement learning has proved to be a powerful tool to solve optimal control problems over the past few years. However, the data-based constrained optimal control problem of nonaffine nonlinear discrete-time systems has rarely been studied yet. To solve this problem, an adaptive optimal control approach is developed by using the value iteration-based Q-learning (VIQL) with the critic-only structure. Most of the existing constrained control methods require the use of a certain performance index and only suit for linear or affine nonlinear systems, which is unreasonable in practice. To overcome this problem, the system transformation is first introduced with the general performance index. Then, the constrained optimal control problem is converted to an unconstrained optimal control problem. By introducing the action-state value function, i.e., Q-function, the VIQL algorithm is proposed to learn the optimal Q-function of the data-based unconstrained optimal control problem. The convergence results of the VIQL algorithm are established with an easy-to-realize initial condition . To implement the VIQL algorithm, the critic-only structure is developed, where only one neural network is required to approximate the Q-function. The converged Q-function obtained from the critic-only VIQL method is employed to design the adaptive constrained optimal controller based on the gradient descent scheme. Finally, the effectiveness of the developed adaptive control method is tested on three examples with computer simulation.

Joint Machine Learning and Game Theory for Rate Control in High Efficiency Video Coding.

PubMed

Gao, Wei; Kwong, Sam; Jia, Yuheng

2017-08-25

In this paper, a joint machine learning and game theory modeling (MLGT) framework is proposed for inter frame coding tree unit (CTU) level bit allocation and rate control (RC) optimization in High Efficiency Video Coding (HEVC). First, a support vector machine (SVM) based multi-classification scheme is proposed to improve the prediction accuracy of CTU-level Rate-Distortion (R-D) model. The legacy "chicken-and-egg" dilemma in video coding is proposed to be overcome by the learning-based R-D model. Second, a mixed R-D model based cooperative bargaining game theory is proposed for bit allocation optimization, where the convexity of the mixed R-D model based utility function is proved, and Nash bargaining solution (NBS) is achieved by the proposed iterative solution search method. The minimum utility is adjusted by the reference coding distortion and frame-level Quantization parameter (QP) change. Lastly, intra frame QP and inter frame adaptive bit ratios are adjusted to make inter frames have more bit resources to maintain smooth quality and bit consumption in the bargaining game optimization. Experimental results demonstrate that the proposed MLGT based RC method can achieve much better R-D performances, quality smoothness, bit rate accuracy, buffer control results and subjective visual quality than the other state-of-the-art one-pass RC methods, and the achieved R-D performances are very close to the performance limits from the FixedQP method.

A transversal approach for patch-based label fusion via matrix completion

PubMed Central

Sanroma, Gerard; Wu, Guorong; Gao, Yaozong; Thung, Kim-Han; Guo, Yanrong; Shen, Dinggang

2015-01-01

Recently, multi-atlas patch-based label fusion has received an increasing interest in the medical image segmentation field. After warping the anatomical labels from the atlas images to the target image by registration, label fusion is the key step to determine the latent label for each target image point. Two popular types of patch-based label fusion approaches are (1) reconstruction-based approaches that compute the target labels as a weighted average of atlas labels, where the weights are derived by reconstructing the target image patch using the atlas image patches; and (2) classification-based approaches that determine the target label as a mapping of the target image patch, where the mapping function is often learned using the atlas image patches and their corresponding labels. Both approaches have their advantages and limitations. In this paper, we propose a novel patch-based label fusion method to combine the above two types of approaches via matrix completion (and hence, we call it transversal). As we will show, our method overcomes the individual limitations of both reconstruction-based and classification-based approaches. Since the labeling confidences may vary across the target image points, we further propose a sequential labeling framework that first labels the highly confident points and then gradually labels more challenging points in an iterative manner, guided by the label information determined in the previous iterations. We demonstrate the performance of our novel label fusion method in segmenting the hippocampus in the ADNI dataset, subcortical and limbic structures in the LONI dataset, and mid-brain structures in the SATA dataset. We achieve more accurate segmentation results than both reconstruction-based and classification-based approaches. Our label fusion method is also ranked 1st in the online SATA Multi-Atlas Segmentation Challenge. PMID:26160394

Integrated and implicit: how residents learn CanMEDS roles by participating in practice.

PubMed

Renting, Nienke; Raat, A N Janet; Dornan, Tim; Wenger-Trayner, Etienne; van der Wal, Martha A; Borleffs, Jan C C; Gans, Rijk O B; Jaarsma, A Debbie C

2017-09-01

Learning outcomes for residency training are defined in competency frameworks such as the CanMEDS framework, which ultimately aim to better prepare residents for their future tasks. Although residents' training relies heavily on learning through participation in the workplace under the supervision of a specialist, it remains unclear how the CanMEDS framework informs practice-based learning and daily interactions between residents and supervisors. This study aimed to explore how the CanMEDS framework informs residents' practice-based training and interactions with supervisors. Constructivist grounded theory guided iterative data collection and analyses. Data were collected by direct observations of residents and supervisors, combined with formal and field interviews. We progressively arrived at an explanatory theory by coding and interpreting the data, building provisional theories and through continuous conversations. Data analysis drew on sensitising insights from communities of practice theory, which provided this study with a social learning perspective. CanMEDS roles occurred in an integrated fashion and usually remained implicit during interactions. The language of CanMEDS was not adopted in clinical practice, which seemed to impede explicit learning interactions. The CanMEDS framework seemed only one of many factors of influence in practice-based training: patient records and other documents were highly influential in daily activities and did not always correspond with CanMEDS roles. Additionally, the position of residents seemed too peripheral to allow them to learn certain aspects of the Health Advocate and Leader roles. The CanMEDS framework did not really guide supervisors' and residents' practice or interactions. It was not explicitly used as a common language in which to talk about resident performance and roles. Therefore, the extent to which CanMEDS actually helps improve residents' learning trajectories and conversations between residents and supervisors about residents' progress remains questionable. This study highlights the fact that the reification of competency frameworks into the complexity of practice-based learning is not a straightforward exercise. © 2017 John Wiley & Sons Ltd and The Association for the Study of Medical Education.

A WEB based approach in biomedical engineering design education.

PubMed

Enderle, J D; Browne, A F; Hallowell, M B

1997-01-01

As part of the accreditation process for university engineering programs, students are required to complete a minimum number of design credits in their course of study, typically at the senior level. Many call this the capstone course. Engineering design is a course or series of courses that bring together concepts and principles that students learn in their field of study--it involves the integration and extension of material learned in their major toward a specific project. Most often, the student is exposed to system-wide analysis, critique and evaluation for the first time. Design is an iterative, decision making process in which the student optimally applies previously learned material to meet a stated objective. At the University of Connecticut, students work in teams of 3-4 members and work on externally sponsored projects. To facilitate working with sponsors, a WEB based approach is used for reporting the progress on projects. Students are responsible for creating their own WEB sites that support both html and pdf formats. Students provide the following deliverables: weekly progress reports, project statement, specifications, project proposal, interim report, and final report. A senior design homepage also provides links to data books and other resources for use by students. We are also planning distance learning experiences between two campuses so students can work on projects that involve the use of video conferencing.

Adaptive Management for Urban Watersheds: The Slavic Village Pilot Project

EPA Science Inventory

Adaptive management is an environmental management strategy that uses an iterative process of decision-making to reduce the uncertainty in environmental management via system monitoring. A central tenet of adaptive management is that management involves a learning process that ca...

Flyback CCM inverter for AC module applications: iterative learning control and convergence analysis

NASA Astrophysics Data System (ADS)

Lee, Sung-Ho; Kim, Minsung

2017-12-01

This paper presents an iterative learning controller (ILC) for an interleaved flyback inverter operating in continuous conduction mode (CCM). The flyback CCM inverter features small output ripple current, high efficiency, and low cost, and hence it is well suited for photovoltaic power applications. However, it exhibits the non-minimum phase behaviour, because its transfer function from control duty to output current has the right-half-plane (RHP) zero. Moreover, the flyback CCM inverter suffers from the time-varying grid voltage disturbance. Thus, conventional control scheme results in inaccurate output tracking. To overcome these problems, the ILC is first developed and applied to the flyback inverter operating in CCM. The ILC makes use of both predictive and current learning terms which help the system output to converge to the reference trajectory. We take into account the nonlinear averaged model and use it to construct the proposed controller. It is proven that the system output globally converges to the reference trajectory in the absence of state disturbances, output noises, or initial state errors. Numerical simulations are performed to validate the proposed control scheme, and experiments using 400-W AC module prototype are carried out to demonstrate its practical feasibility.

The Lessons Oscar Taught Us: Data Science and Media & Entertainment.

PubMed

Gold, Michael; McClarren, Ryan; Gaughan, Conor

2013-06-01

Farsite Group, a data science firm based in Columbus, Ohio, launched a highly visible campaign in early 2013 to use predictive analytics to forecast the winners of the 85th Annual Academy Awards. The initiative was fun and exciting for the millions of Oscar viewers, but it also illustrated how data science could be further deployed in the media and entertainment industries. This article explores the current and potential use cases for big data and predictive analytics in those industries. It further discusses how the Farsite Forecast was built, as well as how the model was iterated, how the projections performed, and what lessons were learned in the process.

PredicT-ML: a tool for automating machine learning model building with big clinical data.

PubMed

Luo, Gang

2016-01-01

Predictive modeling is fundamental to transforming large clinical data sets, or "big clinical data," into actionable knowledge for various healthcare applications. Machine learning is a major predictive modeling approach, but two barriers make its use in healthcare challenging. First, a machine learning tool user must choose an algorithm and assign one or more model parameters called hyper-parameters before model training. The algorithm and hyper-parameter values used typically impact model accuracy by over 40 %, but their selection requires many labor-intensive manual iterations that can be difficult even for computer scientists. Second, many clinical attributes are repeatedly recorded over time, requiring temporal aggregation before predictive modeling can be performed. Many labor-intensive manual iterations are required to identify a good pair of aggregation period and operator for each clinical attribute. Both barriers result in time and human resource bottlenecks, and preclude healthcare administrators and researchers from asking a series of what-if questions when probing opportunities to use predictive models to improve outcomes and reduce costs. This paper describes our design of and vision for PredicT-ML (prediction tool using machine learning), a software system that aims to overcome these barriers and automate machine learning model building with big clinical data. The paper presents the detailed design of PredicT-ML. PredicT-ML will open the use of big clinical data to thousands of healthcare administrators and researchers and increase the ability to advance clinical research and improve healthcare.

Implementing the Science Assessment Standards: Developing and validating a set of laboratory assessment tasks in high school biology

NASA Astrophysics Data System (ADS)

Saha, Gouranga Chandra

Very often a number of factors, especially time, space and money, deter many science educators from using inquiry-based, hands-on, laboratory practical tasks as alternative assessment instruments in science. A shortage of valid inquiry-based laboratory tasks for high school biology has been cited. Driven by this need, this study addressed the following three research questions: (1) How can laboratory-based performance tasks be designed and developed that are doable by students for whom they are designed/written? (2) Do student responses to the laboratory-based performance tasks validly represent at least some of the intended process skills that new biology learning goals want students to acquire? (3) Are the laboratory-based performance tasks psychometrically consistent as individual tasks and as a set? To answer these questions, three tasks were used from the six biology tasks initially designed and developed by an iterative process of trial testing. Analyses of data from 224 students showed that performance-based laboratory tasks that are doable by all students require careful and iterative process of development. Although the students demonstrated more skill in performing than planning and reasoning, their performances at the item level were very poor for some items. Possible reasons for the poor performances have been discussed and suggestions on how to remediate the deficiencies have been made. Empirical evidences for validity and reliability of the instrument have been presented both from the classical and the modern validity criteria point of view. Limitations of the study have been identified. Finally implications of the study and directions for further research have been discussed.

A Model and Simple Iterative Algorithm for Redundancy Analysis.

ERIC Educational Resources Information Center

Fornell, Claes; And Others

1988-01-01

This paper shows that redundancy maximization with J. K. Johansson's extension can be accomplished via a simple iterative algorithm based on H. Wold's Partial Least Squares. The model and the iterative algorithm for the least squares approach to redundancy maximization are presented. (TJH)

Low-dose CT reconstruction with patch based sparsity and similarity constraints

NASA Astrophysics Data System (ADS)

Xu, Qiong; Mou, Xuanqin

2014-03-01

As the rapid growth of CT based medical application, low-dose CT reconstruction becomes more and more important to human health. Compared with other methods, statistical iterative reconstruction (SIR) usually performs better in lowdose case. However, the reconstructed image quality of SIR highly depends on the prior based regularization due to the insufficient of low-dose data. The frequently-used regularization is developed from pixel based prior, such as the smoothness between adjacent pixels. This kind of pixel based constraint cannot distinguish noise and structures effectively. Recently, patch based methods, such as dictionary learning and non-local means filtering, have outperformed the conventional pixel based methods. Patch is a small area of image, which expresses structural information of image. In this paper, we propose to use patch based constraint to improve the image quality of low-dose CT reconstruction. In the SIR framework, both patch based sparsity and similarity are considered in the regularization term. On one hand, patch based sparsity is addressed by sparse representation and dictionary learning methods, on the other hand, patch based similarity is addressed by non-local means filtering method. We conducted a real data experiment to evaluate the proposed method. The experimental results validate this method can lead to better image with less noise and more detail than other methods in low-count and few-views cases.

Iterative Nonlocal Total Variation Regularization Method for Image Restoration

PubMed Central

Xu, Huanyu; Sun, Quansen; Luo, Nan; Cao, Guo; Xia, Deshen

2013-01-01

In this paper, a Bregman iteration based total variation image restoration algorithm is proposed. Based on the Bregman iteration, the algorithm splits the original total variation problem into sub-problems that are easy to solve. Moreover, non-local regularization is introduced into the proposed algorithm, and a method to choose the non-local filter parameter locally and adaptively is proposed. Experiment results show that the proposed algorithms outperform some other regularization methods. PMID:23776560

Iterative channel decoding of FEC-based multiple-description codes.

PubMed

Chang, Seok-Ho; Cosman, Pamela C; Milstein, Laurence B

2012-03-01

Multiple description coding has been receiving attention as a robust transmission framework for multimedia services. This paper studies the iterative decoding of FEC-based multiple description codes. The proposed decoding algorithms take advantage of the error detection capability of Reed-Solomon (RS) erasure codes. The information of correctly decoded RS codewords is exploited to enhance the error correction capability of the Viterbi algorithm at the next iteration of decoding. In the proposed algorithm, an intradescription interleaver is synergistically combined with the iterative decoder. The interleaver does not affect the performance of noniterative decoding but greatly enhances the performance when the system is iteratively decoded. We also address the optimal allocation of RS parity symbols for unequal error protection. For the optimal allocation in iterative decoding, we derive mathematical equations from which the probability distributions of description erasures can be generated in a simple way. The performance of the algorithm is evaluated over an orthogonal frequency-division multiplexing system. The results show that the performance of the multiple description codes is significantly enhanced.

US NDC Modernization Iteration E2 Prototyping Report: User Interface Framework

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lewis, Jennifer E.; Palmer, Melanie A.; Vickers, James Wallace

2014-12-01

During the second iteration of the US NDC Modernization Elaboration phase (E2), the SNL US NDC Modernization project team completed follow-on Rich Client Platform (RCP) exploratory prototyping related to the User Interface Framework (UIF). The team also developed a survey of browser-based User Interface solutions and completed exploratory prototyping for selected solutions. This report presents the results of the browser-based UI survey, summarizes the E2 browser-based UI and RCP prototyping work, and outlines a path forward for the third iteration of the Elaboration phase (E3).

Efficient data communication protocols for wireless networks

NASA Astrophysics Data System (ADS)

Zeydan, Engin

In this dissertation, efficient decentralized algorithms are investigated for cost minimization problems in wireless networks. For wireless sensor networks, we investigate both the reduction in the energy consumption and throughput maximization problems separately using multi-hop data aggregation for correlated data in wireless sensor networks. The proposed algorithms exploit data redundancy using a game theoretic framework. For energy minimization, routes are chosen to minimize the total energy expended by the network using best response dynamics to local data. The cost function used in routing takes into account distance, interference and in-network data aggregation. The proposed energy-efficient correlation-aware routing algorithm significantly reduces the energy consumption in the network and converges in a finite number of steps iteratively. For throughput maximization, we consider both the interference distribution across the network and correlation between forwarded data when establishing routes. Nodes along each route are chosen to minimize the interference impact in their neighborhood and to maximize the in-network data aggregation. The resulting network topology maximizes the global network throughput and the algorithm is guaranteed to converge with a finite number of steps using best response dynamics. For multiple antenna wireless ad-hoc networks, we present distributed cooperative and regret-matching based learning schemes for joint transmit beanformer and power level selection problem for nodes operating in multi-user interference environment. Total network transmit power is minimized while ensuring a constant received signal-to-interference and noise ratio at each receiver. In cooperative and regret-matching based power minimization algorithms, transmit beanformers are selected from a predefined codebook to minimize the total power. By selecting transmit beamformers judiciously and performing power adaptation, the cooperative algorithm is shown to converge to pure strategy Nash equilibrium with high probability throughout the iterations in the interference impaired network. On the other hand, the regret-matching learning algorithm is noncooperative and requires minimum amount of overhead. The proposed cooperative and regret-matching based distributed algorithms are also compared with centralized solutions through simulation results.

Confidence-based learning CME: overcoming barriers in irritable bowel syndrome with constipation.

PubMed

Cash, Brooks; Mitchner, Natasha A; Ravyn, Dana

2011-01-01

Performance of health care professionals depends on both medical knowledge and the certainty with which they possess it. Conventional continuing medical education interventions assess the correctness of learners' responses but do not determine the degree of confidence with which they hold incorrect information. This study describes the use of confidence-based learning (CBL) in an activity designed to enhance learners' knowledge, confidence in their knowledge, and clinical competence with regard to constipation-predominant IBS (IBS-C), a frequently underdiagnosed and misdiagnosed condition. The online CBL activity included multiple-choice questions in 2 modules: Burden of Care (BOC; 28 questions) and Patient Scenarios (PS; 9 case-based questions). After formative assessment, targeted feedback was provided, and the learner focused on material with demonstrated knowledge and/or confidence gaps. The process was repeated until 85% of questions were answered correctly and confidently (ie, mastery was attained). Of 275 participants (24% internal medicine, 13% gastroenterology, 32% family medicine, and 31% other), 249 and 167 completed the BOC and PS modules, respectively. Among all participants, 61.8% and 98.2% achieved mastery in the BOC and PS modules, respectively. Baseline mastery levels between specialties were significantly different in the BOC module (p = 0.002); no significant differences were evident between specialties in final mastery levels. Approximately one-third of learners were confident and wrong in topics of epidemiology, defining IBS and constipation, and treatments in the first iteration. No significant difference was observed between specialties for the PS module in either the first or last iterations. Learners achieved mastery in topics pertaining to IBS-C regardless of baseline knowledge or specialty. These data indicate that CME activities employing CBL can be used to address knowledge and confidence gaps. Copyright © 2010 The Alliance for Continuing Medical Education, the Society for Academic Continuing Medical Education, and the Council on CME, Association for Hospital Medical Education.

Functional electrical stimulation mediated by iterative learning control and 3D robotics reduces motor impairment in chronic stroke

PubMed Central

2012-01-01

Background Novel stroke rehabilitation techniques that employ electrical stimulation (ES) and robotic technologies are effective in reducing upper limb impairments. ES is most effective when it is applied to support the patients’ voluntary effort; however, current systems fail to fully exploit this connection. This study builds on previous work using advanced ES controllers, and aims to investigate the feasibility of Stimulation Assistance through Iterative Learning (SAIL), a novel upper limb stroke rehabilitation system which utilises robotic support, ES, and voluntary effort. Methods Five hemiparetic, chronic stroke participants with impaired upper limb function attended 18, 1 hour intervention sessions. Participants completed virtual reality tracking tasks whereby they moved their impaired arm to follow a slowly moving sphere along a specified trajectory. To do this, the participants’ arm was supported by a robot. ES, mediated by advanced iterative learning control (ILC) algorithms, was applied to the triceps and anterior deltoid muscles. Each movement was repeated 6 times and ILC adjusted the amount of stimulation applied on each trial to improve accuracy and maximise voluntary effort. Participants completed clinical assessments (Fugl-Meyer, Action Research Arm Test) at baseline and post-intervention, as well as unassisted tracking tasks at the beginning and end of each intervention session. Data were analysed using t-tests and linear regression. Results From baseline to post-intervention, Fugl-Meyer scores improved, assisted and unassisted tracking performance improved, and the amount of ES required to assist tracking reduced. Conclusions The concept of minimising support from ES using ILC algorithms was demonstrated. The positive results are promising with respect to reducing upper limb impairments following stroke, however, a larger study is required to confirm this. PMID:22676920

Functional electrical stimulation mediated by iterative learning control and 3D robotics reduces motor impairment in chronic stroke.

PubMed

Meadmore, Katie L; Hughes, Ann-Marie; Freeman, Chris T; Cai, Zhonglun; Tong, Daisy; Burridge, Jane H; Rogers, Eric

2012-06-07

Novel stroke rehabilitation techniques that employ electrical stimulation (ES) and robotic technologies are effective in reducing upper limb impairments. ES is most effective when it is applied to support the patients' voluntary effort; however, current systems fail to fully exploit this connection. This study builds on previous work using advanced ES controllers, and aims to investigate the feasibility of Stimulation Assistance through Iterative Learning (SAIL), a novel upper limb stroke rehabilitation system which utilises robotic support, ES, and voluntary effort. Five hemiparetic, chronic stroke participants with impaired upper limb function attended 18, 1 hour intervention sessions. Participants completed virtual reality tracking tasks whereby they moved their impaired arm to follow a slowly moving sphere along a specified trajectory. To do this, the participants' arm was supported by a robot. ES, mediated by advanced iterative learning control (ILC) algorithms, was applied to the triceps and anterior deltoid muscles. Each movement was repeated 6 times and ILC adjusted the amount of stimulation applied on each trial to improve accuracy and maximise voluntary effort. Participants completed clinical assessments (Fugl-Meyer, Action Research Arm Test) at baseline and post-intervention, as well as unassisted tracking tasks at the beginning and end of each intervention session. Data were analysed using t-tests and linear regression. From baseline to post-intervention, Fugl-Meyer scores improved, assisted and unassisted tracking performance improved, and the amount of ES required to assist tracking reduced. The concept of minimising support from ES using ILC algorithms was demonstrated. The positive results are promising with respect to reducing upper limb impairments following stroke, however, a larger study is required to confirm this.

The recruitment of new members to existing PBSGL small groups: a qualitative study.

PubMed

Park, Julia; Cunningham, David E

2018-04-23

Introduction Practice-Based Small Group Learning (PBSGL) is a learning programme widely adopted by primary healthcare professions (general practitioners, general practice nurses and pharmacists) in Scotland and other countries in the UK. PBSGL groups recruit members and decide on meeting dates and venues. Study aims To determine how groups recruit new members and discern what are the important attributes of the new members. Method A grounded theory approach was used with purposive sampling to recruit PBSGL groups to the study. Focus groups drawn from established PBSGL groups were conducted by two researchers following an iterative process, with interviews audio-recorded and transcribed, and codes and themes constructed. Data saturation was achieved. Results and conclusions Four themes were identified that affected group recruitment: group formation and purpose; group culture and ethos; experience and seniority range of group members; professional socialisation and cross-fertilisation. Groups whose main purpose was learning encouraged diverse membership, while groups that were stricter with recruitment often prioritised friendship, group safety, trust and peer support over learning. The variation in group's openness to recruitment may make it difficult for potential members to find a group and this may affect the development and expansion of the PBSGL programme.

Learning in context: identifying gaps in research on the transfer of medical communication skills to the clinical workplace.

PubMed

van den Eertwegh, Valerie; van Dulmen, Sandra; van Dalen, Jan; Scherpbier, Albert J J A; van der Vleuten, Cees P M

2013-02-01

In order to reduce the inconsistencies of findings and the apparent low transfer of communication skills from training to medical practice, this narrative review identifies some main gaps in research on medical communication skills training and presents insights from theories on learning and transfer to broaden the view for future research. Relevant literature was identified using Pubmed, GoogleScholar, Cochrane database, and Web of Science; and analyzed using an iterative procedure. Research findings on the effectiveness of medical communication training still show inconsistencies and variability. Contemporary theories on learning based on a constructivist paradigm offer the following insights: acquisition of knowledge and skills should be viewed as an ongoing process of exchange between the learner and his environment, so called lifelong learning. This process can neither be atomized nor separated from the context in which it occurs. Four contemporary approaches are presented as examples. The following shift in focus for future research is proposed: beyond isolated single factor effectiveness studies toward constructivist, non-reductionistic studies integrating the context. Future research should investigate how constructivist approaches can be used in the medical context to increase effective learning and transition of communication skills. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Social learning within a community of practice: Investigating interactions about evaluation among zoo education professionals.

PubMed

Khalil, Kathayoon; Ardoin, Nicole M; Wojcik, Deborah

2017-04-01

The accessibility and ubiquity of zoos and aquariums-which reach over 700 million people worldwide annually-make them critical sites for science and environmental learning. Through educational offerings, these sites can generate excitement and curiosity about nature and motivate stewardship behavior, but only if their programs are high quality and meet the needs of their audiences. Evaluation is, therefore, critical: knowing what works, for whom, and under what conditions must be central to these organizations. Yet, many zoo and aquarium educators find evaluation to be daunting, and they are challenged to implement evaluations and/or use the findings iteratively in program development and improvement. This article examines how zoo education professionals engage with one another in a learning community related to evaluation. We use a communities of practice lens and social network analysis to understand the structure of this networked learning community, considering changes over time. Our findings suggest that individuals' roles in a networked learning community are influenced by factors such as communicative convenience and one's perceptions of others' evaluation expertise, which also contribute to forming and sustaining professional relationships. This study illuminates how project-based professional networks can become communities of practice. Copyright © 2016 Elsevier Ltd. All rights reserved.

Sparsity-promoting orthogonal dictionary updating for image reconstruction from highly undersampled magnetic resonance data.

PubMed

Huang, Jinhong; Guo, Li; Feng, Qianjin; Chen, Wufan; Feng, Yanqiu

2015-07-21

Image reconstruction from undersampled k-space data accelerates magnetic resonance imaging (MRI) by exploiting image sparseness in certain transform domains. Employing image patch representation over a learned dictionary has the advantage of being adaptive to local image structures and thus can better sparsify images than using fixed transforms (e.g. wavelets and total variations). Dictionary learning methods have recently been introduced to MRI reconstruction, and these methods demonstrate significantly reduced reconstruction errors compared to sparse MRI reconstruction using fixed transforms. However, the synthesis sparse coding problem in dictionary learning is NP-hard and computationally expensive. In this paper, we present a novel sparsity-promoting orthogonal dictionary updating method for efficient image reconstruction from highly undersampled MRI data. The orthogonality imposed on the learned dictionary enables the minimization problem in the reconstruction to be solved by an efficient optimization algorithm which alternately updates representation coefficients, orthogonal dictionary, and missing k-space data. Moreover, both sparsity level and sparse representation contribution using updated dictionaries gradually increase during iterations to recover more details, assuming the progressively improved quality of the dictionary. Simulation and real data experimental results both demonstrate that the proposed method is approximately 10 to 100 times faster than the K-SVD-based dictionary learning MRI method and simultaneously improves reconstruction accuracy.

Improving access to learning in the workplace using technology in an accredited course.

PubMed

Munro, Kathleen M; Peacock, Susi

2005-03-01

This article gives an account of a case study which seeks to explore the potential for using technology to deliver learning in the workplace: a syringe driver course for nurses. We provide a brief overview of workplace learning, continuing professional development and learning technology in the health sciences. The paper then draws upon a three-year project that involved the transition of a traditionally taught, institution-based face-to-face course to work-based learning using technology. Through the evaluation and discussion of the case study we address key issues that have emerged, such as, marketing of the product; in our case it was decided that the most cost-effective way to provide the course and recuperate some costs was to accredit the course by the Institution. Registered practitioners in the workplace assess learning and are linked to the quality assurance mechanisms of the Institution. We also consider some of the major barriers to implementation, highlighting critical areas for consideration for those undertaking a similar project. These include the lack of technical knowledge in the Group, which resulted in a steep learning curve for all members. This and numerous iterations of materials (including video and animations) lengthened the project considerably whilst technological advances meant other more sophisticated technological solutions that became available during the production process were incorporated. A cost benefit analysis would show that the product has been delivered across Scotland and production costs covered and that there have been unquantifiable gains, including improving the external profile of the academic institution and the NHS Trust, developing the technical skills of the Group and providing invaluable experience of working in a cross-disciplinary collaborative working environment.

Adaptive block online learning target tracking based on super pixel segmentation

NASA Astrophysics Data System (ADS)

Cheng, Yue; Li, Jianzeng

2018-04-01

Video target tracking technology under the unremitting exploration of predecessors has made big progress, but there are still lots of problems not solved. This paper proposed a new algorithm of target tracking based on image segmentation technology. Firstly we divide the selected region using simple linear iterative clustering (SLIC) algorithm, after that, we block the area with the improved density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm. Each sub-block independently trained classifier and tracked, then the algorithm ignore the failed tracking sub-block while reintegrate the rest of the sub-blocks into tracking box to complete the target tracking. The experimental results show that our algorithm can work effectively under occlusion interference, rotation change, scale change and many other problems in target tracking compared with the current mainstream algorithms.

Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network.

PubMed

Kang, Eunhee; Chang, Won; Yoo, Jaejun; Ye, Jong Chul

2018-06-01

Model-based iterative reconstruction algorithms for low-dose X-ray computed tomography (CT) are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the textures were not fully recovered. To address this problem, here we propose a novel framelet-based denoising algorithm using wavelet residual network which synergistically combines the expressive power of deep learning and the performance guarantee from the framelet-based denoising algorithms. The new algorithms were inspired by the recent interpretation of the deep CNN as a cascaded convolution framelet signal representation. Extensive experimental results confirm that the proposed networks have significantly improved performance and preserve the detail texture of the original images.

Data-Driven Based Asynchronous Motor Control for Printing Servo Systems

NASA Astrophysics Data System (ADS)

Bian, Min; Guo, Qingyun

Modern digital printing equipment aims to the environmental-friendly industry with high dynamic performances and control precision and low vibration and abrasion. High performance motion control system of printing servo systems was required. Control system of asynchronous motor based on data acquisition was proposed. Iterative learning control (ILC) algorithm was studied. PID control was widely used in the motion control. However, it was sensitive to the disturbances and model parameters variation. The ILC applied the history error data and present control signals to approximate the control signal directly in order to fully track the expect trajectory without the system models and structures. The motor control algorithm based on the ILC and PID was constructed and simulation results were given. The results show that data-driven control method is effective dealing with bounded disturbances for the motion control of printing servo systems.

Web-Based Virtual Patients in Nursing Education: Development and Validation of Theory-Anchored Design and Activity Models

PubMed Central

2014-01-01

Background Research has shown that nursing students find it difficult to translate and apply their theoretical knowledge in a clinical context. Virtual patients (VPs) have been proposed as a learning activity that can support nursing students in their learning of scientific knowledge and help them integrate theory and practice. Although VPs are increasingly used in health care education, they still lack a systematic consistency that would allow their reuse outside of their original context. There is therefore a need to develop a model for the development and implementation of VPs in nursing education. Objective The aim of this study was to develop and evaluate a virtual patient model optimized to the learning and assessment needs in nursing education. Methods The process of modeling started by reviewing theoretical frameworks reported in the literature and used by practitioners when designing learning and assessment activities. The Outcome-Present State Test (OPT) model was chosen as the theoretical framework. The model was then, in an iterative manner, developed and optimized to the affordances of virtual patients. Content validation was performed with faculty both in terms of the relevance of the chosen theories but also its applicability in nursing education. The virtual patient nursing model was then instantiated in two VPs. The students’ perceived usefulness of the VPs was investigated using a questionnaire. The result was analyzed using descriptive statistics. Results A virtual patient Nursing Design Model (vpNDM) composed of three layers was developed. Layer 1 contains the patient story and ways of interacting with the data, Layer 2 includes aspects of the iterative process of clinical reasoning, and finally Layer 3 includes measurable outcomes. A virtual patient Nursing Activity Model (vpNAM) was also developed as a guide when creating VP-centric learning activities. The students perceived the global linear VPs as a relevant learning activity for the integration of theory and practice. Conclusions Virtual patients that are adapted to the nursing paradigm can support nursing students’ development of clinical reasoning skills. The proposed virtual patient nursing design and activity models will allow the systematic development of different types of virtual patients from a common model and thereby create opportunities for sharing pedagogical designs across technical solutions. PMID:24727709

Compensation for the phase-type spatial periodic modulation of the near-field beam at 1053 nm

NASA Astrophysics Data System (ADS)

Gao, Yaru; Liu, Dean; Yang, Aihua; Tang, Ruyu; Zhu, Jianqiang

2017-10-01

A phase-only spatial light modulator is used to provide and compensate for the spatial periodic modulation (SPM) of the near-field beam at the near infrared at 1053nm wavelength with an improved iterative weight-based method. The transmission characteristics of the incident beam has been changed by a spatial light modulator (SLM) to shape the spatial intensity of the output beam. The propagation and reverse propagation of the light in free space are two important processes in the iterative process. The based theory is the beam angular spectrum transmit formula (ASTF) and the principle of the iterative weight-based method. We have made two improvements to the originally proposed iterative weight-based method. We select the appropriate parameter by choosing the minimum value of the output beam contrast degree and use the MATLAB built-in angle function to acquire the corresponding phase of the light wave function. The required phase that compensates for the intensity distribution of the incident SPM beam is iterated by this algorithm, which can decrease the magnitude of the SPM of the intensity on the observation plane. The experimental results show that the phase-type SPM of the near-field beam is subject to a certain restriction. We have also analyzed some factors that make the results imperfect. The experiment results verifies the possible applicability of this iterative weight-based method to compensate for the SPM of the near-field beam.

Overview of International Thermonuclear Experimental Reactor (ITER) engineering design activities*

NASA Astrophysics Data System (ADS)

Shimomura, Y.

1994-05-01

The International Thermonuclear Experimental Reactor (ITER) [International Thermonuclear Experimental Reactor (ITER) (International Atomic Energy Agency, Vienna, 1988), ITER Documentation Series, No. 1] project is a multiphased project, presently proceeding under the auspices of the International Atomic Energy Agency according to the terms of a four-party agreement among the European Atomic Energy Community (EC), the Government of Japan (JA), the Government of the Russian Federation (RF), and the Government of the United States (US), ``the Parties.'' The ITER project is based on the tokamak, a Russian invention, and has since been brought to a high level of development in all major fusion programs in the world. The objective of ITER is to demonstrate the scientific and technological feasibility of fusion energy for peaceful purposes. The ITER design is being developed, with support from the Parties' four Home Teams and is in progress by the Joint Central Team. An overview of ITER Design activities is presented.

Scenario-based fitted Q-iteration for adaptive control of water reservoir systems under uncertainty

NASA Astrophysics Data System (ADS)

Bertoni, Federica; Giuliani, Matteo; Castelletti, Andrea

2017-04-01

Over recent years, mathematical models have largely been used to support planning and management of water resources systems. Yet, the increasing uncertainties in their inputs - due to increased variability in the hydrological regimes - are a major challenge to the optimal operations of these systems. Such uncertainty, boosted by projected changing climate, violates the stationarity principle generally used for describing hydro-meteorological processes, which assumes time persisting statistical characteristics of a given variable as inferred by historical data. As this principle is unlikely to be valid in the future, the probability density function used for modeling stochastic disturbances (e.g., inflows) becomes an additional uncertain parameter of the problem, which can be described in a deterministic and set-membership based fashion. This study contributes a novel method for designing optimal, adaptive policies for controlling water reservoir systems under climate-related uncertainty. The proposed method, called scenario-based Fitted Q-Iteration (sFQI), extends the original Fitted Q-Iteration algorithm by enlarging the state space to include the space of the uncertain system's parameters (i.e., the uncertain climate scenarios). As a result, sFQI embeds the set-membership uncertainty of the future inflow scenarios in the action-value function and is able to approximate, with a single learning process, the optimal control policy associated to any scenario included in the uncertainty set. The method is demonstrated on a synthetic water system, consisting of a regulated lake operated for ensuring reliable water supply to downstream users. Numerical results show that the sFQI algorithm successfully identifies adaptive solutions to operate the system under different inflow scenarios, which outperform the control policy designed under historical conditions. Moreover, the sFQI policy generalizes over inflow scenarios not directly experienced during the policy design, thus alleviating the risk of mis-adaptation, namely the design of a solution fully adapted to a scenario that is different from the one that will actually realize.

Learning Objects: A User-Centered Design Process

ERIC Educational Resources Information Center

Branon, Rovy F., III

2011-01-01

Design research systematically creates or improves processes, products, and programs through an iterative progression connecting practice and theory (Reinking, 2008; van den Akker, 2006). Developing a new instructional systems design (ISD) processes through design research is necessary when new technologies emerge that challenge existing practices…

Designing Needs Statements in a Systematic Iterative Way

ERIC Educational Resources Information Center

Verstegen, D. M. L.; Barnard, Y. F.; Pilot, A.

2009-01-01

Designing specifications for technically advanced instructional products, such as e-learning, simulations or simulators requires different kinds of expertise. The SLIM method proposes to involve all stakeholders from the beginning in a series of workshops under the guidance of experienced instructional designers. These instructional designers…

The interactive evolution of human communication systems.

PubMed

Fay, Nicolas; Garrod, Simon; Roberts, Leo; Swoboda, Nik

2010-04-01

This paper compares two explanations of the process by which human communication systems evolve: iterated learning and social collaboration. It then reports an experiment testing the social collaboration account. Participants engaged in a graphical communication task either as a member of a community, where they interacted with seven different partners drawn from the same pool, or as a member of an isolated pair, where they interacted with the same partner across the same number of games. Participants' horizontal, pair-wise interactions led "bottom up" to the creation of an effective and efficient shared sign system in the community condition. Furthermore, the community-evolved sign systems were as effective and efficient as the local sign systems developed by isolated pairs. Finally, and as predicted by a social collaboration account, and not by an iterated learning account, interaction was critical to the creation of shared sign systems, with different isolated pairs establishing different local sign systems and different communities establishing different global sign systems. Copyright © 2010 Cognitive Science Society, Inc.

Neural Network Training by Integration of Adjoint Systems of Equations Forward in Time

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1999-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically. it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved. but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. Tbc trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Neural network training by integration of adjoint systems of equations forward in time

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Barhen, Jacob (Inventor)

1992-01-01

A method and apparatus for supervised neural learning of time dependent trajectories exploits the concepts of adjoint operators to enable computation of the gradient of an objective functional with respect to the various parameters of the network architecture in a highly efficient manner. Specifically, it combines the advantage of dramatic reductions in computational complexity inherent in adjoint methods with the ability to solve two adjoint systems of equations together forward in time. Not only is a large amount of computation and storage saved, but the handling of real-time applications becomes also possible. The invention has been applied it to two examples of representative complexity which have recently been analyzed in the open literature and demonstrated that a circular trajectory can be learned in approximately 200 iterations compared to the 12000 reported in the literature. A figure eight trajectory was achieved in under 500 iterations compared to 20000 previously required. The trajectories computed using our new method are much closer to the target trajectories than was reported in previous studies.

Connecting Spatial Literacy and Climate Literacy Using a Place-Based GIS Approach in a Collaborative Online Educational Setting

NASA Astrophysics Data System (ADS)

Low, R.; Boger, R. A.; Mandryk, C. A.

2014-12-01

On-line learning is already revolutionizing higher education, and emerging cloud-based Geographic Information System (GIS) capabilities are poised to revolutionize the acquisition and sharing of spatial knowledge in a variety of fields. In this project, we deployed ESRI's ArcGIS Online in an on-line course environment to provide a place-based quantitative exploration of the impacts of environmental changes specifically related to climate change. As spatial thinking is not necessarily transferrable from one domain to another, we hypothesized that combining spatial literacy and climate change domain knowledge would transform student conceptions and mental models of climate change in measurable ways. To this end, we adapted and employed existing instruments for pre- post testing of general pattern recognition, interpretation, and spatial transformational skills, as well as climate system content knowledge and attitudes. A collaborative on-line course platform offered to students from University of Nebraska, Lincoln and from City College of New York (CUNY) colleges, Brooklyn and Lehman, brought to the discussion distinct urban and rural perspectives, which were the basis of place-based climate, water and food explorations in the course. The course has been offered 3 times in a shared LMS over the past 3 years. Participants in the most recent iteration of the course demonstrated statistically significant improvements in spatial skills, but they did not show the expected statistically significant improvement overall in climate knowledge that we see in other online courses where climate change literacy is the sole focus of the course. Ongoing research by our team shows strong correlation between active peer engagement in online discussions and student learning outcomes. Student-initiated discussions in the GIS-based climate change courses revealed a shift away from discussing the climate change science and a focus on technology and analyzing the spatial products created using GIS. As we improve the effectiveness of this course, we will be developing interventions in the discussion board activities that we hypothesize will increase the effectiveness of climate knowledge construction in future iterations.

Optimal tracking control for a class of nonlinear discrete-time systems with time delays based on heuristic dynamic programming.

PubMed

Zhang, Huaguang; Song, Ruizhuo; Wei, Qinglai; Zhang, Tieyan

2011-12-01

In this paper, a novel heuristic dynamic programming (HDP) iteration algorithm is proposed to solve the optimal tracking control problem for a class of nonlinear discrete-time systems with time delays. The novel algorithm contains state updating, control policy iteration, and performance index iteration. To get the optimal states, the states are also updated. Furthermore, the "backward iteration" is applied to state updating. Two neural networks are used to approximate the performance index function and compute the optimal control policy for facilitating the implementation of HDP iteration algorithm. At last, we present two examples to demonstrate the effectiveness of the proposed HDP iteration algorithm.

Culture: copying, compression, and conventionality.

PubMed

Tamariz, Mónica; Kirby, Simon

2015-01-01

Through cultural transmission, repeated learning by new individuals transforms cultural information, which tends to become increasingly compressible (Kirby, Cornish, & Smith, ; Smith, Tamariz, & Kirby, ). Existing diffusion chain studies include in their design two processes that could be responsible for this tendency: learning (storing patterns in memory) and reproducing (producing the patterns again). This paper manipulates the presence of learning in a simple iterated drawing design experiment. We find that learning seems to be the causal factor behind the increase in compressibility observed in the transmitted information, while reproducing is a source of random heritable innovations. Only a theory invoking these two aspects of cultural learning will be able to explain human culture's fundamental balance between stability and innovation. Copyright © 2014 Cognitive Science Society, Inc.

Semisupervised Clustering by Iterative Partition and Regression with Neuroscience Applications

PubMed Central

Qian, Guoqi; Wu, Yuehua; Ferrari, Davide; Qiao, Puxue; Hollande, Frédéric

2016-01-01

Regression clustering is a mixture of unsupervised and supervised statistical learning and data mining method which is found in a wide range of applications including artificial intelligence and neuroscience. It performs unsupervised learning when it clusters the data according to their respective unobserved regression hyperplanes. The method also performs supervised learning when it fits regression hyperplanes to the corresponding data clusters. Applying regression clustering in practice requires means of determining the underlying number of clusters in the data, finding the cluster label of each data point, and estimating the regression coefficients of the model. In this paper, we review the estimation and selection issues in regression clustering with regard to the least squares and robust statistical methods. We also provide a model selection based technique to determine the number of regression clusters underlying the data. We further develop a computing procedure for regression clustering estimation and selection. Finally, simulation studies are presented for assessing the procedure, together with analyzing a real data set on RGB cell marking in neuroscience to illustrate and interpret the method. PMID:27212939

Learning the inverse kinetics of an octopus-like manipulator in three-dimensional space.

PubMed

Giorelli, M; Renda, F; Calisti, M; Arienti, A; Ferri, G; Laschi, C

2015-05-13

This work addresses the inverse kinematics problem of a bioinspired octopus-like manipulator moving in three-dimensional space. The bioinspired manipulator has a conical soft structure that confers the ability of twirling around objects as a real octopus arm does. Despite the simple design, the soft conical shape manipulator driven by cables is described by nonlinear differential equations, which are difficult to solve analytically. Since exact solutions of the equations are not available, the Jacobian matrix cannot be calculated analytically and the classical iterative methods cannot be used. To overcome the intrinsic problems of methods based on the Jacobian matrix, this paper proposes a neural network learning the inverse kinematics of a soft octopus-like manipulator driven by cables. After the learning phase, a feed-forward neural network is able to represent the relation between manipulator tip positions and forces applied to the cables. Experimental results show that a desired tip position can be achieved in a short time, since heavy computations are avoided, with a degree of accuracy of 8% relative average error with respect to the total arm length.

Adaptive Baseline Enhances EM-Based Policy Search: Validation in a View-Based Positioning Task of a Smartphone Balancer

PubMed Central

Wang, Jiexin; Uchibe, Eiji; Doya, Kenji

2017-01-01

EM-based policy search methods estimate a lower bound of the expected return from the histories of episodes and iteratively update the policy parameters using the maximum of a lower bound of expected return, which makes gradient calculation and learning rate tuning unnecessary. Previous algorithms like Policy learning by Weighting Exploration with the Returns, Fitness Expectation Maximization, and EM-based Policy Hyperparameter Exploration implemented the mechanisms to discard useless low-return episodes either implicitly or using a fixed baseline determined by the experimenter. In this paper, we propose an adaptive baseline method to discard worse samples from the reward history and examine different baselines, including the mean, and multiples of SDs from the mean. The simulation results of benchmark tasks of pendulum swing up and cart-pole balancing, and standing up and balancing of a two-wheeled smartphone robot showed improved performances. We further implemented the adaptive baseline with mean in our two-wheeled smartphone robot hardware to test its performance in the standing up and balancing task, and a view-based approaching task. Our results showed that with adaptive baseline, the method outperformed the previous algorithms and achieved faster, and more precise behaviors at a higher successful rate. PMID:28167910

A machine learning approach as a surrogate of finite element analysis-based inverse method to estimate the zero-pressure geometry of human thoracic aorta.

PubMed

Liang, Liang; Liu, Minliang; Martin, Caitlin; Sun, Wei

2018-05-09

Advances in structural finite element analysis (FEA) and medical imaging have made it possible to investigate the in vivo biomechanics of human organs such as blood vessels, for which organ geometries at the zero-pressure level need to be recovered. Although FEA-based inverse methods are available for zero-pressure geometry estimation, these methods typically require iterative computation, which are time-consuming and may be not suitable for time-sensitive clinical applications. In this study, by using machine learning (ML) techniques, we developed an ML model to estimate the zero-pressure geometry of human thoracic aorta given 2 pressurized geometries of the same patient at 2 different blood pressure levels. For the ML model development, a FEA-based method was used to generate a dataset of aorta geometries of 3125 virtual patients. The ML model, which was trained and tested on the dataset, is capable of recovering zero-pressure geometries consistent with those generated by the FEA-based method. Thus, this study demonstrates the feasibility and great potential of using ML techniques as a fast surrogate of FEA-based inverse methods to recover zero-pressure geometries of human organs. Copyright © 2018 John Wiley & Sons, Ltd.

A Novel Approach to Medical Student Peer-assisted Learning Through Case-based Simulations

PubMed Central

Jauregui, Joshua; Bright, Steven; Strote, Jared; Shandro, Jamie

2018-01-01

Introduction Peer-assisted learning (PAL) is the development of new knowledge and skills through active learning support from peers. Benefits of PAL include introduction of teaching skills for students, creation of a safe learning environment, and efficient use of faculty time. We present a novel approach to PAL in an emergency medicine (EM) clerkship curriculum using an inexpensive, tablet-based app for students to cooperatively present and perform low-fidelity, case-based simulations that promotes accountability for student learning, fosters teaching skills, and economizes faculty presence. Methods We developed five clinical cases in the style of EM oral boards. Fourth-year medical students were each assigned a unique case one week in advance. Students also received an instructional document and a video example detailing how to lead a case. During the 90-minute session, students were placed in small groups of 3–5 students and rotated between facilitating their assigned cases and participating as a team for the cases presented by their fellow students. Cases were supplemented with a half-mannequin that can be intubated, airway supplies, and a tablet-based app (SimMon, $22.99) to remotely display and update vital signs. One faculty member rotated among groups to provide additional assistance and clarification. Three EM faculty members iteratively developed a survey, based on the literature and pilot tested it with fourth-year medical students, to evaluate the course. Results 135 medical students completed the course and course evaluation survey. Learner satisfaction was high with an overall score of 4.6 on a 5-point Likert scale. In written comments, students reported that small groups with minimal faculty involvement provided a safe learning environment and a unique opportunity to lead a group of peers. They felt that PAL was more effective than traditional simulations for learning. Faculty reported that students remained engaged and required minimal oversight. Conclusion Unlike other simulations, our combination of brief, student-assisted cases using low-fidelity simulation provides a cost-, resource- and time-effective way to implement a medical student clerkship educational experience. PMID:29383080

A Novel Approach to Medical Student Peer-assisted Learning Through Case-based Simulations.

PubMed

Jauregui, Joshua; Bright, Steven; Strote, Jared; Shandro, Jamie

2018-01-01

Peer-assisted learning (PAL) is the development of new knowledge and skills through active learning support from peers. Benefits of PAL include introduction of teaching skills for students, creation of a safe learning environment, and efficient use of faculty time. We present a novel approach to PAL in an emergency medicine (EM) clerkship curriculum using an inexpensive, tablet-based app for students to cooperatively present and perform low-fidelity, case-based simulations that promotes accountability for student learning, fosters teaching skills, and economizes faculty presence. We developed five clinical cases in the style of EM oral boards. Fourth-year medical students were each assigned a unique case one week in advance. Students also received an instructional document and a video example detailing how to lead a case. During the 90-minute session, students were placed in small groups of 3-5 students and rotated between facilitating their assigned cases and participating as a team for the cases presented by their fellow students. Cases were supplemented with a half-mannequin that can be intubated, airway supplies, and a tablet-based app (SimMon, $22.99) to remotely display and update vital signs. One faculty member rotated among groups to provide additional assistance and clarification. Three EM faculty members iteratively developed a survey, based on the literature and pilot tested it with fourth-year medical students, to evaluate the course. 135 medical students completed the course and course evaluation survey. Learner satisfaction was high with an overall score of 4.6 on a 5-point Likert scale. In written comments, students reported that small groups with minimal faculty involvement provided a safe learning environment and a unique opportunity to lead a group of peers. They felt that PAL was more effective than traditional simulations for learning. Faculty reported that students remained engaged and required minimal oversight. Unlike other simulations, our combination of brief, student-assisted cases using low-fidelity simulation provides a cost-, resource- and time-effective way to implement a medical student clerkship educational experience.

Manifold regularized matrix completion for multi-label learning with ADMM.

PubMed

Liu, Bin; Li, Yingming; Xu, Zenglin

2018-05-01

Multi-label learning is a common machine learning problem arising from numerous real-world applications in diverse fields, e.g, natural language processing, bioinformatics, information retrieval and so on. Among various multi-label learning methods, the matrix completion approach has been regarded as a promising approach to transductive multi-label learning. By constructing a joint matrix comprising the feature matrix and the label matrix, the missing labels of test samples are regarded as missing values of the joint matrix. With the low-rank assumption of the constructed joint matrix, the missing labels can be recovered by minimizing its rank. Despite its success, most matrix completion based approaches ignore the smoothness assumption of unlabeled data, i.e., neighboring instances should also share a similar set of labels. Thus they may under exploit the intrinsic structures of data. In addition, the matrix completion problem can be less efficient. To this end, we propose to efficiently solve the multi-label learning problem as an enhanced matrix completion model with manifold regularization, where the graph Laplacian is used to ensure the label smoothness over it. To speed up the convergence of our model, we develop an efficient iterative algorithm, which solves the resulted nuclear norm minimization problem with the alternating direction method of multipliers (ADMM). Experiments on both synthetic and real-world data have shown the promising results of the proposed approach. Copyright © 2018 Elsevier Ltd. All rights reserved.

Superresolution radar imaging based on fast inverse-free sparse Bayesian learning for multiple measurement vectors

NASA Astrophysics Data System (ADS)

He, Xingyu; Tong, Ningning; Hu, Xiaowei

2018-01-01

Compressive sensing has been successfully applied to inverse synthetic aperture radar (ISAR) imaging of moving targets. By exploiting the block sparse structure of the target image, sparse solution for multiple measurement vectors (MMV) can be applied in ISAR imaging and a substantial performance improvement can be achieved. As an effective sparse recovery method, sparse Bayesian learning (SBL) for MMV involves a matrix inverse at each iteration. Its associated computational complexity grows significantly with the problem size. To address this problem, we develop a fast inverse-free (IF) SBL method for MMV. A relaxed evidence lower bound (ELBO), which is computationally more amiable than the traditional ELBO used by SBL, is obtained by invoking fundamental property for smooth functions. A variational expectation-maximization scheme is then employed to maximize the relaxed ELBO, and a computationally efficient IF-MSBL algorithm is proposed. Numerical results based on simulated and real data show that the proposed method can reconstruct row sparse signal accurately and obtain clear superresolution ISAR images. Moreover, the running time and computational complexity are reduced to a great extent compared with traditional SBL methods.