Multi-level machine learning prediction of protein-protein interactions in Saccharomyces cerevisiae.

PubMed

Zubek, Julian; Tatjewski, Marcin; Boniecki, Adam; Mnich, Maciej; Basu, Subhadip; Plewczynski, Dariusz

2015-01-01

Accurate identification of protein-protein interactions (PPI) is the key step in understanding proteins' biological functions, which are typically context-dependent. Many existing PPI predictors rely on aggregated features from protein sequences, however only a few methods exploit local information about specific residue contacts. In this work we present a two-stage machine learning approach for prediction of protein-protein interactions. We start with the carefully filtered data on protein complexes available for Saccharomyces cerevisiae in the Protein Data Bank (PDB) database. First, we build linear descriptions of interacting and non-interacting sequence segment pairs based on their inter-residue distances. Secondly, we train machine learning classifiers to predict binary segment interactions for any two short sequence fragments. The final prediction of the protein-protein interaction is done using the 2D matrix representation of all-against-all possible interacting sequence segments of both analysed proteins. The level-I predictor achieves 0.88 AUC for micro-scale, i.e., residue-level prediction. The level-II predictor improves the results further by a more complex learning paradigm. We perform 30-fold macro-scale, i.e., protein-level cross-validation experiment. The level-II predictor using PSIPRED-predicted secondary structure reaches 0.70 precision, 0.68 recall, and 0.70 AUC, whereas other popular methods provide results below 0.6 threshold (recall, precision, AUC). Our results demonstrate that multi-scale sequence features aggregation procedure is able to improve the machine learning results by more than 10% as compared to other sequence representations. Prepared datasets and source code for our experimental pipeline are freely available for download from: http://zubekj.github.io/mlppi/ (open source Python implementation, OS independent).

How Multi-Levels of Individual and Team Learning Interact in a Public Healthcare Organisation: A Conceptual Framework

ERIC Educational Resources Information Center

Doyle, Louise; Kelliher, Felicity; Harrington, Denis

2016-01-01

The aim of this paper is to review the relevant literature on organisational learning and offer a preliminary conceptual framework as a basis to explore how the multi-levels of individual learning and team learning interact in a public healthcare organisation. The organisational learning literature highlights a need for further understanding of…

Using Ensemble Decisions and Active Selection to Improve Low-Cost Labeling for Multi-View Data

NASA Technical Reports Server (NTRS)

Rebbapragada, Umaa; Wagstaff, Kiri L.

2011-01-01

This paper seeks to improve low-cost labeling in terms of training set reliability (the fraction of correctly labeled training items) and test set performance for multi-view learning methods. Co-training is a popular multiview learning method that combines high-confidence example selection with low-cost (self) labeling. However, co-training with certain base learning algorithms significantly reduces training set reliability, causing an associated drop in prediction accuracy. We propose the use of ensemble labeling to improve reliability in such cases. We also discuss and show promising results on combining low-cost ensemble labeling with active (low-confidence) example selection. We unify these example selection and labeling strategies under collaborative learning, a family of techniques for multi-view learning that we are developing for distributed, sensor-network environments.

A Collaborative Learning Network Approach to Improvement: The CUSP Learning Network.

PubMed

Weaver, Sallie J; Lofthus, Jennifer; Sawyer, Melinda; Greer, Lee; Opett, Kristin; Reynolds, Catherine; Wyskiel, Rhonda; Peditto, Stephanie; Pronovost, Peter J

2015-04-01

Collaborative improvement networks draw on the science of collaborative organizational learning and communities of practice to facilitate peer-to-peer learning, coaching, and local adaption. Although significant improvements in patient safety and quality have been achieved through collaborative methods, insight regarding how collaborative networks are used by members is needed. Improvement Strategy: The Comprehensive Unit-based Safety Program (CUSP) Learning Network is a multi-institutional collaborative network that is designed to facilitate peer-to-peer learning and coaching specifically related to CUSP. Member organizations implement all or part of the CUSP methodology to improve organizational safety culture, patient safety, and care quality. Qualitative case studies developed by participating members examine the impact of network participation across three levels of analysis (unit, hospital, health system). In addition, results of a satisfaction survey designed to evaluate member experiences were collected to inform network development. Common themes across case studies suggest that members found value in collaborative learning and sharing strategies across organizational boundaries related to a specific improvement strategy. The CUSP Learning Network is an example of network-based collaborative learning in action. Although this learning network focuses on a particular improvement methodology-CUSP-there is clear potential for member-driven learning networks to grow around other methods or topic areas. Such collaborative learning networks may offer a way to develop an infrastructure for longer-term support of improvement efforts and to more quickly diffuse creative sustainment strategies.

A Sparse Bayesian Learning Algorithm for White Matter Parameter Estimation from Compressed Multi-shell Diffusion MRI.

PubMed

Pisharady, Pramod Kumar; Sotiropoulos, Stamatios N; Sapiro, Guillermo; Lenglet, Christophe

2017-09-01

We propose a sparse Bayesian learning algorithm for improved estimation of white matter fiber parameters from compressed (under-sampled q-space) multi-shell diffusion MRI data. The multi-shell data is represented in a dictionary form using a non-monoexponential decay model of diffusion, based on continuous gamma distribution of diffusivities. The fiber volume fractions with predefined orientations, which are the unknown parameters, form the dictionary weights. These unknown parameters are estimated with a linear un-mixing framework, using a sparse Bayesian learning algorithm. A localized learning of hyperparameters at each voxel and for each possible fiber orientations improves the parameter estimation. Our experiments using synthetic data from the ISBI 2012 HARDI reconstruction challenge and in-vivo data from the Human Connectome Project demonstrate the improvements.

[Emergency Doctor Training for Psychiatric Emergencies: Evaluation of an Interactive Training Program].

PubMed

Flüchter, Peter; Müller, Vincent; Bischof, Felix; Pajonk, Frank-Gerald Bernhard

2017-03-01

Aim Emergency physicians are often confronted with psychiatric emergencies, but are not well trained for it and often feel unable to cope sufficiently with them. The aim of this investigation was to examine whether multisensoric training may improve learning effects in the training of emergency physicians with regard to psychiatric emergencies. Method Participation in a multi-modal, multi-media training program with video case histories and subsequent evaluation by questionnaire. Results 66 emergency physicians assessed their learning effects. 75 % or 73 % rated it as "rather high" or "very high". In particular, in comparison with classical training/self-study 89 % assessed the effects in learning as "rather high" or "very high" . Conclusion This training receives a high level of acceptance. Using videos, learning content may be provided more practice-related. Thus, emergency physicians are able to develop a greater understanding of psychiatric emergencies. © Georg Thieme Verlag KG Stuttgart · New York.

Multi-task feature learning by using trace norm regularization

NASA Astrophysics Data System (ADS)

Jiangmei, Zhang; Binfeng, Yu; Haibo, Ji; Wang, Kunpeng

2017-11-01

Multi-task learning can extract the correlation of multiple related machine learning problems to improve performance. This paper considers applying the multi-task learning method to learn a single task. We propose a new learning approach, which employs the mixture of expert model to divide a learning task into several related sub-tasks, and then uses the trace norm regularization to extract common feature representation of these sub-tasks. A nonlinear extension of this approach by using kernel is also provided. Experiments conducted on both simulated and real data sets demonstrate the advantage of the proposed approach.

Digital case-based learning system in school.

PubMed

Gu, Peipei; Guo, Jiayang

2017-01-01

With the continuing growth of multi-media learning resources, it is important to offer methods helping learners to explore and acquire relevant learning information effectively. As services that organize multi-media learning materials together to support programming learning, the digital case-based learning system is needed. In order to create a case-oriented e-learning system, this paper concentrates on the digital case study of multi-media resources and learning processes with an integrated framework. An integration of multi-media resources, testing and learning strategies recommendation as the learning unit is proposed in the digital case-based learning framework. The learning mechanism of learning guidance, multi-media materials learning and testing feedback is supported in our project. An improved personalized genetic algorithm which incorporates preference information and usage degree into the crossover and mutation process is proposed to assemble the personalized test sheet for each learner. A learning strategies recommendation solution is proposed to recommend learning strategies for learners to help them to learn. The experiments are conducted to prove that the proposed approaches are capable of constructing personalized sheets and the effectiveness of the framework.

Digital case-based learning system in school

PubMed Central

Gu, Peipei

2017-01-01

With the continuing growth of multi-media learning resources, it is important to offer methods helping learners to explore and acquire relevant learning information effectively. As services that organize multi-media learning materials together to support programming learning, the digital case-based learning system is needed. In order to create a case-oriented e-learning system, this paper concentrates on the digital case study of multi-media resources and learning processes with an integrated framework. An integration of multi-media resources, testing and learning strategies recommendation as the learning unit is proposed in the digital case-based learning framework. The learning mechanism of learning guidance, multi-media materials learning and testing feedback is supported in our project. An improved personalized genetic algorithm which incorporates preference information and usage degree into the crossover and mutation process is proposed to assemble the personalized test sheet for each learner. A learning strategies recommendation solution is proposed to recommend learning strategies for learners to help them to learn. The experiments are conducted to prove that the proposed approaches are capable of constructing personalized sheets and the effectiveness of the framework. PMID:29107965

Reading for Pleasure: More than Just a Distant Possibility?

ERIC Educational Resources Information Center

Barber, Karen Slikas

2014-01-01

Much has been written about the importance of extensive reading for the development of language fluency, yet it is not often an activity of choice by students as a means of improving language learning. Many of my multi-level (elementary-intermediate) Adult Migrant English Program (AMEP) Certificates in Spoken and Written English (CSWE) students…

Student Query Trend Assessment with Semantical Annotation and Artificial Intelligent Multi-Agents

ERIC Educational Resources Information Center

Malik, Kaleem Razzaq; Mir, Rizwan Riaz; Farhan, Muhammad; Rafiq, Tariq; Aslam, Muhammad

2017-01-01

Research in era of data representation to contribute and improve key data policy involving the assessment of learning, training and English language competency. Students are required to communicate in English with high level impact using language and influence. The electronic technology works to assess students' questions positively enabling…

Multi-agent Reinforcement Learning Model for Effective Action Selection

NASA Astrophysics Data System (ADS)

Youk, Sang Jo; Lee, Bong Keun

Reinforcement learning is a sub area of machine learning concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In the case of multi-agent, especially, which state space and action space gets very enormous in compared to single agent, so it needs to take most effective measure available select the action strategy for effective reinforcement learning. This paper proposes a multi-agent reinforcement learning model based on fuzzy inference system in order to improve learning collect speed and select an effective action in multi-agent. This paper verifies an effective action select strategy through evaluation tests based on Robocop Keep away which is one of useful test-beds for multi-agent. Our proposed model can apply to evaluate efficiency of the various intelligent multi-agents and also can apply to strategy and tactics of robot soccer system.

Local Implementation Effectiveness of a Multi-Tier System of Support in Elementary School Settings

ERIC Educational Resources Information Center

Houlton, Terry P.

2017-01-01

Ensuring all students learn at high levels is demanding. Multi-tier systems of supports (MTSS) has shown promise as a way to promote high levels of learning for all students while catching students who are struggling to learn. However, implementing MTSS models in school districts and schools has seen its challenges. The context of an individual…

Multi-View Multi-Instance Learning Based on Joint Sparse Representation and Multi-View Dictionary Learning.

PubMed

Li, Bing; Yuan, Chunfeng; Xiong, Weihua; Hu, Weiming; Peng, Houwen; Ding, Xinmiao; Maybank, Steve

2017-12-01

In multi-instance learning (MIL), the relations among instances in a bag convey important contextual information in many applications. Previous studies on MIL either ignore such relations or simply model them with a fixed graph structure so that the overall performance inevitably degrades in complex environments. To address this problem, this paper proposes a novel multi-view multi-instance learning algorithm (MIL) that combines multiple context structures in a bag into a unified framework. The novel aspects are: (i) we propose a sparse -graph model that can generate different graphs with different parameters to represent various context relations in a bag, (ii) we propose a multi-view joint sparse representation that integrates these graphs into a unified framework for bag classification, and (iii) we propose a multi-view dictionary learning algorithm to obtain a multi-view graph dictionary that considers cues from all views simultaneously to improve the discrimination of the MIL. Experiments and analyses in many practical applications prove the effectiveness of the M IL.

Identifying associations between pig pathologies using a multi-dimensional machine learning methodology.

PubMed

Sanchez-Vazquez, Manuel J; Nielen, Mirjam; Edwards, Sandra A; Gunn, George J; Lewis, Fraser I

2012-08-31

Abattoir detected pathologies are of crucial importance to both pig production and food safety. Usually, more than one pathology coexist in a pig herd although it often remains unknown how these different pathologies interrelate to each other. Identification of the associations between different pathologies may facilitate an improved understanding of their underlying biological linkage, and support the veterinarians in encouraging control strategies aimed at reducing the prevalence of not just one, but two or more conditions simultaneously. Multi-dimensional machine learning methodology was used to identify associations between ten typical pathologies in 6485 batches of slaughtered finishing pigs, assisting the comprehension of their biological association. Pathologies potentially associated with septicaemia (e.g. pericarditis, peritonitis) appear interrelated, suggesting on-going bacterial challenges by pathogens such as Haemophilus parasuis and Streptococcus suis. Furthermore, hepatic scarring appears interrelated with both milk spot livers (Ascaris suum) and bacteria-related pathologies, suggesting a potential multi-pathogen nature for this pathology. The application of novel multi-dimensional machine learning methodology provided new insights into how typical pig pathologies are potentially interrelated at batch level. The methodology presented is a powerful exploratory tool to generate hypotheses, applicable to a wide range of studies in veterinary research.

Bi-level multi-source learning for heterogeneous block-wise missing data.

PubMed

Xiang, Shuo; Yuan, Lei; Fan, Wei; Wang, Yalin; Thompson, Paul M; Ye, Jieping

2014-11-15

Bio-imaging technologies allow scientists to collect large amounts of high-dimensional data from multiple heterogeneous sources for many biomedical applications. In the study of Alzheimer's Disease (AD), neuroimaging data, gene/protein expression data, etc., are often analyzed together to improve predictive power. Joint learning from multiple complementary data sources is advantageous, but feature-pruning and data source selection are critical to learn interpretable models from high-dimensional data. Often, the data collected has block-wise missing entries. In the Alzheimer's Disease Neuroimaging Initiative (ADNI), most subjects have MRI and genetic information, but only half have cerebrospinal fluid (CSF) measures, a different half has FDG-PET; only some have proteomic data. Here we propose how to effectively integrate information from multiple heterogeneous data sources when data is block-wise missing. We present a unified "bi-level" learning model for complete multi-source data, and extend it to incomplete data. Our major contributions are: (1) our proposed models unify feature-level and source-level analysis, including several existing feature learning approaches as special cases; (2) the model for incomplete data avoids imputing missing data and offers superior performance; it generalizes to other applications with block-wise missing data sources; (3) we present efficient optimization algorithms for modeling complete and incomplete data. We comprehensively evaluate the proposed models including all ADNI subjects with at least one of four data types at baseline: MRI, FDG-PET, CSF and proteomics. Our proposed models compare favorably with existing approaches. © 2013 Elsevier Inc. All rights reserved.

A requirements engineering approach for improving the quality of diabetes education websites.

PubMed

Shabestari, Omid; Roudsari, Abdul

2011-01-01

Diabetes Mellitus is a major chronic disease with multi-organ involvement and high-cost complications. Although it has been proved that structured education can control the risk of developing these complications, there is big room for improvement in the educational services for these patients. e-learning can be a good solution to fill this gap. Most of the current e-learning solutions for diabetes were designed by computer experts and healthcare professionals but the patients, as end-users of these systems, haven't been deeply involved in the design process. Considering the expectations of the patients, this article investigates a requirement engineering process comparing the level of importance given to different attributes of the e-learning by patients and healthcare professionals. The results of this comparison can be used for improving the currently developed online diabetes education systems.

Talking of Fabric: A Multi-Dimensional Model of Quality in Education

ERIC Educational Resources Information Center

Nikel, Jutta; Lowe, John

2010-01-01

"Improving quality" has become a key phrase in policy and academic discourses on education in low-income countries, reflecting concerns that the success in increasing enrolment and widening access to schooling is being undermined by low-quality teaching and learning, and subsequent low levels of skills and knowledge among school leavers. We wish…

Literacy Coaching to Improve Student Reading Achievement: A Multi-Level Mediation Model

ERIC Educational Resources Information Center

Matsumura, Lindsay Clare; Garnier, Helen E.; Spybrook, Jessaca

2013-01-01

In a longitudinal group-randomized trial, we explore the key role of the quality of classroom text discussions in mediating the effects of Content-Focused Coaching (CFC) on student reading achievement (2983 students, 167 teachers). Schools in the United States serving large numbers of minority and English language learning (ELL) students from…

Nongraded Primary Programs: Possibilities for Improving Practice for Teachers. Practitioner Brief Number 4

ERIC Educational Resources Information Center

McIntyre, Ellen; Kyle, Diane

2002-01-01

In nongraded, multi-age classrooms, children have the opportunity to learn a great deal from their more proficient classmates. Children in multi-age, nongraded programs often learn that children differ, and they learn to assist each other in productive ways. The organizational scheme has the potential to remove much of the competition of…

Efficacy of simulation-based trauma team training of non-technical skills. A systematic review.

PubMed

Gjeraa, K; Møller, T P; Østergaard, D

2014-08-01

Trauma resuscitation is a complex situation, and most organisations have multi-professional trauma teams. Non-technical skills are challenged during trauma resuscitation, and they play an important role in the prevention of critical incidents. Simulation-based training of these is recommended. Our research question was: Does simulation-based trauma team training of non-technical skills have effect on reaction, learning, behaviour or patient outcome? The authors searched PubMed, EMBASE and the Cochrane Library and found 13 studies eligible for analysis. We described and compared the educational interventions and the evaluations of effect according to the four Kirkpatrick levels: reaction, learning (knowledge, skills, attitudes), behaviour (in a clinical setting) and patient outcome. No studies were randomised, controlled and blinded, resulting in a moderate to high risk of bias. The multi-professional trauma teams had positive reactions to simulation-based training of non-technical skills. Knowledge and skills improved in all studies evaluating the effect on learning. Three studies found improvements in team performance (behaviour) in the clinical setting. One of these found difficulties in maintaining these skills. Two studies evaluated on patient outcome, of which none showed improvements in mortality, complication rate or duration of hospitalisation. A significant effect on learning was found after simulation-based training of the multi-professional trauma team in non-technical skills. Three studies demonstrated significantly increased clinical team performance. No effect on patient outcome was found. All studies had a moderate to high risk of bias. More comprehensive randomised studies are needed to evaluate the effect on patient outcome. © 2014 The Acta Anaesthesiologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.

Five years of lesson modification to implement non-traditional learning sessions in a traditional-delivery curriculum: A retrospective assessment using applied implementation variables.

PubMed

Gleason, Shaun E; McNair, Bryan; Kiser, Tyree H; Franson, Kari L

Non-traditional learning (NTL), including aspects of self-directed learning (SDL), may address self-awareness development needs. Many factors can impact successful implementation of NTL. To share our multi-year experience with modifications that aim to improve NTL sessions in a traditional curriculum. To improve understanding of applied implementation variables (some of which were based on successful SDL implementation components) that impact NTL. We delivered a single lesson in a traditional-delivery curriculum once annually for five years, varying delivery annually in response to student learning and reaction-to-learning results. At year 5, we compared student learning and reaction-to-learning to applied implementation factors using logistic regression. Higher instructor involvement and overall NTL levels predicted correct exam responses (p=0.0007 and p<0.0001, respectively). Exam responses were statistically equivalent between the most traditional and highest overall NTL deliveries. Students rated instructor presentation skills and teaching methods higher when greater instructor involvement (p<0.0001, both) and lower overall NTL levels (P<0.0001, both) were used. Students perceived that teaching methods were most effective when lower student involvement and higher technology levels (p<0.0001, both) were used. When implementing NTL sessions as a single lesson in a traditional-delivery curriculum, instructor involvement appears essential, while the impact of student involvement and educational technology levels varies. Copyright © 2017 Elsevier Inc. All rights reserved.

Quicker Q-Learning in Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Agogino, Adrian K.; Tumer, Kagan

2005-01-01

Multi-agent learning in Markov Decisions Problems is challenging because of the presence ot two credit assignment problems: 1) How to credit an action taken at time step t for rewards received at t' greater than t; and 2) How to credit an action taken by agent i considering the system reward is a function of the actions of all the agents. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning OK TD(lambda) The second credit assi,onment problem is typically addressed either by hand-crafting reward functions that assign proper credit to an agent, or by making certain independence assumptions about an agent's state-space and reward function. To address both credit assignment problems simultaneously, we propose the Q Updates with Immediate Counterfactual Rewards-learning (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. Instead of assuming that an agent s value function can be made independent of other agents, this method suppresses the impact of other agents using counterfactual rewards. Results on multi-agent grid-world problems over multiple topologies show that QUICR-learning can achieve up to thirty fold improvements in performance over both conventional and local Q-learning in the largest tested systems.

Toward an Integrated Online Learning Environment

NASA Astrophysics Data System (ADS)

Teodorescu, Raluca E.; Pawl, Andrew; Rayyan, Saif; Barrantes, Analia; Pritchard, David E.

2010-10-01

We are building in LON-CAPA an integrated learning environment that will enable the development, dissemination and evaluation of PER-based material. This environment features a collection of multi-level research-based homework sets organized by topic and cognitive complexity. These sets are associated with learning modules that contain very short exposition of the content supplemented by integrated open-access videos, worked examples, simulations, and tutorials (some from ANDES). To assess students' performance accurately with respect to a system-wide standard, we plan to implement Item Response Theory. Together with other PER assessments and purposeful solicitation of student feedback, this will allow us to measure and improve the efficacy of various research-based materials, while getting insights into teaching and learning.

Exploring the potential of a multi-level approach to improve capability for continuous organizational improvement and learning in a Swedish healthcare region.

PubMed

Nyström, M E; Höög, E; Garvare, R; Andersson Bäck, M; Terris, D D; Hansson, J

2018-05-24

Eldercare and care of people with functional impairments is organized by the municipalities in Sweden. Improving care in these areas is complex, with multiple stakeholders and organizations. Appropriate strategies to develop capability for continuing organizational improvement and learning (COIL) are needed. The purpose of our study was to develop and pilot-test a flexible, multilevel approach for COIL capability building and to identify what it takes to achieve changes in key actors' approaches to COIL. The approach, named "Sustainable Improvement and Development through Strategic and Systematic Approaches" (SIDSSA), was applied through an action-research and action-learning intervention. The SIDSSA approach was tested in a regional research and development (R&D) unit, and in two municipalities handling care of the elderly and people with functional impairments. Our approach included a multilevel strategy, development loops of five flexible phases, and an action-learning loop. The approach was designed to support systems understanding, strategic focus, methodological practices, and change process knowledge - all of which required double-loop learning. Multiple qualitative methods, i.e., repeated interviews, process diaries, and documents, provided data for conventional content analyses. The new approach was successfully tested on all cases and adopted and sustained by the R&D unit. Participants reported new insights and skills. The development loop facilitated a sense of coherence and control during uncertainty, improved planning and problem analysis, enhanced mapping of context and conditions, and supported problem-solving at both the individual and unit levels. The systems-level view and structured approach helped participants to explain, motivate, and implement change initiatives, especially after working more systematically with mapping, analyses, and goal setting. An easily understood and generalizable model internalized by key organizational actors is an important step before more complex development models can be implemented. SIDSSA facilitated individual and group learning through action-learning and supported systems-level views and structured approaches across multiple organizational levels. Active involvement of diverse organizational functions and levels in the learning process was facilitated. However, the time frame was too short to fully test all aspects of the approach, specifically in reaching beyond the involved managers to front-line staff and patients.

Multi-Domain Transfer Learning for Early Diagnosis of Alzheimer's Disease.

PubMed

Cheng, Bo; Liu, Mingxia; Shen, Dinggang; Li, Zuoyong; Zhang, Daoqiang

2017-04-01

Recently, transfer learning has been successfully applied in early diagnosis of Alzheimer's Disease (AD) based on multi-domain data. However, most of existing methods only use data from a single auxiliary domain, and thus cannot utilize the intrinsic useful correlation information from multiple domains. Accordingly, in this paper, we consider the joint learning of tasks in multi-auxiliary domains and the target domain, and propose a novel Multi-Domain Transfer Learning (MDTL) framework for early diagnosis of AD. Specifically, the proposed MDTL framework consists of two key components: 1) a multi-domain transfer feature selection (MDTFS) model that selects the most informative feature subset from multi-domain data, and 2) a multi-domain transfer classification (MDTC) model that can identify disease status for early AD detection. We evaluate our method on 807 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database using baseline magnetic resonance imaging (MRI) data. The experimental results show that the proposed MDTL method can effectively utilize multi-auxiliary domain data for improving the learning performance in the target domain, compared with several state-of-the-art methods.

Generating highly accurate prediction hypotheses through collaborative ensemble learning

NASA Astrophysics Data System (ADS)

Arsov, Nino; Pavlovski, Martin; Basnarkov, Lasko; Kocarev, Ljupco

2017-03-01

Ensemble generation is a natural and convenient way of achieving better generalization performance of learning algorithms by gathering their predictive capabilities. Here, we nurture the idea of ensemble-based learning by combining bagging and boosting for the purpose of binary classification. Since the former improves stability through variance reduction, while the latter ameliorates overfitting, the outcome of a multi-model that combines both strives toward a comprehensive net-balancing of the bias-variance trade-off. To further improve this, we alter the bagged-boosting scheme by introducing collaboration between the multi-model’s constituent learners at various levels. This novel stability-guided classification scheme is delivered in two flavours: during or after the boosting process. Applied among a crowd of Gentle Boost ensembles, the ability of the two suggested algorithms to generalize is inspected by comparing them against Subbagging and Gentle Boost on various real-world datasets. In both cases, our models obtained a 40% generalization error decrease. But their true ability to capture details in data was revealed through their application for protein detection in texture analysis of gel electrophoresis images. They achieve improved performance of approximately 0.9773 AUROC when compared to the AUROC of 0.9574 obtained by an SVM based on recursive feature elimination.

Bi-level Multi-Source Learning for Heterogeneous Block-wise Missing Data

PubMed Central

Xiang, Shuo; Yuan, Lei; Fan, Wei; Wang, Yalin; Thompson, Paul M.; Ye, Jieping

2013-01-01

Bio-imaging technologies allow scientists to collect large amounts of high-dimensional data from multiple heterogeneous sources for many biomedical applications. In the study of Alzheimer's Disease (AD), neuroimaging data, gene/protein expression data, etc., are often analyzed together to improve predictive power. Joint learning from multiple complementary data sources is advantageous, but feature-pruning and data source selection are critical to learn interpretable models from high-dimensional data. Often, the data collected has block-wise missing entries. In the Alzheimer’s Disease Neuroimaging Initiative (ADNI), most subjects have MRI and genetic information, but only half have cerebrospinal fluid (CSF) measures, a different half has FDG-PET; only some have proteomic data. Here we propose how to effectively integrate information from multiple heterogeneous data sources when data is block-wise missing. We present a unified “bi-level” learning model for complete multi-source data, and extend it to incomplete data. Our major contributions are: (1) our proposed models unify feature-level and source-level analysis, including several existing feature learning approaches as special cases; (2) the model for incomplete data avoids imputing missing data and offers superior performance; it generalizes to other applications with block-wise missing data sources; (3) we present efficient optimization algorithms for modeling complete and incomplete data. We comprehensively evaluate the proposed models including all ADNI subjects with at least one of four data types at baseline: MRI, FDG-PET, CSF and proteomics. Our proposed models compare favorably with existing approaches. PMID:23988272

Multi-sensor physical activity recognition in free-living.

PubMed

Ellis, Katherine; Godbole, Suneeta; Kerr, Jacqueline; Lanckriet, Gert

Physical activity monitoring in free-living populations has many applications for public health research, weight-loss interventions, context-aware recommendation systems and assistive technologies. We present a system for physical activity recognition that is learned from a free-living dataset of 40 women who wore multiple sensors for seven days. The multi-level classification system first learns low-level codebook representations for each sensor and uses a random forest classifier to produce minute-level probabilities for each activity class. Then a higher-level HMM layer learns patterns of transitions and durations of activities over time to smooth the minute-level predictions. [Formula: see text].

Lessons learned and way forward from 6 years of Aerosol_cci

NASA Astrophysics Data System (ADS)

Popp, Thomas; de Leeuw, Gerrit; Pinnock, Simon

2017-04-01

Within the ESA Climate Change Initiative (CCI) Aerosol_cci (2010 - 2017) conducts intensive work to improve and qualify algorithms for the retrieval of aerosol information from European sensors. Meanwhile, several validated (multi-) decadal time series of different aerosol parameters from complementary sensors are available: Aerosol Optical Depth (AOD), stratospheric extinction profiles, a qualitative Absorbing Aerosol Index (AAI), fine mode AOD, mineral dust AOD; absorption information and aerosol layer height are in an evaluation phase and the multi-pixel GRASP algorithm for the POLDER instrument is used for selected regions. Validation (vs. AERONET, MAN) and inter-comparison to other satellite datasets (MODIS, MISR, SeaWIFS) proved the high quality of the available datasets comparable to other satellite retrievals and revealed needs for algorithm improvement (for example for higher AOD values) which were taken into account in an iterative evolution cycle. The datasets contain pixel level uncertainty estimates which were also validated and improved in the reprocessing. The use of an ensemble method was tested, where several algorithms are applied to the same sensor. The presentation will summarize and discuss the lessons learned from the 6 years of intensive collaboration and highlight major achievements (significantly improved AOD quality, fine mode AOD, dust AOD, pixel level uncertainties, ensemble approach); also limitations and remaining deficits shall be discussed. An outlook will discuss the way forward for the continuous algorithm improvement and re-processing together with opportunities for time series extension with successor instruments of the Sentinel family and the complementarity of the different satellite aerosol products.

The use of multi representative learning materials: definitive, macroscopic, microscopic, symbolic, and practice in analyzing students’ concept understanding

NASA Astrophysics Data System (ADS)

Susilaningsih, E.; Wulandari, C.; Supartono; Kasmui; Alighiri, D.

2018-03-01

This research aims to compose learning material which contains definitive macroscopic, microscopic and symbolic to analyze students’ conceptual understanding in acid-base learning materials. This research was conducted in eleven grade, natural science class, senior high school 1 (SMAN 1) Karangtengah, Demak province, Indonesia as the low level of students’ conceptual understanding and the high level of students’ misconception. The data collecting technique is by test to assess the cognitive aspect, questionnaire to assess students’ responses to multi representative learning materials (definitive, macroscopic, microscopic, symbolic), and observation to assess students’ macroscopic aspects. Three validators validate the multi-representative learning materials (definitive, macroscopic, microscopic, symbolic). The results of the research show that the multi-representative learning materials (definitive, macroscopic, microscopes, symbolic) being used is valid in the average score 62 of 75. The data is analyzed using the descriptive qualitative method. The results of the research show that 72.934 % students understand, 7.977 % less understand, 8.831 % do not understand, and 10.256 % misconception. In comparison, the second experiment class shows 54.970 % students understand, 5.263% less understand, 11.988 % do not understand, 27.777 % misconception. In conclusion, the application of multi representative learning materials (definitive, macroscopic, microscopic, symbolic) can be used to analyze the students’ understanding of acid-base materials.

Agent Reward Shaping for Alleviating Traffic Congestion

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Agogino, Adrian

2006-01-01

Traffic congestion problems provide a unique environment to study how multi-agent systems promote desired system level behavior. What is particularly interesting in this class of problems is that no individual action is intrinsically "bad" for the system but that combinations of actions among agents lead to undesirable outcomes, As a consequence, agents need to learn how to coordinate their actions with those of other agents, rather than learn a particular set of "good" actions. This problem is ubiquitous in various traffic problems, including selecting departure times for commuters, routes for airlines, and paths for data routers. In this paper we present a multi-agent approach to two traffic problems, where far each driver, an agent selects the most suitable action using reinforcement learning. The agent rewards are based on concepts from collectives and aim to provide the agents with rewards that are both easy to learn and that if learned, lead to good system level behavior. In the first problem, we study how agents learn the best departure times of drivers in a daily commuting environment and how following those departure times alleviates congestion. In the second problem, we study how agents learn to select desirable routes to improve traffic flow and minimize delays for. all drivers.. In both sets of experiments,. agents using collective-based rewards produced near optimal performance (93-96% of optimal) whereas agents using system rewards (63-68%) barely outperformed random action selection (62-64%) and agents using local rewards (48-72%) performed worse than random in some instances.

The effectiveness of multi modal representation text books to improve student's scientific literacy of senior high school students

NASA Astrophysics Data System (ADS)

Zakiya, Hanifah; Sinaga, Parlindungan; Hamidah, Ida

2017-05-01

The results of field studies showed the ability of science literacy of students was still low. One root of the problem lies in the books used in learning is not oriented toward science literacy component. This study focused on the effectiveness of the use of textbook-oriented provisioning capability science literacy by using multi modal representation. The text books development method used Design Representational Approach Learning to Write (DRALW). Textbook design which was applied to the topic of "Kinetic Theory of Gases" is implemented in XI grade students of high school learning. Effectiveness is determined by consideration of the effect and the normalized percentage gain value, while the hypothesis was tested using Independent T-test. The results showed that the textbooks which were developed using multi-mode representation science can improve the literacy skills of students. Based on the size of the effect size textbooks developed with representation multi modal was found effective in improving students' science literacy skills. The improvement was occurred in all the competence and knowledge of scientific literacy. The hypothesis testing showed that there was a significant difference on the ability of science literacy between class that uses textbooks with multi modal representation and the class that uses the regular textbook used in schools.

Multi-Domain Transfer Learning for Early Diagnosis of Alzheimer’s Disease

PubMed Central

Cheng, Bo; Liu, Mingxia; Li, Zuoyong

2017-01-01

Recently, transfer learning has been successfully applied in early diagnosis of Alzheimer’s Disease (AD) based on multi-domain data. However, most of existing methods only use data from a single auxiliary domain, and thus cannot utilize the intrinsic useful correlation information from multiple domains. Accordingly, in this paper, we consider the joint learning of tasks in multi-auxiliary domains and the target domain, and propose a novel Multi-Domain Transfer Learning (MDTL) framework for early diagnosis of AD. Specifically, the proposed MDTL framework consists of two key components: 1) a multi-domain transfer feature selection (MDTFS) model that selects the most informative feature subset from multi-domain data, and 2) a multidomain transfer classification (MDTC) model that can identify disease status for early AD detection. We evaluate our method on 807 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database using baseline magnetic resonance imaging (MRI) data. The experimental results show that the proposed MDTL method can effectively utilize multi-auxiliary domain data for improving the learning performance in the target domain, compared with several state-of-the-art methods. PMID:27928657

Co-Labeling for Multi-View Weakly Labeled Learning.

PubMed

Xu, Xinxing; Li, Wen; Xu, Dong; Tsang, Ivor W

2016-06-01

It is often expensive and time consuming to collect labeled training samples in many real-world applications. To reduce human effort on annotating training samples, many machine learning techniques (e.g., semi-supervised learning (SSL), multi-instance learning (MIL), etc.) have been studied to exploit weakly labeled training samples. Meanwhile, when the training data is represented with multiple types of features, many multi-view learning methods have shown that classifiers trained on different views can help each other to better utilize the unlabeled training samples for the SSL task. In this paper, we study a new learning problem called multi-view weakly labeled learning, in which we aim to develop a unified approach to learn robust classifiers by effectively utilizing different types of weakly labeled multi-view data from a broad range of tasks including SSL, MIL and relative outlier detection (ROD). We propose an effective approach called co-labeling to solve the multi-view weakly labeled learning problem. Specifically, we model the learning problem on each view as a weakly labeled learning problem, which aims to learn an optimal classifier from a set of pseudo-label vectors generated by using the classifiers trained from other views. Unlike traditional co-training approaches using a single pseudo-label vector for training each classifier, our co-labeling approach explores different strategies to utilize the predictions from different views, biases and iterations for generating the pseudo-label vectors, making our approach more robust for real-world applications. Moreover, to further improve the weakly labeled learning on each view, we also exploit the inherent group structure in the pseudo-label vectors generated from different strategies, which leads to a new multi-layer multiple kernel learning problem. Promising results for text-based image retrieval on the NUS-WIDE dataset as well as news classification and text categorization on several real-world multi-view datasets clearly demonstrate that our proposed co-labeling approach achieves state-of-the-art performance for various multi-view weakly labeled learning problems including multi-view SSL, multi-view MIL and multi-view ROD.

Hierarchical Learning of Tree Classifiers for Large-Scale Plant Species Identification.

PubMed

Fan, Jianping; Zhou, Ning; Peng, Jinye; Gao, Ling

2015-11-01

In this paper, a hierarchical multi-task structural learning algorithm is developed to support large-scale plant species identification, where a visual tree is constructed for organizing large numbers of plant species in a coarse-to-fine fashion and determining the inter-related learning tasks automatically. For a given parent node on the visual tree, it contains a set of sibling coarse-grained categories of plant species or sibling fine-grained plant species, and a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly for enhancing their discrimination power. The inter-level relationship constraint, e.g., a plant image must first be assigned to a parent node (high-level non-leaf node) correctly if it can further be assigned to the most relevant child node (low-level non-leaf node or leaf node) on the visual tree, is formally defined and leveraged to learn more discriminative tree classifiers over the visual tree. Our experimental results have demonstrated the effectiveness of our hierarchical multi-task structural learning algorithm on training more discriminative tree classifiers for large-scale plant species identification.

Physics Learning Strategies with Multi-touch Technology

NASA Astrophysics Data System (ADS)

Potter, Mark; Ilie, C.; Schofield, D.

2011-03-01

Advancements in technology have opened doorways to build new teaching and learning methods. Through conjunctive use of these technologies and methods, a classroom can be enriched to stimulate and improve student learning. The purpose of our research is to ascertain whether or not multi-touch technology enhances students' abilities to better comprehend and retain the knowledge taught in physics. At their basis, students learn via visual, aural, reading/writing, and kinesthetic styles. Labs provide for all but the aural style, while lectures lack kinesthetic learning. Pedagogical research indicates that kinesthetic learning is a fundamental, powerful, and ubiquitous learning style. By using multi-touch technology in lecture, not only can we accommodate kinesthetic learners, but we can also enrich the experiences of visual learners. Ushering to this wider array of students will hopefully lead to an increase in meaningful learning.

Argumentation Based Joint Learning: A Novel Ensemble Learning Approach

PubMed Central

Xu, Junyi; Yao, Li; Li, Le

2015-01-01

Recently, ensemble learning methods have been widely used to improve classification performance in machine learning. In this paper, we present a novel ensemble learning method: argumentation based multi-agent joint learning (AMAJL), which integrates ideas from multi-agent argumentation, ensemble learning, and association rule mining. In AMAJL, argumentation technology is introduced as an ensemble strategy to integrate multiple base classifiers and generate a high performance ensemble classifier. We design an argumentation framework named Arena as a communication platform for knowledge integration. Through argumentation based joint learning, high quality individual knowledge can be extracted, and thus a refined global knowledge base can be generated and used independently for classification. We perform numerous experiments on multiple public datasets using AMAJL and other benchmark methods. The results demonstrate that our method can effectively extract high quality knowledge for ensemble classifier and improve the performance of classification. PMID:25966359

Multi-representation based on scientific investigation for enhancing students’ representation skills

NASA Astrophysics Data System (ADS)

Siswanto, J.; Susantini, E.; Jatmiko, B.

2018-03-01

This research aims to implementation learning physics with multi-representation based on the scientific investigation for enhancing students’ representation skills, especially on the magnetic field subject. The research design is one group pretest-posttest. This research was conducted in the department of mathematics education, Universitas PGRI Semarang, with the sample is students of class 2F who take basic physics courses. The data were obtained by representation skills test and documentation of multi-representation worksheet. The Results show gain analysis value of .64 which means some medium improvements. The result of t-test (α = .05) is shows p-value = .001. This learning significantly improves students representation skills.

Learning Behavior Characterization with Multi-Feature, Hierarchical Activity Sequences

ERIC Educational Resources Information Center

Ye, Cheng; Segedy, James R.; Kinnebrew, John S.; Biswas, Gautam

2015-01-01

This paper discusses Multi-Feature Hierarchical Sequential Pattern Mining, MFH-SPAM, a novel algorithm that efficiently extracts patterns from students' learning activity sequences. This algorithm extends an existing sequential pattern mining algorithm by dynamically selecting the level of specificity for hierarchically-defined features…

Group-level spatio-temporal pattern recovery in MEG decoding using multi-task joint feature learning.

PubMed

Kia, Seyed Mostafa; Pedregosa, Fabian; Blumenthal, Anna; Passerini, Andrea

2017-06-15

The use of machine learning models to discriminate between patterns of neural activity has become in recent years a standard analysis approach in neuroimaging studies. Whenever these models are linear, the estimated parameters can be visualized in the form of brain maps which can aid in understanding how brain activity in space and time underlies a cognitive function. However, the recovered brain maps often suffer from lack of interpretability, especially in group analysis of multi-subject data. To facilitate the application of brain decoding in group-level analysis, we present an application of multi-task joint feature learning for group-level multivariate pattern recovery in single-trial magnetoencephalography (MEG) decoding. The proposed method allows for recovering sparse yet consistent patterns across different subjects, and therefore enhances the interpretability of the decoding model. Our experimental results demonstrate that the mutli-task joint feature learning framework is capable of recovering more meaningful patterns of varying spatio-temporally distributed brain activity across individuals while still maintaining excellent generalization performance. We compare the performance of the multi-task joint feature learning in terms of generalization, reproducibility, and quality of pattern recovery against traditional single-subject and pooling approaches on both simulated and real MEG datasets. These results can facilitate the usage of brain decoding for the characterization of fine-level distinctive patterns in group-level inference. Considering the importance of group-level analysis, the proposed approach can provide a methodological shift towards more interpretable brain decoding models. Copyright © 2017 Elsevier B.V. All rights reserved.

Community resilience under multi-hazards: time series measurement and it's strategies for improvement

NASA Astrophysics Data System (ADS)

Tian, Cong-shan; Fang, Yi-ping

2017-04-01

Multi - hazards stress is a big obsession that hampers the social and economic development in disaster - prone areas. There is a need to understand and manage drivers of vulnerability and adaptive capacity to the system of multiple geological hazards. Here we pilot three methods namely the multi - hazards resilience assessment model (new framework), the entropy weight method, and the assess social resilience to flood hazards model to measure the resilience to natural hazards of landslide and debris flow on community scale. Using one typical multi - hazards affected county in southwest China, 32 resilience indicators belonging to antecedent conditions, coping responses, adaptation (including learning), and hazard exposure are selected, and a composite index was calculated under the three methods mentioned above. Results show that the new framework reflected a more detailed fluctuation among the 16 years, despite of the overall similar trend between 2000 and 2015 under the three methods. Medical insurance coverage, unemployment insurance coverage, education degree, and hazard exposure are the main drivers of resilience. The most effective strategies for improving community resilience to multiple hazards are likely to be accelerating the development of education, improving the level of medical security, increasing unemployment insurance, and establishing multi - hazards prevention and mitigation systems.

Learning strategies and general cognitive ability as predictors of gender- specific academic achievement

PubMed Central

Ruffing, Stephanie; Wach, F. -Sophie; Spinath, Frank M.; Brünken, Roland; Karbach, Julia

2015-01-01

Recent research has revealed that learning behavior is associated with academic achievement at the college level, but the impact of specific learning strategies on academic success as well as gender differences therein are still not clear. Therefore, the aim of this study was to investigate gender differences in the incremental contribution of learning strategies over general cognitive ability in the prediction of academic achievement. The relationship between these variables was examined by correlation analyses. A set of t-tests was used to test for gender differences in learning strategies, whereas structural equation modeling as well as multi-group analyses were applied to investigate the incremental contribution of learning strategies for male and female students’ academic performance. The sample consisted of 461 students (mean age = 21.2 years, SD = 3.2). Correlation analyses revealed that general cognitive ability as well as the learning strategies effort, attention, and learning environment were positively correlated with academic achievement. Gender differences were found in the reported application of many learning strategies. Importantly, the prediction of achievement in structural equation modeling revealed that only effort explained incremental variance (10%) over general cognitive ability. Results of multi-group analyses showed no gender differences in this prediction model. This finding provides further knowledge regarding gender differences in learning research and the specific role of learning strategies for academic achievement. The incremental assessment of learning strategy use as well as gender-differences in their predictive value contributes to the understanding and improvement of successful academic development. PMID:26347698

Learning strategies and general cognitive ability as predictors of gender- specific academic achievement.

PubMed

Ruffing, Stephanie; Wach, F-Sophie; Spinath, Frank M; Brünken, Roland; Karbach, Julia

2015-01-01

Recent research has revealed that learning behavior is associated with academic achievement at the college level, but the impact of specific learning strategies on academic success as well as gender differences therein are still not clear. Therefore, the aim of this study was to investigate gender differences in the incremental contribution of learning strategies over general cognitive ability in the prediction of academic achievement. The relationship between these variables was examined by correlation analyses. A set of t-tests was used to test for gender differences in learning strategies, whereas structural equation modeling as well as multi-group analyses were applied to investigate the incremental contribution of learning strategies for male and female students' academic performance. The sample consisted of 461 students (mean age = 21.2 years, SD = 3.2). Correlation analyses revealed that general cognitive ability as well as the learning strategies effort, attention, and learning environment were positively correlated with academic achievement. Gender differences were found in the reported application of many learning strategies. Importantly, the prediction of achievement in structural equation modeling revealed that only effort explained incremental variance (10%) over general cognitive ability. Results of multi-group analyses showed no gender differences in this prediction model. This finding provides further knowledge regarding gender differences in learning research and the specific role of learning strategies for academic achievement. The incremental assessment of learning strategy use as well as gender-differences in their predictive value contributes to the understanding and improvement of successful academic development.

Computer Based Behavioral Biometric Authentication via Multi-Modal Fusion

DTIC Science & Technology

2013-03-01

the decisions made by each individual modality. Fusion of features is the simple concatenation of feature vectors from multiple modalities to be...of Features BayesNet MDL 330 LibSVM PCA 80 J48 Wrapper Evaluator 11 3.5.3 Ensemble Based Decision Level Fusion. In ensemble learning multiple ...The high fusion percentages validate our hypothesis that by combining features from multiple modalities, classification accuracy can be improved. As

Can we use Earth Observations to improve monthly water level forecasts?

NASA Astrophysics Data System (ADS)

Slater, L. J.; Villarini, G.

2017-12-01

Dynamical-statistical hydrologic forecasting approaches benefit from different strengths in comparison with traditional hydrologic forecasting systems: they are computationally efficient, can integrate and `learn' from a broad selection of input data (e.g., General Circulation Model (GCM) forecasts, Earth Observation time series, teleconnection patterns), and can take advantage of recent progress in machine learning (e.g. multi-model blending, post-processing and ensembling techniques). Recent efforts to develop a dynamical-statistical ensemble approach for forecasting seasonal streamflow using both GCM forecasts and changing land cover have shown promising results over the U.S. Midwest. Here, we use climate forecasts from several GCMs of the North American Multi Model Ensemble (NMME) alongside 15-minute stage time series from the National River Flow Archive (NRFA) and land cover classes extracted from the European Space Agency's Climate Change Initiative 300 m annual Global Land Cover time series. With these data, we conduct systematic long-range probabilistic forecasting of monthly water levels in UK catchments over timescales ranging from one to twelve months ahead. We evaluate the improvement in model fit and model forecasting skill that comes from using land cover classes as predictors in the models. This work opens up new possibilities for combining Earth Observation time series with GCM forecasts to predict a variety of hazards from space using data science techniques.

A Flipped Pedagogy for Expert Problem Solving

NASA Astrophysics Data System (ADS)

Pritchard, David

The internet provides free learning opportunities for declarative (Wikipedia, YouTube) and procedural (Kahn Academy, MOOCs) knowledge, challenging colleges to provide learning at a higher cognitive level. Our ``Modeling Applied to Problem Solving'' pedagogy for Newtonian Mechanics imparts strategic knowledge - how to systematically determine which concepts to apply and why. Declarative and procedural knowledge is learned online before class via an e-text, checkpoint questions, and homework on edX.org (see http://relate.mit.edu/physicscourse); it is organized into five Core Models. Instructors then coach students on simple ``touchstone problems'', novel exercises, and multi-concept problems - meanwhile exercising three of the four C's: communication, collaboration, critical thinking and problem solving. Students showed 1.2 standard deviations improvement on the MIT final exam after three weeks instruction, a significant positive shift in 7 of the 9 categories in the CLASS, and their grades improved by 0.5 standard deviation in their following physics course (Electricity and Magnetism).

Action Learning for Organizational and Systemic Development: Towards a "Both-and" Understanding of "I" and "We"

ERIC Educational Resources Information Center

Rigg, Clare

2008-01-01

In public services delivery, action learning is increasingly employed in the hope of improving capacity to address complex, multi-casual and "wicked" social issues to improve the lives of citizens. Yet the understanding of how and why action learning might have potential for enhancing organizational or systemic capability rarely goes…

Chronic Heart Failure Follow-up Management Based on Agent Technology.

PubMed

Mohammadzadeh, Niloofar; Safdari, Reza

2015-10-01

Monitoring heart failure patients through continues assessment of sign and symptoms by information technology tools lead to large reduction in re-hospitalization. Agent technology is one of the strongest artificial intelligence areas; therefore, it can be expected to facilitate, accelerate, and improve health services especially in home care and telemedicine. The aim of this article is to provide an agent-based model for chronic heart failure (CHF) follow-up management. This research was performed in 2013-2014 to determine appropriate scenarios and the data required to monitor and follow-up CHF patients, and then an agent-based model was designed. Agents in the proposed model perform the following tasks: medical data access, communication with other agents of the framework and intelligent data analysis, including medical data processing, reasoning, negotiation for decision-making, and learning capabilities. The proposed multi-agent system has ability to learn and thus improve itself. Implementation of this model with more and various interval times at a broader level could achieve better results. The proposed multi-agent system is no substitute for cardiologists, but it could assist them in decision-making.

Using a multi-state Learning Community as an implementation strategy for immediate postpartum long-acting reversible contraception.

PubMed

DeSisto, Carla L; Estrich, Cameron; Kroelinger, Charlan D; Goodman, David A; Pliska, Ellen; Mackie, Christine N; Waddell, Lisa F; Rankin, Kristin M

2017-11-21

Implementation strategies are imperative for the successful adoption and sustainability of complex evidence-based public health practices. Creating a learning collaborative is one strategy that was part of a recently published compilation of implementation strategy terms and definitions. In partnership with the Centers for Disease Control and Prevention and other partner agencies, the Association of State and Territorial Health Officials recently convened a multi-state Learning Community to support cross-state collaboration and provide technical assistance for improving state capacity to increase access to long-acting reversible contraception (LARC) in the immediate postpartum period, an evidence-based practice with the potential for reducing unintended pregnancy and improving maternal and child health outcomes. During 2015-2016, the Learning Community included multi-disciplinary, multi-agency teams of state health officials, payers, clinicians, and health department staff from 13 states. This qualitative study was conducted to better understand the successes, challenges, and strategies that the 13 US states in the Learning Community used for increasing access to immediate postpartum LARC. We conducted telephone interviews with each team in the Learning Community. Interviews were semi-structured and organized by the eight domains of the Learning Community. We coded transcribed interviews for facilitators, barriers, and implementation strategies, using a recent compilation of expert-defined implementation strategies as a foundation for coding the latter. Data analysis showed three ways that the activities of the Learning Community helped in policy implementation work: structure and accountability, validity, and preparing for potential challenges and opportunities. Further, the qualitative data demonstrated that the Learning Community integrated six other implementation strategies from the literature: organize clinician implementation team meetings, conduct educational meetings, facilitation, promote network weaving, provide ongoing consultation, and distribute educational materials. Convening a multi-state learning collaborative is a promising approach for facilitating the implementation of new reimbursement policies for evidence-based practices complicated by systems challenges. By integrating several implementation strategies, the Learning Community serves as a meta-strategy for supporting implementation.

Redesigning Schools: To Reach Every Student with Excellent Teachers. Financial Planning for Secondary-Level Time-Technology Swap + Multi-Classroom Leadership

ERIC Educational Resources Information Center

Public Impact, 2013

2013-01-01

This brief shows how middle and high school teachers in a Time-Technology Swap school model, with or without Multi-Classroom Leaders, may earn more while reaching more students, sustainably. In this model, students alternate between learning with teachers and working in a digital learning lab, where they learn online and engage in offline skill…

Global adaptation in networks of selfish components: emergent associative memory at the system scale.

PubMed

Watson, Richard A; Mills, Rob; Buckley, C L

2011-01-01

In some circumstances complex adaptive systems composed of numerous self-interested agents can self-organize into structures that enhance global adaptation, efficiency, or function. However, the general conditions for such an outcome are poorly understood and present a fundamental open question for domains as varied as ecology, sociology, economics, organismic biology, and technological infrastructure design. In contrast, sufficient conditions for artificial neural networks to form structures that perform collective computational processes such as associative memory/recall, classification, generalization, and optimization are well understood. Such global functions within a single agent or organism are not wholly surprising, since the mechanisms (e.g., Hebbian learning) that create these neural organizations may be selected for this purpose; but agents in a multi-agent system have no obvious reason to adhere to such a structuring protocol or produce such global behaviors when acting from individual self-interest. However, Hebbian learning is actually a very simple and fully distributed habituation or positive feedback principle. Here we show that when self-interested agents can modify how they are affected by other agents (e.g., when they can influence which other agents they interact with), then, in adapting these inter-agent relationships to maximize their own utility, they will necessarily alter them in a manner homologous with Hebbian learning. Multi-agent systems with adaptable relationships will thereby exhibit the same system-level behaviors as neural networks under Hebbian learning. For example, improved global efficiency in multi-agent systems can be explained by the inherent ability of associative memory to generalize by idealizing stored patterns and/or creating new combinations of subpatterns. Thus distributed multi-agent systems can spontaneously exhibit adaptive global behaviors in the same sense, and by the same mechanism, as with the organizational principles familiar in connectionist models of organismic learning.

Deep learning for hybrid EEG-fNIRS brain-computer interface: application to motor imagery classification.

PubMed

Chiarelli, Antonio Maria; Croce, Pierpaolo; Merla, Arcangelo; Zappasodi, Filippo

2018-06-01

Brain-computer interface (BCI) refers to procedures that link the central nervous system to a device. BCI was historically performed using electroencephalography (EEG). In the last years, encouraging results were obtained by combining EEG with other neuroimaging technologies, such as functional near infrared spectroscopy (fNIRS). A crucial step of BCI is brain state classification from recorded signal features. Deep artificial neural networks (DNNs) recently reached unprecedented complex classification outcomes. These performances were achieved through increased computational power, efficient learning algorithms, valuable activation functions, and restricted or back-fed neurons connections. By expecting significant overall BCI performances, we investigated the capabilities of combining EEG and fNIRS recordings with state-of-the-art deep learning procedures. We performed a guided left and right hand motor imagery task on 15 subjects with a fixed classification response time of 1 s and overall experiment length of 10 min. Left versus right classification accuracy of a DNN in the multi-modal recording modality was estimated and it was compared to standalone EEG and fNIRS and other classifiers. At a group level we obtained significant increase in performance when considering multi-modal recordings and DNN classifier with synergistic effect. BCI performances can be significantly improved by employing multi-modal recordings that provide electrical and hemodynamic brain activity information, in combination with advanced non-linear deep learning classification procedures.

Deep learning for hybrid EEG-fNIRS brain–computer interface: application to motor imagery classification

NASA Astrophysics Data System (ADS)

Chiarelli, Antonio Maria; Croce, Pierpaolo; Merla, Arcangelo; Zappasodi, Filippo

2018-06-01

Objective. Brain–computer interface (BCI) refers to procedures that link the central nervous system to a device. BCI was historically performed using electroencephalography (EEG). In the last years, encouraging results were obtained by combining EEG with other neuroimaging technologies, such as functional near infrared spectroscopy (fNIRS). A crucial step of BCI is brain state classification from recorded signal features. Deep artificial neural networks (DNNs) recently reached unprecedented complex classification outcomes. These performances were achieved through increased computational power, efficient learning algorithms, valuable activation functions, and restricted or back-fed neurons connections. By expecting significant overall BCI performances, we investigated the capabilities of combining EEG and fNIRS recordings with state-of-the-art deep learning procedures. Approach. We performed a guided left and right hand motor imagery task on 15 subjects with a fixed classification response time of 1 s and overall experiment length of 10 min. Left versus right classification accuracy of a DNN in the multi-modal recording modality was estimated and it was compared to standalone EEG and fNIRS and other classifiers. Main results. At a group level we obtained significant increase in performance when considering multi-modal recordings and DNN classifier with synergistic effect. Significance. BCI performances can be significantly improved by employing multi-modal recordings that provide electrical and hemodynamic brain activity information, in combination with advanced non-linear deep learning classification procedures.

Multi-Atlas Based Segmentation of Brainstem Nuclei from MR Images by Deep Hyper-Graph Learning.

PubMed

Dong, Pei; Guo, Yangrong; Gao, Yue; Liang, Peipeng; Shi, Yonghong; Wang, Qian; Shen, Dinggang; Wu, Guorong

2016-10-01

Accurate segmentation of brainstem nuclei (red nucleus and substantia nigra) is very important in various neuroimaging applications such as deep brain stimulation and the investigation of imaging biomarkers for Parkinson's disease (PD). Due to iron deposition during aging, image contrast in the brainstem is very low in Magnetic Resonance (MR) images. Hence, the ambiguity of patch-wise similarity makes the recently successful multi-atlas patch-based label fusion methods have difficulty to perform as competitive as segmenting cortical and sub-cortical regions from MR images. To address this challenge, we propose a novel multi-atlas brainstem nuclei segmentation method using deep hyper-graph learning. Specifically, we achieve this goal in three-fold. First , we employ hyper-graph to combine the advantage of maintaining spatial coherence from graph-based segmentation approaches and the benefit of harnessing population priors from multi-atlas based framework. Second , besides using low-level image appearance, we also extract high-level context features to measure the complex patch-wise relationship. Since the context features are calculated on a tentatively estimated label probability map, we eventually turn our hyper-graph learning based label propagation into a deep and self-refining model. Third , since anatomical labels on some voxels (usually located in uniform regions) can be identified much more reliably than other voxels (usually located at the boundary between two regions), we allow these reliable voxels to propagate their labels to the nearby difficult-to-label voxels. Such hierarchical strategy makes our proposed label fusion method deep and dynamic. We evaluate our proposed label fusion method in segmenting substantia nigra (SN) and red nucleus (RN) from 3.0 T MR images, where our proposed method achieves significant improvement over the state-of-the-art label fusion methods.

A data-driven multi-model methodology with deep feature selection for short-term wind forecasting

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

Feng, Cong; Cui, Mingjian; Hodge, Bri-Mathias

With the growing wind penetration into the power system worldwide, improving wind power forecasting accuracy is becoming increasingly important to ensure continued economic and reliable power system operations. In this paper, a data-driven multi-model wind forecasting methodology is developed with a two-layer ensemble machine learning technique. The first layer is composed of multiple machine learning models that generate individual forecasts. A deep feature selection framework is developed to determine the most suitable inputs to the first layer machine learning models. Then, a blending algorithm is applied in the second layer to create an ensemble of the forecasts produced by firstmore » layer models and generate both deterministic and probabilistic forecasts. This two-layer model seeks to utilize the statistically different characteristics of each machine learning algorithm. A number of machine learning algorithms are selected and compared in both layers. This developed multi-model wind forecasting methodology is compared to several benchmarks. The effectiveness of the proposed methodology is evaluated to provide 1-hour-ahead wind speed forecasting at seven locations of the Surface Radiation network. Numerical results show that comparing to the single-algorithm models, the developed multi-model framework with deep feature selection procedure has improved the forecasting accuracy by up to 30%.« less

Data-driven train set crash dynamics simulation

NASA Astrophysics Data System (ADS)

Tang, Zhao; Zhu, Yunrui; Nie, Yinyu; Guo, Shihui; Liu, Fengjia; Chang, Jian; Zhang, Jianjun

2017-02-01

Traditional finite element (FE) methods are arguably expensive in computation/simulation of the train crash. High computational cost limits their direct applications in investigating dynamic behaviours of an entire train set for crashworthiness design and structural optimisation. On the contrary, multi-body modelling is widely used because of its low computational cost with the trade-off in accuracy. In this study, a data-driven train crash modelling method is proposed to improve the performance of a multi-body dynamics simulation of train set crash without increasing the computational burden. This is achieved by the parallel random forest algorithm, which is a machine learning approach that extracts useful patterns of force-displacement curves and predicts a force-displacement relation in a given collision condition from a collection of offline FE simulation data on various collision conditions, namely different crash velocities in our analysis. Using the FE simulation results as a benchmark, we compared our method with traditional multi-body modelling methods and the result shows that our data-driven method improves the accuracy over traditional multi-body models in train crash simulation and runs at the same level of efficiency.

From learning taxonomies to phylogenetic learning: integration of 16S rRNA gene data into FAME-based bacterial classification.

PubMed

Slabbinck, Bram; Waegeman, Willem; Dawyndt, Peter; De Vos, Paul; De Baets, Bernard

2010-01-30

Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial species. Summarized, by phylogenetic learning we are able to situate and evaluate FAME-based bacterial species classification in a more informative context.

From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

PubMed Central

2010-01-01

Background Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification. Results In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model. Conclusions FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial species. Summarized, by phylogenetic learning we are able to situate and evaluate FAME-based bacterial species classification in a more informative context. PMID:20113515

Conditional Random Field (CRF)-Boosting: Constructing a Robust Online Hybrid Boosting Multiple Object Tracker Facilitated by CRF Learning

PubMed Central

Yang, Ehwa; Gwak, Jeonghwan; Jeon, Moongu

2017-01-01

Due to the reasonably acceptable performance of state-of-the-art object detectors, tracking-by-detection is a standard strategy for visual multi-object tracking (MOT). In particular, online MOT is more demanding due to its diverse applications in time-critical situations. A main issue of realizing online MOT is how to associate noisy object detection results on a new frame with previously being tracked objects. In this work, we propose a multi-object tracker method called CRF-boosting which utilizes a hybrid data association method based on online hybrid boosting facilitated by a conditional random field (CRF) for establishing online MOT. For data association, learned CRF is used to generate reliable low-level tracklets and then these are used as the input of the hybrid boosting. To do so, while existing data association methods based on boosting algorithms have the necessity of training data having ground truth information to improve robustness, CRF-boosting ensures sufficient robustness without such information due to the synergetic cascaded learning procedure. Further, a hierarchical feature association framework is adopted to further improve MOT accuracy. From experimental results on public datasets, we could conclude that the benefit of proposed hybrid approach compared to the other competitive MOT systems is noticeable. PMID:28304366

Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning

NASA Astrophysics Data System (ADS)

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

2017-04-01

This paper proposes the combination of two model-free controller tuning techniques, namely linear virtual reference feedback tuning (VRFT) and nonlinear state-feedback Q-learning, referred to as a new mixed VRFT-Q learning approach. VRFT is first used to find stabilising feedback controller using input-output experimental data from the process in a model reference tracking setting. Reinforcement Q-learning is next applied in the same setting using input-state experimental data collected under perturbed VRFT to ensure good exploration. The Q-learning controller learned with a batch fitted Q iteration algorithm uses two neural networks, one for the Q-function estimator and one for the controller, respectively. The VRFT-Q learning approach is validated on position control of a two-degrees-of-motion open-loop stable multi input-multi output (MIMO) aerodynamic system (AS). Extensive simulations for the two independent control channels of the MIMO AS show that the Q-learning controllers clearly improve performance over the VRFT controllers.

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.

Lung nodule malignancy prediction using multi-task convolutional neural network

NASA Astrophysics Data System (ADS)

Li, Xiuli; Kao, Yueying; Shen, Wei; Li, Xiang; Xie, Guotong

2017-03-01

In this paper, we investigated the problem of diagnostic lung nodule malignancy prediction using thoracic Computed Tomography (CT) screening. Unlike most existing studies classify the nodules into two types benign and malignancy, we interpreted the nodule malignancy prediction as a regression problem to predict continuous malignancy level. We proposed a joint multi-task learning algorithm using Convolutional Neural Network (CNN) to capture nodule heterogeneity by extracting discriminative features from alternatingly stacked layers. We trained a CNN regression model to predict the nodule malignancy, and designed a multi-task learning mechanism to simultaneously share knowledge among 9 different nodule characteristics (Subtlety, Calcification, Sphericity, Margin, Lobulation, Spiculation, Texture, Diameter and Malignancy), and improved the final prediction result. Each CNN would generate characteristic-specific feature representations, and then we applied multi-task learning on the features to predict the corresponding likelihood for that characteristic. We evaluated the proposed method on 2620 nodules CT scans from LIDC-IDRI dataset with the 5-fold cross validation strategy. The multitask CNN regression result for regression RMSE and mapped classification ACC were 0.830 and 83.03%, while the results for single task regression RMSE 0.894 and mapped classification ACC 74.9%. Experiments show that the proposed method could predict the lung nodule malignancy likelihood effectively and outperforms the state-of-the-art methods. The learning framework could easily be applied in other anomaly likelihood prediction problem, such as skin cancer and breast cancer. It demonstrated the possibility of our method facilitating the radiologists for nodule staging assessment and individual therapeutic planning.

Modeling development of natural multi-sensory integration using neural self-organisation and probabilistic population codes

NASA Astrophysics Data System (ADS)

Bauer, Johannes; Dávila-Chacón, Jorge; Wermter, Stefan

2015-10-01

Humans and other animals have been shown to perform near-optimally in multi-sensory integration tasks. Probabilistic population codes (PPCs) have been proposed as a mechanism by which optimal integration can be accomplished. Previous approaches have focussed on how neural networks might produce PPCs from sensory input or perform calculations using them, like combining multiple PPCs. Less attention has been given to the question of how the necessary organisation of neurons can arise and how the required knowledge about the input statistics can be learned. In this paper, we propose a model of learning multi-sensory integration based on an unsupervised learning algorithm in which an artificial neural network learns the noise characteristics of each of its sources of input. Our algorithm borrows from the self-organising map the ability to learn latent-variable models of the input and extends it to learning to produce a PPC approximating a probability density function over the latent variable behind its (noisy) input. The neurons in our network are only required to perform simple calculations and we make few assumptions about input noise properties and tuning functions. We report on a neurorobotic experiment in which we apply our algorithm to multi-sensory integration in a humanoid robot to demonstrate its effectiveness and compare it to human multi-sensory integration on the behavioural level. We also show in simulations that our algorithm performs near-optimally under certain plausible conditions, and that it reproduces important aspects of natural multi-sensory integration on the neural level.

Effects of an Interdisciplinary Science Professional Development Program on Teacher Pedagogical Content Knowledge, Science Inquiry Instruction, and Student Understanding of Science Crosscutting Concepts in Twelve Public Schools: A Multi-Level Modeling Study

ERIC Educational Resources Information Center

Yang, Yang

2017-01-01

Systematic studies on effectiveness of in-service teacher professional development (PD) are important for science education research and practice. Previous studies mostly focus on one certain aspect of the entire program, for example, effectiveness of PD on improvement of teachers' knowledge or students' learning outcomes. This study, however,…

Automatic multi-organ segmentation using learning-based segmentation and level set optimization.

PubMed

Kohlberger, Timo; Sofka, Michal; Zhang, Jingdan; Birkbeck, Neil; Wetzl, Jens; Kaftan, Jens; Declerck, Jérôme; Zhou, S Kevin

2011-01-01

We present a novel generic segmentation system for the fully automatic multi-organ segmentation from CT medical images. Thereby we combine the advantages of learning-based approaches on point cloud-based shape representation, such a speed, robustness, point correspondences, with those of PDE-optimization-based level set approaches, such as high accuracy and the straightforward prevention of segment overlaps. In a benchmark on 10-100 annotated datasets for the liver, the lungs, and the kidneys we show that the proposed system yields segmentation accuracies of 1.17-2.89 mm average surface errors. Thereby the level set segmentation (which is initialized by the learning-based segmentations) contributes with an 20%-40% increase in accuracy.

Enhancing the Teaching of Introductory Economics with a Team-Based, Multi-Section Competition

ERIC Educational Resources Information Center

Beaudin, Laura; Berdiev, Aziz N.; Kaminaga, Allison Shwachman; Mirmirani, Sam; Tebaldi, Edinaldo

2017-01-01

The authors describe a unique approach to enhancing student learning at the introductory economics level that utilizes a multi-section, team-based competition. The competition is structured to supplement learning throughout the entire introductory course. Student teams are presented with current economic issues, trends, or events, and use economic…

Designing Ensemble Based Security Framework for M-Learning System

ERIC Educational Resources Information Center

Mahalingam, Sheila; Abdollah, Mohd Faizal; bin Sahibuddin, Shahrin

2014-01-01

Mobile Learning has a potential to improve efficiency in the education sector and expand educational opportunities to underserved remote area in higher learning institutions. However there are multi challenges in different altitude faced when introducing and implementing m-learning. Despite the evolution of technology changes in education,…

Developing models to predict 8th grade students' achievement levels on timss science based on opportunity-to-learn variables

NASA Astrophysics Data System (ADS)

Whitford, Melinda M.

Science educational reforms have placed major emphasis on improving science classroom instruction and it is therefore vital to study opportunity-to-learn (OTL) variables related to student science learning experiences and teacher teaching practices. This study will identify relationships between OTL and student science achievement and will identify OTL predictors of students' attainment at various distinct achievement levels (low/intermediate/high/advanced). Specifically, the study (a) address limitations of previous studies by examining a large number of independent and control variables that may impact students' science achievement and (b) it will test hypotheses of structural relations to how the identified predictors and mediating factors impact on student achievement levels. The study will follow a multi-stage and integrated bottom-up and top-down approach to identify predictors of students' achievement levels on standardized tests using TIMSS 2011 dataset. Data mining or pattern recognition, a bottom-up approach will identify the most prevalent association patterns between different student achievement levels and variables related to student science learning experiences, teacher teaching practices and home and school environments. The second stage is a top-down approach, testing structural equation models of relations between the significant predictors and students' achievement levels according.

Sentiment classification technology based on Markov logic networks

NASA Astrophysics Data System (ADS)

He, Hui; Li, Zhigang; Yao, Chongchong; Zhang, Weizhe

2016-07-01

With diverse online media emerging, there is a growing concern of sentiment classification problem. At present, text sentiment classification mainly utilizes supervised machine learning methods, which feature certain domain dependency. On the basis of Markov logic networks (MLNs), this study proposed a cross-domain multi-task text sentiment classification method rooted in transfer learning. Through many-to-one knowledge transfer, labeled text sentiment classification, knowledge was successfully transferred into other domains, and the precision of the sentiment classification analysis in the text tendency domain was improved. The experimental results revealed the following: (1) the model based on a MLN demonstrated higher precision than the single individual learning plan model. (2) Multi-task transfer learning based on Markov logical networks could acquire more knowledge than self-domain learning. The cross-domain text sentiment classification model could significantly improve the precision and efficiency of text sentiment classification.

Multi-Unit Considerations for Human Reliability Analysis

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

St. Germain, S.; Boring, R.; Banaseanu, G.

This paper uses the insights from the Standardized Plant Analysis Risk-Human Reliability Analysis (SPAR-H) methodology to help identify human actions currently modeled in the single unit PSA that may need to be modified to account for additional challenges imposed by a multi-unit accident as well as identify possible new human actions that might be modeled to more accurately characterize multi-unit risk. In identifying these potential human action impacts, the use of the SPAR-H strategy to include both errors in diagnosis and errors in action is considered as well as identifying characteristics of a multi-unit accident scenario that may impact themore » selection of the performance shaping factors (PSFs) used in SPAR-H. The lessons learned from the Fukushima Daiichi reactor accident will be addressed to further help identify areas where improved modeling may be required. While these multi-unit impacts may require modifications to a Level 1 PSA model, it is expected to have much more importance for Level 2 modeling. There is little currently written specifically about multi-unit HRA issues. A review of related published research will be presented. While this paper cannot answer all issues related to multi-unit HRA, it will hopefully serve as a starting point to generate discussion and spark additional ideas towards the proper treatment of HRA in a multi-unit PSA.« less

A diagram retrieval method with multi-label learning

NASA Astrophysics Data System (ADS)

Fu, Songping; Lu, Xiaoqing; Liu, Lu; Qu, Jingwei; Tang, Zhi

2015-01-01

In recent years, the retrieval of plane geometry figures (PGFs) has attracted increasing attention in the fields of mathematics education and computer science. However, the high cost of matching complex PGF features leads to the low efficiency of most retrieval systems. This paper proposes an indirect classification method based on multi-label learning, which improves retrieval efficiency by reducing the scope of compare operation from the whole database to small candidate groups. Label correlations among PGFs are taken into account for the multi-label classification task. The primitive feature selection for multi-label learning and the feature description of visual geometric elements are conducted individually to match similar PGFs. The experiment results show the competitive performance of the proposed method compared with existing PGF retrieval methods in terms of both time consumption and retrieval quality.

Multi-Level and Multi-Scale Feature Aggregation Using Pretrained Convolutional Neural Networks for Music Auto-Tagging

NASA Astrophysics Data System (ADS)

Lee, Jongpil; Nam, Juhan

2017-08-01

Music auto-tagging is often handled in a similar manner to image classification by regarding the 2D audio spectrogram as image data. However, music auto-tagging is distinguished from image classification in that the tags are highly diverse and have different levels of abstractions. Considering this issue, we propose a convolutional neural networks (CNN)-based architecture that embraces multi-level and multi-scaled features. The architecture is trained in three steps. First, we conduct supervised feature learning to capture local audio features using a set of CNNs with different input sizes. Second, we extract audio features from each layer of the pre-trained convolutional networks separately and aggregate them altogether given a long audio clip. Finally, we put them into fully-connected networks and make final predictions of the tags. Our experiments show that using the combination of multi-level and multi-scale features is highly effective in music auto-tagging and the proposed method outperforms previous state-of-the-arts on the MagnaTagATune dataset and the Million Song Dataset. We further show that the proposed architecture is useful in transfer learning.

Image processing and machine learning for fully automated probabilistic evaluation of medical images.

PubMed

Sajn, Luka; Kukar, Matjaž

2011-12-01

The paper presents results of our long-term study on using image processing and data mining methods in a medical imaging. Since evaluation of modern medical images is becoming increasingly complex, advanced analytical and decision support tools are involved in integration of partial diagnostic results. Such partial results, frequently obtained from tests with substantial imperfections, are integrated into ultimate diagnostic conclusion about the probability of disease for a given patient. We study various topics such as improving the predictive power of clinical tests by utilizing pre-test and post-test probabilities, texture representation, multi-resolution feature extraction, feature construction and data mining algorithms that significantly outperform medical practice. Our long-term study reveals three significant milestones. The first improvement was achieved by significantly increasing post-test diagnostic probabilities with respect to expert physicians. The second, even more significant improvement utilizes multi-resolution image parametrization. Machine learning methods in conjunction with the feature subset selection on these parameters significantly improve diagnostic performance. However, further feature construction with the principle component analysis on these features elevates results to an even higher accuracy level that represents the third milestone. With the proposed approach clinical results are significantly improved throughout the study. The most significant result of our study is improvement in the diagnostic power of the whole diagnostic process. Our compound approach aids, but does not replace, the physician's judgment and may assist in decisions on cost effectiveness of tests. Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.

Multi-Level Adaptation in End-User Development of 3D Virtual Chemistry Experiments

ERIC Educational Resources Information Center

Liu, Chang; Zhong, Ying

2014-01-01

Multi-level adaptation in end-user development (EUD) is an effective way to enable non-technical end users such as educators to gradually introduce more functionality with increasing complexity to 3D virtual learning environments developed by themselves using EUD approaches. Parameterization, integration, and extension are three levels of…

Improving Engagement in Science: A Biosocial System Perspective.

ERIC Educational Resources Information Center

Hanrahan, Mary U.

The goal of my multi-study research program has been to learn how to engage all students in learning science. Most learning theories applied to science pedagogy take either a psychological or a sociocultural perspective and hence ignore either sociocultural or motivational factors when considering classroom learning. Based on my own research…

An Automatic Detection System of Lung Nodule Based on Multi-Group Patch-Based Deep Learning Network.

PubMed

Jiang, Hongyang; Ma, He; Qian, Wei; Gao, Mengdi; Li, Yan

2017-07-14

High-efficiency lung nodule detection dramatically contributes to the risk assessment of lung cancer. It is a significant and challenging task to quickly locate the exact positions of lung nodules. Extensive work has been done by researchers around this domain for approximately two decades. However, previous computer aided detection (CADe) schemes are mostly intricate and time-consuming since they may require more image processing modules, such as the computed tomography (CT) image transformation, the lung nodule segmentation and the feature extraction, to construct a whole CADe system. It is difficult for those schemes to process and analyze enormous data when the medical images continue to increase. Besides, some state of the art deep learning schemes may be strict in the standard of database. This study proposes an effective lung nodule detection scheme based on multi-group patches cut out from the lung images, which are enhanced by the Frangi filter. Through combining two groups of images, a four-channel convolution neural networks (CNN) model is designed to learn the knowledge of radiologists for detecting nodules of four levels. This CADe scheme can acquire the sensitivity of 80.06% with 4.7 false positives per scan and the sensitivity of 94% with 15.1 false positives per scan. The results demonstrate that the multi-group patch-based learning system is efficient to improve the performance of lung nodule detection and greatly reduce the false positives under a huge amount of image data.

Using Survey Data to Improve Student Learning: A Team Approach

ERIC Educational Resources Information Center

Fitzgerald, Darlene

2009-01-01

"What did you do in school today?" is about reflecting on thoughtful questions and using data to make improvements. It is a multi-year research and development initiative of the Canadian Education Association (CEA), funded through collaboration with the Canadian Council on Learning (CCL) and a number of Canadian school districts.…

Social Tools And Rules for Teens (The START Program): Program Description and Preliminary Outcomes of an Experiential Socialization Intervention for Adolescents with Autism Spectrum Disorder.

PubMed

Vernon, Ty W; Miller, Amber R; Ko, Jordan A; Wu, Victoria L

2016-05-01

Experiential learning is an essential process in the development of core social competencies. Unfortunately, adolescents with autism spectrum disorders often do not possess the prerequisite skillset and motivation to sustain the level of social immersion needed to benefit from this learning process. These persisting social vulnerabilities can limit their long-term relational success and associated quality of life, creating a need for comprehensive social programming. This paper describes a multi-component socialization intervention that simultaneously targets motivational, conceptual, and skill deficits using a hybrid experiential/didactic treatment approach. Evidence of social competence improvements was noted in survey and live conversational measures, indicating that the START program may hold promise as a method for improving the social success of participating adolescents with ASD.

Chronic Heart Failure Follow-up Management Based on Agent Technology

PubMed Central

Safdari, Reza

2015-01-01

Objectives Monitoring heart failure patients through continues assessment of sign and symptoms by information technology tools lead to large reduction in re-hospitalization. Agent technology is one of the strongest artificial intelligence areas; therefore, it can be expected to facilitate, accelerate, and improve health services especially in home care and telemedicine. The aim of this article is to provide an agent-based model for chronic heart failure (CHF) follow-up management. Methods This research was performed in 2013-2014 to determine appropriate scenarios and the data required to monitor and follow-up CHF patients, and then an agent-based model was designed. Results Agents in the proposed model perform the following tasks: medical data access, communication with other agents of the framework and intelligent data analysis, including medical data processing, reasoning, negotiation for decision-making, and learning capabilities. Conclusions The proposed multi-agent system has ability to learn and thus improve itself. Implementation of this model with more and various interval times at a broader level could achieve better results. The proposed multi-agent system is no substitute for cardiologists, but it could assist them in decision-making. PMID:26618038

Medicaid medical directors quality improvement studies: a case study of evolving methods for a research network.

PubMed

Fairbrother, Gerry; Trudnak, Tara; Griffith, Katherine

2014-01-01

To describe the evolution of methods and share lessons learned from conducting multi-state studies with Medicaid Medical Directors (MMD) using state administrative data. There was a great need for these studies, but also much to be learned about conducting network-based research and ensuring comparability of results. This was a network-level case study. The findings were drawn from the experience developing and executing network analyses with the MMDs, as well as from participant feedback on lessons learned. For the latter, nine interviews with MMD project leads, state data analysts, and outside researchers involved with the projects were conducted. Interviews were transcribed, coded and analyzed using NVivo 10.0 analytic software. MMD study methodology involved many steps: developing research questions, defining data specifications, organizing an aggregated data collection spreadsheet form, assuring quality through review, and analyzing and reporting state data at the national level. State analysts extracted the data from their state Medicaid administrative (claims) databases (and sometimes other datasets). Analysis at the national level aggregated state data overall, by demographics and other sub groups, and displayed descriptive statistics and cross-tabs. Projects in the MMD multi-state network address high-priority clinical issues in Medicaid and impact quality of care through sharing of data and policies among states. Further, these studies contribute not only to high-quality, cost-effective health care for Medicaid beneficiaries, but also add to our knowledge of network-based research. Continuation of these studies requires funding for a permanent research infrastructure nationally, as well as at the state-level to strengthen capacity.

Discriminative Multi-View Interactive Image Re-Ranking.

PubMed

Li, Jun; Xu, Chang; Yang, Wankou; Sun, Changyin; Tao, Dacheng

2017-07-01

Given an unreliable visual patterns and insufficient query information, content-based image retrieval is often suboptimal and requires image re-ranking using auxiliary information. In this paper, we propose a discriminative multi-view interactive image re-ranking (DMINTIR), which integrates user relevance feedback capturing users' intentions and multiple features that sufficiently describe the images. In DMINTIR, heterogeneous property features are incorporated in the multi-view learning scheme to exploit their complementarities. In addition, a discriminatively learned weight vector is obtained to reassign updated scores and target images for re-ranking. Compared with other multi-view learning techniques, our scheme not only generates a compact representation in the latent space from the redundant multi-view features but also maximally preserves the discriminative information in feature encoding by the large-margin principle. Furthermore, the generalization error bound of the proposed algorithm is theoretically analyzed and shown to be improved by the interactions between the latent space and discriminant function learning. Experimental results on two benchmark data sets demonstrate that our approach boosts baseline retrieval quality and is competitive with the other state-of-the-art re-ranking strategies.

Primer for Perception: A Manual Designed to Help Professionals, Para-Professionals and Volunteers Help Children "Learn to Learn".

ERIC Educational Resources Information Center

Goldzer, Beatrice F.

This manual for use by professionals, paraprofessionals, and tutors provides 10 multi-level, multi-purpose units for teaching children with reading, writing, or speech problems. The units were designed for use with preschool through sixth-grade students and consist of games, exercises, drills, evaluation, and suggestions for activities. The manual…

Efficient multi-atlas abdominal segmentation on clinically acquired CT with SIMPLE context learning.

PubMed

Xu, Zhoubing; Burke, Ryan P; Lee, Christopher P; Baucom, Rebeccah B; Poulose, Benjamin K; Abramson, Richard G; Landman, Bennett A

2015-08-01

Abdominal segmentation on clinically acquired computed tomography (CT) has been a challenging problem given the inter-subject variance of human abdomens and complex 3-D relationships among organs. Multi-atlas segmentation (MAS) provides a potentially robust solution by leveraging label atlases via image registration and statistical fusion. We posit that the efficiency of atlas selection requires further exploration in the context of substantial registration errors. The selective and iterative method for performance level estimation (SIMPLE) method is a MAS technique integrating atlas selection and label fusion that has proven effective for prostate radiotherapy planning. Herein, we revisit atlas selection and fusion techniques for segmenting 12 abdominal structures using clinically acquired CT. Using a re-derived SIMPLE algorithm, we show that performance on multi-organ classification can be improved by accounting for exogenous information through Bayesian priors (so called context learning). These innovations are integrated with the joint label fusion (JLF) approach to reduce the impact of correlated errors among selected atlases for each organ, and a graph cut technique is used to regularize the combined segmentation. In a study of 100 subjects, the proposed method outperformed other comparable MAS approaches, including majority vote, SIMPLE, JLF, and the Wolz locally weighted vote technique. The proposed technique provides consistent improvement over state-of-the-art approaches (median improvement of 7.0% and 16.2% in DSC over JLF and Wolz, respectively) and moves toward efficient segmentation of large-scale clinically acquired CT data for biomarker screening, surgical navigation, and data mining. Copyright © 2015 Elsevier B.V. All rights reserved.

Application of Multi-Objective Human Learning Optimization Method to Solve AC/DC Multi-Objective Optimal Power Flow Problem

NASA Astrophysics Data System (ADS)

Cao, Jia; Yan, Zheng; He, Guangyu

2016-06-01

This paper introduces an efficient algorithm, multi-objective human learning optimization method (MOHLO), to solve AC/DC multi-objective optimal power flow problem (MOPF). Firstly, the model of AC/DC MOPF including wind farms is constructed, where includes three objective functions, operating cost, power loss, and pollutant emission. Combining the non-dominated sorting technique and the crowding distance index, the MOHLO method can be derived, which involves individual learning operator, social learning operator, random exploration learning operator and adaptive strategies. Both the proposed MOHLO method and non-dominated sorting genetic algorithm II (NSGAII) are tested on an improved IEEE 30-bus AC/DC hybrid system. Simulation results show that MOHLO method has excellent search efficiency and the powerful ability of searching optimal. Above all, MOHLO method can obtain more complete pareto front than that by NSGAII method. However, how to choose the optimal solution from pareto front depends mainly on the decision makers who stand from the economic point of view or from the energy saving and emission reduction point of view.

NREL and IBM Improve Solar Forecasting with Big Data | Energy Systems

Science.gov Websites

forecasting model using deep-machine-learning technology. The multi-scale, multi-model tool, named Watt-sun the first standard suite of metrics for this purpose. Validating Watt-sun at multiple sites across the

Orion Flight Test 1 Architecture: Observed Benefits of a Model Based Engineering Approach

NASA Technical Reports Server (NTRS)

Simpson, Kimberly A.; Sindiy, Oleg V.; McVittie, Thomas I.

2012-01-01

This paper details how a NASA-led team is using a model-based systems engineering approach to capture, analyze and communicate the end-to-end information system architecture supporting the first unmanned orbital flight of the Orion Multi-Purpose Crew Exploration Vehicle. Along with a brief overview of the approach and its products, the paper focuses on the observed program-level benefits, challenges, and lessons learned; all of which may be applied to improve system engineering tasks for characteristically similarly challenges

The learner's perspective in GP teaching practices with multi-level learners: a qualitative study.

PubMed

Thomson, Jennifer S; Anderson, Katrina; Haesler, Emily; Barnard, Amanda; Glasgow, Nicholas

2014-03-19

Medical students, junior hospital doctors on rotation and general practice (GP) registrars are undertaking their training in clinical general practices in increasing numbers in Australia. Some practices have four levels of learner. This study aimed to explore how multi-level teaching (also called vertical integration of GP education and training) is occurring in clinical general practice and the impact of such teaching on the learner. A qualitative research methodology was used with face-to-face, semi-structured interviews of medical students, junior hospital doctors, GP registrars and GP teachers in eight training practices in the region that taught all levels of learners. Interviews were audio-recorded and transcribed. Qualitative analysis was conducted using thematic analysis techniques aided by the use of the software package N-Vivo 9. Primary themes were identified and categorised by the co-investigators. 52 interviews were completed and analysed. Themes were identified relating to both the practice learning environment and teaching methods used.A practice environment where there is a strong teaching culture, enjoyment of learning, and flexible learning methods, as well as learning spaces and organised teaching arrangements, all contribute to positive learning from a learners' perspective.Learners identified a number of innovative teaching methods and viewed them as positive. These included multi-level learner group tutorials in the practice, being taught by a team of teachers, including GP registrars and other health professionals, and access to a supernumerary GP supervisor (also termed "GP consultant teacher"). Other teaching methods that were viewed positively were parallel consulting, informal learning and rural hospital context integrated learning. Vertical integration of GP education and training generally impacted positively on all levels of learner. This research has provided further evidence about the learning culture, structures and teaching processes that have a positive impact on learners in the clinical general practice setting where there are multiple levels of learners. It has also identified some innovative teaching methods that will need further examination. The findings reinforce the importance of the environment for learning and learner centred approaches and will be important for training organisations developing vertically integrated practices and in their training of GP teachers.

The learner’s perspective in GP teaching practices with multi-level learners: a qualitative study

PubMed Central

2014-01-01

Background Medical students, junior hospital doctors on rotation and general practice (GP) registrars are undertaking their training in clinical general practices in increasing numbers in Australia. Some practices have four levels of learner. This study aimed to explore how multi-level teaching (also called vertical integration of GP education and training) is occurring in clinical general practice and the impact of such teaching on the learner. Methods A qualitative research methodology was used with face-to-face, semi-structured interviews of medical students, junior hospital doctors, GP registrars and GP teachers in eight training practices in the region that taught all levels of learners. Interviews were audio-recorded and transcribed. Qualitative analysis was conducted using thematic analysis techniques aided by the use of the software package N-Vivo 9. Primary themes were identified and categorised by the co-investigators. Results 52 interviews were completed and analysed. Themes were identified relating to both the practice learning environment and teaching methods used. A practice environment where there is a strong teaching culture, enjoyment of learning, and flexible learning methods, as well as learning spaces and organised teaching arrangements, all contribute to positive learning from a learners’ perspective. Learners identified a number of innovative teaching methods and viewed them as positive. These included multi-level learner group tutorials in the practice, being taught by a team of teachers, including GP registrars and other health professionals, and access to a supernumerary GP supervisor (also termed “GP consultant teacher”). Other teaching methods that were viewed positively were parallel consulting, informal learning and rural hospital context integrated learning. Conclusions Vertical integration of GP education and training generally impacted positively on all levels of learner. This research has provided further evidence about the learning culture, structures and teaching processes that have a positive impact on learners in the clinical general practice setting where there are multiple levels of learners. It has also identified some innovative teaching methods that will need further examination. The findings reinforce the importance of the environment for learning and learner centred approaches and will be important for training organisations developing vertically integrated practices and in their training of GP teachers. PMID:24645670

Predicting human protein function with multi-task deep neural networks.

PubMed

Fa, Rui; Cozzetto, Domenico; Wan, Cen; Jones, David T

2018-01-01

Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.

Work-based learning in health care environments.

PubMed

Spouse, J

2001-03-01

In reviewing contemporary literature and theories about work-based learning, this paper explores recent trends promoting life-long learning. In the process the paper reviews and discusses some implications of implementing recent policies and fostering le arning in health care practice settings. Recent Government policies designed to provide quality health care services and to improve staffing levels in the nursing workforce, have emphasized the importance of life-long learning whilst learning-on-the-job and the need to recognize and credit experiential learning. Such calls include negotiation of personal development plans tailored to individual educational need and context-sensitive learning activities. To be implemented effectively, this policy cann ot be seen as a cheap option but requires considerable financial resourcing for preparation of staff and the conduct of such activities. Successful work-based learning requires investment in staff at all levels as well as changes to staffing structures in organizations and trusts; changes designed to free people up to work and learn collaboratively. Creating an organizational environment where learning is prized depends upon a climate of trust; a climate where investigation and speculation are fostered and where time is protected for engaging in discussions about practice. Such a change may be radical for many health care organizations and may require a review of current policies and practices ensuring that they include education at all levels. The nature of such education also requires reconceptualizing. In the past, learning in practice settings was seen as formal lecturing or demonstration, and relied upon behaviourist principles of learning. Contemporary thinking suggests effective learning in work-settings is multi-faceted and draws on previously acquired formal knowledge, contextualizes it and moulds it according to situations at hand. Thinking about work-based learning in this way raises questions about how such learning can be supported and facilitated.

Multi-fidelity machine learning models for accurate bandgap predictions of solids

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

Pilania, Ghanshyam; Gubernatis, James E.; Lookman, Turab

Here, we present a multi-fidelity co-kriging statistical learning framework that combines variable-fidelity quantum mechanical calculations of bandgaps to generate a machine-learned model that enables low-cost accurate predictions of the bandgaps at the highest fidelity level. Additionally, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. In using a set of 600 elpasolite compounds as an example dataset and using semi-local and hybrid exchange correlation functionals within density functional theory as two levels of fidelities, we demonstrate the excellent learning performance of the method against actual high fidelitymore » quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way.« less

Multi-fidelity machine learning models for accurate bandgap predictions of solids

DOE PAGES

Pilania, Ghanshyam; Gubernatis, James E.; Lookman, Turab

2016-12-28

Here, we present a multi-fidelity co-kriging statistical learning framework that combines variable-fidelity quantum mechanical calculations of bandgaps to generate a machine-learned model that enables low-cost accurate predictions of the bandgaps at the highest fidelity level. Additionally, the adopted Gaussian process regression formulation allows us to predict the underlying uncertainties as a measure of our confidence in the predictions. In using a set of 600 elpasolite compounds as an example dataset and using semi-local and hybrid exchange correlation functionals within density functional theory as two levels of fidelities, we demonstrate the excellent learning performance of the method against actual high fidelitymore » quantum mechanical calculations of the bandgaps. The presented statistical learning method is not restricted to bandgaps or electronic structure methods and extends the utility of high throughput property predictions in a significant way.« less

The development of multi-level critical care competency statements for self-assessment by ICU nurses.

PubMed

Bourgault, Annette M; Smith, Sherry

2004-01-01

Multi-levelled critical care competency statements were developed based on the levels of novice to expert (Benner, 1984). These competency statements provide a framework for the development of knowledge and skills specific to critical care. The purpose of this tool is to guide personal development in critical care, facilitating the assessment of individual learning needs. Competency levels are attained through the completion of performance criteria. Multi-levelled competency statements define clear expectations for the new orientee, in addition to providing a framework for the advancement of the intermediate and experienced nurse.

Multi-Modality Cascaded Convolutional Neural Networks for Alzheimer's Disease Diagnosis.

PubMed

Liu, Manhua; Cheng, Danni; Wang, Kundong; Wang, Yaping

2018-03-23

Accurate and early diagnosis of Alzheimer's disease (AD) plays important role for patient care and development of future treatment. Structural and functional neuroimages, such as magnetic resonance images (MRI) and positron emission tomography (PET), are providing powerful imaging modalities to help understand the anatomical and functional neural changes related to AD. In recent years, machine learning methods have been widely studied on analysis of multi-modality neuroimages for quantitative evaluation and computer-aided-diagnosis (CAD) of AD. Most existing methods extract the hand-craft imaging features after image preprocessing such as registration and segmentation, and then train a classifier to distinguish AD subjects from other groups. This paper proposes to construct cascaded convolutional neural networks (CNNs) to learn the multi-level and multimodal features of MRI and PET brain images for AD classification. First, multiple deep 3D-CNNs are constructed on different local image patches to transform the local brain image into more compact high-level features. Then, an upper high-level 2D-CNN followed by softmax layer is cascaded to ensemble the high-level features learned from the multi-modality and generate the latent multimodal correlation features of the corresponding image patches for classification task. Finally, these learned features are combined by a fully connected layer followed by softmax layer for AD classification. The proposed method can automatically learn the generic multi-level and multimodal features from multiple imaging modalities for classification, which are robust to the scale and rotation variations to some extent. No image segmentation and rigid registration are required in pre-processing the brain images. Our method is evaluated on the baseline MRI and PET images of 397 subjects including 93 AD patients, 204 mild cognitive impairment (MCI, 76 pMCI +128 sMCI) and 100 normal controls (NC) from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Experimental results show that the proposed method achieves an accuracy of 93.26% for classification of AD vs. NC and 82.95% for classification pMCI vs. NC, demonstrating the promising classification performance.

Development of a prototype interactive learning system using multi-media technology for mission independent training program

NASA Technical Reports Server (NTRS)

Matson, Jack E.

1992-01-01

The Spacelab Mission Independent Training Program provides an overview of payload operations. Most of the training material is currently presented in workbook form with some lecture sessions to supplement selected topics. The goal of this project was to develop a prototype interactive learning system for one of the Mission Independent Training topics to demonstrate how the learning process can be improved by incorporating multi-media technology into an interactive system. This report documents the development process and some of the problems encountered during the analysis, design, and production phases of this system.

TargetCrys: protein crystallization prediction by fusing multi-view features with two-layered SVM.

PubMed

Hu, Jun; Han, Ke; Li, Yang; Yang, Jing-Yu; Shen, Hong-Bin; Yu, Dong-Jun

2016-11-01

The accurate prediction of whether a protein will crystallize plays a crucial role in improving the success rate of protein crystallization projects. A common critical problem in the development of machine-learning-based protein crystallization predictors is how to effectively utilize protein features extracted from different views. In this study, we aimed to improve the efficiency of fusing multi-view protein features by proposing a new two-layered SVM (2L-SVM) which switches the feature-level fusion problem to a decision-level fusion problem: the SVMs in the 1st layer of the 2L-SVM are trained on each of the multi-view feature sets; then, the outputs of the 1st layer SVMs, which are the "intermediate" decisions made based on the respective feature sets, are further ensembled by a 2nd layer SVM. Based on the proposed 2L-SVM, we implemented a sequence-based protein crystallization predictor called TargetCrys. Experimental results on several benchmark datasets demonstrated the efficacy of the proposed 2L-SVM for fusing multi-view features. We also compared TargetCrys with existing sequence-based protein crystallization predictors and demonstrated that the proposed TargetCrys outperformed most of the existing predictors and is competitive with the state-of-the-art predictors. The TargetCrys webserver and datasets used in this study are freely available for academic use at: http://csbio.njust.edu.cn/bioinf/TargetCrys .

Implications of Research on Effective Learning Environments for Initial Teacher Education

ERIC Educational Resources Information Center

Conner, Lindsey; Sliwka, Anne

2014-01-01

As a result of multi-disciplinary research on learning, a consistent and comprehensive body of knowledge on effective learning environments is currently emerging (OECD 2010). While this evidence is increasingly influencing the academic and policy discourse on the improvement and innovation of schools, its impact on the design principles of…

Developing affordable multi-touch technologies for use in physics

NASA Astrophysics Data System (ADS)

Potter, Mark; Ilie, Carolina; Schofield, Damian; Vampola, David

2012-02-01

Physics is one of many areas which has the ability to benefit from a number of different teaching styles and sophisticated instructional tools due to it having both theoretical and practical applications which can be explored. The purpose of this research is to develop affordable large scale multi-touch interfaces which can be used within and outside of the classroom as both an instruction technology and a computer supported collaborative learning tool. Not only can this technology be implemented at university levels, but also at the K-12 level of education. Pedagogical research indicates that kinesthetic learning is a fundamental, powerful, and ubiquitous learning style [1]. Through the use of these types of multi-touch tools and teaching methods which incorporate them, the classroom can be enriched to allow for better comprehension and retention of information. This is due in part to a wider range of learning styles, such as kinesthetic learning, which are being catered to within the classroom. [4pt] [1] Wieman, C.E, Perkins, K.K., Adams, W.K., ``Oersted Medal Lecture 2007: Interactive Simulations for teaching physics: What works, what doesn't and why,'' American Journal of Physics. 76 393-99.

X-framework: Space system failure analysis framework

NASA Astrophysics Data System (ADS)

Newman, John Steven

Space program and space systems failures result in financial losses in the multi-hundred million dollar range every year. In addition to financial loss, space system failures may also represent the loss of opportunity, loss of critical scientific, commercial and/or national defense capabilities, as well as loss of public confidence. The need exists to improve learning and expand the scope of lessons documented and offered to the space industry project team. One of the barriers to incorporating lessons learned include the way in which space system failures are documented. Multiple classes of space system failure information are identified, ranging from "sound bite" summaries in space insurance compendia, to articles in journals, lengthy data-oriented (what happened) reports, and in some rare cases, reports that treat not only the what, but also the why. In addition there are periodically published "corporate crisis" reports, typically issued after multiple or highly visible failures that explore management roles in the failure, often within a politically oriented context. Given the general lack of consistency, it is clear that a good multi-level space system/program failure framework with analytical and predictive capability is needed. This research effort set out to develop such a model. The X-Framework (x-fw) is proposed as an innovative forensic failure analysis approach, providing a multi-level understanding of the space system failure event beginning with the proximate cause, extending to the directly related work or operational processes and upward through successive management layers. The x-fw focus is on capability and control at the process level and examines: (1) management accountability and control, (2) resource and requirement allocation, and (3) planning, analysis, and risk management at each level of management. The x-fw model provides an innovative failure analysis approach for acquiring a multi-level perspective, direct and indirect causation of failures, and generating better and more consistent reports. Through this approach failures can be more fully understood, existing programs can be evaluated and future failures avoided. The x-fw development involved a review of the historical failure analysis and prevention literature, coupled with examination of numerous failure case studies. Analytical approaches included use of a relational failure "knowledge base" for classification and sorting of x-fw elements and attributes for each case. In addition a novel "management mapping" technique was developed as a means of displaying an integrated snapshot of indirect causes within the management chain. Further research opportunities will extend the depth of knowledge available for many of the component level cases. In addition, the x-fw has the potential to expand the scope of space sector lessons learned, and contribute to knowledge management and organizational learning.

Sharpening coarse-to-fine stereo vision by perceptual learning: asymmetric transfer across the spatial frequency spectrum

PubMed Central

Tran, Truyet T.; Craven, Ashley P.; Leung, Tsz-Wing; Chat, Sandy W.; Levi, Dennis M.

2016-01-01

Neurons in the early visual cortex are finely tuned to different low-level visual features, forming a multi-channel system analysing the visual image formed on the retina in a parallel manner. However, little is known about the potential ‘cross-talk’ among these channels. Here, we systematically investigated whether stereoacuity, over a large range of target spatial frequencies, can be enhanced by perceptual learning. Using narrow-band visual stimuli, we found that practice with coarse (low spatial frequency) targets substantially improves performance, and that the improvement spreads from coarse to fine (high spatial frequency) three-dimensional perception, generalizing broadly across untrained spatial frequencies and orientations. Notably, we observed an asymmetric transfer of learning across the spatial frequency spectrum. The bandwidth of transfer was broader when training was at a high spatial frequency than at a low spatial frequency. Stereoacuity training is most beneficial when trained with fine targets. This broad transfer of stereoacuity learning contrasts with the highly specific learning reported for other basic visual functions. We also revealed strategies to boost learning outcomes ‘beyond-the-plateau’. Our investigations contribute to understanding the functional properties of the network subserving stereovision. The ability to generalize may provide a key principle for restoring impaired binocular vision in clinical situations. PMID:26909178

The effect of incremental changes in phonotactic probability and neighborhood density on word learning by preschool children

PubMed Central

Storkel, Holly L.; Bontempo, Daniel E.; Aschenbrenner, Andrew J.; Maekawa, Junko; Lee, Su-Yeon

2013-01-01

Purpose Phonotactic probability or neighborhood density have predominately been defined using gross distinctions (i.e., low vs. high). The current studies examined the influence of finer changes in probability (Experiment 1) and density (Experiment 2) on word learning. Method The full range of probability or density was examined by sampling five nonwords from each of four quartiles. Three- and 5-year-old children received training on nonword-nonobject pairs. Learning was measured in a picture-naming task immediately following training and 1-week after training. Results were analyzed using multi-level modeling. Results A linear spline model best captured nonlinearities in phonotactic probability. Specifically word learning improved as probability increased in the lowest quartile, worsened as probability increased in the midlow quartile, and then remained stable and poor in the two highest quartiles. An ordinary linear model sufficiently described neighborhood density. Here, word learning improved as density increased across all quartiles. Conclusion Given these different patterns, phonotactic probability and neighborhood density appear to influence different word learning processes. Specifically, phonotactic probability may affect recognition that a sound sequence is an acceptable word in the language and is a novel word for the child, whereas neighborhood density may influence creation of a new representation in long-term memory. PMID:23882005

Machine Learning Based Multi-Physical-Model Blending for Enhancing Renewable Energy Forecast -- Improvement via Situation Dependent Error Correction

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

Lu, Siyuan; Hwang, Youngdeok; Khabibrakhmanov, Ildar

With increasing penetration of solar and wind energy to the total energy supply mix, the pressing need for accurate energy forecasting has become well-recognized. Here we report the development of a machine-learning based model blending approach for statistically combining multiple meteorological models for improving the accuracy of solar/wind power forecast. Importantly, we demonstrate that in addition to parameters to be predicted (such as solar irradiance and power), including additional atmospheric state parameters which collectively define weather situations as machine learning input provides further enhanced accuracy for the blended result. Functional analysis of variance shows that the error of individual modelmore » has substantial dependence on the weather situation. The machine-learning approach effectively reduces such situation dependent error thus produces more accurate results compared to conventional multi-model ensemble approaches based on simplistic equally or unequally weighted model averaging. Validation over an extended period of time results show over 30% improvement in solar irradiance/power forecast accuracy compared to forecasts based on the best individual model.« less

Multi-Level Analysis of Peer Support, Internet Self-Efficacy and E-Learning Outcomes--The Contextual Effects of Collectivism and Group Potency

ERIC Educational Resources Information Center

Chu, Regina Juchun; Chu, Anita Zichun

2010-01-01

The present study intends to explore the role of collectivism and group potency at group level in predicting individual Internet self-efficacy (ISE) and individual e-learning outcomes for people aged over 45. Group learning has been widely discussed in the research into online formats. However, less study has been carried out about how…

Implementing service improvement projects within pre-registration nursing education: a multi-method case study evaluation.

PubMed

Baillie, Lesley; Bromley, Barbara; Walker, Moira; Jones, Rebecca; Mhlanga, Fortune

2014-01-01

Preparing healthcare students for quality and service improvement is important internationally. A United Kingdom (UK) initiative aims to embed service improvement in pre-registration education. A UK university implemented service improvement teaching for all nursing students. In addition, the degree pathway students conducted service improvement projects as the basis for their dissertations. The study aimed to evaluate the implementation of service improvement projects within a pre-registration nursing curriculum. A multi-method case study was conducted, using student questionnaires, focus groups with students and academic staff, and observation of action learning sets. Questionnaire data were analysed using SPSS v19. Qualitative data were analysed using Ritchie and Spencer's (1994) Framework Approach. Students were very positive about service improvement. The degree students, who conducted service improvement projects in practice, felt more knowledgeable than advanced diploma students. Selecting the project focus was a key issue and students encountered some challenges in practice. Support for student service improvement projects came from action learning sets, placement staff, and academic staff. Service improvement projects had a positive effect on students' learning. An effective partnership between the university and partner healthcare organisations, and support for students in practice, is essential. Copyright © 2013 Elsevier Ltd. All rights reserved.

Dissemination and adoption of the advanced primary care model in the Maryland multi-payer patient centered medical home program.

PubMed

Khanna, Niharika; Shaya, Fadia; Chirikov, Viktor; Steffen, Ben; Sharp, David

2014-02-01

The Maryland Learning Collaborative together with the Maryland Multi-Payer Program transformed 52 medical practices into patient-centered medical homes (PCMH). The Maryland Learning Collaborative developed an Internet-based 14-question Likert scale survey to assess the impact of the PCMH model on practices and providers, concerning how this new method is affecting patient care and outcomes. The survey was sent to 339 practitioners and 52 care management teams at 18 months into the program. Sixty-seven survey results were received and analyzed. After 18 months of participation in the PCMH initiative, participants demonstrated a better understanding of the PCMH initiative, improved patient access to care, improved care coordination, and increased health information technology optimization (p > .001). The findings from the survey evaluation suggest that practice participation in the Maryland Multi-Payer Program has enhanced access to care, influenced patient outcomes, improved care coordination, and increased use of health information technology.

Representability of algebraic topology for biomolecules in machine learning based scoring and virtual screening

PubMed Central

Mu, Lin

2018-01-01

This work introduces a number of algebraic topology approaches, including multi-component persistent homology, multi-level persistent homology, and electrostatic persistence for the representation, characterization, and description of small molecules and biomolecular complexes. In contrast to the conventional persistent homology, multi-component persistent homology retains critical chemical and biological information during the topological simplification of biomolecular geometric complexity. Multi-level persistent homology enables a tailored topological description of inter- and/or intra-molecular interactions of interest. Electrostatic persistence incorporates partial charge information into topological invariants. These topological methods are paired with Wasserstein distance to characterize similarities between molecules and are further integrated with a variety of machine learning algorithms, including k-nearest neighbors, ensemble of trees, and deep convolutional neural networks, to manifest their descriptive and predictive powers for protein-ligand binding analysis and virtual screening of small molecules. Extensive numerical experiments involving 4,414 protein-ligand complexes from the PDBBind database and 128,374 ligand-target and decoy-target pairs in the DUD database are performed to test respectively the scoring power and the discriminatory power of the proposed topological learning strategies. It is demonstrated that the present topological learning outperforms other existing methods in protein-ligand binding affinity prediction and ligand-decoy discrimination. PMID:29309403

A Multi-Level Assessment of the Impact of Orientation Programs on Student Learning

ERIC Educational Resources Information Center

Mayhew, Matthew J.; Vanderlinden, Kim; Kim, Eun Kyung

2010-01-01

The purpose of this study was to investigate the influence of orientation programs on student academic and social learning. Moving beyond previous studies, we examined how participation in orientation programming affected student learning and how the impact of these programs on learning varied by organizational characteristics (i.e., institutional…

Initial Skill Acquisition of Handrim Wheelchair Propulsion: A New Perspective.

PubMed

Vegter, Riemer J K; de Groot, Sonja; Lamoth, Claudine J; Veeger, Dirkjan Hej; van der Woude, Lucas H V

2014-01-01

To gain insight into cyclic motor learning processes, hand rim wheelchair propulsion is a suitable cyclic task, to be learned during early rehabilitation and novel to almost every individual. To propel in an energy efficient manner, wheelchair users must learn to control bimanually applied forces onto the rims, preserving both speed and direction of locomotion. The purpose of this study was to evaluate mechanical efficiency and propulsion technique during the initial stage of motor learning. Therefore, 70 naive able-bodied men received 12-min uninstructed wheelchair practice, consisting of three 4-min blocks separated by 2 min rest. Practice was performed on a motor-driven treadmill at a fixed belt speed and constant power output relative to body mass. Energy consumption and the kinetics of propulsion technique were continuously measured. Participants significantly increased their mechanical efficiency and changed their propulsion technique from a high frequency mode with a lot of negative work to a longer-slower movement pattern with less power losses. Furthermore a multi-level model showed propulsion technique to relate to mechanical efficiency. Finally improvers and non-improvers were identified. The non-improving group was already more efficient and had a better propulsion technique in the first block of practice (i.e., the fourth minute). These findings link propulsion technique to mechanical efficiency, support the importance of a correct propulsion technique for wheelchair users and show motor learning differences.

Learning Natural Selection in 4th Grade with Multi-Agent-Based Computational Models

ERIC Educational Resources Information Center

Dickes, Amanda Catherine; Sengupta, Pratim

2013-01-01

In this paper, we investigate how elementary school students develop multi-level explanations of population dynamics in a simple predator-prey ecosystem, through scaffolded interactions with a multi-agent-based computational model (MABM). The term "agent" in an MABM indicates individual computational objects or actors (e.g., cars), and these…

Predictors of Self-Directed Learning for Low-Qualified Employees: A Multi-Level Analysis

ERIC Educational Resources Information Center

Raemdonck, Isabel; van der Leeden, Rien; Valcke, Martin; Segers, Mien; Thijssen, Jo

2012-01-01

Purpose: This study aims to examine which variables at the level of the individual employee and at the company level are predictors of self-directed learning in low-qualified employees. Methodology: Results were obtained from a sample of 408 low-qualified employees from 35 different companies. The companies were selected from the energy sector,…

Improved Sparse Multi-Class SVM and Its Application for Gene Selection in Cancer Classification

PubMed Central

Huang, Lingkang; Zhang, Hao Helen; Zeng, Zhao-Bang; Bushel, Pierre R.

2013-01-01

Background Microarray techniques provide promising tools for cancer diagnosis using gene expression profiles. However, molecular diagnosis based on high-throughput platforms presents great challenges due to the overwhelming number of variables versus the small sample size and the complex nature of multi-type tumors. Support vector machines (SVMs) have shown superior performance in cancer classification due to their ability to handle high dimensional low sample size data. The multi-class SVM algorithm of Crammer and Singer provides a natural framework for multi-class learning. Despite its effective performance, the procedure utilizes all variables without selection. In this paper, we propose to improve the procedure by imposing shrinkage penalties in learning to enforce solution sparsity. Results The original multi-class SVM of Crammer and Singer is effective for multi-class classification but does not conduct variable selection. We improved the method by introducing soft-thresholding type penalties to incorporate variable selection into multi-class classification for high dimensional data. The new methods were applied to simulated data and two cancer gene expression data sets. The results demonstrate that the new methods can select a small number of genes for building accurate multi-class classification rules. Furthermore, the important genes selected by the methods overlap significantly, suggesting general agreement among different variable selection schemes. Conclusions High accuracy and sparsity make the new methods attractive for cancer diagnostics with gene expression data and defining targets of therapeutic intervention. Availability: The source MATLAB code are available from http://math.arizona.edu/~hzhang/software.html. PMID:23966761

An Improved Iris Recognition Algorithm Based on Hybrid Feature and ELM

NASA Astrophysics Data System (ADS)

Wang, Juan

2018-03-01

The iris image is easily polluted by noise and uneven light. This paper proposed an improved extreme learning machine (ELM) based iris recognition algorithm with hybrid feature. 2D-Gabor filters and GLCM is employed to generate a multi-granularity hybrid feature vector. 2D-Gabor filter and GLCM feature work for capturing low-intermediate frequency and high frequency texture information, respectively. Finally, we utilize extreme learning machine for iris recognition. Experimental results reveal our proposed ELM based multi-granularity iris recognition algorithm (ELM-MGIR) has higher accuracy of 99.86%, and lower EER of 0.12% under the premise of real-time performance. The proposed ELM-MGIR algorithm outperforms other mainstream iris recognition algorithms.

The Heart of School Improvement: A Multi-Site Case Study of Leadership for Teacher Learning in Vietnam

ERIC Educational Resources Information Center

Tran, Ngoc H.; Hallinger, Philip; Truong, Thang

2018-01-01

This study addressed the research question: How do Vietnamese principals lead the professional learning of teachers? The research was comprised of a multiple-site case study of leadership and teacher learning in four Vietnamese schools. Qualitative data analysis aimed at identifying modal practices adopted by these Vietnamese principals to lead…

[Pancreatoduodenectomy: learning curve within single multi-field center].

PubMed

Kaprin, A D; Kostin, A A; Nikiforov, P V; Egorov, V I; Grishin, N A; Lozhkin, M V; Petrov, L O; Bykasov, S A; Sidorov, D V

2018-01-01

To analyze learning curve by using of immediate results of pancreatoduodenectomy at multi-field oncology institute. For the period 2010-2016 at Abdominal Oncology Department of Herzen Moscow Oncology Research Institute 120 pancreatoduodenal resections were consistently performed. All patients were divided into two groups: the first 60 procedures (group A) and subsequent 60 operations (group B). Herewith, first 60 operations were performed within the first 4.5 years of study period, the next 60 operations - within remaining 2.5 years. Learning curves showed significantly variable intraoperative blood loss (1100 ml and 725 ml), surgery time (589 min and 513 min) and postoperative hospital-stay (15 days and 13 days) in group A followed by gradual improvement of these values in group B. Incidence of negative resection margin (R0) was also significantly improved in the last 60 operations (70 and 92%, respectively). Despite pancreatoduodenectomy is one of the most difficult surgical interventions in abdominal surgery learning curve will differ from one surgeon to another.

Radiologist participation in multi-disciplinary teams in breast cancer improves reflective practice, decision making and isolation.

PubMed

Alcantara, S B; Reed, W; Willis, K; Lee, W; Brennan, P; Lewis, S

2014-09-01

This study aims to explore Australian radiologists' experiences of participating in breast cancer multi-disciplinary team (MDT) meetings to identify enablers and barriers to participation as well their perception of confidence and patient care. Qualitative methods incorporating observation and interviews were used. Twenty-one breast cancer MDT meetings were observed across Sydney to study the dynamics of the meetings, the level of participation by radiologists and their most important interactions. Qualitative semi-structured interviews were conducted with 10 radiologists participating in these meetings regarding participation, educational opportunities and improvements to work practices. Radiologists' participation in breast cancer MDT meetings is influenced by the type of meeting they attend with higher levels of participation and a more dominant 'valued' role being evident in pre-interventional meetings. The key themes to emerge from the data include the importance of 'sharing experiences', the 'radiologist-pathologist relationship' and the value of 'continuing participation'. Radiologists believed their confidence in their clinical decision making increased when there was immediate feedback from pathologists. This study highlights the benefits of radiologists regularly participating in breast cancer MDT meetings in terms of continuing professional education resulting from collegial experiential learning. Radiologists' perceived patient care and workplace isolation were improved by sharing experiences with other cancer care colleagues. © 2013 John Wiley & Sons Ltd.

Integrating the Core Curriculum through Cooperative Learning. Lesson Plans for Teachers.

ERIC Educational Resources Information Center

Winget, Patricia L., Ed.

Cooperative learning strategies are used to facilitate the integration of multicultural and multi-ability level students into California regular education classrooms. This handbook is a sampling of innovative lesson plans using cooperative learning activities developed by teachers to incorporate the core curriculum into their instruction. Three…

IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion.

PubMed

Dehzangi, Omid; Taherisadr, Mojtaba; ChangalVala, Raghvendar

2017-11-27

The wide spread usage of wearable sensors such as in smart watches has provided continuous access to valuable user generated data such as human motion that could be used to identify an individual based on his/her motion patterns such as, gait. Several methods have been suggested to extract various heuristic and high-level features from gait motion data to identify discriminative gait signatures and distinguish the target individual from others. However, the manual and hand crafted feature extraction is error prone and subjective. Furthermore, the motion data collected from inertial sensors have complex structure and the detachment between manual feature extraction module and the predictive learning models might limit the generalization capabilities. In this paper, we propose a novel approach for human gait identification using time-frequency (TF) expansion of human gait cycles in order to capture joint 2 dimensional (2D) spectral and temporal patterns of gait cycles. Then, we design a deep convolutional neural network (DCNN) learning to extract discriminative features from the 2D expanded gait cycles and jointly optimize the identification model and the spectro-temporal features in a discriminative fashion. We collect raw motion data from five inertial sensors placed at the chest, lower-back, right hand wrist, right knee, and right ankle of each human subject synchronously in order to investigate the impact of sensor location on the gait identification performance. We then present two methods for early (input level) and late (decision score level) multi-sensor fusion to improve the gait identification generalization performance. We specifically propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual DCNN scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and hence, the problem is a 10-class identification task. Based on our experimental results, 91% subject identification accuracy was achieved using the best individual IMU and 2DTF-DCNN. We then investigated our proposed early and late sensor fusion approaches, which improved the gait identification accuracy of the system to 93.36% and 97.06%, respectively.

Assessing intervention fidelity in a multi-level, multi-component, multi-site program: the Children's Healthy Living (CHL) program.

PubMed

Butel, Jean; Braun, Kathryn L; Novotny, Rachel; Acosta, Mark; Castro, Rose; Fleming, Travis; Powers, Julianne; Nigg, Claudio R

2015-12-01

Addressing complex chronic disease prevention, like childhood obesity, requires a multi-level, multi-component culturally relevant approach with broad reach. Models are lacking to guide fidelity monitoring across multiple levels, components, and sites engaged in such interventions. The aim of this study is to describe the fidelity-monitoring approach of The Children's Healthy Living (CHL) Program, a multi-level multi-component intervention in five Pacific jurisdictions. A fidelity-monitoring rubric was developed. About halfway during the intervention, community partners were randomly selected and interviewed independently by local CHL staff and by Coordinating Center representatives to assess treatment fidelity. Ratings were compared and discussed by local and Coordinating Center staff. There was good agreement between the teams (Kappa = 0.50, p < 0.001), and intervention improvement opportunities were identified through data review and group discussion. Fidelity for the multi-level, multi-component, multi-site CHL intervention was successfully assessed, identifying adaptations as well as ways to improve intervention delivery prior to the end of the intervention.

A Look inside a MUVE Design Process: Blending Instructional Design and Game Principles to Target Writing Skills

ERIC Educational Resources Information Center

Warren, Scott J.; Stein, Richard A.; Dondlinger, Mary Jo; Barab, Sasha A.

2009-01-01

The number of games, simulations, and multi-user virtual environments designed to promote learning, engagement with subject matter, or intended to contextualize learning has been steadily increasing over the past decade. While the use of these digital designs in educational settings has begun to show promise for improving learning, motivation, and…

Learning Multirobot Hose Transportation and Deployment by Distributed Round-Robin Q-Learning.

PubMed

Fernandez-Gauna, Borja; Etxeberria-Agiriano, Ismael; Graña, Manuel

2015-01-01

Multi-Agent Reinforcement Learning (MARL) algorithms face two main difficulties: the curse of dimensionality, and environment non-stationarity due to the independent learning processes carried out by the agents concurrently. In this paper we formalize and prove the convergence of a Distributed Round Robin Q-learning (D-RR-QL) algorithm for cooperative systems. The computational complexity of this algorithm increases linearly with the number of agents. Moreover, it eliminates environment non sta tionarity by carrying a round-robin scheduling of the action selection and execution. That this learning scheme allows the implementation of Modular State-Action Vetoes (MSAV) in cooperative multi-agent systems, which speeds up learning convergence in over-constrained systems by vetoing state-action pairs which lead to undesired termination states (UTS) in the relevant state-action subspace. Each agent's local state-action value function learning is an independent process, including the MSAV policies. Coordination of locally optimal policies to obtain the global optimal joint policy is achieved by a greedy selection procedure using message passing. We show that D-RR-QL improves over state-of-the-art approaches, such as Distributed Q-Learning, Team Q-Learning and Coordinated Reinforcement Learning in a paradigmatic Linked Multi-Component Robotic System (L-MCRS) control problem: the hose transportation task. L-MCRS are over-constrained systems with many UTS induced by the interaction of the passive linking element and the active mobile robots.

The Potential for Double-Loop Learning to Enable Landscape Conservation Efforts

NASA Astrophysics Data System (ADS)

Petersen, Brian; Montambault, Jensen; Koopman, Marni

2014-10-01

As conservation increases its emphasis on implementing change at landscape-level scales, multi-agency, cross-boundary, and multi-stakeholder networks become more important. These elements complicate traditional notions of learning. To investigate this further, we examined structures of learning in the Landscape Conservation Cooperatives (LCCs), which include the entire US and its territories, as well as parts of Canada, Mexico, and Caribbean and Pacific island states. We used semi-structured interviews, transcribed and analyzed using NVivo, as well as a charrette-style workshop to understand the difference between the original stated goals of individual LCCs and the values and purposes expressed as the collaboration matured. We suggest double-loop learning as a theoretical framework appropriate to landscape-scale conservation, recognizing that concerns about accountability are among the valid points of view that must be considered in multi-stakeholder collaborations. Methods from the social sciences and public health sectors provide insights on how such learning might be actualized.

Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

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

Aziz, H. M. Abdul; Zhu, Feng; Ukkusuri, Satish V.

Here, this research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. Additionally, the comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better atmore » higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO 2, NO x, VOC, PM 10) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.« less

Drug related webpages classification using images and text information based on multi-kernel learning

NASA Astrophysics Data System (ADS)

Hu, Ruiguang; Xiao, Liping; Zheng, Wenjuan

2015-12-01

In this paper, multi-kernel learning(MKL) is used for drug-related webpages classification. First, body text and image-label text are extracted through HTML parsing, and valid images are chosen by the FOCARSS algorithm. Second, text based BOW model is used to generate text representation, and image-based BOW model is used to generate images representation. Last, text and images representation are fused with a few methods. Experimental results demonstrate that the classification accuracy of MKL is higher than those of all other fusion methods in decision level and feature level, and much higher than the accuracy of single-modal classification.

Multi-centre diagnostic classification of individual structural neuroimaging scans from patients with major depressive disorder.

PubMed

Mwangi, Benson; Ebmeier, Klaus P; Matthews, Keith; Steele, J Douglas

2012-05-01

Quantitative abnormalities of brain structure in patients with major depressive disorder have been reported at a group level for decades. However, these structural differences appear subtle in comparison with conventional radiologically defined abnormalities, with considerable inter-subject variability. Consequently, it has not been possible to readily identify scans from patients with major depressive disorder at an individual level. Recently, machine learning techniques such as relevance vector machines and support vector machines have been applied to predictive classification of individual scans with variable success. Here we describe a novel hybrid method, which combines machine learning with feature selection and characterization, with the latter aimed at maximizing the accuracy of machine learning prediction. The method was tested using a multi-centre dataset of T(1)-weighted 'structural' scans. A total of 62 patients with major depressive disorder and matched controls were recruited from referred secondary care clinical populations in Aberdeen and Edinburgh, UK. The generalization ability and predictive accuracy of the classifiers was tested using data left out of the training process. High prediction accuracy was achieved (~90%). While feature selection was important for maximizing high predictive accuracy with machine learning, feature characterization contributed only a modest improvement to relevance vector machine-based prediction (~5%). Notably, while the only information provided for training the classifiers was T(1)-weighted scans plus a categorical label (major depressive disorder versus controls), both relevance vector machine and support vector machine 'weighting factors' (used for making predictions) correlated strongly with subjective ratings of illness severity. These results indicate that machine learning techniques have the potential to inform clinical practice and research, as they can make accurate predictions about brain scan data from individual subjects. Furthermore, machine learning weighting factors may reflect an objective biomarker of major depressive disorder illness severity, based on abnormalities of brain structure.

Developing an Instrument to Characterise Peer-Led Groups in Collaborative Learning Environments: Assessing Problem-Solving Approach and Group Interaction

ERIC Educational Resources Information Center

Pazos, Pilar; Micari, Marina; Light, Gregory

2010-01-01

Collaborative learning is being used extensively by educators at all levels. Peer-led team learning in a version of collaborative learning that has shown consistent success in science, technology, engineering and mathematics disciplines. Using a multi-phase research study we describe the development of an observation instrument that can be used to…

Behavior generation strategy of artificial behavioral system by self-learning paradigm for autonomous robot tasks

NASA Astrophysics Data System (ADS)

Dağlarli, Evren; Temeltaş, Hakan

2008-04-01

In this study, behavior generation and self-learning paradigms are investigated for the real-time applications of multi-goal mobile robot tasks. The method is capable to generate new behaviors and it combines them in order to achieve multi goal tasks. The proposed method is composed from three layers: Behavior Generating Module, Coordination Level and Emotion -Motivation Level. Last two levels use Hidden Markov models to manage dynamical structure of behaviors. The kinematics and dynamic model of the mobile robot with non-holonomic constraints are considered in the behavior based control architecture. The proposed method is tested on a four-wheel driven and four-wheel steered mobile robot with constraints in simulation environment and results are obtained successfully.

Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico study

PubMed Central

2010-01-01

Background Gene silencing using exogenous small interfering RNAs (siRNAs) is now a widespread molecular tool for gene functional study and new-drug target identification. The key mechanism in this technique is to design efficient siRNAs that incorporated into the RNA-induced silencing complexes (RISC) to bind and interact with the mRNA targets to repress their translations to proteins. Although considerable progress has been made in the computational analysis of siRNA binding efficacy, few joint analysis of different RNAi experiments conducted under different experimental scenarios has been done in research so far, while the joint analysis is an important issue in cross-platform siRNA efficacy prediction. A collective analysis of RNAi mechanisms for different datasets and experimental conditions can often provide new clues on the design of potent siRNAs. Results An elegant multi-task learning paradigm for cross-platform siRNA efficacy prediction is proposed. Experimental studies were performed on a large dataset of siRNA sequences which encompass several RNAi experiments recently conducted by different research groups. By using our multi-task learning method, the synergy among different experiments is exploited and an efficient multi-task predictor for siRNA efficacy prediction is obtained. The 19 most popular biological features for siRNA according to their jointly importance in multi-task learning were ranked. Furthermore, the hypothesis is validated out that the siRNA binding efficacy on different messenger RNAs(mRNAs) have different conditional distribution, thus the multi-task learning can be conducted by viewing tasks at an "mRNA"-level rather than at the "experiment"-level. Such distribution diversity derived from siRNAs bound to different mRNAs help indicate that the properties of target mRNA have important implications on the siRNA binding efficacy. Conclusions The knowledge gained from our study provides useful insights on how to analyze various cross-platform RNAi data for uncovering of their complex mechanism. PMID:20380733

Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico study.

PubMed

Liu, Qi; Xu, Qian; Zheng, Vincent W; Xue, Hong; Cao, Zhiwei; Yang, Qiang

2010-04-10

Gene silencing using exogenous small interfering RNAs (siRNAs) is now a widespread molecular tool for gene functional study and new-drug target identification. The key mechanism in this technique is to design efficient siRNAs that incorporated into the RNA-induced silencing complexes (RISC) to bind and interact with the mRNA targets to repress their translations to proteins. Although considerable progress has been made in the computational analysis of siRNA binding efficacy, few joint analysis of different RNAi experiments conducted under different experimental scenarios has been done in research so far, while the joint analysis is an important issue in cross-platform siRNA efficacy prediction. A collective analysis of RNAi mechanisms for different datasets and experimental conditions can often provide new clues on the design of potent siRNAs. An elegant multi-task learning paradigm for cross-platform siRNA efficacy prediction is proposed. Experimental studies were performed on a large dataset of siRNA sequences which encompass several RNAi experiments recently conducted by different research groups. By using our multi-task learning method, the synergy among different experiments is exploited and an efficient multi-task predictor for siRNA efficacy prediction is obtained. The 19 most popular biological features for siRNA according to their jointly importance in multi-task learning were ranked. Furthermore, the hypothesis is validated out that the siRNA binding efficacy on different messenger RNAs(mRNAs) have different conditional distribution, thus the multi-task learning can be conducted by viewing tasks at an "mRNA"-level rather than at the "experiment"-level. Such distribution diversity derived from siRNAs bound to different mRNAs help indicate that the properties of target mRNA have important implications on the siRNA binding efficacy. The knowledge gained from our study provides useful insights on how to analyze various cross-platform RNAi data for uncovering of their complex mechanism.

Do Online Learning Patterns Exhibit Regional and Demographic Differences?

ERIC Educational Resources Information Center

Hsieh, Tsui-Chuan; Yang, Chyan

2012-01-01

This paper used a multi-level latent class model to evaluate whether online learning patterns exhibit regional differences and demographics. This study discovered that the Internet learning pattern consists of five segments, and the region of Taiwan is divided into two segments and further found that both the user and the regional segments are…

Exploring Adaptability through Learning Layers and Learning Loops

ERIC Educational Resources Information Center

Lof, Annette

2010-01-01

Adaptability in social-ecological systems results from individual and collective action, and multi-level interactions. It can be understood in a dual sense as a system's ability to adapt to disturbance and change, and to navigate system transformation. Inherent in this conception, as found in resilience thinking, are the concepts of learning and…

Intervening or Ignoring: Learning about Teaching in New Times

ERIC Educational Resources Information Center

Blaise, Mindy; Elsden-Clifton, Jennifer

2007-01-01

In response to the rise of collaborative learning within education, two teacher educators redesigned their courses to explore the complexities of pedagogy within a New Learning framework. Multi-age grouping provided opportunities for pre-service teachers to work with others from different year levels on an interdisciplinary assessment task. As a…

An Embodied Multi-Sensor Fusion Approach to Visual Motion Estimation Using Unsupervised Deep Networks.

PubMed

Shamwell, E Jared; Nothwang, William D; Perlis, Donald

2018-05-04

Aimed at improving size, weight, and power (SWaP)-constrained robotic vision-aided state estimation, we describe our unsupervised, deep convolutional-deconvolutional sensor fusion network, Multi-Hypothesis DeepEfference (MHDE). MHDE learns to intelligently combine noisy heterogeneous sensor data to predict several probable hypotheses for the dense, pixel-level correspondence between a source image and an unseen target image. We show how our multi-hypothesis formulation provides increased robustness against dynamic, heteroscedastic sensor and motion noise by computing hypothesis image mappings and predictions at 76⁻357 Hz depending on the number of hypotheses being generated. MHDE fuses noisy, heterogeneous sensory inputs using two parallel, inter-connected architectural pathways and n (1⁻20 in this work) multi-hypothesis generating sub-pathways to produce n global correspondence estimates between a source and a target image. We evaluated MHDE on the KITTI Odometry dataset and benchmarked it against the vision-only DeepMatching and Deformable Spatial Pyramids algorithms and were able to demonstrate a significant runtime decrease and a performance increase compared to the next-best performing method.

Technology to Enhance Learning in the Multi-Lingual Classroom

ERIC Educational Resources Information Center

Hollenbeck, James E.; Hollenbeck, Darina Z.

2004-01-01

Research and various studies have showed that using multimedia in the classroom increases creativity, innovation problem solving and improves communication between people. Technology addresses equity and access issues for learners. Technology allows educators to refine teaching strategies and learning processes, and to be more inclusive of all…

Children Who Desperately Want To Read, But Are Not Working at Grade Level: Use Movement Patterns As "Windows" To Discover Why. Part II: The Transverse Midline.

ERIC Educational Resources Information Center

Corso, Marjorie

This paper discusses a multi-part longitudinal study which compared the developmental movement levels and the academic learning level in young children, noting that the relationship between movement education and academic education is based on the assumption that both realms of learning are dependent on the adequate development of the brain. The…

Satellite Imagery Analysis for Automated Global Food Security Forecasting

NASA Astrophysics Data System (ADS)

Moody, D.; Brumby, S. P.; Chartrand, R.; Keisler, R.; Mathis, M.; Beneke, C. M.; Nicholaeff, D.; Skillman, S.; Warren, M. S.; Poehnelt, J.

2017-12-01

The recent computing performance revolution has driven improvements in sensor, communication, and storage technology. Multi-decadal remote sensing datasets at the petabyte scale are now available in commercial clouds, with new satellite constellations generating petabytes/year of daily high-resolution global coverage imagery. Cloud computing and storage, combined with recent advances in machine learning, are enabling understanding of the world at a scale and at a level of detail never before feasible. We present results from an ongoing effort to develop satellite imagery analysis tools that aggregate temporal, spatial, and spectral information and that can scale with the high-rate and dimensionality of imagery being collected. We focus on the problem of monitoring food crop productivity across the Middle East and North Africa, and show how an analysis-ready, multi-sensor data platform enables quick prototyping of satellite imagery analysis algorithms, from land use/land cover classification and natural resource mapping, to yearly and monthly vegetative health change trends at the structural field level.

Using the mixed media according to internet-based on the instructional multimedia for developing students' learning achievements in biology course on foundational cell issue of secondary students at the 10th grade level in Rangsit University demonstration school

NASA Astrophysics Data System (ADS)

Kangloan, Pichet; Chayaburakul, Kanokporn; Santiboon, Toansakul

2018-01-01

The aims of this research study were 1) to develop students' learning achievements in biology course on foundational cell issue, 2) to examine students' satisfactions of their learning activities through the mixed media according to internet-based multi-instruction in biology on foundational cell issue at the 10th grade level were used in the first semester in the academic year 2014, which a sample size of 17 students in Rangsit University Demonstration School with cluster random sampling was selected. Students' learning administrations were instructed with the 3-instructional lesson plans according to the 5-Step Ladder Learning Management Plan (LLMP) namely; the maintaining lesson plan on the equilibrium of cell issue, a lesson plan for learning how to communicate between cell and cell division. Students' learning achievements were assessed with the 30-item Assessment of Learning Biology Test (ALBT), students' perceptions of their satisfactions were satisfied with the 20-item Questionnaire on Students Satisfaction (QSS), and students' learning activities were assessed with the Mixed Media Internet-Based Instruction (MMIBI) on foundational cell issue was designed. The results of this research study have found that: statistically significant of students' post-learning achievements were higher than their pre-learning outcomes and indicated that the differences were significant at the .05 level. Students' performances of their satisfaction to their perceptions toward biology class with the mixed media according to internet-based multi instruction in biology on foundational cell issue were the highest level and evidence of average mean score as 4.59.

Performance evaluation of MLP and RBF feed forward neural network for the recognition of off-line handwritten characters

NASA Astrophysics Data System (ADS)

Rishi, Rahul; Choudhary, Amit; Singh, Ravinder; Dhaka, Vijaypal Singh; Ahlawat, Savita; Rao, Mukta

2010-02-01

In this paper we propose a system for classification problem of handwritten text. The system is composed of preprocessing module, supervised learning module and recognition module on a very broad level. The preprocessing module digitizes the documents and extracts features (tangent values) for each character. The radial basis function network is used in the learning and recognition modules. The objective is to analyze and improve the performance of Multi Layer Perceptron (MLP) using RBF transfer functions over Logarithmic Sigmoid Function. The results of 35 experiments indicate that the Feed Forward MLP performs accurately and exhaustively with RBF. With the change in weight update mechanism and feature-drawn preprocessing module, the proposed system is competent with good recognition show.

Balancing Bologna: opportunities for university teaching that integrates academic and practical learning outcomes

NASA Astrophysics Data System (ADS)

Probst, Lorenz; Pflug, Verena; Brandenburg, Christiane; Guggenberger, Thomas; Mentler, Axel; Wurzinger, Maria

2014-05-01

In the course of the Bologna Process, the quality of university teaching has become more prominent in the discourse on higher education. More attention is now paid to didactics and methods and learner-oriented modes of teaching are introduced. The application of knowledge, practical skills and in consequence the employability of university graduates have become requirements for university teaching. Yet, the lecture-style approach still dominates European universities, although empirical evidence confirms that student-centred, interdisciplinary and experiential learning is more effective. Referring to the learning taxonomy introduced by Bloom, we argue that standard approaches rarely move beyond the learning level of comprehension and fail to reach the levels of application, analysis, synthesis and evaluation. Considering the rapid changes and multiple challenges society faces today, responsible practitioners and scientists who can improve the current management of natural resources are urgently needed. Universities are expected to equip their graduates with the necessary skills to reflect and evaluate their actions when addressing 'real world' problems in order to improve impact and relevance of their work. Higher education thus faces the challenge of providing multi-level learning opportunities for students with diverse practical and theoretical learning needs. In this study, we reflect on three cases of university teaching attempting to bridge theory and practice and based on the principles of systemic, problem based learning. The described courses focus on organic farming, rural development and landscape planning and take place in Uganda, Nicaragua and Italy. We show that being part of a real-world community of stakeholders requires hands-on learning and the reflection and evaluation of actions. This prepares students in a more effective and realistic way for their future roles as responsible decision makers in complex social, economic and ecological systems. We thus conclude that in order (1) to meet the goals of the Bologna process; and (2) to bridge the gap between theory and practice in higher education, university teaching needs to radically reconsider its standard forms of teaching. We propose a fundamental shift towards action learning in real-world settings, empowering students to become responsible actors.

Cross-domain and multi-task transfer learning of deep convolutional neural network for breast cancer diagnosis in digital breast tomosynthesis

NASA Astrophysics Data System (ADS)

Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir; Helvie, Mark A.; Richter, Caleb; Cha, Kenny

2018-02-01

We propose a cross-domain, multi-task transfer learning framework to transfer knowledge learned from non-medical images by a deep convolutional neural network (DCNN) to medical image recognition task while improving the generalization by multi-task learning of auxiliary tasks. A first stage cross-domain transfer learning was initiated from ImageNet trained DCNN to mammography trained DCNN. 19,632 regions-of-interest (ROI) from 2,454 mass lesions were collected from two imaging modalities: digitized-screen film mammography (SFM) and full-field digital mammography (DM), and split into training and test sets. In the multi-task transfer learning, the DCNN learned the mass classification task simultaneously from the training set of SFM and DM. The best transfer network for mammography was selected from three transfer networks with different number of convolutional layers frozen. The performance of single-task and multitask transfer learning on an independent SFM test set in terms of the area under the receiver operating characteristic curve (AUC) was 0.78+/-0.02 and 0.82+/-0.02, respectively. In the second stage cross-domain transfer learning, a set of 12,680 ROIs from 317 mass lesions on DBT were split into validation and independent test sets. We first studied the data requirements for the first stage mammography trained DCNN by varying the mammography training data from 1% to 100% and evaluated its learning on the DBT validation set in inference mode. We found that the entire available mammography set provided the best generalization. The DBT validation set was then used to train only the last four fully connected layers, resulting in an AUC of 0.90+/-0.04 on the independent DBT test set.

The Robust Learning Model (RLM): A Comprehensive Approach to a New Online University

ERIC Educational Resources Information Center

Neumann, Yoram; Neumann, Edith F.

2010-01-01

This paper outlines the components of the Robust Learning Model (RLM) as a conceptual framework for creating a new online university offering numerous degree programs at all degree levels. The RLM is a multi-factorial model based on the basic belief that successful learning outcomes depend on multiple factors employed together in a holistic…

Future applications of artificial intelligence to Mission Control Centers

NASA Technical Reports Server (NTRS)

Friedland, Peter

1991-01-01

Future applications of artificial intelligence to Mission Control Centers are presented in the form of the viewgraphs. The following subject areas are covered: basic objectives of the NASA-wide AI program; inhouse research program; constraint-based scheduling; learning and performance improvement for scheduling; GEMPLAN multi-agent planner; planning, scheduling, and control; Bayesian learning; efficient learning algorithms; ICARUS (an integrated architecture for learning); design knowledge acquisition and retention; computer-integrated documentation; and some speculation on future applications.

Designing Virtual Worlds for Use in Mathematics Education.

ERIC Educational Resources Information Center

Winn, William; Bricken, William

Virtual Reality (VR) is a computer generated, multi-dimensional, inclusive environment that can build axioms of algebra into the behavior of the world. This paper discusses the use of VR to represent part of the algebra curriculum in order to improve students' classroom experiences in learning algebra. Students learn to construct their knowledge…

How to Improve Integrated Care for People with Chronic Conditions: Key Findings from EU FP-7 Project INTEGRATE and Beyond.

PubMed

Borgermans, Liesbeth; Marchal, Yannick; Busetto, Loraine; Kalseth, Jorid; Kasteng, Frida; Suija, Kadri; Oona, Marje; Tigova, Olena; Rösenmuller, Magda; Devroey, Dirk

2017-09-25

Political and public health leaders increasingly recognize the need to take urgent action to address the problem of chronic diseases and multi-morbidity. European countries are facing unprecedented demand to find new ways to deliver care to improve patient-centredness and personalization, and to avoid unnecessary time in hospitals. People-centred and integrated care has become a central part of policy initiatives to improve the access, quality, continuity, effectiveness and sustainability of healthcare systems and are thus preconditions for the economic sustainability of the EU health and social care systems. This study presents an overview of lessons learned and critical success factors to policy making on integrated care based on findings from the EU FP-7 Project Integrate, a literature review, other EU projects with relevance to this study, a number of best practices on integrated care and our own experiences with research and policy making in integrated care at the national and international level. Seven lessons learned and critical success factors to policy making on integrated care were identified. The lessons learned and critical success factors to policy making on integrated care show that a comprehensive systems perspective should guide the development of integrated care towards better health practices, education, research and policy.

How to Improve Integrated Care for People with Chronic Conditions: Key Findings from EU FP-7 Project INTEGRATE and Beyond

PubMed Central

Marchal, Yannick; Busetto, Loraine; Kalseth, Jorid; Kasteng, Frida; Suija, Kadri; Oona, Marje; Tigova, Olena; Rösenmuller, Magda; Devroey, Dirk

2017-01-01

Background: Political and public health leaders increasingly recognize the need to take urgent action to address the problem of chronic diseases and multi-morbidity. European countries are facing unprecedented demand to find new ways to deliver care to improve patient-centredness and personalization, and to avoid unnecessary time in hospitals. People-centred and integrated care has become a central part of policy initiatives to improve the access, quality, continuity, effectiveness and sustainability of healthcare systems and are thus preconditions for the economic sustainability of the EU health and social care systems. Purpose: This study presents an overview of lessons learned and critical success factors to policy making on integrated care based on findings from the EU FP-7 Project Integrate, a literature review, other EU projects with relevance to this study, a number of best practices on integrated care and our own experiences with research and policy making in integrated care at the national and international level. Results: Seven lessons learned and critical success factors to policy making on integrated care were identified. Conclusion: The lessons learned and critical success factors to policy making on integrated care show that a comprehensive systems perspective should guide the development of integrated care towards better health practices, education, research and policy. PMID:29588630

An inference method from multi-layered structure of biomedical data.

PubMed

Kim, Myungjun; Nam, Yonghyun; Shin, Hyunjung

2017-05-18

Biological system is a multi-layered structure of omics with genome, epigenome, transcriptome, metabolome, proteome, etc., and can be further stretched to clinical/medical layers such as diseasome, drugs, and symptoms. One advantage of omics is that we can figure out an unknown component or its trait by inferring from known omics components. The component can be inferred by the ones in the same level of omics or the ones in different levels. To implement the inference process, an algorithm that can be applied to the multi-layered complex system is required. In this study, we develop a semi-supervised learning algorithm that can be applied to the multi-layered complex system. In order to verify the validity of the inference, it was applied to the prediction problem of disease co-occurrence with a two-layered network composed of symptom-layer and disease-layer. The symptom-disease layered network obtained a fairly high value of AUC, 0.74, which is regarded as noticeable improvement when comparing 0.59 AUC of single-layered disease network. If further stretched to whole layered structure of omics, the proposed method is expected to produce more promising results. This research has novelty in that it is a new integrative algorithm that incorporates the vertical structure of omics data, on contrary to other existing methods that integrate the data in parallel fashion. The results can provide enhanced guideline for disease co-occurrence prediction, thereby serve as a valuable tool for inference process of multi-layered biological system.

Multi-modal gesture recognition using integrated model of motion, audio and video

NASA Astrophysics Data System (ADS)

Goutsu, Yusuke; Kobayashi, Takaki; Obara, Junya; Kusajima, Ikuo; Takeichi, Kazunari; Takano, Wataru; Nakamura, Yoshihiko

2015-07-01

Gesture recognition is used in many practical applications such as human-robot interaction, medical rehabilitation and sign language. With increasing motion sensor development, multiple data sources have become available, which leads to the rise of multi-modal gesture recognition. Since our previous approach to gesture recognition depends on a unimodal system, it is difficult to classify similar motion patterns. In order to solve this problem, a novel approach which integrates motion, audio and video models is proposed by using dataset captured by Kinect. The proposed system can recognize observed gestures by using three models. Recognition results of three models are integrated by using the proposed framework and the output becomes the final result. The motion and audio models are learned by using Hidden Markov Model. Random Forest which is the video classifier is used to learn the video model. In the experiments to test the performances of the proposed system, the motion and audio models most suitable for gesture recognition are chosen by varying feature vectors and learning methods. Additionally, the unimodal and multi-modal models are compared with respect to recognition accuracy. All the experiments are conducted on dataset provided by the competition organizer of MMGRC, which is a workshop for Multi-Modal Gesture Recognition Challenge. The comparison results show that the multi-modal model composed of three models scores the highest recognition rate. This improvement of recognition accuracy means that the complementary relationship among three models improves the accuracy of gesture recognition. The proposed system provides the application technology to understand human actions of daily life more precisely.

Multi-Objective Reinforcement Learning-based Deep Neural Networks for Cognitive Space Communications

NASA Technical Reports Server (NTRS)

Ferreria, Paulo; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy; Bilen, Sven; Reinhart, Richard; Mortensen, Dale

2017-01-01

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

Multi-Objective Reinforcement Learning-Based Deep Neural Networks for Cognitive Space Communications

NASA Technical Reports Server (NTRS)

Ferreria, Paulo Victor R.; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy M.; Bilen, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

2017-01-01

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

Relationship between learning styles and interpersonal communication skills of nursing student in Medical Sciences Tehran University in 2012

PubMed Central

Azari, S; Mokhtari, S; Mousavi, H; Mohammadi, M; Aliyari, A; Salimi, M; Azari, GH

2015-01-01

Introduction: interpersonal communication skills are required for training and represent one of the most significant parts concerning the character of student learning. In another idea, learning is a constant method and learners favor a position of knowledge forms according to their character and individual practices. Evaluate the correlation between the learning methods and interpersonal conversation abilities of the nursing undergraduate in Medical Sciences Tehran University in 2012 was the purpose of this research. Methods: In this regular detailed cross-sectional analysis, 361 students from the School of Nursing and Midwifery were chosen during a census method. The information collection instruments were regulated, giving a questionnaire called Interpersonal Communication Skills Standards exam and VARK Learning Styles questionnaire. Data was examined by SPSS application (18th edition) by using Mann-Whitney and Kruskal-Wallis test. Results: 320 questionnaires were finished. 60.6% of the members were females. The average number of the students’ conversation abilities level was 101.91 ± 10.35. More than half of the samples (58.8%) preferred multi-modal learning styles (Bi-Tri and Quad Modals) and 41.2% of the students preferred single modal learning styles. There were no significant differences between the Interpersonal Communication Skills and the learning styles (P= 0.46). Conclusion: According to no significant relationship between the communication skills of students with learning style and Demographic changeable and Lack of proper form of communication skills, we were ready to build different systems and courses related to improving the skills’ level. PMID:28316687

The relationship between learning style preferences and gender, educational major and status in first year medical students: a survey study from iran.

PubMed

Sarabi-Asiabar, Ali; Jafari, Mehdi; Sadeghifar, Jamil; Tofighi, Shahram; Zaboli, Rouhollah; Peyman, Hadi; Salimi, Mohammad; Shams, Lida

2015-01-01

Identifying and employing appropriate learning styles could play an important role in selecting teaching styles in order to improve education. This study aimed to determine the relationship between learning styles preferences and gender, educational major and status in first year students at Isfahan University of Medical Sciences. A cross-sectional study employing the visual-aural-read/write-kinesthetic (VARK) learning style's questionnaire was done on 184 first year students of medicine, pharmacy, dentistry, nursing and health services management at Isfahan University of Medical Sciences in 2012. The validity of the questionnaire was assessed through experts' views and reliability was calculated using Cronbach's alpha coefficients (α = 0.86). Data were analyzed using the SPSS ver.18 software and x(2) test. Out of 184 participants who responded to and returned the questionnaire, 122 (66.3%) were female; more than two-thirds (68.5%) of the enrolled students were at the professional doctorate level (medicine, pharmacy, dentistry) and 31.5% at the undergraduate level (nursing and health services management). Eighty-nine (48.4%) students preferred a single-modal learning style. In contrast, the remaining 95 students (51.6%) preferred multi-modal learning styles. A significant relationship between gender and single modal learning styles (P = 0.009) and between status and learning styles (P = 0.04) was observed. According to the results, male students preferred to use the kinesthetic learning style more than females, while, female students preferred the aural learning style. Knowledge about the learning styles of students at educational institutes is valuable and helps solve learning problems among students, and allows students to become better learners.

The Relationship Between Learning Style Preferences and Gender, Educational Major and Status in First Year Medical Students: A Survey Study From Iran

PubMed Central

Sarabi-Asiabar, Ali; Jafari, Mehdi; Sadeghifar, Jamil; Tofighi, Shahram; Zaboli, Rouhollah; Peyman, Hadi; Salimi, Mohammad; Shams, Lida

2014-01-01

Background: Identifying and employing appropriate learning styles could play an important role in selecting teaching styles in order to improve education. Objectives: This study aimed to determine the relationship between learning styles preferences and gender, educational major and status in first year students at Isfahan University of Medical Sciences. Patients and Methods: A cross-sectional study employing the visual-aural-read/write-kinesthetic (VARK) learning style’s questionnaire was done on 184 first year students of medicine, pharmacy, dentistry, nursing and health services management at Isfahan University of Medical Sciences in 2012. The validity of the questionnaire was assessed through experts’ views and reliability was calculated using Cronbach’s alpha coefficients (α = 0.86). Data were analyzed using the SPSS ver.18 software and x2 test. Results: Out of 184 participants who responded to and returned the questionnaire, 122 (66.3%) were female; more than two-thirds (68.5%) of the enrolled students were at the professional doctorate level (medicine, pharmacy, dentistry) and 31.5% at the undergraduate level (nursing and health services management). Eighty-nine (48.4%) students preferred a single-modal learning style. In contrast, the remaining 95 students (51.6%) preferred multi-modal learning styles. A significant relationship between gender and single modal learning styles (P = 0.009) and between status and learning styles (P = 0.04) was observed. Conclusions: According to the results, male students preferred to use the kinesthetic learning style more than females, while, female students preferred the aural learning style. Knowledge about the learning styles of students at educational institutes is valuable and helps solve learning problems among students, and allows students to become better learners. PMID:25763269

Multi-Scale Distributed Representation for Deep Learning and its Application to b-Jet Tagging

NASA Astrophysics Data System (ADS)

Lee, Jason Sang Hun; Park, Inkyu; Park, Sangnam

2018-06-01

Recently machine learning algorithms based on deep layered artificial neural networks (DNNs) have been applied to a wide variety of high energy physics problems such as jet tagging or event classification. We explore a simple but effective preprocessing step which transforms each realvalued observational quantity or input feature into a binary number with a fixed number of digits. Each binary digit represents the quantity or magnitude in different scales. We have shown that this approach improves the performance of DNNs significantly for some specific tasks without any further complication in feature engineering. We apply this multi-scale distributed binary representation to deep learning on b-jet tagging using daughter particles' momenta and vertex information.

Clinical Assessment of Risk Management: an INtegrated Approach (CARMINA).

PubMed

Tricarico, Pierfrancesco; Tardivo, Stefano; Sotgiu, Giovanni; Moretti, Francesca; Poletti, Piera; Fiore, Alberto; Monturano, Massimo; Mura, Ida; Privitera, Gaetano; Brusaferro, Silvio

2016-08-08

Purpose - The European Union recommendations for patient safety calls for shared clinical risk management (CRM) safety standards able to guide organizations in CRM implementation. The purpose of this paper is to develop a self-evaluation tool to measure healthcare organization performance on CRM and guide improvements over time. Design/methodology/approach - A multi-step approach was implemented including: a systematic literature review; consensus meetings with an expert panel from eight Italian leader organizations to get to an agreement on the first version; field testing to test instrument feasibility and flexibility; Delphi strategy with a second expert panel for content validation and balanced scoring system development. Findings - The self-assessment tool - Clinical Assessment of Risk Management: an INtegrated Approach includes seven areas (governance, communication, knowledge and skills, safe environment, care processes, adverse event management, learning from experience) and 52 standards. Each standard is evaluated according to four performance levels: minimum; monitoring; outcomes; and improvement actions, which resulted in a feasible, flexible and valid instrument to be used throughout different organizations. Practical implications - This tool allows practitioners to assess their CRM activities compared to minimum levels, monitor performance, benchmarking with other institutions and spreading results to different stakeholders. Originality/value - The multi-step approach allowed us to identify core minimum CRM levels in a field where no consensus has been reached. Most standards may be easily adopted in other countries.

Cooperative photometric redshift estimation

NASA Astrophysics Data System (ADS)

Cavuoti, S.; Tortora, C.; Brescia, M.; Longo, G.; Radovich, M.; Napolitano, N. R.; Amaro, V.; Vellucci, C.

2017-06-01

In the modern galaxy surveys photometric redshifts play a central role in a broad range of studies, from gravitational lensing and dark matter distribution to galaxy evolution. Using a dataset of ~ 25,000 galaxies from the second data release of the Kilo Degree Survey (KiDS) we obtain photometric redshifts with five different methods: (i) Random forest, (ii) Multi Layer Perceptron with Quasi Newton Algorithm, (iii) Multi Layer Perceptron with an optimization network based on the Levenberg-Marquardt learning rule, (iv) the Bayesian Photometric Redshift model (or BPZ) and (v) a classical SED template fitting procedure (Le Phare). We show how SED fitting techniques could provide useful information on the galaxy spectral type which can be used to improve the capability of machine learning methods constraining systematic errors and reduce the occurrence of catastrophic outliers. We use such classification to train specialized regression estimators, by demonstrating that such hybrid approach, involving SED fitting and machine learning in a single collaborative framework, is capable to improve the overall prediction accuracy of photometric redshifts.

Automatic classification and detection of clinically relevant images for diabetic retinopathy

NASA Astrophysics Data System (ADS)

Xu, Xinyu; Li, Baoxin

2008-03-01

We proposed a novel approach to automatic classification of Diabetic Retinopathy (DR) images and retrieval of clinically-relevant DR images from a database. Given a query image, our approach first classifies the image into one of the three categories: microaneurysm (MA), neovascularization (NV) and normal, and then it retrieves DR images that are clinically-relevant to the query image from an archival image database. In the classification stage, the query DR images are classified by the Multi-class Multiple-Instance Learning (McMIL) approach, where images are viewed as bags, each of which contains a number of instances corresponding to non-overlapping blocks, and each block is characterized by low-level features including color, texture, histogram of edge directions, and shape. McMIL first learns a collection of instance prototypes for each class that maximizes the Diverse Density function using Expectation- Maximization algorithm. A nonlinear mapping is then defined using the instance prototypes and maps every bag to a point in a new multi-class bag feature space. Finally a multi-class Support Vector Machine is trained in the multi-class bag feature space. In the retrieval stage, we retrieve images from the archival database who bear the same label with the query image, and who are the top K nearest neighbors of the query image in terms of similarity in the multi-class bag feature space. The classification approach achieves high classification accuracy, and the retrieval of clinically-relevant images not only facilitates utilization of the vast amount of hidden diagnostic knowledge in the database, but also improves the efficiency and accuracy of DR lesion diagnosis and assessment.

Improving English Language Learners' Academic Writing: A Multi-Strategy Approach to a Multi-Dimensional Challenge

ERIC Educational Resources Information Center

Marulanda Ángel, Nora Lucía; Martínez García, Juan Manuel

2017-01-01

The demands of the academic field and the constraints students have while learning how to write appropriately call for better approaches to teach academic writing. This research study examines the effect of a multifaceted academic writing module on pre-service teachers' composition skills in an English teacher preparation program at a medium sized…

Aircraft Fault Detection and Classification Using Multi-Level Immune Learning Detection

NASA Technical Reports Server (NTRS)

Wong, Derek; Poll, Scott; KrishnaKumar, Kalmanje

2005-01-01

This work is an extension of a recently developed software tool called MILD (Multi-level Immune Learning Detection), which implements a negative selection algorithm for anomaly and fault detection that is inspired by the human immune system. The immunity-based approach can detect a broad spectrum of known and unforeseen faults. We extend MILD by applying a neural network classifier to identify the pattern of fault detectors that are activated during fault detection. Consequently, MILD now performs fault detection and identification of the system under investigation. This paper describes the application of MILD to detect and classify faults of a generic transport aircraft augmented with an intelligent flight controller. The intelligent control architecture is designed to accommodate faults without the need to explicitly identify them. Adding knowledge about the existence and type of a fault will improve the handling qualities of a degraded aircraft and impact tactical and strategic maneuvering decisions. In addition, providing fault information to the pilot is important for maintaining situational awareness so that he can avoid performing an action that might lead to unexpected behavior - e.g., an action that exceeds the remaining control authority of the damaged aircraft. We discuss the detection and classification results of simulated failures of the aircraft's control system and show that MILD is effective at determining the problem with low false alarm and misclassification rates.

A Robust Deep Model for Improved Classification of AD/MCI Patients

PubMed Central

Li, Feng; Tran, Loc; Thung, Kim-Han; Ji, Shuiwang; Shen, Dinggang; Li, Jiang

2015-01-01

Accurate classification of Alzheimer’s Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), plays a critical role in possibly preventing progression of memory impairment and improving quality of life for AD patients. Among many research tasks, it is of particular interest to identify noninvasive imaging biomarkers for AD diagnosis. In this paper, we present a robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans. We utilized the dropout technique to improve classical deep learning by preventing its weight co-adaptation, which is a typical cause of over-fitting in deep learning. In addition, we incorporated stability selection, an adaptive learning factor, and a multi-task learning strategy into the deep learning framework. We applied the proposed method to the ADNI data set and conducted experiments for AD and MCI conversion diagnosis. Experimental results showed that the dropout technique is very effective in AD diagnosis, improving the classification accuracies by 5.9% on average as compared to the classical deep learning methods. PMID:25955998

Learning together for effective collaboration in school-based occupational therapy practice.

PubMed

Villeneuve, Michelle A; Shulha, Lyn M

2012-12-01

School-based occupational therapy (SBOT) practice takes place within a complex system that includes service recipients, service providers, and program decision makers across health and education sectors. Despite the promotion of collaborative consultation at a policy level, there is little practical guidance about how to coordinate multi-agency service and interprofessional collaboration among these stakeholders. This paper reports on a process used to engage program administrators in an examination of SBOT collaborative consultation practice in one region of Ontario to provide an evidence-informed foundation for decision making about implementation of these services. Within an appreciative inquiry framework (Cooperrider, Whitney, & Stavros, 2008), Developmental Work Research methods (Engeström, 2000) were used to facilitate shared learning for improved SBOT collaborative consultation. Program administrators participated alongside program providers and service recipients in a series of facilitated workshops to develop principles that will guide future planning and decision making about the delivery of SBOT services. Facilitated discussion among stakeholders led to the articulation of 12 principles for effective collaborative practice. Program administrators used their shared understanding to propose a new model for delivering SBOT services. Horizontal and vertical learning across agency and professional boundaries led to the development of powerful solutions for program improvement.

SU-C-BRA-04: Automated Segmentation of Head-And-Neck CT Images for Radiotherapy Treatment Planning Via Multi-Atlas Machine Learning (MAML)

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

Ren, X; Gao, H; Sharp, G

Purpose: Accurate image segmentation is a crucial step during image guided radiation therapy. This work proposes multi-atlas machine learning (MAML) algorithm for automated segmentation of head-and-neck CT images. Methods: As the first step, the algorithm utilizes normalized mutual information as similarity metric, affine registration combined with multiresolution B-Spline registration, and then fuses together using the label fusion strategy via Plastimatch. As the second step, the following feature selection strategy is proposed to extract five feature components from reference or atlas images: intensity (I), distance map (D), box (B), center of gravity (C) and stable point (S). The box feature Bmore » is novel. It describes a relative position from each point to minimum inscribed rectangle of ROI. The center-of-gravity feature C is the 3D Euclidean distance from a sample point to the ROI center of gravity, and then S is the distance of the sample point to the landmarks. Then, we adopt random forest (RF) in Scikit-learn, a Python module integrating a wide range of state-of-the-art machine learning algorithms as classifier. Different feature and atlas strategies are used for different ROIs for improved performance, such as multi-atlas strategy with reference box for brainstem, and single-atlas strategy with reference landmark for optic chiasm. Results: The algorithm was validated on a set of 33 CT images with manual contours using a leave-one-out cross-validation strategy. Dice similarity coefficients between manual contours and automated contours were calculated: the proposed MAML method had an improvement from 0.79 to 0.83 for brainstem and 0.11 to 0.52 for optic chiasm with respect to multi-atlas segmentation method (MA). Conclusion: A MAML method has been proposed for automated segmentation of head-and-neck CT images with improved performance. It provides the comparable result in brainstem and the improved result in optic chiasm compared with MA. Xuhua Ren and Hao Gao were partially supported by the NSFC (#11405105), the 973 Program (#2015CB856000), and the Shanghai Pujiang Talent Program (#14PJ1404500).« less

A resilient and efficient CFD framework: Statistical learning tools for multi-fidelity and heterogeneous information fusion

NASA Astrophysics Data System (ADS)

Lee, Seungjoon; Kevrekidis, Ioannis G.; Karniadakis, George Em

2017-09-01

Exascale-level simulations require fault-resilient algorithms that are robust against repeated and expected software and/or hardware failures during computations, which may render the simulation results unsatisfactory. If each processor can share some global information about the simulation from a coarse, limited accuracy but relatively costless auxiliary simulator we can effectively fill-in the missing spatial data at the required times by a statistical learning technique - multi-level Gaussian process regression, on the fly; this has been demonstrated in previous work [1]. Based on the previous work, we also employ another (nonlinear) statistical learning technique, Diffusion Maps, that detects computational redundancy in time and hence accelerate the simulation by projective time integration, giving the overall computation a "patch dynamics" flavor. Furthermore, we are now able to perform information fusion with multi-fidelity and heterogeneous data (including stochastic data). Finally, we set the foundations of a new framework in CFD, called patch simulation, that combines information fusion techniques from, in principle, multiple fidelity and resolution simulations (and even experiments) with a new adaptive timestep refinement technique. We present two benchmark problems (the heat equation and the Navier-Stokes equations) to demonstrate the new capability that statistical learning tools can bring to traditional scientific computing algorithms. For each problem, we rely on heterogeneous and multi-fidelity data, either from a coarse simulation of the same equation or from a stochastic, particle-based, more "microscopic" simulation. We consider, as such "auxiliary" models, a Monte Carlo random walk for the heat equation and a dissipative particle dynamics (DPD) model for the Navier-Stokes equations. More broadly, in this paper we demonstrate the symbiotic and synergistic combination of statistical learning, domain decomposition, and scientific computing in exascale simulations.

E-Learning in Photogrammetry, Remote Sensing and Spatial Information Science

NASA Astrophysics Data System (ADS)

Vyas, Anjana; König, Gerhard

2016-06-01

Science and technology are evolving leaps and bounds. The advancements in GI-Science for natural and built environment helps in improving the quality of life. Learning through education and training needs to be at par with those advancements, which plays a vital role in utilization of technology. New technologies that creates new opportunities have enabled Geomatics to broaden the horizon (skills and competencies). Government policies and decisions support the use of geospatial science in various sectors of governance. Mapping, Land management, Urban planning, Environmental planning, Industrialization are some of the areas where the geomatics has become a baseline for decision making at national level. There is a need to bridge the gap between developments in geospatial science and its utilization and implementation. To prepare a framework for standardisation it is important to understand the theories of education and prevailing practices, with articulate goals exploring variety of teaching techniques. E-Learning is an erudition practice shaped for facilitating learning and improving performance by creating, using and managing appropriate technological processes and resources through digital and network-enabled technology. It is a shift from traditional education or training to ICT-based flexible and collaborative learning based on the community of learners, academia, professionals, experts and facilitators. Developments in e-learning is focussed on computer assisted learning which has become popular because of its potential for providing more flexible access to content and instruction at any time, from any place (Means et al, 2009). With the advent of the geo-spatial technology, fast development in the software and hardware, the demand for skilled manpower is increasing and the need is for training, education, research and dissemination. It suggests inter-organisational cooperation between academia, industry, government and international collaboration. There is a nascent need to adopt multi-specialisation approach to examine the issues and challenges of research in such a valued topic of education and training in multi-disciplinary areas. Learning involve a change in an individual's knowledge, ability to perform a skill, participate and communicate. There is considerable variation among the theories about the nature of this change. This paper derives from a scientific research grant received from ISPRS, reveals a summary result from assessing various theories and methods of evaluation of learning through education, system and structure of it for GeoInformatics.

Principal and Teacher Collaboration: An Exploration of Distributed Leadership in Professional Learning Communities

ERIC Educational Resources Information Center

DeMatthews, David

2014-01-01

Professional Learning Communities (PLCs) can be powerful tools for school improvement but require principals and teachers to collaborate and work together. This article reports on a qualitative multi-case study focused on six elementary schools in West Texas that had been identified for having effective PLCs. Principals and teachers were observed…

Using Formative Assessment and Self-Regulated Learning to Help Developmental Mathematics Students Achieve: A Multi-Campus Program

ERIC Educational Resources Information Center

Hudesman, John; Crosby, Sara; Ziehmke, Niesha; Everson, Howard; Issac, Sharlene; Flugman, Bert; Zimmerman, Barry; Moylan, Adam

2014-01-01

The authors describe an Enhanced Formative Assessment and Self-Regulated Learning (EFA-SRL) program designed to improve the achievement of community college students enrolled in developmental mathematics courses. Their model includes the use of specially formatted quizzes designed to assess both the students' mathematics and metacognitive skill…

The Impact of a Discipline-Based Learning Community on Transfer Students: A Multi-Dimensional Pilot Study

ERIC Educational Resources Information Center

Lord, Vivian B.; Coston, Charisse T. M.; Blowers, Anita N.; Davis, Boyd; Johannes, Kenia S.

2012-01-01

Learning communities (LCs) have become a popular strategy for developing structured programming aimed at enhancing student success and retention. While most LCs have focused on improving the quality of education for first-year students, little attention has been placed on addressing their usefulness for enhancing the success of transfer students.…

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.

PubMed

Choi, Joon Yul; Yoo, Tae Keun; Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

2017-01-01

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen's kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

A Replication Study on the Multi-Dimensionality of Online Social Presence

ERIC Educational Resources Information Center

Mykota, David B.

2015-01-01

The purpose of the present study is to conduct an external replication into the multi-dimensionality of social presence as measured by the Computer-Mediated Communication Questionnaire (Tu, 2005). Online social presence is one of the more important constructs for determining the level of interaction and effectiveness of learning in an online…

Skills in Clinical Communication: Are We Correctly Assessing Them at Undergraduate Level?

ERIC Educational Resources Information Center

Zamora Cervantes, Alberto; Carrión Ribas, Carme; Cordón Granados, Ferran; Galí Pla, Bibiana; Balló Peña, Elisabet; Quesada Sabate, Miquel; Grau Martin, Armand; Castro Guardiola, Antoni; Torrent Goñi, Silvia; Vargas Vila, Susanna; Vilert Garrofa, Esther; Subirats Bayego, Enric; Coll de Tuero, Gabriel; Muñoz Ortiz, Laura; Cerezo Goyeneche, Carlos; Torán Monserrat, Pere

2014-01-01

Traditional learning and assessment systems are overwhelmed when it comes to addressing the complex and multi-dimensional problems of clinical communication and professional practice. This paper shows results of a training program in clinical communication under Problem Based Learning (PBL) methodology and correlation between student…

Model-free learning on robot kinematic chains using a nested multi-agent topology

NASA Astrophysics Data System (ADS)

Karigiannis, John N.; Tzafestas, Costas S.

2016-11-01

This paper proposes a model-free learning scheme for the developmental acquisition of robot kinematic control and dexterous manipulation skills. The approach is based on a nested-hierarchical multi-agent architecture that intuitively encapsulates the topology of robot kinematic chains, where the activity of each independent degree-of-freedom (DOF) is finally mapped onto a distinct agent. Each one of those agents progressively evolves a local kinematic control strategy in a game-theoretic sense, that is, based on a partial (local) view of the whole system topology, which is incrementally updated through a recursive communication process according to the nested-hierarchical topology. Learning is thus approached not through demonstration and training but through an autonomous self-exploration process. A fuzzy reinforcement learning scheme is employed within each agent to enable efficient exploration in a continuous state-action domain. This paper constitutes in fact a proof of concept, demonstrating that global dexterous manipulation skills can indeed evolve through such a distributed iterative learning of local agent sensorimotor mappings. The main motivation behind the development of such an incremental multi-agent topology is to enhance system modularity, to facilitate extensibility to more complex problem domains and to improve robustness with respect to structural variations including unpredictable internal failures. These attributes of the proposed system are assessed in this paper through numerical experiments in different robot manipulation task scenarios, involving both single and multi-robot kinematic chains. The generalisation capacity of the learning scheme is experimentally assessed and robustness properties of the multi-agent system are also evaluated with respect to unpredictable variations in the kinematic topology. Furthermore, these numerical experiments demonstrate the scalability properties of the proposed nested-hierarchical architecture, where new agents can be recursively added in the hierarchy to encapsulate individual active DOFs. The results presented in this paper demonstrate the feasibility of such a distributed multi-agent control framework, showing that the solutions which emerge are plausible and near-optimal. Numerical efficiency and computational cost issues are also discussed.

E-learning process maturity level: a conceptual framework

NASA Astrophysics Data System (ADS)

Rahmah, A.; Santoso, H. B.; Hasibuan, Z. A.

2018-03-01

ICT advancement is a sure thing with the impact influencing many domains, including learning in both formal and informal situations. It leads to a new mindset that we should not only utilize the given ICT to support the learning process, but also improve it gradually involving a lot of factors. These phenomenon is called e-learning process evolution. Accordingly, this study attempts to explore maturity level concept to provide the improvement direction gradually and progression monitoring for the individual e-learning process. Extensive literature review, observation, and forming constructs are conducted to develop a conceptual framework for e-learning process maturity level. The conceptual framework consists of learner, e-learning process, continuous improvement, evolution of e-learning process, technology, and learning objectives. Whilst, evolution of e-learning process depicted as current versus expected conditions of e-learning process maturity level. The study concludes that from the e-learning process maturity level conceptual framework, it may guide the evolution roadmap for e-learning process, accelerate the evolution, and decrease the negative impact of ICT. The conceptual framework will be verified and tested in the future study.

Learning Natural Selection in 4th Grade with Multi-Agent-Based Computational Models

NASA Astrophysics Data System (ADS)

Dickes, Amanda Catherine; Sengupta, Pratim

2013-06-01

In this paper, we investigate how elementary school students develop multi-level explanations of population dynamics in a simple predator-prey ecosystem, through scaffolded interactions with a multi-agent-based computational model (MABM). The term "agent" in an MABM indicates individual computational objects or actors (e.g., cars), and these agents obey simple rules assigned or manipulated by the user (e.g., speeding up, slowing down, etc.). It is the interactions between these agents, based on the rules assigned by the user, that give rise to emergent, aggregate-level behavior (e.g., formation and movement of the traffic jam). Natural selection is such an emergent phenomenon, which has been shown to be challenging for novices (K16 students) to understand. Whereas prior research on learning evolutionary phenomena with MABMs has typically focused on high school students and beyond, we investigate how elementary students (4th graders) develop multi-level explanations of some introductory aspects of natural selection—species differentiation and population change—through scaffolded interactions with an MABM that simulates predator-prey dynamics in a simple birds-butterflies ecosystem. We conducted a semi-clinical interview based study with ten participants, in which we focused on the following: a) identifying the nature of learners' initial interpretations of salient events or elements of the represented phenomena, b) identifying the roles these interpretations play in the development of their multi-level explanations, and c) how attending to different levels of the relevant phenomena can make explicit different mechanisms to the learners. In addition, our analysis also shows that although there were differences between high- and low-performing students (in terms of being able to explain population-level behaviors) in the pre-test, these differences disappeared in the post-test.

Human Activity Recognition from Smart-Phone Sensor Data using a Multi-Class Ensemble Learning in Home Monitoring.

PubMed

Ghose, Soumya; Mitra, Jhimli; Karunanithi, Mohan; Dowling, Jason

2015-01-01

Home monitoring of chronically ill or elderly patient can reduce frequent hospitalisations and hence provide improved quality of care at a reduced cost to the community, therefore reducing the burden on the healthcare system. Activity recognition of such patients is of high importance in such a design. In this work, a system for automatic human physical activity recognition from smart-phone inertial sensors data is proposed. An ensemble of decision trees framework is adopted to train and predict the multi-class human activity system. A comparison of our proposed method with a multi-class traditional support vector machine shows significant improvement in activity recognition accuracies.

3D multi-scale FCN with random modality voxel dropout learning for Intervertebral Disc Localization and Segmentation from Multi-modality MR Images.

PubMed

Li, Xiaomeng; Dou, Qi; Chen, Hao; Fu, Chi-Wing; Qi, Xiaojuan; Belavý, Daniel L; Armbrecht, Gabriele; Felsenberg, Dieter; Zheng, Guoyan; Heng, Pheng-Ann

2018-04-01

Intervertebral discs (IVDs) are small joints that lie between adjacent vertebrae. The localization and segmentation of IVDs are important for spine disease diagnosis and measurement quantification. However, manual annotation is time-consuming and error-prone with limited reproducibility, particularly for volumetric data. In this work, our goal is to develop an automatic and accurate method based on fully convolutional networks (FCN) for the localization and segmentation of IVDs from multi-modality 3D MR data. Compared with single modality data, multi-modality MR images provide complementary contextual information, which contributes to better recognition performance. However, how to effectively integrate such multi-modality information to generate accurate segmentation results remains to be further explored. In this paper, we present a novel multi-scale and modality dropout learning framework to locate and segment IVDs from four-modality MR images. First, we design a 3D multi-scale context fully convolutional network, which processes the input data in multiple scales of context and then merges the high-level features to enhance the representation capability of the network for handling the scale variation of anatomical structures. Second, to harness the complementary information from different modalities, we present a random modality voxel dropout strategy which alleviates the co-adaption issue and increases the discriminative capability of the network. Our method achieved the 1st place in the MICCAI challenge on automatic localization and segmentation of IVDs from multi-modality MR images, with a mean segmentation Dice coefficient of 91.2% and a mean localization error of 0.62 mm. We further conduct extensive experiments on the extended dataset to validate our method. We demonstrate that the proposed modality dropout strategy with multi-modality images as contextual information improved the segmentation accuracy significantly. Furthermore, experiments conducted on extended data collected from two different time points demonstrate the efficacy of our method on tracking the morphological changes in a longitudinal study. Copyright © 2018 Elsevier B.V. All rights reserved.

Multi-Label Learning via Random Label Selection for Protein Subcellular Multi-Locations Prediction.

PubMed

Wang, Xiao; Li, Guo-Zheng

2013-03-12

Prediction of protein subcellular localization is an important but challenging problem, particularly when proteins may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular localization methods are only used to deal with the single-location proteins. In the past few years, only a few methods have been proposed to tackle proteins with multiple locations. However, they only adopt a simple strategy, that is, transforming the multi-location proteins to multiple proteins with single location, which doesn't take correlations among different subcellular locations into account. In this paper, a novel method named RALS (multi-label learning via RAndom Label Selection), is proposed to learn from multi-location proteins in an effective and efficient way. Through five-fold cross validation test on a benchmark dataset, we demonstrate our proposed method with consideration of label correlations obviously outperforms the baseline BR method without consideration of label correlations, indicating correlations among different subcellular locations really exist and contribute to improvement of prediction performance. Experimental results on two benchmark datasets also show that our proposed methods achieve significantly higher performance than some other state-of-the-art methods in predicting subcellular multi-locations of proteins. The prediction web server is available at http://levis.tongji.edu.cn:8080/bioinfo/MLPred-Euk/ for the public usage.

Hygiene and sanitation promotion strategies among ethnic minority communities in northern Vietnam: a stakeholder analysis.

PubMed

Rheinländer, Thilde; Xuan, Le Thi Thanh; Hoat, Luu Ngoc; Dalsgaard, Anders; Konradsen, Flemming

2012-10-01

Effective rural hygiene and sanitation promotion (RHSP) is a major challenge for many low-income countries. This paper investigates strategies and stakeholders' roles and responsibilities in RHSP implementation in a multi-ethnic area of northern Vietnam, in order to identify lessons learned for future RHSP. A stakeholder analysis was performed, based on 49 semi-structured individual interviews and one group interview with stakeholders in RHSP in a northern province of Vietnam. Participants came from three sectors (agriculture, health and education), unions supported by the Vietnamese government and from four administrative levels (village, commune, district and province). The study villages represented four ethnic minority groups including lowland and highland communities. Stakeholders' roles, responsibilities and promotion methods were outlined, and implementation constraints and opportunities were identified and analysed using thematic content analysis. Effective RHSP in Vietnam is severely constrained despite supporting policies and a multi-sectorial and multi-level framework. Four main barriers for effective implementation of RHSP were identified: (1) weak inter-sectorial collaborations; (2) constraints faced by frontline promoters; (3) almost exclusive information-based and passive promotion methods applied; and (4) context unadjusted promotion strategies across ethnic groups, including a limited focus on socio-economic differences, language barriers and gender roles in the target groups. Highland communities were identified as least targeted and clearly in need of more intensive and effective RHSP. It is recommended that the Vietnamese government gives priority to increasing capacities of and collaboration among stakeholders implementing RHSP activities. This should focus on frontline promoters to perform effective behaviour change communication. It is also recommended to support more participatory and community-based initiatives, which can address the complex socio-economic and cultural determinants of health in multi-ethnic population groups. These lessons learned can improve future RHSP in Vietnam and are also of relevance for health promotion in other minority population groups in the region and globally.

Mouse genetic differences in voluntary wheel running, adult hippocampal neurogenesis and learning on the multi-strain-adapted plus water maze

PubMed Central

Merritt, Jennifer; Rhodes, Justin S.

2014-01-01

Moderate levels of aerobic exercise broadly enhance cognition throughout the lifespan. One hypothesized contributing mechanism is increased adult hippocampal neurogenesis. Recently, we measured the effects of voluntary wheel running on adult hippocampal neurogenesis in 12 different mouse strains, and found increased neurogenesis in all strains, ranging from 2 to 5 fold depending on the strain. The purpose of this study was to determine the extent to which increased neurogenesis from wheel running is associated with enhanced performance on the water maze for 5 of the 12 strains, chosen based on their levels of neurogenesis observed in the previous study (C57BL/6J, 129S1/SvImJ, B6129SF1/J, DBA/2J, and B6D2F1/J). Mice were housed with or without a running wheels for 30 days then tested for learning and memory on the plus water maze, adapted for multiple strains, and rotarod test of motor performance. The first 10 days, animals were injected with BrdU to label dividing cells. After behavioral testing animals were euthanized to measure adult hippocampal neurogenesis using standard methods. Levels of neurogenesis depended on strain but all mice had a similar increase in neurogenesis in response to exercise. All mice acquired the water maze but performance depended on strain. Exercise improved water maze performance in all strains to a similar degree. Rotarod performance depended on strain. Exercise improved rotarod performance only in DBA/2J and B6D2F1/J mice. Taken together, results demonstrate that despite different levels of neurogenesis, memory performance and motor coordination in these mouse strains, all strains have the capacity to increase neurogenesis and improve learning on the water maze through voluntary wheel running. PMID:25435316

There is No Free Lunch: Tradeoffs in the Utility of Learned Knowledge

NASA Technical Reports Server (NTRS)

Kedar, Smadar T.; McKusick, Kathleen B.

1992-01-01

With the recent introduction of learning in integrated systems, there is a need to measure the utility of learned knowledge for these more complex systems. A difficulty arrises when there are multiple, possibly conflicting, utility metrics to be measured. In this paper, we present schemes which trade off conflicting utility metrics in order to achieve some global performance objectives. In particular, we present a case study of a multi-strategy machine learning system, mutual theory refinement, which refines world models for an integrated reactive system, the Entropy Reduction Engine. We provide experimental results on the utility of learned knowledge in two conflicting metrics - improved accuracy and degraded efficiency. We then demonstrate two ways to trade off these metrics. In each, some learned knowledge is either approximated or dynamically 'forgotten' so as to improve efficiency while degrading accuracy only slightly.

Investigating the use of patient involvement and patient experience in quality improvement in Norway: rhetoric or reality?

PubMed Central

2013-01-01

Background Patient involvement in health care decision making is part of a wider trend towards a more bottom-up approach to service planning and provision, and patient experience is increasingly conceptualized as a core dimension of health care quality. The aim of this multi-level study is two-fold: 1) to describe and analyze how governmental organizations expect acute hospitals to incorporate patient involvement and patient experiences into their quality improvement (QI) efforts and 2) to analyze how patient involvement and patient experiences are used by hospitals to try to improve the quality of care they provide. Methods This multi-level case study combines analysis of national policy documents and regulations at the macro level with semi-structured interviews and non-participant observation of key meetings and shadowing of staff at the meso and micro levels in two purposively sampled Norwegian hospitals. Fieldwork at the meso and micro levels was undertaken over a 12-month period (2011–2012). Results Governmental documents and regulations at the macro level demonstrated wide-ranging expectations for the integration of patient involvement and patient experiences in QI work in hospitals. The expectations span from systematic collection of patients’ and family members’ experiences for the purpose of improving service quality through establishing patient-oriented arenas for ongoing collaboration with staff to the support of individual involvement in decision making. However, the extent of involvement of patients and application of patient experiences in QI work was limited at both hospitals. Even though patient involvement was gaining prominence at the meso level − and to a lesser extent at the micro level − relevant tools for measuring and using patient experiences in QI work were lacking, and available measures of patient experience were not being used meaningfully or systematically. Conclusions The relative lack of expertise in Norwegian hospitals of adapting and implementing tools and methods for improving patient involvement and patient experiences at the meso and micro levels mark a need for health care policymakers and hospital leaders to learn from experiences of other industries and countries that have successfully integrated user experiences into QI work. Hospital managers need to design and implement wider strategies to help their staff members recognize and value the contribution that patient involvement and patient experiences can make to the improvement of healthcare quality. PMID:23742265

The feasibility of e-learning as a quality improvement tool.

PubMed

Kobewka, Daniel; Backman, Chantal; Hendry, Paul; Hamstra, Stanley J; Suh, Kathryn N; Code, Catherine; Forster, Alan J

2014-10-01

Many quality problems exist in health care. We aim to investigate the feasibility and acceptability of using e-learning (defined as computer-based learning modules) to address gaps in quality of care. We performed a qualitative evaluation of participants in a pilot e-learning program. Physician members of six medical teaching units (MTUs) at a multi-site tertiary care teaching hospital were asked to complete two e-learning modules addressing hand hygiene practices and management of community-acquired pneumonia (CAP). An e-learning design team created online modules that were made available to members of the six MTUs for 4 weeks using a password secured website. Use of the modules was voluntary. Participants' perceptions of module content, mode of delivery, and suggestions for improvement were determined through focus groups. We then performed content analysis on the transcripts. We used system data to define patterns of module access. Out of 55 eligible users, 30 (55%) logged onto the system at least once. Residents (14/30, 47%) were less likely to use the system than medical students (9/14, 64%) and attending staff (7/11, 64%). Learners at all levels thought the modules were easy to use. Participants liked the knowledge-based material in the CAP module because it directly applied to their work. There were less favourable opinions of the hand hygiene module Generating e-learning modules targeted at gaps in quality of care is feasible and acceptable to learners. Future studies should assess whether these approaches lead to desired changes in behavior. © 2014 John Wiley & Sons, Ltd.

Teachers and Game-Based Learning: Improving Understanding of How to Increase Efficacy of Adoption

ERIC Educational Resources Information Center

Ketelhut, Diane Jass; Schifter, Catherine C.

2011-01-01

Interest in game-based learning for K-12 is growing. Thus, helping teachers understand how to use these new pedagogies is important. This paper presents a cross-case study of the development of teacher professional development for the River City project, a games-based multi-user virtual environment science curriculum project for middle school…

Lessons from medical students' perceptions of learning reflective skills: a multi-institutional study.

PubMed

Vivekananda-Schmidt, Pirashanthie; Marshall, Michelle; Stark, Patsy; McKendree, Jean; Sandars, John; Smithson, Sarah

2011-01-01

A core competency during undergraduate medical training is the development of reflective learning. The current literature is limited to demonstrating how reflective learning has been implemented or the approaches to its development. There is a lack of insight into students' perceptions of reflection and the factors that support development of reflective practice. Bridging this gap may provide insight into how reflective learning within the curriculum can be better developed to increase engagement from learners. Eight focus group interviews with second year students from four UK medical schools were held. Results were thematically analysed. Students have a high level of understanding of the purpose of reflection in practice but they perceive that there is a tension between public and private reflections. Assessment of the reflective process was perceived to be useful for developing reflective skills but grading of their reflective writing was not considered to be useful. Staff who champion the development of reflective skills and mentor students were perceived to play key roles in aiding the development of reflective skills. Appropriate experiences were seen to be a key part of developing reflective skills. These findings highlight potential ways to revise and improve engagement with the reflective learning components of undergraduate courses.

Four Families of Multi-Variant Issues in Graduate-Level Asynchronous Online Courses

ERIC Educational Resources Information Center

Gisburne, Jaclyn M.; Fairchild, Patricia J.

2004-01-01

This is the first of several papers developed from a faculty and student perspective describing a new distance learning (DL) model. Integral to the model are four interrelated families of multi-variant issues, referred to here as (a) the academic divide, (b) student misalignment, (c) administrative influences, and (d) the use of student…

A multi-level differential item functioning analysis of trends in international mathematics and science study: Potential sources of gender and minority difference among U.S. eighth graders' science achievement

NASA Astrophysics Data System (ADS)

Qian, Xiaoyu

Science is an area where a large achievement gap has been observed between White and minority, and between male and female students. The science minority gap has continued as indicated by the National Assessment of Educational Progress and the Trends in International Mathematics and Science Studies (TIMSS). TIMSS also shows a gender gap favoring males emerging at the eighth grade. Both gaps continue to be wider in the number of doctoral degrees and full professorships awarded (NSF, 2008). The current study investigated both minority and gender achievement gaps in science utilizing a multi-level differential item functioning (DIF) methodology (Kamata, 2001) within fully Bayesian framework. All dichotomously coded items from TIMSS 2007 science assessment at eighth grade were analyzed. Both gender DIF and minority DIF were studied. Multi-level models were employed to identify DIF items and sources of DIF at both student and teacher levels. The study found that several student variables were potential sources of achievement gaps. It was also found that gender DIF favoring male students was more noticeable in the content areas of physics and earth science than biology and chemistry. In terms of item type, the majority of these gender DIF items were multiple choice than constructed response items. Female students also performed less well on items requiring visual-spatial ability. Minority students performed significantly worse on physics and earth science items as well. A higher percentage of minority DIF items in earth science and biology were constructed response than multiple choice items, indicating that literacy may be the cause of minority DIF. Three-level model results suggested that some teacher variables may be the cause of DIF variations from teacher to teacher. It is essential for both middle school science teachers and science educators to find instructional methods that work more effectively to improve science achievement of both female and minority students. Physics and earth science are two areas to be improved for both groups. Curriculum and instruction need to enhance female students' learning interests and give them opportunities to improve their visual perception skills. Science instruction should address improving minority students' literacy skills while teaching science.

Explaining Hong Kong Students' International Achievement in Civic Learning

ERIC Educational Resources Information Center

Kennedy, Kerry J.; Lijuan, Li

2016-01-01

This study identifies predictors of Hong Kong students' civic learning. It has adopted a cross-sectional quantitative design using secondary data from the 2009 International Civics and Citizenship Education Study (ICCS 2009; Schulz et al., 2010). Multi-level analysis reveals that most of the variance in student achievement can be accounted for by…

A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson's disease.

PubMed

Peng, Bo; Wang, Suhong; Zhou, Zhiyong; Liu, Yan; Tong, Baotong; Zhang, Tao; Dai, Yakang

2017-06-09

Machine learning methods have been widely used in recent years for detection of neuroimaging biomarkers in regions of interest (ROIs) and assisting diagnosis of neurodegenerative diseases. The innovation of this study is to use multilevel-ROI-features-based machine learning method to detect sensitive morphometric biomarkers in Parkinson's disease (PD). Specifically, the low-level ROI features (gray matter volume, cortical thickness, etc.) and high-level correlative features (connectivity between ROIs) are integrated to construct the multilevel ROI features. Filter- and wrapper- based feature selection method and multi-kernel support vector machine (SVM) are used in the classification algorithm. T1-weighted brain magnetic resonance (MR) images of 69 PD patients and 103 normal controls from the Parkinson's Progression Markers Initiative (PPMI) dataset are included in the study. The machine learning method performs well in classification between PD patients and normal controls with an accuracy of 85.78%, a specificity of 87.79%, and a sensitivity of 87.64%. The most sensitive biomarkers between PD patients and normal controls are mainly distributed in frontal lobe, parental lobe, limbic lobe, temporal lobe, and central region. The classification performance of our method with multilevel ROI features is significantly improved comparing with other classification methods using single-level features. The proposed method shows promising identification ability for detecting morphometric biomarkers in PD, thus confirming the potentiality of our method in assisting diagnosis of the disease. Copyright © 2017 Elsevier B.V. All rights reserved.

Classification of breast MRI lesions using small-size training sets: comparison of deep learning approaches

NASA Astrophysics Data System (ADS)

Amit, Guy; Ben-Ari, Rami; Hadad, Omer; Monovich, Einat; Granot, Noa; Hashoul, Sharbell

2017-03-01

Diagnostic interpretation of breast MRI studies requires meticulous work and a high level of expertise. Computerized algorithms can assist radiologists by automatically characterizing the detected lesions. Deep learning approaches have shown promising results in natural image classification, but their applicability to medical imaging is limited by the shortage of large annotated training sets. In this work, we address automatic classification of breast MRI lesions using two different deep learning approaches. We propose a novel image representation for dynamic contrast enhanced (DCE) breast MRI lesions, which combines the morphological and kinetics information in a single multi-channel image. We compare two classification approaches for discriminating between benign and malignant lesions: training a designated convolutional neural network and using a pre-trained deep network to extract features for a shallow classifier. The domain-specific trained network provided higher classification accuracy, compared to the pre-trained model, with an area under the ROC curve of 0.91 versus 0.81, and an accuracy of 0.83 versus 0.71. Similar accuracy was achieved in classifying benign lesions, malignant lesions, and normal tissue images. The trained network was able to improve accuracy by using the multi-channel image representation, and was more robust to reductions in the size of the training set. A small-size convolutional neural network can learn to accurately classify findings in medical images using only a few hundred images from a few dozen patients. With sufficient data augmentation, such a network can be trained to outperform a pre-trained out-of-domain classifier. Developing domain-specific deep-learning models for medical imaging can facilitate technological advancements in computer-aided diagnosis.

Quality improvement for patient safety: project-level versus program-level learning.

PubMed

Rivard, Peter E; Parker, Victoria A; Rosen, Amy K

2013-01-01

Improving quality and patient safety is of increasing strategic importance to health care organizations. However, simply increasing the volume of quality improvement (QI) activity does not necessarily improve patient outcomes. There is a need for greater understanding of QI success factors. This study looked for differences in QI implementation across hospitals with a range of performance on Patient Safety Indicators. We conducted an exploratory comparative case study of 4 Veterans Health Administration hospitals including site visits and interviews with leaders and staff. Two themes emerged. Project-level QI learning is assessing and modifying specific QI projects relative to expectations. Program-level QI learning is assessing and modifying the overall QI endeavor. The nature of project-level QI learning was similar across sites, whereas we identified qualitative differences across organizations in program-level QI learning. The highest performing organization was evaluating and refining its overall approach to QI, whereas the others were learning how to build and control QI programs. Program-level QI learning may be key if a QI program is to succeed in improving patient outcomes. This type of organizational learning entails a big-picture, organization-wide view of QI. It also entails second-order organizational learning based on assessment not only of whether QI is being done correctly but also whether the right QI activities are being done, for the right reasons. The organization is "learning to learn." In addition to gaining mastery and control of QI, leaders regularly engage with staff in rethinking QI and experimenting with new approaches. Leaders also assess how QI activity fits in the organization's developmental journey and how it supports realization of strategy.

ICPL: Intelligent Cooperative Planning and Learning for Multi-agent Systems

DTIC Science & Technology

2012-02-29

objective was to develop a new planning approach for teams!of multiple UAVs that tightly integrates learning and cooperative!control algorithms at... algorithms at multiple levels of the planning architecture. The research results enabled a team of mobile agents to learn to adapt and react to uncertainty in...expressive representation that incorporates feature conjunctions. Our algorithm is simple to implement, fast to execute, and can be combined with any

A national stakeholder consensus study of challenges and priorities for clinical learning environments in postgraduate medical education.

PubMed

Kilty, Caroline; Wiese, Anel; Bergin, Colm; Flood, Patrick; Fu, Na; Horgan, Mary; Higgins, Agnes; Maher, Bridget; O'Kane, Grainne; Prihodova, Lucia; Slattery, Dubhfeasa; Stoyanov, Slavi; Bennett, Deirdre

2017-11-22

High quality clinical learning environments (CLE) are critical to postgraduate medical education (PGME). The understaffed and overcrowded environments in which many residents work present a significant challenge to learning. The purpose of this study was to develop a national expert group consensus amongst stakeholders in PGME to; (i) identify important barriers and facilitators of learning in CLEs and (ii) indicate priority areas for improvement. Our objective was to provide information to focus efforts to provide high quality CLEs. Group Concept Mapping (GCM) is an integrated mixed methods approach to generating expert group consensus. A multi-disciplinary group of experts were invited to participate in the GCM process via an online platform. Multi-dimensional scaling and hierarchical cluster analysis were used to analyse participant inputs in regard to barriers, facilitators and priorities. Participants identified facilitators and barriers in ten domains within clinical learning environments. Domains rated most important were those which related to residents' connection to and engagement with more senior doctors. Organisation and conditions of work and Time to learn with senior doctors during patient care were rated as the most difficult areas in which to make improvements. High quality PGME requires that residents engage and connect with senior doctors during patient care, and that they are valued and supported both as learners and service providers. Academic medicine and health service managers must work together to protect these elements of CLEs, which not only shape learning, but impact quality of care and patient safety.

A label distance maximum-based classifier for multi-label learning.

PubMed

Liu, Xiaoli; Bao, Hang; Zhao, Dazhe; Cao, Peng

2015-01-01

Multi-label classification is useful in many bioinformatics tasks such as gene function prediction and protein site localization. This paper presents an improved neural network algorithm, Max Label Distance Back Propagation Algorithm for Multi-Label Classification. The method was formulated by modifying the total error function of the standard BP by adding a penalty term, which was realized by maximizing the distance between the positive and negative labels. Extensive experiments were conducted to compare this method against state-of-the-art multi-label methods on three popular bioinformatic benchmark datasets. The results illustrated that this proposed method is more effective for bioinformatic multi-label classification compared to commonly used techniques.

Does peer learning or higher levels of e-learning improve learning abilities? A randomized controlled trial

PubMed Central

Worm, Bjarne Skjødt; Jensen, Kenneth

2013-01-01

Background and aims The fast development of e-learning and social forums demands us to update our understanding of e-learning and peer learning. We aimed to investigate if higher, pre-defined levels of e-learning or social interaction in web forums improved students’ learning ability. Methods One hundred and twenty Danish medical students were randomized to six groups all with 20 students (eCases level 1, eCases level 2, eCases level 2+, eTextbook level 1, eTextbook level 2, and eTextbook level 2+). All students participated in a pre-test, Group 1 participated in an interactive case-based e-learning program, while Group 2 was presented with textbook material electronically. The 2+ groups were able to discuss the material between themselves in a web forum. The subject was head injury and associated treatment and observation guidelines in the emergency room. Following the e-learning, all students completed a post-test. Pre- and post-tests both consisted of 25 questions randomly chosen from a pool of 50 different questions. Results All students concluded the study with comparable pre-test results. Students at Level 2 (in both groups) improved statistically significant compared to students at level 1 (p>0.05). There was no statistically significant difference between level 2 and level 2+. However, level 2+ was associated with statistically significant greater student's satisfaction than the rest of the students (p>0.05). Conclusions This study applies a new way of comparing different types of e-learning using a pre-defined level division and the possibility of peer learning. Our findings show that higher levels of e-learning does in fact provide better results when compared with the same type of e-learning at lower levels. While social interaction in web forums increase student satisfaction, learning ability does not seem to change. Both findings are relevant when designing new e-learning materials. PMID:24229729

Does peer learning or higher levels of e-learning improve learning abilities? A randomized controlled trial.

PubMed

Worm, Bjarne Skjødt; Jensen, Kenneth

2013-01-01

Background and aims The fast development of e-learning and social forums demands us to update our understanding of e-learning and peer learning. We aimed to investigate if higher, pre-defined levels of e-learning or social interaction in web forums improved students' learning ability. Methods One hundred and twenty Danish medical students were randomized to six groups all with 20 students (eCases level 1, eCases level 2, eCases level 2+, eTextbook level 1, eTextbook level 2, and eTextbook level 2+). All students participated in a pre-test, Group 1 participated in an interactive case-based e-learning program, while Group 2 was presented with textbook material electronically. The 2+ groups were able to discuss the material between themselves in a web forum. The subject was head injury and associated treatment and observation guidelines in the emergency room. Following the e-learning, all students completed a post-test. Pre- and post-tests both consisted of 25 questions randomly chosen from a pool of 50 different questions. Results All students concluded the study with comparable pre-test results. Students at Level 2 (in both groups) improved statistically significant compared to students at level 1 (p>0.05). There was no statistically significant difference between level 2 and level 2+. However, level 2+ was associated with statistically significant greater student's satisfaction than the rest of the students (p>0.05). Conclusions This study applies a new way of comparing different types of e-learning using a pre-defined level division and the possibility of peer learning. Our findings show that higher levels of e-learning does in fact provide better results when compared with the same type of e-learning at lower levels. While social interaction in web forums increase student satisfaction, learning ability does not seem to change. Both findings are relevant when designing new e-learning materials.

Application of Multi-task Lasso Regression in the Stellar Parametrization

NASA Astrophysics Data System (ADS)

Chang, L. N.; Zhang, P. A.

2015-01-01

The multi-task learning approaches have attracted the increasing attention in the fields of machine learning, computer vision, and artificial intelligence. By utilizing the correlations in tasks, learning multiple related tasks simultaneously is better than learning each task independently. An efficient multi-task Lasso (Least Absolute Shrinkage Selection and Operator) regression algorithm is proposed in this paper to estimate the physical parameters of stellar spectra. It not only makes different physical parameters share the common features, but also can effectively preserve their own peculiar features. Experiments were done based on the ELODIE data simulated with the stellar atmospheric simulation model, and on the SDSS data released by the American large survey Sloan. The precision of the model is better than those of the methods in the related literature, especially for the acceleration of gravity (lg g) and the chemical abundance ([Fe/H]). In the experiments, we changed the resolution of the spectrum, and applied the noises with different signal-to-noise ratio (SNR) to the spectrum, so as to illustrate the stability of the model. The results show that the model is influenced by both the resolution and the noise. But the influence of the noise is larger than that of the resolution. In general, the multi-task Lasso regression algorithm is easy to operate, has a strong stability, and also can improve the overall accuracy of the model.

Improving education under work-hour restrictions: comparing learning and teaching preferences of faculty, residents, and students.

PubMed

Jack, Megan C; Kenkare, Sonya B; Saville, Benjamin R; Beidler, Stephanie K; Saba, Sam C; West, Alisha N; Hanemann, Michael S; van Aalst, John A

2010-01-01

Faced with work-hour restrictions, educators are mandated to improve the efficiency of resident and medical student education. Few studies have assessed learning styles in medicine; none have compared teaching and learning preferences. Validated tools exist to study these deficiencies. Kolb describes 4 learning styles: converging (practical), diverging (imaginative), assimilating (inductive), and accommodating (active). Grasha Teaching Styles are categorized into "clusters": 1 (teacher-centered, knowledge acquisition), 2 (teacher-centered, role modeling), 3 (student-centered, problem-solving), and 4 (student-centered, facilitative). Kolb's Learning Style Inventory (HayGroup, Philadelphia, Pennsylvania) and Grasha-Riechmann's TSS were administered to surgical faculty (n = 61), residents (n = 96), and medical students (n = 183) at a tertiary academic medical center, after informed consent was obtained (IRB # 06-0612). Statistical analysis was performed using χ(2) and Fisher exact tests. Surgical residents preferred active learning (p = 0.053), whereas faculty preferred reflective learning (p < 0.01). As a result of a comparison of teaching preferences, although both groups preferred student-centered, facilitative teaching, faculty preferred teacher-centered, role-modeling instruction (p = 0.02) more often. Residents had no dominant teaching style more often than surgical faculty (p = 0.01). Medical students preferred converging learning (42%) and cluster 4 teaching (35%). Statistical significance was unchanged when corrected for gender, resident training level, and subspecialization. Significant differences exist between faculty and residents in both learning and teaching preferences; this finding suggests inefficiency in resident education, as previous research suggests that learning styles parallel teaching styles. Absence of a predominant teaching style in residents suggests these individuals are learning to be teachers. The adaptation of faculty teaching methods to account for variations in resident learning styles may promote a better learning environment and more efficient faculty-resident interaction. Additional, multi-institutional studies using these tools are needed to elucidate these findings fully. Copyright © 2010 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

A multi-level system quality improvement intervention to reduce racial disparities in hypertension care and control: study protocol

PubMed Central

2013-01-01

Background Racial disparities in blood pressure control have been well documented in the United States. Research suggests that many factors contribute to this disparity, including barriers to care at patient, clinician, healthcare system, and community levels. To date, few interventions aimed at reducing hypertension disparities have addressed factors at all of these levels. This paper describes the design of Project ReD CHiP (Reducing Disparities and Controlling Hypertension in Primary Care), a multi-level system quality improvement project. By intervening on multiple levels, this project aims to reduce disparities in blood pressure control and improve guideline concordant hypertension care. Methods Using a pragmatic trial design, we are implementing three complementary multi-level interventions designed to improve blood pressure measurement, provide patient care management services and offer expanded provider education resources in six primary care clinics in Baltimore, Maryland. We are staggering the introduction of the interventions and will use Statistical Process Control (SPC) charting to determine if there are changes in outcomes at each clinic after implementation of each intervention. The main hypothesis is that each intervention will have an additive effect on improvements in guideline concordant care and reductions in hypertension disparities, but the combination of all three interventions will result in the greatest impact, followed by blood pressure measurement with care management support, blood pressure measurement with provider education, and blood pressure measurement only. This study also examines how organizational functioning and cultural competence affect the success of the interventions. Discussion As a quality improvement project, Project ReD CHiP employs a novel study design that specifically targets multi-level factors known to contribute to hypertension disparities. To facilitate its implementation and improve its sustainability, we have incorporated stakeholder input and tailored components of the interventions to meet the specific needs of the involved clinics and communities. Results from this study will provide knowledge about how integrated multi-level interventions can improve hypertension care and reduce disparities. Trial Registration ClinicalTrials.gov NCT01566864 PMID:23734703

Collaborative filtering on a family of biological targets.

PubMed

Erhan, Dumitru; L'heureux, Pierre-Jean; Yue, Shi Yi; Bengio, Yoshua

2006-01-01

Building a QSAR model of a new biological target for which few screening data are available is a statistical challenge. However, the new target may be part of a bigger family, for which we have more screening data. Collaborative filtering or, more generally, multi-task learning, is a machine learning approach that improves the generalization performance of an algorithm by using information from related tasks as an inductive bias. We use collaborative filtering techniques for building predictive models that link multiple targets to multiple examples. The more commonalities between the targets, the better the multi-target model that can be built. We show an example of a multi-target neural network that can use family information to produce a predictive model of an undersampled target. We evaluate JRank, a kernel-based method designed for collaborative filtering. We show their performance on compound prioritization for an HTS campaign and the underlying shared representation between targets. JRank outperformed the neural network both in the single- and multi-target models.

Modeling change in learning strategies throughout higher education: a multi-indicator latent growth perspective.

PubMed

Coertjens, Liesje; Donche, Vincent; De Maeyer, Sven; Vanthournout, Gert; Van Petegem, Peter

2013-01-01

The change in learning strategies during higher education is an important topic of research in the Student Approaches to Learning field. Although the studies on this topic are increasingly longitudinal, analyses have continued to rely primarily on traditional statistical methods. The present research is innovative in the way it uses a multi-indicator latent growth analysis in order to more accurately estimate the general and differential development in learning strategy scales. Moreover, the predictive strength of the latent growth models are estimated. The sample consists of one cohort of Flemish University College students, 245 of whom participated in the three measurement waves by filling out the processing and regulation strategies scales of the Inventory of Learning Styles--Short Versions. Independent-samples t-tests revealed that the longitudinal group is a non-random subset of students starting University College. For each scale, a multi-indicator latent growth model is estimated using Mplus 6.1. Results suggest that, on average, during higher education, students persisting in their studies in a non-delayed manner seem to shift towards high-quality learning and away from undirected and surface-oriented learning. Moreover, students from the longitudinal group are found to vary in their initial levels, while, unexpectedly, not in their change over time. Although the growth models fit the data well, significant residual variances in the latent factors remain.

Modeling Change in Learning Strategies throughout Higher Education: A Multi-Indicator Latent Growth Perspective

PubMed Central

Coertjens, Liesje; Donche, Vincent; De Maeyer, Sven; Vanthournout, Gert; Van Petegem, Peter

2013-01-01

The change in learning strategies during higher education is an important topic of research in the Student Approaches to Learning field. Although the studies on this topic are increasingly longitudinal, analyses have continued to rely primarily on traditional statistical methods. The present research is innovative in the way it uses a multi-indicator latent growth analysis in order to more accurately estimate the general and differential development in learning strategy scales. Moreover, the predictive strength of the latent growth models are estimated. The sample consists of one cohort of Flemish University College students, 245 of whom participated in the three measurement waves by filling out the processing and regulation strategies scales of the Inventory of Learning Styles – Short Versions. Independent-samples t-tests revealed that the longitudinal group is a non-random subset of students starting University College. For each scale, a multi-indicator latent growth model is estimated using Mplus 6.1. Results suggest that, on average, during higher education, students persisting in their studies in a non-delayed manner seem to shift towards high-quality learning and away from undirected and surface-oriented learning. Moreover, students from the longitudinal group are found to vary in their initial levels, while, unexpectedly, not in their change over time. Although the growth models fit the data well, significant residual variances in the latent factors remain. PMID:23844112

A framework for learning about improvement: embedded implementation and evaluation design to optimize learning

PubMed Central

Barry, Danika; Kimble, Leighann E; Nambiar, Bejoy; Parry, Gareth; Jha, Ashish; Chattu, Vijay Kumar; Massoud, M Rashad; Goldmann, Don

2018-01-01

Abstract Improving health care involves many actors, often working in complex adaptive systems. Interventions tend to be multi-factorial, implementation activities diverse, and contexts dynamic and complicated. This makes improvement initiatives challenging to describe and evaluate as matching evaluation and program designs can be difficult, requiring collaboration, trust and transparency. Collaboration is required to address important epidemiological principles of bias and confounding. If this does not take place, results may lack credibility because the association between interventions implemented and outcomes achieved is obscure and attribution uncertain. Moreover, lack of clarity about what was implemented, how it was implemented, and the context in which it was implemented often lead to disappointment or outright failure of spread and scale-up efforts. The input of skilled evaluators into the design and conduct of improvement initiatives can be helpful in mitigating these potential problems. While evaluation must be rigorous, if it is too rigid necessary adaptation and learning may be compromised. This article provides a framework and guidance on how improvers and evaluators can work together to design, implement and learn about improvement interventions more effectively. PMID:29873794

Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning.

PubMed

Shi, Jun; Liu, Xiao; Li, Yan; Zhang, Qi; Li, Yingjie; Ying, Shihui

2015-10-30

Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. Collaborative representation (CR) is an effective data coding method used as a classifier. Here we use CR as a data representation method to learn features from the EEG signal. A joint collaboration model is established to develop a multi-view learning algorithm, and generate joint CR (JCR) codes to fuse and represent multi-channel EEG signals. A two-stage multi-view learning-based sleep staging framework is then constructed, in which JCR and joint sparse representation (JSR) algorithms first fuse and learning the feature representation from multi-channel EEG signals, respectively. Multi-view JCR and JSR features are then integrated and sleep stages recognized by a multiple kernel extreme learning machine (MK-ELM) algorithm with grid search. The proposed two-stage multi-view learning algorithm achieves superior performance for sleep staging. With a K-means clustering based dictionary, the mean classification accuracy, sensitivity and specificity are 81.10 ± 0.15%, 71.42 ± 0.66% and 94.57 ± 0.07%, respectively; while with the dictionary learned using the submodular optimization method, they are 80.29 ± 0.22%, 71.26 ± 0.78% and 94.38 ± 0.10%, respectively. The two-stage multi-view learning based sleep staging framework outperforms all other classification methods compared in this work, while JCR is superior to JSR. The proposed multi-view learning framework has the potential for sleep staging based on multi-channel or multi-modality polysomnography signals. Copyright © 2015 Elsevier B.V. All rights reserved.

Coaching and leadership for the diffusion of innovation in health care: a different type of multi-organization improvement collaborative.

PubMed

Green, Paul L; Plsek, Paul E

2002-02-01

Health care organizations have suffered a steady decrease in operating margins in recent years while facing increased competition and pressure to provide ever-higher levels of customer service, quality of care, and innovation in delivery methodologies. The ability to rapidly find and implement changes that will lead to strategic improvement is critical. To assist member organizations in dealing with these issues, VHA Upper Midwest launched the Coaching and Leadership Initiative (VHA-CLI) in January 1999. The initiative was intended to develop new methods of collaborating for organizational learning of best practices, with a focus on generalizable change and deliberate leadership supports for deployment, diffusion, and sustainability. The emphasis was on the spread of ideas for improvement into all relevant corners of the organization. The structure of the VHA-CLI collaborative involved four waves of demonstration teams during 2 years. Each meeting of the collaborative included an executive session, team learning sessions (concepts applied to their improvement projects), and planning for the 6-month action period following the meeting. An important feature of the collaborative is the way in which teams in the various waves overlapped. For example, the Wave 1 team for a given organization came to a learning session in January 1999. At the second collaborative meeting in June 1999, the Wave 1 teams reported on the progress in their pilot sites. This meeting was also the kick-off session for the Wave 2 teams, which could learn about organizational culture and the improvement model from the efforts of their colleagues on Wave 1. Wave 1 teams also learned about and planned for spreading their efforts to other sites beyond the pilot. The pattern of multiple teams stretching across two waves of activity was repeated at every meeting of the collaborative. Each organization in the collaborative has achieved improved outcomes around its selected clinical topics. In total, 26 teams have made significant improvement in 17 different topic areas. In addition, each organization has been able to successfully spread tested improvements to other individuals, teams, or locations, and the improvement work has become easier and more rapid with each successive cycle. The learning process initiated by this project will continue for at least another year in the VHA Upper Midwest region and will be expanded as participating organizations in other regions enroll in the VHA's national effort.

Multi-level gene/MiRNA feature selection using deep belief nets and active learning.

PubMed

Ibrahim, Rania; Yousri, Noha A; Ismail, Mohamed A; El-Makky, Nagwa M

2014-01-01

Selecting the most discriminative genes/miRNAs has been raised as an important task in bioinformatics to enhance disease classifiers and to mitigate the dimensionality curse problem. Original feature selection methods choose genes/miRNAs based on their individual features regardless of how they perform together. Considering group features instead of individual ones provides a better view for selecting the most informative genes/miRNAs. Recently, deep learning has proven its ability in representing the data in multiple levels of abstraction, allowing for better discrimination between different classes. However, the idea of using deep learning for feature selection is not widely used in the bioinformatics field yet. In this paper, a novel multi-level feature selection approach named MLFS is proposed for selecting genes/miRNAs based on expression profiles. The approach is based on both deep and active learning. Moreover, an extension to use the technique for miRNAs is presented by considering the biological relation between miRNAs and genes. Experimental results show that the approach was able to outperform classical feature selection methods in hepatocellular carcinoma (HCC) by 9%, lung cancer by 6% and breast cancer by around 10% in F1-measure. Results also show the enhancement in F1-measure of our approach over recently related work in [1] and [2].

Hierarchical graphical-based human pose estimation via local multi-resolution convolutional neural network

NASA Astrophysics Data System (ADS)

Zhu, Aichun; Wang, Tian; Snoussi, Hichem

2018-03-01

This paper addresses the problems of the graphical-based human pose estimation in still images, including the diversity of appearances and confounding background clutter. We present a new architecture for estimating human pose using a Convolutional Neural Network (CNN). Firstly, a Relative Mixture Deformable Model (RMDM) is defined by each pair of connected parts to compute the relative spatial information in the graphical model. Secondly, a Local Multi-Resolution Convolutional Neural Network (LMR-CNN) is proposed to train and learn the multi-scale representation of each body parts by combining different levels of part context. Thirdly, a LMR-CNN based hierarchical model is defined to explore the context information of limb parts. Finally, the experimental results demonstrate the effectiveness of the proposed deep learning approach for human pose estimation.

Work Organisation, Forms of Employee Learning and National Systems of Education and Training

ERIC Educational Resources Information Center

Lorenz, Edward; Lundvall, Bengt-Åke; Kraemer-Mbula, Erika; Rasmussen, Palle

2016-01-01

This article uses a multi-level framework to investigate for 17 European nations the links between forms of work organisation and style of employee learning at the workplace on the one hand, and the characteristics of national educational and training systems on the other. The analysis shows that forms of work organisation characterised by…

Increasing the Social Studies Reading Comprehension of Middle School Students with Learning Disabilities

ERIC Educational Resources Information Center

Bryski, Crystal

2009-01-01

This action research project sets out to identify which component of multi-text instruction is most effective in increasing the reading comprehension level of middle school students with learning disabilities. The research is going to be conducted over a two-week time period during the Spring 2009 with three male middle school students with…

Exploring the Use of Three-Dimensional Multi-User Virtual Environments for Online Problem-Based Learning

ERIC Educational Resources Information Center

Omale, Nicholas M.

2010-01-01

This exploratory case study examines how three media attributes in 3-D MUVEs--avatars, 3-D spaces and bubble dialogue boxes--affect interaction in an online problem-based learning (PBL) activity. The study participants were eleven undergraduate students enrolled in a 200-level, three-credit-hour technology integration course at a Midwestern…

Learning Science Content through Socio-Scientific Issues-Based Instruction: A Multi-Level Assessment Study

ERIC Educational Resources Information Center

Sadler, Troy D.; Romine, William L.; Topçu, Mustafa Sami

2016-01-01

Science educators have presented numerous conceptual and theoretical arguments in favor of teaching science through the exploration of socio-scientific issues (SSI). However, the empirical knowledge base regarding the extent to which SSI-based instruction supports student learning of science content is limited both in terms of the number of…

SVM-Fold: a tool for discriminative multi-class protein fold and superfamily recognition

PubMed Central

Melvin, Iain; Ie, Eugene; Kuang, Rui; Weston, Jason; Stafford, William Noble; Leslie, Christina

2007-01-01

Background Predicting a protein's structural class from its amino acid sequence is a fundamental problem in computational biology. Much recent work has focused on developing new representations for protein sequences, called string kernels, for use with support vector machine (SVM) classifiers. However, while some of these approaches exhibit state-of-the-art performance at the binary protein classification problem, i.e. discriminating between a particular protein class and all other classes, few of these studies have addressed the real problem of multi-class superfamily or fold recognition. Moreover, there are only limited software tools and systems for SVM-based protein classification available to the bioinformatics community. Results We present a new multi-class SVM-based protein fold and superfamily recognition system and web server called SVM-Fold, which can be found at . Our system uses an efficient implementation of a state-of-the-art string kernel for sequence profiles, called the profile kernel, where the underlying feature representation is a histogram of inexact matching k-mer frequencies. We also employ a novel machine learning approach to solve the difficult multi-class problem of classifying a sequence of amino acids into one of many known protein structural classes. Binary one-vs-the-rest SVM classifiers that are trained to recognize individual structural classes yield prediction scores that are not comparable, so that standard "one-vs-all" classification fails to perform well. Moreover, SVMs for classes at different levels of the protein structural hierarchy may make useful predictions, but one-vs-all does not try to combine these multiple predictions. To deal with these problems, our method learns relative weights between one-vs-the-rest classifiers and encodes information about the protein structural hierarchy for multi-class prediction. In large-scale benchmark results based on the SCOP database, our code weighting approach significantly improves on the standard one-vs-all method for both the superfamily and fold prediction in the remote homology setting and on the fold recognition problem. Moreover, our code weight learning algorithm strongly outperforms nearest-neighbor methods based on PSI-BLAST in terms of prediction accuracy on every structure classification problem we consider. Conclusion By combining state-of-the-art SVM kernel methods with a novel multi-class algorithm, the SVM-Fold system delivers efficient and accurate protein fold and superfamily recognition. PMID:17570145

An Improved Botanical Search Application for Middle-and High-School Students

ERIC Educational Resources Information Center

Kajiyama, Tomoko

2016-01-01

A previously reported botanical data retrieval application has been improved to make it better suited for use in middle-and high-school science classes. This search interface is ring-structured and treats multi-faceted metadata intuitively, enabling students not only to search for plant names but also to learn about the morphological features and…

Experiential Learning and Its Role in Training and Improved Practice in High Level Sports Officiating

ERIC Educational Resources Information Center

Grover, Kenda S.

2014-01-01

This qualitative study investigated how high level sports officials engage in experiential learning to improve their practice. Adult learning occurs in formal, nonformal and informal environments, and in some cases it is difficult to differentiate between these settings. In the case of cycling officials, learning begins in a nonformal environment…

Reducing fatalities and severe injuries on Florida's high-speed multi-lane arterial corridors : part IV, safety improvements on multilane arterials in Florida--a before and after evaluation, final report, April 2009.

DOT National Transportation Integrated Search

2009-03-28

This study examines the safety effects of the improvements made on multi-lane arterials. The improvements were divided into two categories: 1) corridor level improvements, and 2) intersection improvements. Empirical Bayes method, which is one of the ...

Deep Hashing for Scalable Image Search.

PubMed

Lu, Jiwen; Liong, Venice Erin; Zhou, Jie

2017-05-01

In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for scalable image search. Unlike most existing binary codes learning methods, which usually seek a single linear projection to map each sample into a binary feature vector, we develop a deep neural network to seek multiple hierarchical non-linear transformations to learn these binary codes, so that the non-linear relationship of samples can be well exploited. Our model is learned under three constraints at the top layer of the developed deep network: 1) the loss between the compact real-valued code and the learned binary vector is minimized, 2) the binary codes distribute evenly on each bit, and 3) different bits are as independent as possible. To further improve the discriminative power of the learned binary codes, we extend DH into supervised DH (SDH) and multi-label SDH by including a discriminative term into the objective function of DH, which simultaneously maximizes the inter-class variations and minimizes the intra-class variations of the learned binary codes with the single-label and multi-label settings, respectively. Extensive experimental results on eight widely used image search data sets show that our proposed methods achieve very competitive results with the state-of-the-arts.

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database

PubMed Central

Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

2017-01-01

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen’s kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals. PMID:29095872

Scoping Study of Machine Learning Techniques for Visualization and Analysis of Multi-source Data in Nuclear Safeguards

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

Cui, Yonggang

In implementation of nuclear safeguards, many different techniques are being used to monitor operation of nuclear facilities and safeguard nuclear materials, ranging from radiation detectors, flow monitors, video surveillance, satellite imagers, digital seals to open source search and reports of onsite inspections/verifications. Each technique measures one or more unique properties related to nuclear materials or operation processes. Because these data sets have no or loose correlations, it could be beneficial to analyze the data sets together to improve the effectiveness and efficiency of safeguards processes. Advanced visualization techniques and machine-learning based multi-modality analysis could be effective tools in such integratedmore » analysis. In this project, we will conduct a survey of existing visualization and analysis techniques for multi-source data and assess their potential values in nuclear safeguards.« less

Using Direct Policy Search to Identify Robust Strategies in Adapting to Uncertain Sea Level Rise and Storm Surge

NASA Astrophysics Data System (ADS)

Garner, G. G.; Keller, K.

2017-12-01

Sea-level rise poses considerable risks to coastal communities, ecosystems, and infrastructure. Decision makers are faced with deeply uncertain sea-level projections when designing a strategy for coastal adaptation. The traditional methods have provided tremendous insight into this decision problem, but are often silent on tradeoffs as well as the effects of tail-area events and of potential future learning. Here we reformulate a simple sea-level rise adaptation model to address these concerns. We show that Direct Policy Search yields improved solution quality, with respect to Pareto-dominance in the objectives, over the traditional approach under uncertain sea-level rise projections and storm surge. Additionally, the new formulation produces high quality solutions with less computational demands than the traditional approach. Our results illustrate the utility of multi-objective adaptive formulations for the example of coastal adaptation, the value of information provided by observations, and point to wider-ranging application in climate change adaptation decision problems.

A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in Lung nodule CAD.

PubMed

Cao, Peng; Liu, Xiaoli; Zhang, Jian; Li, Wei; Zhao, Dazhe; Huang, Min; Zaiane, Osmar

2017-03-01

The aim of this paper is to describe a novel algorithm for False Positive Reduction in lung nodule Computer Aided Detection(CAD). In this paper, we describes a new CT lung CAD method which aims to detect solid nodules. Specially, we proposed a multi-kernel classifier with a ℓ 2, 1 norm regularizer for heterogeneous feature fusion and selection from the feature subset level, and designed two efficient strategies to optimize the parameters of kernel weights in non-smooth ℓ 2, 1 regularized multiple kernel learning algorithm. The first optimization algorithm adapts a proximal gradient method for solving the ℓ 2, 1 norm of kernel weights, and use an accelerated method based on FISTA; the second one employs an iterative scheme based on an approximate gradient descent method. The results demonstrates that the FISTA-style accelerated proximal descent method is efficient for the ℓ 2, 1 norm formulation of multiple kernel learning with the theoretical guarantee of the convergence rate. Moreover, the experimental results demonstrate the effectiveness of the proposed methods in terms of Geometric mean (G-mean) and Area under the ROC curve (AUC), and significantly outperforms the competing methods. The proposed approach exhibits some remarkable advantages both in heterogeneous feature subsets fusion and classification phases. Compared with the fusion strategies of feature-level and decision level, the proposed ℓ 2, 1 norm multi-kernel learning algorithm is able to accurately fuse the complementary and heterogeneous feature sets, and automatically prune the irrelevant and redundant feature subsets to form a more discriminative feature set, leading a promising classification performance. Moreover, the proposed algorithm consistently outperforms the comparable classification approaches in the literature. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Predicting plant protein subcellular multi-localization by Chou's PseAAC formulation based multi-label homolog knowledge transfer learning.

PubMed

Mei, Suyu

2012-10-07

Recent years have witnessed much progress in computational modeling for protein subcellular localization. However, there are far few computational models for predicting plant protein subcellular multi-localization. In this paper, we propose a multi-label multi-kernel transfer learning model for predicting multiple subcellular locations of plant proteins (MLMK-TLM). The method proposes a multi-label confusion matrix and adapts one-against-all multi-class probabilistic outputs to multi-label learning scenario, based on which we further extend our published work MK-TLM (multi-kernel transfer learning based on Chou's PseAAC formulation for protein submitochondria localization) for plant protein subcellular multi-localization. By proper homolog knowledge transfer, MLMK-TLM is applicable to novel plant protein subcellular localization in multi-label learning scenario. The experiments on plant protein benchmark dataset show that MLMK-TLM outperforms the baseline model. Unlike the existing models, MLMK-TLM also reports its misleading tendency, which is important for comprehensive survey of model's multi-labeling performance. Copyright © 2012 Elsevier Ltd. All rights reserved.

Changing the Behaviour of Traditional Bakers in a Chinese Multi-Family Owned Food Company through Workplace Action Learning in Hong Kong

ERIC Educational Resources Information Center

Elsey, Barry; Tse, Rex Chi-Hang

2007-01-01

Purpose: The purpose of this paper is to explain the rationale for designing and implementing an action learning and research process to significantly transform the work behaviour of tradition-bound bakers to embrace leading ideas of a new workplace culture in order to diversify the product range of the moon cake and generally improve the…

Team training in obstetrics: A multi-level evaluation.

PubMed

Sonesh, Shirley C; Gregory, Megan E; Hughes, Ashley M; Feitosa, Jennifer; Benishek, Lauren E; Verhoeven, Dana; Patzer, Brady; Salazar, Maritza; Gonzalez, Laura; Salas, Eduardo

2015-09-01

Obstetric complications and adverse patient events are often preventable. Teamwork and situational awareness (SA) can improve detection and coordination of critical obstetric (OB) emergencies, subsequently improving decision making and patient outcomes. The purpose of this study was to assess the effectiveness of a team training intervention in improving learning and transfer of teamwork, SA, decision making, and cognitive bias as well as patient outcomes in OB. An adapted TeamSTEPPS training program was delivered to OB clinicians. Training targeted communication, mutual support, situation monitoring, leadership, SA, and cognitive bias. We conducted a repeated measures multilevel evaluation of the training using Kirkpatrick's (1994) framework of training evaluation to determine impact on trainee reactions, learning, transfer, and results. Data were collected using surveys, situational judgment tests (SJTs), observations, and patient chart reviews. Participants perceived the training as useful. Additionally, participants acquired knowledge of communication strategies, though knowledge of other team competencies did not significantly improve nor did self-reported teamwork on the unit. Although SJT decision accuracy did not significantly improve for all scenarios, results of behavioral observation suggest that decision accuracy significantly improved on the job, and there was a marginally significant reduction in babies' hospital length of stay. These findings indicate that the training intervention was partially effective, but more work needs to be done to determine the conditions under which training is most effective, and the ways in which to sustain improvements. Future research is needed to confirm its generalizability to additional OB units and departments. (c) 2015 APA, all rights reserved).

A hybrid binary particle swarm optimization for large capacitated multi item multi level lot sizing (CMIMLLS) problem

NASA Astrophysics Data System (ADS)

Mishra, S. K.; Sahithi, V. V. D.; Rao, C. S. P.

2016-09-01

The lot sizing problem deals with finding optimal order quantities which minimizes the ordering and holding cost of product mix. when multiple items at multiple levels with all capacity restrictions are considered, the lot sizing problem become NP hard. Many heuristics were developed in the past have inevitably failed due to size, computational complexity and time. However the authors were successful in the development of PSO based technique namely iterative improvement binary particles swarm technique to address very large capacitated multi-item multi level lot sizing (CMIMLLS) problem. First binary particle Swarm Optimization algorithm is used to find a solution in a reasonable time and iterative improvement local search mechanism is employed to improvise the solution obtained by BPSO algorithm. This hybrid mechanism of using local search on the global solution is found to improve the quality of solutions with respect to time thus IIBPSO method is found best and show excellent results.

Optimize scientific communication skills on work and energy concept with implementation of interactive conceptual instruction and multi representation approach

NASA Astrophysics Data System (ADS)

Patriot, E. A.; Suhandi, A.; Chandra, D. T.

2018-05-01

The ultimate goal of learning in the curriculum 2013 is that learning must improve and balance between soft skills and hard skills of learners. In addition to the knowledge aspect, one of the other skills to be trained in the learning process using a scientific approach is communication skills. This study aims to get an overview of the implementation of interactive conceptual instruction with multi representation to optimize the achievement of students’ scientific communication skills on work and energy concept. The scientific communication skills contains the sub-skills were searching the information, scientific writing, group discussion and knowledge presentation. This study was descriptive research with observation method. Subjects in this study were 35 students of class X in Senior High School at Sumedang. The results indicate an achievement of optimal scientific communication skills. The greatest achievement of KKI based on observation is at fourth meeting of KKI-3, which is a sub-skill of resume writing of 89%. Allmost students responded positively to the implication of interactive conceptual instruction with multi representation approach. It can be concluded that the implication of interactive conceptual instruction with multi representation approach can optimize the achievement of students’ scientific communication skill on work and energy concept.

Interdisciplinarity in Swiss Schools: A Difficult Step into the Future

ERIC Educational Resources Information Center

Ghisla, Gianni; Bausch, Luca; Bonoli, Lorenzo

2010-01-01

Multi- and interdisciplinary education is a major postulate in the Swiss school system and has considerable weight in educational programs and learning objectives, both in compulsory school and at the upper secondary school level. However, materializing this postulate still poses problems at the political and institutional level, where the…

A Multi-Cultural Transformative Approach to Learning: Assessing Attitude Change in Doctoral Students following an Online Diversity Course

ERIC Educational Resources Information Center

Enger, Kathy; Lajimodiere, Denise

2011-01-01

Purpose: The purpose of this paper is to examine the attitudes of students following the completion of an online doctoral level multicultural diversity course at a university in the Midwestern USA based on Banks' transformative approach to learning in an effort to determine if the online environment could successfully intervene to change student…

Missing Modality Transfer Learning via Latent Low-Rank Constraint.

PubMed

Ding, Zhengming; Shao, Ming; Fu, Yun

2015-11-01

Transfer learning is usually exploited to leverage previously well-learned source domain for evaluating the unknown target domain; however, it may fail if no target data are available in the training stage. This problem arises when the data are multi-modal. For example, the target domain is in one modality, while the source domain is in another. To overcome this, we first borrow an auxiliary database with complete modalities, then consider knowledge transfer across databases and across modalities within databases simultaneously in a unified framework. The contributions are threefold: 1) a latent factor is introduced to uncover the underlying structure of the missing modality from the known data; 2) transfer learning in two directions allows the data alignment between both modalities and databases, giving rise to a very promising recovery; and 3) an efficient solution with theoretical guarantees to the proposed latent low-rank transfer learning algorithm. Comprehensive experiments on multi-modal knowledge transfer with missing target modality verify that our method can successfully inherit knowledge from both auxiliary database and source modality, and therefore significantly improve the recognition performance even when test modality is inaccessible in the training stage.

Multi-level multi-task learning for modeling cross-scale interactions in nested geospatial data

USGS Publications Warehouse

Yuan, Shuai; Zhou, Jiayu; Tan, Pang-Ning; Fergus, Emi; Wagner, Tyler; Sorrano, Patricia

2017-01-01

Predictive modeling of nested geospatial data is a challenging problem as the models must take into account potential interactions among variables defined at different spatial scales. These cross-scale interactions, as they are commonly known, are particularly important to understand relationships among ecological properties at macroscales. In this paper, we present a novel, multi-level multi-task learning framework for modeling nested geospatial data in the lake ecology domain. Specifically, we consider region-specific models to predict lake water quality from multi-scaled factors. Our framework enables distinct models to be developed for each region using both its local and regional information. The framework also allows information to be shared among the region-specific models through their common set of latent factors. Such information sharing helps to create more robust models especially for regions with limited or no training data. In addition, the framework can automatically determine cross-scale interactions between the regional variables and the local variables that are nested within them. Our experimental results show that the proposed framework outperforms all the baseline methods in at least 64% of the regions for 3 out of 4 lake water quality datasets evaluated in this study. Furthermore, the latent factors can be clustered to obtain a new set of regions that is more aligned with the response variables than the original regions that were defined a priori from the ecology domain.

Application of Multi-task Lasso Regression in the Parametrization of Stellar Spectra

NASA Astrophysics Data System (ADS)

Chang, Li-Na; Zhang, Pei-Ai

2015-07-01

The multi-task learning approaches have attracted the increasing attention in the fields of machine learning, computer vision, and artificial intelligence. By utilizing the correlations in tasks, learning multiple related tasks simultaneously is better than learning each task independently. An efficient multi-task Lasso (Least Absolute Shrinkage Selection and Operator) regression algorithm is proposed in this paper to estimate the physical parameters of stellar spectra. It not only can obtain the information about the common features of the different physical parameters, but also can preserve effectively their own peculiar features. Experiments were done based on the ELODIE synthetic spectral data simulated with the stellar atmospheric model, and on the SDSS data released by the American large-scale survey Sloan. The estimation precision of our model is better than those of the methods in the related literature, especially for the estimates of the gravitational acceleration (lg g) and the chemical abundance ([Fe/H]). In the experiments we changed the spectral resolution, and applied the noises with different signal-to-noise ratios (SNRs) to the spectral data, so as to illustrate the stability of the model. The results show that the model is influenced by both the resolution and the noise. But the influence of the noise is larger than that of the resolution. In general, the multi-task Lasso regression algorithm is easy to operate, it has a strong stability, and can also improve the overall prediction accuracy of the model.

How interdisciplinary teams can create multi-disciplinary education: the interplay between team processes and educational quality.

PubMed

Stalmeijer, Renee E; Gijselaers, Wim H; Wolfhagen, Ineke H A P; Harendza, Sigrid; Scherpbier, Albert J J A

2007-11-01

Many undergraduate medical education programmes offer integrated multi-disciplinary courses, which are generally developed by a team of teachers from different disciplines. Research has shown that multi-disciplinary teams may encounter problems, which can be detrimental to productive co-operation, which in turn may diminish educational quality. Because we expected that charting these problems might yield suggestions for addressing them, we examined the relationships between team diversity, team processes and course quality. We administered a questionnaire to participants from 21 interdisciplinary teams from 1 Dutch and 1 German medical school, both of which were reforming their curriculum. An adapted questionnaire on team learning behaviours, which had been validated in business contexts, was used to collect data on team processes, team learning behaviours and diversity within teams. We examined the relationship between the team factors and educational quality measures of the courses designed by the teams. A total of 84 teachers (60%) completed the questionnaire. Bivariate correlation analysis showed that several aspects of diversity, conflict, working climate and learning behaviour were correlated with course quality. The negative effects of the diversity measures, notably, value diversity, on other team processes and course quality and the positive association between psychological safety and team learning suggest that educational quality might be improved by enhancing the functioning of multi-disciplinary teams responsible for course development. The relationship between team processes and educational quality should be studied among larger study populations. Student ratings should also be considered in measuring educational quality.

Using PPI network autocorrelation in hierarchical multi-label classification trees for gene function prediction.

PubMed

Stojanova, Daniela; Ceci, Michelangelo; Malerba, Donato; Dzeroski, Saso

2013-09-26

Ontologies and catalogs of gene functions, such as the Gene Ontology (GO) and MIPS-FUN, assume that functional classes are organized hierarchically, that is, general functions include more specific ones. This has recently motivated the development of several machine learning algorithms for gene function prediction that leverages on this hierarchical organization where instances may belong to multiple classes. In addition, it is possible to exploit relationships among examples, since it is plausible that related genes tend to share functional annotations. Although these relationships have been identified and extensively studied in the area of protein-protein interaction (PPI) networks, they have not received much attention in hierarchical and multi-class gene function prediction. Relations between genes introduce autocorrelation in functional annotations and violate the assumption that instances are independently and identically distributed (i.i.d.), which underlines most machine learning algorithms. Although the explicit consideration of these relations brings additional complexity to the learning process, we expect substantial benefits in predictive accuracy of learned classifiers. This article demonstrates the benefits (in terms of predictive accuracy) of considering autocorrelation in multi-class gene function prediction. We develop a tree-based algorithm for considering network autocorrelation in the setting of Hierarchical Multi-label Classification (HMC). We empirically evaluate the proposed algorithm, called NHMC (Network Hierarchical Multi-label Classification), on 12 yeast datasets using each of the MIPS-FUN and GO annotation schemes and exploiting 2 different PPI networks. The results clearly show that taking autocorrelation into account improves the predictive performance of the learned models for predicting gene function. Our newly developed method for HMC takes into account network information in the learning phase: When used for gene function prediction in the context of PPI networks, the explicit consideration of network autocorrelation increases the predictive performance of the learned models. Overall, we found that this holds for different gene features/ descriptions, functional annotation schemes, and PPI networks: Best results are achieved when the PPI network is dense and contains a large proportion of function-relevant interactions.

On-chip phase-change photonic memory and computing

NASA Astrophysics Data System (ADS)

Cheng, Zengguang; Ríos, Carlos; Youngblood, Nathan; Wright, C. David; Pernice, Wolfram H. P.; Bhaskaran, Harish

2017-08-01

The use of photonics in computing is a hot topic of interest, driven by the need for ever-increasing speed along with reduced power consumption. In existing computing architectures, photonic data storage would dramatically improve the performance by reducing latencies associated with electrical memories. At the same time, the rise of `big data' and `deep learning' is driving the quest for non-von Neumann and brain-inspired computing paradigms. To succeed in both aspects, we have demonstrated non-volatile multi-level photonic memory avoiding the von Neumann bottleneck in the existing computing paradigm and a photonic synapse resembling the biological synapses for brain-inspired computing using phase-change materials (Ge2Sb2Te5).

Confidence level estimation in multi-target classification problems

NASA Astrophysics Data System (ADS)

Chang, Shi; Isaacs, Jason; Fu, Bo; Shin, Jaejeong; Zhu, Pingping; Ferrari, Silvia

2018-04-01

This paper presents an approach for estimating the confidence level in automatic multi-target classification performed by an imaging sensor on an unmanned vehicle. An automatic target recognition algorithm comprised of a deep convolutional neural network in series with a support vector machine classifier detects and classifies targets based on the image matrix. The joint posterior probability mass function of target class, features, and classification estimates is learned from labeled data, and recursively updated as additional images become available. Based on the learned joint probability mass function, the approach presented in this paper predicts the expected confidence level of future target classifications, prior to obtaining new images. The proposed approach is tested with a set of simulated sonar image data. The numerical results show that the estimated confidence level provides a close approximation to the actual confidence level value determined a posteriori, i.e. after the new image is obtained by the on-board sensor. Therefore, the expected confidence level function presented in this paper can be used to adaptively plan the path of the unmanned vehicle so as to optimize the expected confidence levels and ensure that all targets are classified with satisfactory confidence after the path is executed.

Intelligent multiagent coordination based on reinforcement hierarchical neuro-fuzzy models.

PubMed

Mendoza, Leonardo Forero; Vellasco, Marley; Figueiredo, Karla

2014-12-01

This paper presents the research and development of two hybrid neuro-fuzzy models for the hierarchical coordination of multiple intelligent agents. The main objective of the models is to have multiple agents interact intelligently with each other in complex systems. We developed two new models of coordination for intelligent multiagent systems, which integrates the Reinforcement Learning Hierarchical Neuro-Fuzzy model with two proposed coordination mechanisms: the MultiAgent Reinforcement Learning Hierarchical Neuro-Fuzzy with a market-driven coordination mechanism (MA-RL-HNFP-MD) and the MultiAgent Reinforcement Learning Hierarchical Neuro-Fuzzy with graph coordination (MA-RL-HNFP-CG). In order to evaluate the proposed models and verify the contribution of the proposed coordination mechanisms, two multiagent benchmark applications were developed: the pursuit game and the robot soccer simulation. The results obtained demonstrated that the proposed coordination mechanisms greatly improve the performance of the multiagent system when compared with other strategies.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

NASA Astrophysics Data System (ADS)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Deep multi-scale convolutional neural network for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Zhang, Feng-zhe; Yang, Xia

2018-04-01

In this paper, we proposed a multi-scale convolutional neural network for hyperspectral image classification task. Firstly, compared with conventional convolution, we utilize multi-scale convolutions, which possess larger respective fields, to extract spectral features of hyperspectral image. We design a deep neural network with a multi-scale convolution layer which contains 3 different convolution kernel sizes. Secondly, to avoid overfitting of deep neural network, dropout is utilized, which randomly sleeps neurons, contributing to improve the classification accuracy a bit. In addition, new skills like ReLU in deep learning is utilized in this paper. We conduct experiments on University of Pavia and Salinas datasets, and obtained better classification accuracy compared with other methods.

Transductive multi-view zero-shot learning.

PubMed

Fu, Yanwei; Hospedales, Timothy M; Xiang, Tao; Gong, Shaogang

2015-11-01

Most existing zero-shot learning approaches exploit transfer learning via an intermediate semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A projection from a low-level feature space to the semantic representation space is learned from the auxiliary dataset and applied without adaptation to the target dataset. In this paper we identify two inherent limitations with these approaches. First, due to having disjoint and potentially unrelated classes, the projection functions learned from the auxiliary dataset/domain are biased when applied directly to the target dataset/domain. We call this problem the projection domain shift problem and propose a novel framework, transductive multi-view embedding, to solve it. The second limitation is the prototype sparsity problem which refers to the fact that for each target class, only a single prototype is available for zero-shot learning given a semantic representation. To overcome this problem, a novel heterogeneous multi-view hypergraph label propagation method is formulated for zero-shot learning in the transductive embedding space. It effectively exploits the complementary information offered by different semantic representations and takes advantage of the manifold structures of multiple representation spaces in a coherent manner. We demonstrate through extensive experiments that the proposed approach (1) rectifies the projection shift between the auxiliary and target domains, (2) exploits the complementarity of multiple semantic representations, (3) significantly outperforms existing methods for both zero-shot and N-shot recognition on three image and video benchmark datasets, and (4) enables novel cross-view annotation tasks.

Technology for Improving Early Reading in Multi-Lingual Settings: Evidence from Rural South Africa

ERIC Educational Resources Information Center

Castillo, Nathan M.

2017-01-01

In September 2015, the United Nations ratified 17 Sustainable Development Goals (SDGs), including a central goal to improve the quality of learning, and attain universal literacy. As part of this effort, the UN and other funding agencies see technology as a major enabling tool for achievement of the SDGs. However, little evidence exists concerning…

Using the Significant Learning Taxonomy and Active Learning to Improve Accounting Education

ERIC Educational Resources Information Center

Killian, Larita J.; Brandon, Christopher D.

2009-01-01

Like other members of the academy, accounting professors are challenged to improve student learning. We must help students move beyond the "bean counter" role and develop higher-level skills such as analysis, synthesis, and problem-solving. The Significant Learning Taxonomy was used as a template to improve learning in an introductory accounting…

A National Partnership-Based Summer Learning Initiative to Engage Underrepresented Students with Science, Technology, Engineering and Mathematics

NASA Technical Reports Server (NTRS)

Melvin, Leland

2010-01-01

In response to the White House Educate to Innovate campaign, NASA developed a new science, technology, engineering, and mathematics (STEM) education program for non-traditional audiences that also focused on public-private partnerships and nationwide participation. NASA recognized that summer break is an often overlooked but opportune time to engage youth in STEM experiences, and elevated its ongoing commitment to the cultivation of diversity. The Summer of Innovation (SoI) is the resulting initiative that uses NASA's unique missions and resources to boost summer learning, particularly for students who are underrepresented, underserved and underperforming in STEM. The SoI pilot, launched in June 2010, is a multi-faceted effort designed to improve STEM teaching and learning through partnership, multi-week summer learning programs, special events, a national concluding event, and teacher development. The SoI pilot features strategic infusion of NASA content and educational resource materials, sustainability through STEM Learning Communities, and assessments of effectiveness of SoI interventions with other pilot efforts. This paper examines the inception and development of the Summer of Innovation pilot project, including achievements and effectiveness, as well as lessons learned for future efforts.

MultiDK: A Multiple Descriptor Multiple Kernel Approach for Molecular Discovery and Its Application to Organic Flow Battery Electrolytes.

PubMed

Kim, Sungjin; Jinich, Adrián; Aspuru-Guzik, Alán

2017-04-24

We propose a multiple descriptor multiple kernel (MultiDK) method for efficient molecular discovery using machine learning. We show that the MultiDK method improves both the speed and accuracy of molecular property prediction. We apply the method to the discovery of electrolyte molecules for aqueous redox flow batteries. Using multiple-type-as opposed to single-type-descriptors, we obtain more relevant features for machine learning. Following the principle of "wisdom of the crowds", the combination of multiple-type descriptors significantly boosts prediction performance. Moreover, by employing multiple kernels-more than one kernel function for a set of the input descriptors-MultiDK exploits nonlinear relations between molecular structure and properties better than a linear regression approach. The multiple kernels consist of a Tanimoto similarity kernel and a linear kernel for a set of binary descriptors and a set of nonbinary descriptors, respectively. Using MultiDK, we achieve an average performance of r 2 = 0.92 with a test set of molecules for solubility prediction. We also extend MultiDK to predict pH-dependent solubility and apply it to a set of quinone molecules with different ionizable functional groups to assess their performance as flow battery electrolytes.

Multi-Task Convolutional Neural Network for Pose-Invariant Face Recognition

NASA Astrophysics Data System (ADS)

Yin, Xi; Liu, Xiaoming

2018-02-01

This paper explores multi-task learning (MTL) for face recognition. We answer the questions of how and why MTL can improve the face recognition performance. First, we propose a multi-task Convolutional Neural Network (CNN) for face recognition where identity classification is the main task and pose, illumination, and expression estimations are the side tasks. Second, we develop a dynamic-weighting scheme to automatically assign the loss weight to each side task, which is a crucial problem in MTL. Third, we propose a pose-directed multi-task CNN by grouping different poses to learn pose-specific identity features, simultaneously across all poses. Last but not least, we propose an energy-based weight analysis method to explore how CNN-based MTL works. We observe that the side tasks serve as regularizations to disentangle the variations from the learnt identity features. Extensive experiments on the entire Multi-PIE dataset demonstrate the effectiveness of the proposed approach. To the best of our knowledge, this is the first work using all data in Multi-PIE for face recognition. Our approach is also applicable to in-the-wild datasets for pose-invariant face recognition and achieves comparable or better performance than state of the art on LFW, CFP, and IJB-A datasets.

Bayesian Kernel Methods for Non-Gaussian Distributions: Binary and Multi-class Classification Problems

DTIC Science & Technology

2013-05-28

those of the support vector machine and relevance vector machine, and the model runs more quickly than the other algorithms . When one class occurs...incremental support vector machine algorithm for online learning when fewer than 50 data points are available. (a) Papers published in peer-reviewed journals...learning environments, where data processing occurs one observation at a time and the classification algorithm improves over time with new

Perceptual learning modules in mathematics: enhancing students' pattern recognition, structure extraction, and fluency.

PubMed

Kellman, Philip J; Massey, Christine M; Son, Ji Y

2010-04-01

Learning in educational settings emphasizes declarative and procedural knowledge. Studies of expertise, however, point to other crucial components of learning, especially improvements produced by experience in the extraction of information: perceptual learning (PL). We suggest that such improvements characterize both simple sensory and complex cognitive, even symbolic, tasks through common processes of discovery and selection. We apply these ideas in the form of perceptual learning modules (PLMs) to mathematics learning. We tested three PLMs, each emphasizing different aspects of complex task performance, in middle and high school mathematics. In the MultiRep PLM, practice in matching function information across multiple representations improved students' abilities to generate correct graphs and equations from word problems. In the Algebraic Transformations PLM, practice in seeing equation structure across transformations (but not solving equations) led to dramatic improvements in the speed of equation solving. In the Linear Measurement PLM, interactive trials involving extraction of information about units and lengths produced successful transfer to novel measurement problems and fraction problem solving. Taken together, these results suggest (a) that PL techniques have the potential to address crucial, neglected dimensions of learning, including discovery and fluent processing of relations; (b) PL effects apply even to complex tasks that involve symbolic processing; and (c) appropriately designed PL technology can produce rapid and enduring advances in learning. Copyright © 2009 Cognitive Science Society, Inc.

Exploring the Use of Individualized, Reflective Guidance In an Educational Multi-User Virtual Environment

NASA Astrophysics Data System (ADS)

Nelson, Brian C.

2007-02-01

This study examines the patterns of use and potential impact of individualized, reflective guidance in an educational Multi-User Virtual Environment (MUVE). A guidance system embedded within a MUVE-based scientific inquiry curriculum was implemented with a sample of middle school students in an exploratory study investigating (a) whether access to the guidance system was associated with improved learning, (b) whether students viewing more guidance messages saw greater improvement on content tests than those viewing less, and (c) whether there were any differences in guidance use among boys and girls. Initial experimental findings showed that basic access to individualized guidance used with a MUVE had no measurable impact on learning. However, post-hoc exploratory analyses indicated that increased use of the system among those with access to it was positively associated with content test score gains. In addition, differences were found in overall learning outcomes by gender and in patterns of guidance use by boys and girls, with girls outperforming boys across a spectrum of guidance system use. Based on these exploratory findings, the paper suggests design guidelines for the development of guidance systems embedded in MUVEs and outlines directions for further research.

Impact of Different Levels of Epistemic Beliefs on Learning Processes and Outcomes in Vocational Education and Training

ERIC Educational Resources Information Center

Berding, Florian; Rolf-Wittlake, Katharina; Buschenlange, Janes

2017-01-01

Epistemic beliefs are individuals' beliefs about knowledge and knowing. Modelling them is currently based on two central assumptions. First, epistemic beliefs are conceptualized as a multi-level construct, i.e. they exist on a general, academic, domain-specific and/or topic-specific level. Second, research assumes that their more concrete levels…

Effective Multi-Query Expansions: Collaborative Deep Networks for Robust Landmark Retrieval.

PubMed

Wang, Yang; Lin, Xuemin; Wu, Lin; Zhang, Wenjie

2017-03-01

Given a query photo issued by a user (q-user), the landmark retrieval is to return a set of photos with their landmarks similar to those of the query, while the existing studies on the landmark retrieval focus on exploiting geometries of landmarks for similarity matches between candidate photos and a query photo. We observe that the same landmarks provided by different users over social media community may convey different geometry information depending on the viewpoints and/or angles, and may, subsequently, yield very different results. In fact, dealing with the landmarks with low quality shapes caused by the photography of q-users is often nontrivial and has seldom been studied. In this paper, we propose a novel framework, namely, multi-query expansions, to retrieve semantically robust landmarks by two steps. First, we identify the top- k photos regarding the latent topics of a query landmark to construct multi-query set so as to remedy its possible low quality shape. For this purpose, we significantly extend the techniques of Latent Dirichlet Allocation. Then, motivated by the typical collaborative filtering methods, we propose to learn a collaborative deep networks-based semantically, nonlinear, and high-level features over the latent factor for landmark photo as the training set, which is formed by matrix factorization over collaborative user-photo matrix regarding the multi-query set. The learned deep network is further applied to generate the features for all the other photos, meanwhile resulting into a compact multi-query set within such space. Then, the final ranking scores are calculated over the high-level feature space between the multi-query set and all other photos, which are ranked to serve as the final ranking list of landmark retrieval. Extensive experiments are conducted on real-world social media data with both landmark photos together with their user information to show the superior performance over the existing methods, especially our recently proposed multi-query based mid-level pattern representation method [1].

Collective Machine Learning: Team Learning and Classification in Multi-Agent Systems

ERIC Educational Resources Information Center

Gifford, Christopher M.

2009-01-01

This dissertation focuses on the collaboration of multiple heterogeneous, intelligent agents (hardware or software) which collaborate to learn a task and are capable of sharing knowledge. The concept of collaborative learning in multi-agent and multi-robot systems is largely under studied, and represents an area where further research is needed to…

YASS: A System Simulator for Operating System and Computer Architecture Teaching and Learning

ERIC Educational Resources Information Center

Mustafa, Besim

2013-01-01

A highly interactive, integrated and multi-level simulator has been developed specifically to support both the teachers and the learners of modern computer technologies at undergraduate level. The simulator provides a highly visual and user configurable environment with many pedagogical features aimed at facilitating deep understanding of concepts…

Memory: As It Relates to Children Ages 9 to 12 Years. Skills Essential to Learning Television Project: Working Paper.

ERIC Educational Resources Information Center

Perry, Fred L., Jr.

An overview of theory and research in memory as it relates to developmental differences is offered in this paper, which is intended to provide background information for the staff of the Skills Essential to Learning Television Project (a multi-level series of video and print resources for classroom use). A model for viewing information processing…

Employing the EPEC Hierarchy of Conditions (Version II) to Evaluate the Effectiveness of Using Synchronous Technologies with Multi-Location Student Cohorts in the Tertiary Education Setting

ERIC Educational Resources Information Center

Eady, Michelle J.; Woodcock, Stuart; Sisco, Ashley

2017-01-01

As e-learning maintains its popularity worldwide, and university enrolments continue to rise, online tertiary level coursework is increasingly being designed for groups of distributed learners, as opposed to individual students. Many institutions struggle with incorporating all facets of online learning and teaching capabilities with the range and…

Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples.

PubMed

Zhang, He-Hua; Yang, Liuyang; Liu, Yuchuan; Wang, Pin; Yin, Jun; Li, Yongming; Qiu, Mingguo; Zhu, Xueru; Yan, Fang

2016-11-16

The use of speech based data in the classification of Parkinson disease (PD) has been shown to provide an effect, non-invasive mode of classification in recent years. Thus, there has been an increased interest in speech pattern analysis methods applicable to Parkinsonism for building predictive tele-diagnosis and tele-monitoring models. One of the obstacles in optimizing classifications is to reduce noise within the collected speech samples, thus ensuring better classification accuracy and stability. While the currently used methods are effect, the ability to invoke instance selection has been seldomly examined. In this study, a PD classification algorithm was proposed and examined that combines a multi-edit-nearest-neighbor (MENN) algorithm and an ensemble learning algorithm. First, the MENN algorithm is applied for selecting optimal training speech samples iteratively, thereby obtaining samples with high separability. Next, an ensemble learning algorithm, random forest (RF) or decorrelated neural network ensembles (DNNE), is used to generate trained samples from the collected training samples. Lastly, the trained ensemble learning algorithms are applied to the test samples for PD classification. This proposed method was examined using a more recently deposited public datasets and compared against other currently used algorithms for validation. Experimental results showed that the proposed algorithm obtained the highest degree of improved classification accuracy (29.44%) compared with the other algorithm that was examined. Furthermore, the MENN algorithm alone was found to improve classification accuracy by as much as 45.72%. Moreover, the proposed algorithm was found to exhibit a higher stability, particularly when combining the MENN and RF algorithms. This study showed that the proposed method could improve PD classification when using speech data and can be applied to future studies seeking to improve PD classification methods.

Multi-segmental movement patterns reflect juggling complexity and skill level.

PubMed

Zago, Matteo; Pacifici, Ilaria; Lovecchio, Nicola; Galli, Manuela; Federolf, Peter Andreas; Sforza, Chiarella

2017-08-01

The juggling action of six experts and six intermediates jugglers was recorded with a motion capture system and decomposed into its fundamental components through Principal Component Analysis. The aim was to quantify trends in movement dimensionality, multi-segmental patterns and rhythmicity as a function of proficiency level and task complexity. Dimensionality was quantified in terms of Residual Variance, while the Relative Amplitude was introduced to account for individual differences in movement components. We observed that: experience-related modifications in multi-segmental actions exist, such as the progressive reduction of error-correction movements, especially in complex task condition. The systematic identification of motor patterns sensitive to the acquisition of specific experience could accelerate the learning process. Copyright © 2017 Elsevier B.V. All rights reserved.

Coccomyxa Gloeobotrydiformis Improves Learning and Memory in Intrinsic Aging Rats.

PubMed

Sun, Luning; Jin, Ying; Dong, Liming; Sui, Hai-Juan; Sumi, Ryo; Jahan, Rabita; Hu, Dahai; Li, Zhi

2015-01-01

Declining in learning and memory is one of the most common and prominent problems during the aging process. Neurotransmitter changes, oxidative stress, mitochondrial dysfunction and abnormal signal transduction were considered to participate in this process. In the present study, we examined the effects of Coccomyxa gloeobotrydiformis (CGD) on learning and memory ability of intrinsic aging rats. As a result, CGD treated (50 mg/kg·d or 100 mg/kg ·d for a duration of 8 weeks) 22-month-old male rats, which have shown significant improvement on learning and spatial memory ability compared with control, which was evidently revealed in both the hidden platform tasks and probe trials. The following immunohistochemistry and Western blot experiments suggested that CGD could increase the content of Ach and thereby improve the function of the cholinergic neurons in the hippocampus, and therefore also improving learning and memory ability of the aged rats by acting as an anti-inflammatory agent. The effects of CGD on learning and memory might also have an association with the ERK/CREB signalling. The results above suggest that the naturally made drug CGD may have several great benefit as a multi-target drug in the process of prevention and/or treatment of age-dependent cognitive decline and aging process.

Iterative learning-based decentralized adaptive tracker for large-scale systems: a digital redesign approach.

PubMed

Tsai, Jason Sheng-Hong; Du, Yan-Yi; Huang, Pei-Hsiang; Guo, Shu-Mei; Shieh, Leang-San; Chen, Yuhua

2011-07-01

In this paper, a digital redesign methodology of the iterative learning-based decentralized adaptive tracker is proposed to improve the dynamic performance of sampled-data linear large-scale control systems consisting of N interconnected multi-input multi-output subsystems, so that the system output will follow any trajectory which may not be presented by the analytic reference model initially. To overcome the interference of each sub-system and simplify the controller design, the proposed model reference decentralized adaptive control scheme constructs a decoupled well-designed reference model first. Then, according to the well-designed model, this paper develops a digital decentralized adaptive tracker based on the optimal analog control and prediction-based digital redesign technique for the sampled-data large-scale coupling system. In order to enhance the tracking performance of the digital tracker at specified sampling instants, we apply the iterative learning control (ILC) to train the control input via continual learning. As a result, the proposed iterative learning-based decentralized adaptive tracker not only has robust closed-loop decoupled property but also possesses good tracking performance at both transient and steady state. Besides, evolutionary programming is applied to search for a good learning gain to speed up the learning process of ILC. Copyright © 2011 ISA. Published by Elsevier Ltd. All rights reserved.

A Multi-scale, Multi-Model, Machine-Learning Solar Forecasting Technology

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

Hamann, Hendrik F.

The goal of the project was the development and demonstration of a significantly improved solar forecasting technology (short: Watt-sun), which leverages new big data processing technologies and machine-learnt blending between different models and forecast systems. The technology aimed demonstrating major advances in accuracy as measured by existing and new metrics which themselves were developed as part of this project. Finally, the team worked with Independent System Operators (ISOs) and utilities to integrate the forecasts into their operations.

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.

Assessment of learning, memory and attention in developmental neurotoxicity regulatory studies: Introduction.

PubMed

Makris, Susan L; Vorhees, Charles V

2015-01-01

There are a variety of chemicals, including pharmaceuticals, that alter neurobehavior following developmental exposure and guidelines for the conduct of studies to detect such effects by statute in the United States and Europe. Guidelines for Developmental Neurotoxicity Testing (DNT) studies issued by the U.S. Environmental Protection Agency (EPA) under prevailing law and European Organization for Economic Cooperation and Development (OECD) recommendations to member countries provide that such studies include a series of neurobehavioral and neuropathological assessments. Among these are assessment of cognitive function, specifically learning and memory. After reviewing 69 DNT studies submitted to the EPA, tests of learning and memory were noted to have detected the lowest observed adverse effect level (LOAELs) less frequently than behavioral tests of locomotor activity and acoustic/auditory startle, but slightly more than for the developmental Functional Observational Battery (devFOB; which is less extensive than the full FOB), but the reasons for the lower LOAEL detection rate for learning and memory assessment could not be determined. A major concern identified in the review, however, was the adequacy of the methods employed in these studies rather than on the importance of learning and memory to the proper assessment of brain function. Accordingly, a symposium was conducted to consider how the guidelines for tests of learning and memory might be improved. Four laboratories with established histories investigating the effects of chemical exposures during development on learning, memory, and attention, were invited to review the topic and offer recommendations, both theoretical and practical, on approaches to improve the assessment of these vital CNS functions. Reviewers were asked to recommend methods that are grounded in functional importance to CNS integrity, well-validated, reliable, and amenable to the context of regulatory studies as well as to basic research on the underlying processes they measure. This Introduction sets the stage for the reviews by providing the background and regulatory context for improved tests for learning and memory in DNT and other regulatory studies, such as single- or multi-generational studies where similar methods are incorporated. Copyright © 2015 Elsevier Inc. All rights reserved.

Engagement and learning: an exploratory study of situated practice in multi-disciplinary stroke rehabilitation.

PubMed

Horton, Simon; Howell, Alison; Humby, Kate; Ross, Alexandra

2011-01-01

Active participation is considered to be a key factor in stroke rehabilitation. Patient engagement in learning is an important part of this process. This study sets out to explore how active participation and engagement are 'produced' in the course of day-to-day multi-disciplinary stroke rehabilitation. Ethnographic observation, analytic concepts drawn from discourse analysis (DA) and the perspective and methods of conversation analysis (CA) were applied to videotaped data from three sessions of rehabilitation therapy each for two patients with communication impairments (dysarthria, aphasia). Engagement was facilitated (and hindered) through the interactional work of patients and healthcare professionals. An institutional ethos of 'right practice' was evidenced in the working practices of therapists and aligned with or resisted by patients; therapeutic activity type (impairment, activity or functional focus) impacted on the ways in which patient engagement was developed and sustained. This exploration of multi-disciplinary rehabilitation practice adds a new dimension to our understanding of the barriers and facilitators to patient engagement in the learning process and provides scope for further research. Harmonising the rehabilitation process across disciplines through more focused attention to ways in which patient participation is enhanced may help improve the consistency and quality of patient engagement.

Improved NSGA model for multi objective operation scheduling and its evaluation

NASA Astrophysics Data System (ADS)

Li, Weining; Wang, Fuyu

2017-09-01

Reasonable operation can increase the income of the hospital and improve the patient’s satisfactory level. In this paper, by using multi object operation scheduling method with improved NSGA algorithm, it shortens the operation time, reduces the operation costand lowers the operation risk, the multi-objective optimization model is established for flexible operation scheduling, through the MATLAB simulation method, the Pareto solution is obtained, the standardization of data processing. The optimal scheduling scheme is selected by using entropy weight -Topsis combination method. The results show that the algorithm is feasible to solve the multi-objective operation scheduling problem, and provide a reference for hospital operation scheduling.

Improving Interoperability between Registries and EHRs

PubMed Central

Blumenthal, Seth

2018-01-01

National performance measurement needs clinical data that track the performance of multi disciplinary teams across episodes of care. Clinical registries are ideal platforms for this work due to their capture of structured, specific data across specialties. Because registries collect data at a national level, and registry data are captured in a consistent structure and format within each registry, registry data are useful for measurement and analysis “out of the box”. Registry business models are hampered by the cost of collecting data from EHRs and other source systems and abstracting or mapping them to fit registry data models. The National Quality Registry Network (NQRN) has launched Registries on FHIR, an initiative to lower barriers to achieving semantic interoperability between registries and source data systems. In 2017 Registries on FHIR conducted an information gathering campaign to learn where registries want better interoperability, and how to go about improving it. PMID:29888033

Health Literacy Training for Public Health Nurses in Fukushima: A Multi-site Program Evaluation.

PubMed

Goto, Aya; Lai, Alden Yuanhong; Rudd, Rima E

2015-09-01

Public health nurses (PHNs) are community residents' access points to health information and services in Japan. After the Fukushima nuclear accident, they were challenged to communicate radiation-related health information to best meet community needs. We previously developed and evaluated the outcome of a single-site health literacy training program to augment PHNs' ability to improve community residents' access to written health information. This paper presents an evaluation of an identical training program using data combined from multiple sites, and further included proximal and distal evaluations to document the impact of health literacy training in a post-disaster setting. A total of 64 participants, primarily experienced PHNs, attended one of three multi-session health literacy workshops conducted in multiple sites across Fukushima. Quantitative and qualitative data on PHNs' training satisfaction, self-evaluation of achievements regarding training goals, and application of learned skills were collected and analyzed. Each workshop consisted of two 2-hour sessions introducing health literacy and assessment tools and developing skills to improve written materials, followed by a one-month follow-up assessment on PHNs' application of the gained skills in the field. Post-training evaluations on the appropriateness and usefulness of the workshop were highly positive. At the end of the one-month follow-up, 45% of participants had gained confidence in assessing and revising written materials and had applied the skills they had gained to develop and communicate health information in various settings and modes. This increase in confidence was associated with further application of the learned skills at the municipal level. However, participants reported difficulties in explaining risks, and the need to learn more about plain language to be able to paraphrase professional terms. This paper highlighs the positive outcomes of health literacy training among PHNs. Practical strategies to reinforce their skills to use plain language and communicate the epidemiological concept of risk are also recommended.

Evoked prior learning experience and approach to learning as predictors of academic achievement.

PubMed

Trigwell, Keith; Ashwin, Paul; Millan, Elena S

2013-09-01

In separate studies and research from different perspectives, five factors are found to be among those related to higher quality outcomes of student learning (academic achievement). Those factors are higher self-efficacy, deeper approaches to learning, higher quality teaching, students' perceptions that their workload is appropriate, and greater learning motivation. University learning improvement strategies have been built on these research results. To investigate how students' evoked prior experience, perceptions of their learning environment, and their approaches to learning collectively contribute to academic achievement. This is the first study to investigate motivation and self-efficacy in the same educational context as conceptions of learning, approaches to learning and perceptions of the learning environment. Undergraduate students (773) from the full range of disciplines were part of a group of over 2,300 students who volunteered to complete a survey of their learning experience. On completing their degrees 6 and 18 months later, their academic achievement was matched with their learning experience survey data. A 77-item questionnaire was used to gather students' self-report of their evoked prior experience (self-efficacy, learning motivation, and conceptions of learning), perceptions of learning context (teaching quality and appropriate workload), and approaches to learning (deep and surface). Academic achievement was measured using the English honours degree classification system. Analyses were conducted using correlational and multi-variable (structural equation modelling) methods. The results from the correlation methods confirmed those found in numerous earlier studies. The results from the multi-variable analyses indicated that surface approach to learning was the strongest predictor of academic achievement, with self-efficacy and motivation also found to be directly related. In contrast to the correlation results, a deep approach to learning was not related to academic achievement, and teaching quality and conceptions of learning were only indirectly related to achievement. Research aimed at understanding how students experience their learning environment and how that experience relates to the quality of their learning needs to be conducted using a wider range of variables and more sophisticated analytical methods. In this study of one context, some of the relations found in earlier bivariate studies, and on which learning intervention strategies have been built, are not confirmed when more holistic teaching-learning contexts are analysed using multi-variable methods. © 2012 The British Psychological Society.

Learning Challenges Involved in Developing Leading for Learning

ERIC Educational Resources Information Center

Timperley, Helen S.

2006-01-01

The study in this article seeks to understand the learning challenges involved in developing learning-centered leadership in schools. It is based on Southworth's (1998, 2004) ideas of leadership for improving schools, which comprise promoting learning-centered improvement at all levels through professional development and a focus on the quality of…

The Inclusive Classroom. Professional's Guide.

ERIC Educational Resources Information Center

Grenot-Scheyer, Marquita; And Others

Inclusive education reflects the changing culture of contemporary schools with emphasis on active learning, authentic assessment practices, applied curriculum, multi-level instructional approaches, and increased attention to diverse student needs and individualization. This guide is intended to help teachers implement inclusive educational…

Hybrid E-Learning Tool TransLearning: Video Storytelling to Foster Vicarious Learning within Multi-Stakeholder Collaboration Networks

ERIC Educational Resources Information Center

van der Meij, Marjoleine G.; Kupper, Frank; Beers, Pieter J.; Broerse, Jacqueline E. W.

2016-01-01

E-learning and storytelling approaches can support informal vicarious learning within geographically widely distributed multi-stakeholder collaboration networks. This case study evaluates hybrid e-learning and video-storytelling approach "TransLearning" by investigation into how its storytelling e-tool supported informal vicarious…

Application of Multi-task Sparse Lasso Feature Extraction and Support Vector Machine Regression in the Stellar Atmospheric Parameterization

NASA Astrophysics Data System (ADS)

Gao, Wei; Li, Xiang-ru

2017-07-01

The multi-task learning takes the multiple tasks together to make analysis and calculation, so as to dig out the correlations among them, and therefore to improve the accuracy of the analyzed results. This kind of methods have been widely applied to the machine learning, pattern recognition, computer vision, and other related fields. This paper investigates the application of multi-task learning in estimating the stellar atmospheric parameters, including the surface temperature (Teff), surface gravitational acceleration (lg g), and chemical abundance ([Fe/H]). Firstly, the spectral features of the three stellar atmospheric parameters are extracted by using the multi-task sparse group Lasso algorithm, then the support vector machine is used to estimate the atmospheric physical parameters. The proposed scheme is evaluated on both the Sloan stellar spectra and the theoretical spectra computed from the Kurucz's New Opacity Distribution Function (NEWODF) model. The mean absolute errors (MAEs) on the Sloan spectra are: 0.0064 for lg (Teff /K), 0.1622 for lg (g/(cm · s-2)), and 0.1221 dex for [Fe/H]; the MAEs on the synthetic spectra are 0.0006 for lg (Teff /K), 0.0098 for lg (g/(cm · s-2)), and 0.0082 dex for [Fe/H]. Experimental results show that the proposed scheme has a rather high accuracy for the estimation of stellar atmospheric parameters.

Symbiosis-Based Alternative Learning Multi-Swarm Particle Swarm Optimization.

PubMed

Niu, Ben; Huang, Huali; Tan, Lijing; Duan, Qiqi

2017-01-01

Inspired by the ideas from the mutual cooperation of symbiosis in natural ecosystem, this paper proposes a new variant of PSO, named Symbiosis-based Alternative Learning Multi-swarm Particle Swarm Optimization (SALMPSO). A learning probability to select one exemplar out of the center positions, the local best position, and the historical best position including the experience of internal and external multiple swarms, is used to keep the diversity of the population. Two different levels of social interaction within and between multiple swarms are proposed. In the search process, particles not only exchange social experience with others that are from their own sub-swarms, but also are influenced by the experience of particles from other fellow sub-swarms. According to the different exemplars and learning strategy, this model is instantiated as four variants of SALMPSO and a set of 15 test functions are conducted to compare with some variants of PSO including 10, 30 and 50 dimensions, respectively. Experimental results demonstrate that the alternative learning strategy in each SALMPSO version can exhibit better performance in terms of the convergence speed and optimal values on most multimodal functions in our simulation.

The dynamic sustainability framework: addressing the paradox of sustainment amid ongoing change

PubMed Central

2013-01-01

Background Despite growth in implementation research, limited scientific attention has focused on understanding and improving sustainability of health interventions. Models of sustainability have been evolving to reflect challenges in the fit between intervention and context. Discussion We examine the development of concepts of sustainability, and respond to two frequent assumptions —'voltage drop,’ whereby interventions are expected to yield lower benefits as they move from efficacy to effectiveness to implementation and sustainability, and 'program drift,’ whereby deviation from manualized protocols is assumed to decrease benefit. We posit that these assumptions limit opportunities to improve care, and instead argue for understanding the changing context of healthcare to continuously refine and improve interventions as they are sustained. Sustainability has evolved from being considered as the endgame of a translational research process to a suggested 'adaptation phase’ that integrates and institutionalizes interventions within local organizational and cultural contexts. These recent approaches locate sustainability in the implementation phase of knowledge transfer, but still do not address intervention improvement as a central theme. We propose a Dynamic Sustainability Framework that involves: continued learning and problem solving, ongoing adaptation of interventions with a primary focus on fit between interventions and multi-level contexts, and expectations for ongoing improvement as opposed to diminishing outcomes over time. Summary A Dynamic Sustainability Framework provides a foundation for research, policy and practice that supports development and testing of falsifiable hypotheses and continued learning to advance the implementation, transportability and impact of health services research. PMID:24088228

The dynamic sustainability framework: addressing the paradox of sustainment amid ongoing change.

PubMed

Chambers, David A; Glasgow, Russell E; Stange, Kurt C

2013-10-02

Despite growth in implementation research, limited scientific attention has focused on understanding and improving sustainability of health interventions. Models of sustainability have been evolving to reflect challenges in the fit between intervention and context. We examine the development of concepts of sustainability, and respond to two frequent assumptions -'voltage drop,' whereby interventions are expected to yield lower benefits as they move from efficacy to effectiveness to implementation and sustainability, and 'program drift,' whereby deviation from manualized protocols is assumed to decrease benefit. We posit that these assumptions limit opportunities to improve care, and instead argue for understanding the changing context of healthcare to continuously refine and improve interventions as they are sustained. Sustainability has evolved from being considered as the endgame of a translational research process to a suggested 'adaptation phase' that integrates and institutionalizes interventions within local organizational and cultural contexts. These recent approaches locate sustainability in the implementation phase of knowledge transfer, but still do not address intervention improvement as a central theme. We propose a Dynamic Sustainability Framework that involves: continued learning and problem solving, ongoing adaptation of interventions with a primary focus on fit between interventions and multi-level contexts, and expectations for ongoing improvement as opposed to diminishing outcomes over time. A Dynamic Sustainability Framework provides a foundation for research, policy and practice that supports development and testing of falsifiable hypotheses and continued learning to advance the implementation, transportability and impact of health services research.

A game theory-reinforcement learning (GT-RL) method to develop optimal operation policies for multi-operator reservoir systems

NASA Astrophysics Data System (ADS)

Madani, Kaveh; Hooshyar, Milad

2014-11-01

Reservoir systems with multiple operators can benefit from coordination of operation policies. To maximize the total benefit of these systems the literature has normally used the social planner's approach. Based on this approach operation decisions are optimized using a multi-objective optimization model with a compound system's objective. While the utility of the system can be increased this way, fair allocation of benefits among the operators remains challenging for the social planner who has to assign controversial weights to the system's beneficiaries and their objectives. Cooperative game theory provides an alternative framework for fair and efficient allocation of the incremental benefits of cooperation. To determine the fair and efficient utility shares of the beneficiaries, cooperative game theory solution methods consider the gains of each party in the status quo (non-cooperation) as well as what can be gained through the grand coalition (social planner's solution or full cooperation) and partial coalitions. Nevertheless, estimation of the benefits of different coalitions can be challenging in complex multi-beneficiary systems. Reinforcement learning can be used to address this challenge and determine the gains of the beneficiaries for different levels of cooperation, i.e., non-cooperation, partial cooperation, and full cooperation, providing the essential input for allocation based on cooperative game theory. This paper develops a game theory-reinforcement learning (GT-RL) method for determining the optimal operation policies in multi-operator multi-reservoir systems with respect to fairness and efficiency criteria. As the first step to underline the utility of the GT-RL method in solving complex multi-agent multi-reservoir problems without a need for developing compound objectives and weight assignment, the proposed method is applied to a hypothetical three-agent three-reservoir system.

Human Memory Limitations in Multi-Object Tracking.

DTIC Science & Technology

1982-06-01

processing concepts of Norman (1968) and Atkinson and Shiffrin (1968), and from the " levels of processing " formulation of Craik and Lockhart ...distinct memory representations that result from different levels of processing . Craik and Lockhart (1972) have argued convincingly for a process -oriented...learning and motivation (Vol. 2). New York: Academic Press, 1968, pp. 89-105. Craik , F. I. M., & Lockhart , R. S. Levels of processing

Teaching of the Society for Fetal Urology grading system for pediatric hydronephrosis is improved by e-Learning using Computer Enhanced Visual Learning (CEVL): A multi-institutional trial.

PubMed

Liu, Dennis B; Palmer, Blake; Herndon, C D Anthony; Maizels, Max

2015-08-01

It is unclear how clinicians learn to grade pediatric hydronephrosis (HN) and how effective their training has been. We sought to: 1. Assess how clinicians learn to grade HN and their confidence in their training and abilities and 2. To assess Computer Enhanced Visual Learning (CEVL) e-Learning to learn the Society for Fetal Urology (SFU) grading system for pediatric HN. A multi-institutional online survey was distributed to pediatric urologists, nephrologists, and radiologists. Respondents used a 6-point Likert scale (0 = not confident to 5 = very confident) to assess their confidence in knowledge of the criteria, indications, and ability to grade HN, and how they learned to grade. Participants assigned SFU grades to 15 neonatal ultrasounds (US). A CEVL module on the SFU grading system was accessed and a post-CEVL survey completed. Changes in confidence and accuracy of grading were compared before and after CEVL e-Learning. The most common method of learning was "casually during training" (44.5%). Significant increases in confidence in knowledge of criteria, indications, and ability to grade, as well as the accuracy of grading were seen following CEVL e-Learning (Figure A and B). Although the SFU grading system is considered the predominant grading system for HN, its application in clinical practice has been inconsistent. While this may be due to the grading system itself, it is possible that deficient training and confidence are the root causes. Our data supports this by demonstrating that most clinicians receive only casual training and accordingly, report low confidence in their knowledge and ability to grade HN. Therefore, we conclude that there exists a strong need to improve the teaching of the SFU grading system. e-Learning has been shown to be effective in teaching difficult topics and skills. We demonstrate that e-Learning with CEVL is effective in increasing both the confidence and accuracy of SFU grading of pediatric HN. Limitations of our study include a small sample size, low response rate, and discrepant participation. Furthermore, we did not assess the extent to which the CEVL module was used or include a control group learning through traditional means. Therefore, we were unable to evaluate the efficiency of learning or be certain that the improvements seen were derived exclusively from CEVL. Current training in SFU grading of HN is mostly unstructured and inaccurate grading is common. Learners who use CEVL show improvements in their confidence and ability to SFU grade HN. Copyright © 2015 Journal of Pediatric Urology Company. Published by Elsevier Ltd. All rights reserved.

A novel biomedical image indexing and retrieval system via deep preference learning.

PubMed

Pang, Shuchao; Orgun, Mehmet A; Yu, Zhezhou

2018-05-01

The traditional biomedical image retrieval methods as well as content-based image retrieval (CBIR) methods originally designed for non-biomedical images either only consider using pixel and low-level features to describe an image or use deep features to describe images but still leave a lot of room for improving both accuracy and efficiency. In this work, we propose a new approach, which exploits deep learning technology to extract the high-level and compact features from biomedical images. The deep feature extraction process leverages multiple hidden layers to capture substantial feature structures of high-resolution images and represent them at different levels of abstraction, leading to an improved performance for indexing and retrieval of biomedical images. We exploit the current popular and multi-layered deep neural networks, namely, stacked denoising autoencoders (SDAE) and convolutional neural networks (CNN) to represent the discriminative features of biomedical images by transferring the feature representations and parameters of pre-trained deep neural networks from another domain. Moreover, in order to index all the images for finding the similarly referenced images, we also introduce preference learning technology to train and learn a kind of a preference model for the query image, which can output the similarity ranking list of images from a biomedical image database. To the best of our knowledge, this paper introduces preference learning technology for the first time into biomedical image retrieval. We evaluate the performance of two powerful algorithms based on our proposed system and compare them with those of popular biomedical image indexing approaches and existing regular image retrieval methods with detailed experiments over several well-known public biomedical image databases. Based on different criteria for the evaluation of retrieval performance, experimental results demonstrate that our proposed algorithms outperform the state-of-the-art techniques in indexing biomedical images. We propose a novel and automated indexing system based on deep preference learning to characterize biomedical images for developing computer aided diagnosis (CAD) systems in healthcare. Our proposed system shows an outstanding indexing ability and high efficiency for biomedical image retrieval applications and it can be used to collect and annotate the high-resolution images in a biomedical database for further biomedical image research and applications. Copyright © 2018 Elsevier B.V. All rights reserved.

Leadership for health improvement--implementation and evaluation.

PubMed

Carr, Susan M; Carr, Sue; Lhussier, Monique; Reynolds, Joanna; Hunter, David J; Hannaway, Catherine

2009-01-01

The purpose of this paper is to present a co-authored reflection on the health improvement leadership development programme and the key evaluation messages derived from piloting in an English National Health Service region. It highlights the specific attributes of this approach to health improvement leadership development and clarifies health improvement development issues. Appreciative inquiry and soft systems methodology are combined in an evaluation approach designed to capture individual as well as organisation learning and how it impacts on leadership in specific contexts. The evaluation exposes the health improvement leadership needs of a multi-organisation cohort, offers some explanations for successful achievement of learning needs while also exposing of the challenges and paradoxes faced in this endeavour. There are limited reported templates of how to develop leadership for health improvement. This paper details a whole systems approach, acknowledging the impact of context on leadership and an approach to evaluating such complex initiatives.

Automatic sleep staging using multi-dimensional feature extraction and multi-kernel fuzzy support vector machine.

PubMed

Zhang, Yanjun; Zhang, Xiangmin; Liu, Wenhui; Luo, Yuxi; Yu, Enjia; Zou, Keju; Liu, Xiaoliang

2014-01-01

This paper employed the clinical Polysomnographic (PSG) data, mainly including all-night Electroencephalogram (EEG), Electrooculogram (EOG) and Electromyogram (EMG) signals of subjects, and adopted the American Academy of Sleep Medicine (AASM) clinical staging manual as standards to realize automatic sleep staging. Authors extracted eighteen different features of EEG, EOG and EMG in time domains and frequency domains to construct the vectors according to the existing literatures as well as clinical experience. By adopting sleep samples self-learning, the linear combination of weights and parameters of multiple kernels of the fuzzy support vector machine (FSVM) were learned and the multi-kernel FSVM (MK-FSVM) was constructed. The overall agreement between the experts' scores and the results presented was 82.53%. Compared with previous results, the accuracy of N1 was improved to some extent while the accuracies of other stages were approximate, which well reflected the sleep structure. The staging algorithm proposed in this paper is transparent, and worth further investigation.

Technology-Rich Learning Environments in Elementary and Secondary Schools: An Interactive Study of Physical Settings and Educational Change.

ERIC Educational Resources Information Center

Stuebing, Susan; And Others

This paper reviews an ongoing study on the physical settings of education with technology at the elementary and high school levels. The study, which is multi-disciplinary in nature, is based in sites in the process of change in teaching strategies, using learning technology as a catalyst for this change to take place. The focus of the study is on…

The Effects of Learning Strategies on Mathematical Literacy: A Comparison between Lower and Higher Achieving Countries

ERIC Educational Resources Information Center

Magen-Nagar, Noga

2016-01-01

The purpose of the current study is to explore the effects of learning strategies on Mathematical Literacy (ML) of students in higher and lower achieving countries. To address this issue, the study utilizes PISA2002 data to conduct a multi-level analysis (HLM) of Hong Kong and Israel students. In PISA2002, Israel was rated 31st in Mathematics,…

Mapping groundwater contamination risk of multiple aquifers using multi-model ensemble of machine learning algorithms.

PubMed

Barzegar, Rahim; Moghaddam, Asghar Asghari; Deo, Ravinesh; Fijani, Elham; Tziritis, Evangelos

2018-04-15

Constructing accurate and reliable groundwater risk maps provide scientifically prudent and strategic measures for the protection and management of groundwater. The objectives of this paper are to design and validate machine learning based-risk maps using ensemble-based modelling with an integrative approach. We employ the extreme learning machines (ELM), multivariate regression splines (MARS), M5 Tree and support vector regression (SVR) applied in multiple aquifer systems (e.g. unconfined, semi-confined and confined) in the Marand plain, North West Iran, to encapsulate the merits of individual learning algorithms in a final committee-based ANN model. The DRASTIC Vulnerability Index (VI) ranged from 56.7 to 128.1, categorized with no risk, low and moderate vulnerability thresholds. The correlation coefficient (r) and Willmott's Index (d) between NO 3 concentrations and VI were 0.64 and 0.314, respectively. To introduce improvements in the original DRASTIC method, the vulnerability indices were adjusted by NO 3 concentrations, termed as the groundwater contamination risk (GCR). Seven DRASTIC parameters utilized as the model inputs and GCR values utilized as the outputs of individual machine learning models were served in the fully optimized committee-based ANN-predictive model. The correlation indicators demonstrated that the ELM and SVR models outperformed the MARS and M5 Tree models, by virtue of a larger d and r value. Subsequently, the r and d metrics for the ANN-committee based multi-model in the testing phase were 0.8889 and 0.7913, respectively; revealing the superiority of the integrated (or ensemble) machine learning models when compared with the original DRASTIC approach. The newly designed multi-model ensemble-based approach can be considered as a pragmatic step for mapping groundwater contamination risks of multiple aquifer systems with multi-model techniques, yielding the high accuracy of the ANN committee-based model. Copyright © 2017 Elsevier B.V. All rights reserved.

Professional Learning Communities Focusing on Results and Data-Use to Improve Student Learning: The Right Implementation Matters

ERIC Educational Resources Information Center

Muñoz, Marco A.; Branham, Karen E.

2016-01-01

Professional Learning Communities are an important means toward the goal of improving schools so that students can learn at high levels. Professional Learning Communities, when well-implemented, have a laser-focus on learning, work collaboratively, and hold themselves accountable for results. In this article, the central concept of…

Genistein improves spatial learning and memory in male rats with elevated glucose level during memory consolidation.

PubMed

Kohara, Yumi; Kawaguchi, Shinichiro; Kuwahara, Rika; Uchida, Yutaro; Oku, Yushi; Yamashita, Kimihiro

2015-03-01

Cognitive dysfunction due to higher blood glucose level has been reported previously. Genistein (GEN) is a phytoestrogen that we hypothesized might lead to improved memory, despite elevated blood glucose levels at the time of memory consolidation. To investigate this hypothesis, we compared the effects of orally administered GEN on the central nervous system in normal versus glucose-loaded adult male rats. A battery of behavioral assessments was carried out. In the MAZE test, which measured spatial learning and memory, the time of normal rats was shortened by GEN treatment compared to the vehicle group, but only in the early stages of testing. In the glucose-loaded group, GEN treatment improved performance as mazes were advanced. In the open-field test, GEN treatment delayed habituation to the new environment in normal rats, and increased the exploratory behaviors of glucose-loaded rats. There were no significant differences observed for emotionality or fear-motivated learning and memory. Together, these results indicate that GEN treatment improved spatial learning and memory only in the early stages of testing in the normal state, but improved spatial learning and memory when glucose levels increased during memory consolidation. Copyright © 2014 Elsevier Inc. All rights reserved.

Optimal control in microgrid using multi-agent reinforcement learning.

PubMed

Li, Fu-Dong; Wu, Min; He, Yong; Chen, Xin

2012-11-01

This paper presents an improved reinforcement learning method to minimize electricity costs on the premise of satisfying the power balance and generation limit of units in a microgrid with grid-connected mode. Firstly, the microgrid control requirements are analyzed and the objective function of optimal control for microgrid is proposed. Then, a state variable "Average Electricity Price Trend" which is used to express the most possible transitions of the system is developed so as to reduce the complexity and randomicity of the microgrid, and a multi-agent architecture including agents, state variables, action variables and reward function is formulated. Furthermore, dynamic hierarchical reinforcement learning, based on change rate of key state variable, is established to carry out optimal policy exploration. The analysis shows that the proposed method is beneficial to handle the problem of "curse of dimensionality" and speed up learning in the unknown large-scale world. Finally, the simulation results under JADE (Java Agent Development Framework) demonstrate the validity of the presented method in optimal control for a microgrid with grid-connected mode. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.

The Implementation of Levels of Inquiry With Writing-To-Learn Assignment To Improve Vocational School Student’s Science Literacy

NASA Astrophysics Data System (ADS)

Amarulloh, R. R.; Utari, S.; Feranie, S.

2017-02-01

The aim of this study was to investigate the effectiveness of writing-to-learn assignment in a levels of inquiry learning to improve vocational school student’s science literacy competence and knowledge on the subject of temperature and heat. This study used quasi experiment research methods. The data were obtained using 16 item of science literacy instrument with essay format. The result shows that there was a significant difference on the improvement of science literacy ability between the experimental class and control class. A significant difference occurred in the evaluating and designing experiments competency, interpretating data and science evidence competency, and procedural knowledge. Therefore it can be concluded that the implementation of levels of inquiry with writing-to-learn assignment can improve vocational student’s science literacy competence and knowledge.

A multi-group firefly algorithm for numerical optimization

NASA Astrophysics Data System (ADS)

Tong, Nan; Fu, Qiang; Zhong, Caiming; Wang, Pengjun

2017-08-01

To solve the problem of premature convergence of firefly algorithm (FA), this paper analyzes the evolution mechanism of the algorithm, and proposes an improved Firefly algorithm based on modified evolution model and multi-group learning mechanism (IMGFA). A Firefly colony is divided into several subgroups with different model parameters. Within each subgroup, the optimal firefly is responsible for leading the others fireflies to implement the early global evolution, and establish the information mutual system among the fireflies. And then, each firefly achieves local search by following the brighter firefly in its neighbors. At the same time, learning mechanism among the best fireflies in various subgroups to exchange information can help the population to obtain global optimization goals more effectively. Experimental results verify the effectiveness of the proposed algorithm.

Organizational determinants of evaluation practice in Australian prevention agencies.

PubMed

Schwarzman, J; Bauman, A; Gabbe, B; Rissel, C; Shilton, T; Smith, B J

2018-06-01

Program evaluation is essential to inform decision making, contribute to the evidence base for strategies, and facilitate learning in health promotion and disease prevention organizations. Theoretical frameworks of organizational learning, and studies of evaluation capacity building describe the organization as central to evaluation capacity. Australian prevention organizations recognize limitations to current evaluation effectiveness and are seeking guidance to build evaluation capacity. This qualitative study identifies organizational facilitators and barriers to evaluation practice, and explores their interactions in Australian prevention organizations. We conducted semi-structured interviews with 40 experienced practitioners from government and non-government organizations. Using thematic analysis, we identified seven key themes that influence evaluation practice: leadership, organizational culture, organizational systems and structures, partnerships, resources, workforce development and training and recruitment and skills mix. We found organizational determinants of evaluation to have multi-level interactions. Leadership and organizational culture influenced organizational systems, resource allocation and support of staff. Partnerships were important to overcome resource deficits, and systems were critical to embed evaluation within the organization. Organizational factors also influenced the opportunities for staff to develop skills and confidence. We argue that investment to improve these factors would allow organizations to address evaluation capacity at multiple levels, and ultimately facilitate effective evaluation practice.

Improving the social and emotional climate of classrooms: a clustered randomized controlled trial testing the RULER Approach.

PubMed

Rivers, Susan E; Brackett, Marc A; Reyes, Maria R; Elbertson, Nicole A; Salovey, Peter

2013-02-01

The RULER Approach ("RULER") is a setting-level, social and emotional learning program that is grounded in theory and evidence. RULER is designed to modify the quality of classroom social interactions so that the climate becomes more supportive, empowering, and engaging. This is accomplished by integrating skill-building lessons and tools so that teachers and students develop their emotional literacy. In a clustered randomized control trial, we tested the hypothesis that RULER improves the social and emotional climate of classrooms. Depending upon condition assignment, 62 schools either integrated RULER into fifth- and sixth-grade English language arts (ELA) classrooms or served as comparison schools, using their standard ELA curriculum only. Multi-level modeling analyses showed that compared to classrooms in comparison schools, classrooms in RULER schools were rated as having higher degrees of warmth and connectedness between teachers and students, more autonomy and leadership among students, and teachers who focused more on students' interests and motivations. These findings suggest that RULER enhances classrooms in ways that can promote positive youth development.

Functional consequences of experience-dependent plasticity on tactile perception following perceptual learning.

PubMed

Trzcinski, Natalie K; Gomez-Ramirez, Manuel; Hsiao, Steven S

2016-09-01

Continuous training enhances perceptual discrimination and promotes neural changes in areas encoding the experienced stimuli. This type of experience-dependent plasticity has been demonstrated in several sensory and motor systems. Particularly, non-human primates trained to detect consecutive tactile bar indentations across multiple digits showed expanded excitatory receptive fields (RFs) in somatosensory cortex. However, the perceptual implications of these anatomical changes remain undetermined. Here, we trained human participants for 9 days on a tactile task that promoted expansion of multi-digit RFs. Participants were required to detect consecutive indentations of bar stimuli spanning multiple digits. Throughout the training regime we tracked participants' discrimination thresholds on spatial (grating orientation) and temporal tasks on the trained and untrained hands in separate sessions. We hypothesized that training on the multi-digit task would decrease perceptual thresholds on tasks that require stimulus processing across multiple digits, while also increasing thresholds on tasks requiring discrimination on single digits. We observed an increase in orientation thresholds on a single digit. Importantly, this effect was selective for the stimulus orientation and hand used during multi-digit training. We also found that temporal acuity between digits improved across trained digits, suggesting that discriminating the temporal order of multi-digit stimuli can transfer to temporal discrimination of other tactile stimuli. These results suggest that experience-dependent plasticity following perceptual learning improves and interferes with tactile abilities in manners predictive of the task and stimulus features used during training. © 2016 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

Functional consequences of experience-dependent plasticity on tactile perception following perceptual learning

PubMed Central

Trzcinski, Natalie K; Gomez-Ramirez, Manuel; Hsiao, Steven S.

2016-01-01

Continuous training enhances perceptual discrimination and promotes neural changes in areas encoding the experienced stimuli. This type of experience-dependent plasticity has been demonstrated in several sensory and motor systems. Particularly, non-human primates trained to detect consecutive tactile bar indentations across multiple digits showed expanded excitatory receptive fields (RFs) in somatosensory cortex. However, the perceptual implications of these anatomical changes remain undetermined. Here, we trained human participants for nine days on a tactile task that promoted expansion of multi-digit RFs. Participants were required to detect consecutive indentations of bar stimuli spanning multiple digits. Throughout the training regime we tracked participants’ discrimination thresholds on spatial (grating orientation) and temporal tasks on the trained and untrained hands in separate sessions. We hypothesized that training on the multi-digit task would decrease perceptual thresholds on tasks that require stimulus processing across multiple digits, while also increasing thresholds on tasks requiring discrimination on single digits. We observed an increase in orientation thresholds on a single-digit. Importantly, this effect was selective for the stimulus orientation and hand used during multi-digit training. We also found that temporal acuity between digits improved across trained digits, suggesting that discriminating the temporal order of multi-digit stimuli can transfer to temporal discrimination of other tactile stimuli. These results suggest that experience-dependent plasticity following perceptual learning improves and interferes with tactile abilities in manners predictive of the task and stimulus features used during training. PMID:27422224

The Moderating Effect of Health-Improving Workplace Environment on Promoting Physical Activity in White-Collar Employees: A Multi-Site Longitudinal Study Using Multi-Level Structural Equation Modeling.

PubMed

Watanabe, Kazuhiro; Otsuka, Yasumasa; Shimazu, Akihito; Kawakami, Norito

2016-02-01

This longitudinal study aimed to investigate the moderating effect of health-improving workplace environment on relationships between physical activity, self-efficacy, and psychological distress. Data were collected from 16 worksites and 129 employees at two time-points. Health-improving workplace environment was measured using the Japanese version of the Environmental Assessment Tool. Physical activity, self-efficacy, and psychological distress were also measured. Multi-level structural equation modeling was used to investigate the moderating effect of health-improving workplace environment on relationships between psychological distress, self-efficacy, and physical activity. Psychological distress was negatively associated with physical activity via low self-efficacy. Physical activity was negatively related to psychological distress. Physical activity/fitness facilities in the work environment exaggerated the positive relationship between self-efficacy and physical activity. Physical activity/fitness facilities in the workplace may promote employees' physical activity.

PhET Interactive Simulations: Transformative Tools for Teaching Chemistry

ERIC Educational Resources Information Center

Moore, Emily B.; Chamberlain, Julia M.; Parson, Robert; Perkins, Katherine K.

2014-01-01

Developing fluency across symbolic-, macroscopic-, and particulate-level representations is central to learning chemistry. Within the chemistry education community, animations and simulations that support multi-representational fluency are considered critical. With advances in the accessibility and sophistication of technology,…

Multi-Dimensional Parental Involvement in Schools: A Principal's Guide

ERIC Educational Resources Information Center

Rapp, Nicole; Duncan, Heather

2012-01-01

Parental involvement is an important indicator of students' success in school. When schools engage families in a manner connected to improving learning, students do make greater gains. Creating and implementing an effective parental involvement model is an essential component in increasing student achievement in school. This article addresses the…

Study on the Implementation of Interaction Teaching Mode in Distance Education

ERIC Educational Resources Information Center

Zhou, Chunyu; Xu, Zhenhui

2015-01-01

By analyzing the learning characteristics of learners and the features of interactive teaching in distance education, this paper proposes the curriculum implementation subject of network education, namely objects multi-directional interaction teaching mode, so as to improve teaching effectiveness and achieve teaching objectives to ensure the…

Cardiovascular Event Prediction by Machine Learning: The Multi-Ethnic Study of Atherosclerosis.

PubMed

Ambale-Venkatesh, Bharath; Yang, Xiaoying; Wu, Colin O; Liu, Kiang; Hundley, W Gregory; McClelland, Robyn; Gomes, Antoinette S; Folsom, Aaron R; Shea, Steven; Guallar, Eliseo; Bluemke, David A; Lima, João A C

2017-10-13

Machine learning may be useful to characterize cardiovascular risk, predict outcomes, and identify biomarkers in population studies. To test the ability of random survival forests, a machine learning technique, to predict 6 cardiovascular outcomes in comparison to standard cardiovascular risk scores. We included participants from the MESA (Multi-Ethnic Study of Atherosclerosis). Baseline measurements were used to predict cardiovascular outcomes over 12 years of follow-up. MESA was designed to study progression of subclinical disease to cardiovascular events where participants were initially free of cardiovascular disease. All 6814 participants from MESA, aged 45 to 84 years, from 4 ethnicities, and 6 centers across the United States were included. Seven-hundred thirty-five variables from imaging and noninvasive tests, questionnaires, and biomarker panels were obtained. We used the random survival forests technique to identify the top-20 predictors of each outcome. Imaging, electrocardiography, and serum biomarkers featured heavily on the top-20 lists as opposed to traditional cardiovascular risk factors. Age was the most important predictor for all-cause mortality. Fasting glucose levels and carotid ultrasonography measures were important predictors of stroke. Coronary Artery Calcium score was the most important predictor of coronary heart disease and all atherosclerotic cardiovascular disease combined outcomes. Left ventricular structure and function and cardiac troponin-T were among the top predictors for incident heart failure. Creatinine, age, and ankle-brachial index were among the top predictors of atrial fibrillation. TNF-α (tissue necrosis factor-α) and IL (interleukin)-2 soluble receptors and NT-proBNP (N-Terminal Pro-B-Type Natriuretic Peptide) levels were important across all outcomes. The random survival forests technique performed better than established risk scores with increased prediction accuracy (decreased Brier score by 10%-25%). Machine learning in conjunction with deep phenotyping improves prediction accuracy in cardiovascular event prediction in an initially asymptomatic population. These methods may lead to greater insights on subclinical disease markers without apriori assumptions of causality. URL: http://www.clinicaltrials.gov. Unique identifier: NCT00005487. © 2017 American Heart Association, Inc.

Learning Design for Creating a Lifelong Learning Organization

NASA Astrophysics Data System (ADS)

Widmark, Ulla; Koroma, Eeva

Our learning design for lifelong learning has been developed during the past ten years at the Teacher Education unit at Stockholm University. The same design but with different content has been used to higher the competence of different target groups; teachers in the field, policemen, medical personal, headmasters etc. As an example we will present our learning design for the course “Steps for Skills” which was a government appointed, multi-year national initiative to support municipalities’ long-term quality and skills development in health and social care for older people. The purpose of the Steps for Skills was to improve the internal quality of health and social care. This was to be achieved by developing the skills of the staff working close to older people.

A map of community-based obesity prevention initiatives in Australia following obesity funding 2009–2013

PubMed Central

Whelan, Jillian; Love, Penny; Romanus, Anne; Pettman, Tahna; Bolton, Kristy; Smith, Erin; Gill, Tim; Coveney, John; Waters, Elizabeth; Allender, Steve

2015-01-01

Abstract Objective: Obesity is the single biggest public health threat to developed and developing economies. In concert with healthy public policy, multi-strategy, multi-level community-based initiatives appear promising in preventing obesity, with several countries trialling this approach. In Australia, multiple levels of government have funded and facilitated a range of community-based obesity prevention initiatives (CBI), heterogeneous in their funding, timing, target audience and structure. This paper aims to present a central repository of CBI operating in Australia during 2013, to facilitate knowledge exchange and shared opportunities for learning, and to guide professional development towards best practice for CBI practitioners. Methods: A comprehensive search of government, non-government and community websites was undertaken to identify CBI in Australia in 2013. This was supplemented with data drawn from available reports, personal communication and key informant interviews. The data was translated into an interactive map for use by preventive health practitioners and other parties. Results: We identified 259 CBI; with the majority (84%) having a dual focus on physical activity and healthy eating. Few initiatives, (n=37) adopted a four-pronged multi-strategy approach implementing policy, built environment, social marketing and/or partnership building. Conclusion: This comprehensive overview of Australian CBI has the potential to facilitate engagement and collaboration through knowledge exchange and information sharing amongst CBI practitioners, funders, communities and researchers. Implications: An enhanced understanding of current practice highlights areas of strengths and opportunities for improvement to maximise the impact of obesity prevention initiatives. PMID:25561083

A map of community-based obesity prevention initiatives in Australia following obesity funding 2009-2013.

PubMed

Whelan, Jillian; Love, Penny; Romanus, Anne; Pettman, Tahna; Bolton, Kristy; Smith, Erin; Gill, Tim; Coveney, John; Waters, Elizabeth; Allender, Steve

2015-04-01

Obesity is the single biggest public health threat to developed and developing economies. In concert with healthy public policy, multi-strategy, multi-level community-based initiatives appear promising in preventing obesity, with several countries trialling this approach. In Australia, multiple levels of government have funded and facilitated a range of community-based obesity prevention initiatives (CBI), heterogeneous in their funding, timing, target audience and structure. This paper aims to present a central repository of CBI operating in Australia during 2013, to facilitate knowledge exchange and shared opportunities for learning, and to guide professional development towards best practice for CBI practitioners. A comprehensive search of government, non-government and community websites was undertaken to identify CBI in Australia in 2013. This was supplemented with data drawn from available reports, personal communication and key informant interviews. The data was translated into an interactive map for use by preventive health practitioners and other parties. We identified 259 CBI; with the majority (84%) having a dual focus on physical activity and healthy eating. Few initiatives, (n=37) adopted a four-pronged multi-strategy approach implementing policy, built environment, social marketing and/or partnership building. This comprehensive overview of Australian CBI has the potential to facilitate engagement and collaboration through knowledge exchange and information sharing amongst CBI practitioners, funders, communities and researchers. An enhanced understanding of current practice highlights areas of strengths and opportunities for improvement to maximise the impact of obesity prevention initiatives. © 2015 Public Health Association of Australia.

Concurrent Learning of Control in Multi agent Sequential Decision Tasks

DTIC Science & Technology

2018-04-17

Concurrent Learning of Control in Multi-agent Sequential Decision Tasks The overall objective of this project was to develop multi-agent reinforcement...learning (MARL) approaches for intelligent agents to autonomously learn distributed control policies in decentral- ized partially observable...shall be subject to any oenalty for failing to comply with a collection of information if it does not display a currently valid OMB control number

Return of the Pig: Standards for Learning Improvement

ERIC Educational Resources Information Center

Fulcher, Keston H.; Smith, Kristen L.; Sanchez, Elizabeth R. H.; Ames, Allison J.; Meixner, Cara

2017-01-01

Higher education has made impressive progress concerning student learning outcomes assessment practices. Yet--despite the assumption that better assessment would lead to better student learning--few examples of demonstrable student learning improvement exist at the academic degree or university levels. In 2014 Fulcher, Good, Coleman, and Smith…

Continuous professional development of Liberia's midwifery workforce-A coordinated multi-stakeholder approach.

PubMed

Michel-Schuldt, Michaela; Billy Dayon, Matilda; Toft Klar, Robin; Subah, Marion; King-Lincoln, Esther; Kpangbala-Flomo, Cecelia; Broniatowski, Raphaël

2018-03-03

Maternal and newborn mortality remains high in Liberia. There is a severe rural-urban gap in accessibility to health care services. A competent midwifery workforce is able to meet the needs of mothers and newborns. Evidence shows that competence can be assured through initial education along with continuous professional development (CPD). In the past, CPD was not regulated and coordinated in Liberia which is cpommon in the African region. To Support a competent regulated midwifery workforce through continuous professional development. A new CPD model was developed by the Liberian Board for Nursing and Midwifery. With its establishment, all midwives and nurses are required to undertake CPD programmes consisting of certified training and mentoring in order to renew their practicing license. The new model is being piloted in one county in which regular mentoring visits that include skills training are being conducted combined with the use of mobile learning applications addressing maternity health issues. Quality control of the CPD pilot is assured by the Liberian Board for Nursing and Midwifery. The mentoring visits are conducted on a clinical level but are coordinated on the national and county level. CPD using mobile learning on smartphones and regular mentoring visits not only improved knowledge and skills of midwives and nurses but also provided a solution to enhance accessibility in rural areas through improved communication and transportation, as well as improved career development of health personnel working in remote areas. Mentors were trained on a national, county, and health facility level in the pilot county with mentoring visits conducted regularly. The CPD programme of the Liberian Board for Nursing and Midwifery, currently in pilot-testing by various partners, aims to highlight the positive impact of the coordinating role of both the regulatory body and health authorities. Using regular process and programme reviews to improve capacity, knowledge, and skills of health professionals. Copyright © 2018 Elsevier Ltd. All rights reserved.

Learning new sequential stepping patterns requires striatal plasticity during the earliest phase of acquisition.

PubMed

Nakamura, Toru; Nagata, Masatoshi; Yagi, Takeshi; Graybiel, Ann M; Yamamori, Tetsuo; Kitsukawa, Takashi

2017-04-01

Animals including humans execute motor behavior to reach their goals. For this purpose, they must choose correct strategies according to environmental conditions and shape many parameters of their movements, including their serial order and timing. To investigate the neurobiology underlying such skills, we used a multi-sensor equipped, motor-driven running wheel with adjustable sequences of foothold pegs on which mice ran to obtain water reward. When the peg patterns changed from a familiar pattern to a new pattern, the mice had to learn and implement new locomotor strategies in order to receive reward. We found that the accuracy of stepping and the achievement of water reward improved with the new learning after changes in the peg-pattern, and c-Fos expression levels assayed after the first post-switch session were high in both dorsolateral striatum and motor cortex, relative to post-switch plateau levels. Combined in situ hybridization and immunohistochemistry of striatal sections demonstrated that both enkephalin-positive (indirect pathway) neurons and substance P-positive (direct pathway) neurons were recruited specifically after the pattern switches, as were interneurons expressing neuronal nitric oxide synthase. When we blocked N-methyl-D-aspartate (NMDA) receptors in the dorsolateral striatum by injecting the NMDA receptor antagonist, D-2-amino-5-phosphonopentanoic acid (AP5), we found delays in early post-switch improvement in performance. These findings suggest that the dorsolateral striatum is activated on detecting shifts in environment to adapt motor behavior to the new context via NMDA-dependent plasticity, and that this plasticity may underlie forming and breaking skills and habits as well as to behavioral difficulties in clinical disorders. © 2017 Federation of European Neuroscience Societies and John Wiley & Sons Ltd.

Effects of a case-based interactive e-learning course on knowledge and attitudes about patient safety: a quasi-experimental study with third-year medical students.

PubMed

Gaupp, Rainer; Körner, Mirjam; Fabry, Götz

2016-07-11

Patient safety (PS) is influenced by a set of factors on various levels of the healthcare system. Therefore, a systems-level approach and systems thinking is required to understand and improve PS. The use of e-learning may help to develop a systems thinking approach in medical students, as case studies featuring audiovisual media can be used to visualize systemic relationships in organizations. The goal of this quasi-experimental study was to determine if an e-learning can be utilized to improve systems thinking, knowledge, and attitudes towards PS. A quasi-experimental, longitudinal within- subjects design was employed. Participants were 321 third-year medical students who received online surveys before and after they participated in an e-learning course on PS. Primary outcome measures where levels of systems thinking and attitudes towards PS. Secondary outcome measures were the improvement of PS specific knowledge through the e-learning course. Levels of systems thinking showed significant improvement (58.72 vs. 61.27; p < .001) after the e-learning. Student's attitudes towards patient safety improved in several dimensions: After the course, students rated the influence of fatigue on safety higher (6.23 vs. 6.42, p < .01), considered patient empowerment more important (5.16 vs. 5.93, p < .001) and realized more often that human error is inevitable (5.75 vs. 5.97, p < .05). Knowledge on PS improved from 36.27 % correct answers before to 76.45 % after the e-learning (p < .001). Our results suggest that e-learning can be used to teach PS. Attitudes towards PS improved on several dimensions. Furthermore, we were able to demonstrate that a specifically designed e-learning program can foster the development of conceptual frameworks such as systems thinking, which facilitates the understanding of complex socio-technical systems within healthcare organisations.

Functioning information in the learning health system.

PubMed

Stucki, Gerold; Bickenbach, Jerome

2017-02-01

In this methodological note on applying the ICF in rehabilitation, we introduce functioning information as fundamental for the "learning health system" and the continuous improvement of the health system's response to people's functioning needs by means of the provision of rehabilitation. A learning health system for rehabilitation operates at the micro-level of the individual patient, meso-level of operational management, and the macro-level of policy that guides rehabilitation programming. All three levels rely on the capacity of the informational system of the health system for standardized documentation and coding of functioning information, and the development of national rehabilitation quality management systems. This methodological note describes how functioning information is used for the continuous improvement of functioning outcomes in a learning health system across these three levels.

Multi-scale heat and mass transfer modelling of cell and tissue cryopreservation

PubMed Central

Xu, Feng; Moon, Sangjun; Zhang, Xiaohui; Shao, Lei; Song, Young Seok; Demirci, Utkan

2010-01-01

Cells and tissues undergo complex physical processes during cryopreservation. Understanding the underlying physical phenomena is critical to improve current cryopreservation methods and to develop new techniques. Here, we describe multi-scale approaches for modelling cell and tissue cryopreservation including heat transfer at macroscale level, crystallization, cell volume change and mass transport across cell membranes at microscale level. These multi-scale approaches allow us to study cell and tissue cryopreservation. PMID:20047939

Smart-system of distance learning of visually impaired people based on approaches of artificial intelligence

NASA Astrophysics Data System (ADS)

Samigulina, Galina A.; Shayakhmetova, Assem S.

2016-11-01

Research objective is the creation of intellectual innovative technology and information Smart-system of distance learning for visually impaired people. The organization of the available environment for receiving quality education for visually impaired people, their social adaptation in society are important and topical issues of modern education.The proposed Smart-system of distance learning for visually impaired people can significantly improve the efficiency and quality of education of this category of people. The scientific novelty of proposed Smart-system is using intelligent and statistical methods of processing multi-dimensional data, and taking into account psycho-physiological characteristics of perception and awareness learning information by visually impaired people.

Artificial vision by multi-layered neural networks: neocognitron and its advances.

PubMed

Fukushima, Kunihiko

2013-01-01

The neocognitron is a neural network model proposed by Fukushima (1980). Its architecture was suggested by neurophysiological findings on the visual systems of mammals. It is a hierarchical multi-layered network. It acquires the ability to robustly recognize visual patterns through learning. Although the neocognitron has a long history, modifications of the network to improve its performance are still going on. For example, a recent neocognitron uses a new learning rule, named add-if-silent, which makes the learning process much simpler and more stable. Nevertheless, a high recognition rate can be kept with a smaller scale of the network. Referring to the history of the neocognitron, this paper discusses recent advances in the neocognitron. We also show that various new functions can be realized by, for example, introducing top-down connections to the neocognitron: mechanism of selective attention, recognition and completion of partly occluded patterns, restoring occluded contours, and so on. Copyright © 2012 Elsevier Ltd. All rights reserved.

Interaction Design and Usability of Learning Spaces in 3D Multi-user Virtual Worlds

NASA Astrophysics Data System (ADS)

Minocha, Shailey; Reeves, Ahmad John

Three-dimensional virtual worlds are multimedia, simulated environments, often managed over the Web, which users can 'inhabit' and interact via their own graphical, self-representations known as 'avatars'. 3D virtual worlds are being used in many applications: education/training, gaming, social networking, marketing and commerce. Second Life is the most widely used 3D virtual world in education. However, problems associated with usability, navigation and way finding in 3D virtual worlds may impact on student learning and engagement. Based on empirical investigations of learning spaces in Second Life, this paper presents design guidelines to improve the usability and ease of navigation in 3D spaces. Methods of data collection include semi-structured interviews with Second Life students, educators and designers. The findings have revealed that design principles from the fields of urban planning, Human- Computer Interaction, Web usability, geography and psychology can influence the design of spaces in 3D multi-user virtual environments.

Developing Expert System for Tuberculosis Diagnose to Support Knowledge Sharing in the Era of National Health Insurance System

NASA Astrophysics Data System (ADS)

Lidya, L.

2017-03-01

National Health Insurance has been implemented since 1st January 2014. A number of new policies have been established including multilevel referral system. The multilevel referral system classified health care center into three levels, it determined that the flow of patient treatment should be started from first level health care center. There are 144 kind of diseases that must be treat in the first level which mainly consists of general physicians. Unfortunately, competence of the physician in the first level may not fulfil the standard competence yet. To improved the physisians knowledge, government has created many events to accelerate knowledge sharing. However, it still needs times and many resources to give significan results. Expert system is kind of software that provide consulting services to non-expert users in accordance with the area of its expertise. It can improved effectivity and efficiency of knowledge sharing and learning. This research was developed a model of TB diagnose expert system which comply with the standard procedure of TB diagnosis and regulation. The proposed expert system has characteristics as follows provide facility to manage multimedia clinical data, supporting the complexity of TB diagnosis (combine rule-based and case-based expert system), interactive interface, good usability, multi-platform, evolutionary.

Principles to Products: Toward Realizing MOS 2.0

NASA Technical Reports Server (NTRS)

Bindschadler, Duane L.; Delp, Christopher L.

2012-01-01

This is a report on the Operations Revitalization Initiative, part of the ongoing NASA-funded Advanced Multi-Mission Operations Systems (AMMOS) program. We are implementing products that significantly improve efficiency and effectiveness of Mission Operations Systems (MOS) for deep-space missions. We take a multi-mission approach, in keeping with our organization's charter to "provide multi-mission tools and services that enable mission customers to operate at a lower total cost to NASA." Focusing first on architectural fundamentals of the MOS, we review the effort's progress. In particular, we note the use of stakeholder interactions and consideration of past lessons learned to motivate a set of Principles that guide the evolution of the AMMOS. Thus guided, we have created essential patterns and connections (detailed in companion papers) that are explicitly modeled and support elaboration at multiple levels of detail (system, sub-system, element...) throughout a MOS. This architecture is realized in design and implementation products that provide lifecycle support to a Mission at the system and subsystem level. The products include adaptable multi-mission engineering documentation that describes essentials such as operational concepts and scenarios, requirements, interfaces and agreements, information models, and mission operations processes. Because we have adopted a model-based system engineering method, these documents and their contents are meaningfully related to one another and to the system model. This means they are both more rigorous and reusable (from mission to mission) than standard system engineering products. The use of models also enables detailed, early (e.g., formulation phase) insight into the impact of changes (e.g., to interfaces or to software) that is rigorous and complete, allowing better decisions on cost or technical trades. Finally, our work provides clear and rigorous specification of operations needs to software developers, further enabling significant gains in productivity.

Modeling of BN Lifetime Prediction of a System Based on Integrated Multi-Level Information

PubMed Central

Wang, Xiaohong; Wang, Lizhi

2017-01-01

Predicting system lifetime is important to ensure safe and reliable operation of products, which requires integrated modeling based on multi-level, multi-sensor information. However, lifetime characteristics of equipment in a system are different and failure mechanisms are inter-coupled, which leads to complex logical correlations and the lack of a uniform lifetime measure. Based on a Bayesian network (BN), a lifetime prediction method for systems that combine multi-level sensor information is proposed. The method considers the correlation between accidental failures and degradation failure mechanisms, and achieves system modeling and lifetime prediction under complex logic correlations. This method is applied in the lifetime prediction of a multi-level solar-powered unmanned system, and the predicted results can provide guidance for the improvement of system reliability and for the maintenance and protection of the system. PMID:28926930

Modeling of BN Lifetime Prediction of a System Based on Integrated Multi-Level Information.

PubMed

Wang, Jingbin; Wang, Xiaohong; Wang, Lizhi

2017-09-15

Predicting system lifetime is important to ensure safe and reliable operation of products, which requires integrated modeling based on multi-level, multi-sensor information. However, lifetime characteristics of equipment in a system are different and failure mechanisms are inter-coupled, which leads to complex logical correlations and the lack of a uniform lifetime measure. Based on a Bayesian network (BN), a lifetime prediction method for systems that combine multi-level sensor information is proposed. The method considers the correlation between accidental failures and degradation failure mechanisms, and achieves system modeling and lifetime prediction under complex logic correlations. This method is applied in the lifetime prediction of a multi-level solar-powered unmanned system, and the predicted results can provide guidance for the improvement of system reliability and for the maintenance and protection of the system.

E-Learning Capability Maturity Level in Kingdom of Bahrain

ERIC Educational Resources Information Center

Al-Ammary, Jaflah; Mohammed, Zainab; Omran, Fatima

2016-01-01

Despite the effectiveness of using e-learning, educational institutions are still facing many challenges with the e-learning infrastructure and technical aspects, practices and capabilities, and improvement in learning outcome. Hence, a need for framework to benchmark the e-learning capability maturity level and measure the extent to what it is…

Multi-instance multi-label distance metric learning for genome-wide protein function prediction.

PubMed

Xu, Yonghui; Min, Huaqing; Song, Hengjie; Wu, Qingyao

2016-08-01

Multi-instance multi-label (MIML) learning has been proven to be effective for the genome-wide protein function prediction problems where each training example is associated with not only multiple instances but also multiple class labels. To find an appropriate MIML learning method for genome-wide protein function prediction, many studies in the literature attempted to optimize objective functions in which dissimilarity between instances is measured using the Euclidean distance. But in many real applications, Euclidean distance may be unable to capture the intrinsic similarity/dissimilarity in feature space and label space. Unlike other previous approaches, in this paper, we propose to learn a multi-instance multi-label distance metric learning framework (MIMLDML) for genome-wide protein function prediction. Specifically, we learn a Mahalanobis distance to preserve and utilize the intrinsic geometric information of both feature space and label space for MIML learning. In addition, we try to deal with the sparsely labeled data by giving weight to the labeled data. Extensive experiments on seven real-world organisms covering the biological three-domain system (i.e., archaea, bacteria, and eukaryote; Woese et al., 1990) show that the MIMLDML algorithm is superior to most state-of-the-art MIML learning algorithms. Copyright © 2016 Elsevier Ltd. All rights reserved.

Illustrating performance indicators and course characteristics to support students' self-regulated learning in CS1

NASA Astrophysics Data System (ADS)

Ott, Claudia; Robins, Anthony; Haden, Patricia; Shephard, Kerry

2015-04-01

In higher education, quality feedback for students is regarded as one of the main contributors to improve student learning. Feedback to support students' development into self-regulated learners, who set their own goals, self-monitor their actual performance according to these goals, and adjust learning strategies if necessary, is seen as an important aspect of contemporary feedback practice. However, only those students who are aware of the course demands and the impact of certain study behaviors on their final achievement are in a position to self-regulate their learning on an informed basis. Learning analytics is an emerging field primarily concerned with using predictive models to inform educational instructors or learners about projected study outcomes. In a scoping study, over 200 students of an introductory programming course (CS1) were supplied with information revealing performance indicators for different stages on the course and projecting final performance for various achievement levels. The study was set out to explore the impact of this type of feedback in the confined context of a CS1 course as well as to learn about students' attitudes toward diagnostic course data in general. The results from the study suggest that students valued the information, but, despite high engagement with the information, students' study behavior and learning outcome remained rather unaffected for the aspects investigated. Given these multi-layered results, we suggest further exploration on the provision of feedback based on diagnostic course data - a vital step toward more transparency for students to foster their active role in the learning process.

Salzburg Global Seminar Session 565—‘Better Health Care: how do we learn about improvement?’

PubMed Central

Massoud, M Rashad; Kimble, Leighann E; Goldmann, Don; Ovretveit, John; Dixon, Nancy

2018-01-01

Abstract A fundamental question for the field of healthcare improvement is the extent to which the results achieved can be attributed to the changes that were implemented and whether or not these changes are generalizable. Answering these questions is particularly challenging because the healthcare context is complex, and the interventions themselves tend to be complex and multi-dimensional. The Salzburg Global Seminar Session 565—‘Better Health Care: How do we learn about improvement?’ was convened to address questions of attribution, generalizability and rigor, and to think through how to approach these concerns in the field of quality improvement. The Salzburg Global Seminar Session 565 brought together 61 leaders in improvement from 22 countries, including researchers, evaluators and improvers. The primary conclusion that resulted from the session was the need for evaluation to be embedded as an integral part of the improvement. We have invited participants of the seminar to contribute to writing this supplement, which consists of eight articles reflecting insights and learning from the Salzburg Global Seminar. This editorial serves as an introduction to the supplement. The supplement explains results and insights from Salzburg Global Seminar Session 565. PMID:29462415

Project Based Learning in Multi-Grade Class

ERIC Educational Resources Information Center

Ciftci, Sabahattin; Baykan, Ayse Aysun

2013-01-01

The purpose of this study is to evaluate project based learning in multi-grade classes. This study, based on a student-centered learning approach, aims to analyze students' and parents' interpretations. The study was done in a primary village school belonging to the Centre of Batman, already adapting multi-grade classes in their education system,…

EEG classification for motor imagery and resting state in BCI applications using multi-class Adaboost extreme learning machine

NASA Astrophysics Data System (ADS)

Gao, Lin; Cheng, Wei; Zhang, Jinhua; Wang, Jue

2016-08-01

Brain-computer interface (BCI) systems provide an alternative communication and control approach for people with limited motor function. Therefore, the feature extraction and classification approach should differentiate the relative unusual state of motion intention from a common resting state. In this paper, we sought a novel approach for multi-class classification in BCI applications. We collected electroencephalographic (EEG) signals registered by electrodes placed over the scalp during left hand motor imagery, right hand motor imagery, and resting state for ten healthy human subjects. We proposed using the Kolmogorov complexity (Kc) for feature extraction and a multi-class Adaboost classifier with extreme learning machine as base classifier for classification, in order to classify the three-class EEG samples. An average classification accuracy of 79.5% was obtained for ten subjects, which greatly outperformed commonly used approaches. Thus, it is concluded that the proposed method could improve the performance for classification of motor imagery tasks for multi-class samples. It could be applied in further studies to generate the control commands to initiate the movement of a robotic exoskeleton or orthosis, which finally facilitates the rehabilitation of disabled people.

Self-Learning Power Control in Wireless Sensor Networks.

PubMed

Chincoli, Michele; Liotta, Antonio

2018-01-27

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay.

Self-Learning Power Control in Wireless Sensor Networks

PubMed Central

Liotta, Antonio

2018-01-01

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay. PMID:29382072

Multi-Tier Mental Health Program for Refugee Youth

ERIC Educational Resources Information Center

Ellis, B. Heidi; Miller, Alisa B.; Abdi, Saida; Barrett, Colleen; Blood, Emily A.; Betancourt, Theresa S.

2013-01-01

Objective: We sought to establish that refugee youths who receive a multi-tiered approach to services, Project SHIFA, would show high levels of engagement in treatment appropriate to their level of mental health distress, improvements in mental health symptoms, and a decrease in resource hardships. Method: Study participants were 30 Somali and…

Advancing Ecological Models to Compare Scale in Multi-Level Educational Change

ERIC Educational Resources Information Center

Woo, David James

2016-01-01

Education systems as units of analysis have been metaphorically likened to ecologies to model change. However, ecological models to date have been ineffective in modelling educational change that is multi-scale and occurs across multiple levels of an education system. Thus, this paper advances two innovative, ecological frameworks that improve on…

Designing across ages: Multi-agent-based models and learning electricity

NASA Astrophysics Data System (ADS)

Sengupta, Pratim

Electricity is regarded as one of the most challenging topics for students at all levels -- middle school -- college (Cohen, Eylon, & Ganiel, 1983; Belcher & Olbert, 2003; Eylon & Ganiel, 1990; Steinberg et al., 1985). Several researchers have suggested that naive misconceptions about electricity stem from a deep incommensurability (Slotta & Chi, 2006; Chi, 2005) or incompatibility (Chi, Slotta & Leauw, 1994; Reiner, Slotta, Chi, & Resnick, 2000) between naive and expert knowledge structures. I first present an alternative theoretical framework that adopts an emergent levels-based perspective as proposed by Wilensky & Resnick (1999). From this perspective, macro-level phenomena such as electric current and resistance, as well as behavior of linear electric circuits, can be conceived of as emergent from simple, body-syntonic interactions between electrons and ions in a circuit. I argue that adopting such a perspective enables us to reconceive commonly noted misconceptions in electricity as behavioral evidences of "slippage between levels" -- i.e., these misconceptions appear when otherwise productive knowledge elements are sometimes inappropriately activated due to certain macro-level phenomenological cues only -- and, that the same knowledge elements when activated due to phenomenological cues at both micro- and macro-levels, can engender a deeper, expert-like understanding. I will then introduce NIELS (NetLogo Investigations In Electromagnetism, Sengupta & Wilensky, 2006, 2008, 2009), a low-threshold high-ceiling (LTHC) learning environment of multi-agent-based computational models that represent phenomena such as electric current and resistance, as well as the behavior of linear electric circuits, as emergent. I also present results from implementations of NIELS in 5th, 7th and 12th grade classrooms that show the following: (a) how leveraging certain "design elements" over others in NIELS models can create new phenomenological cues, which in turn can be appropriated for learners in different grades; (b) how learners' existing knowledge structures can be bootstrapped to generate deep understanding; (c) how these knowledge structures evolve as the learners progress through the implemented curriculum; (d) improvement of learners' understanding in the post-test compared to the pre-test; and (e) how NIELS students compare with a comparison group of 12th grade students who underwent traditional classroom instruction.

Poster Development and Presentation to Improve Scientific Inquiry and Broaden Effective Scientific Communication Skills.

PubMed

Rauschenbach, Ines; Keddis, Ramaydalis; Davis, Diane

2018-01-01

We have redesigned a tried-and-true laboratory exercise into an inquiry-based team activity exploring microbial growth control, and implemented this activity as the basis for preparing a scientific poster in a large, multi-section laboratory course. Spanning most of the semester, this project culminates in a poster presentation of data generated from a student-designed experiment. Students use and apply the scientific method and improve written and verbal communication skills. The guided inquiry format of this exercise provides the opportunity for student collaboration through cooperative learning. For each learning objective, a percentage score was tabulated (learning objective score = points awarded/total possible points). A score of 80% was our benchmark for achieving each objective. At least 76% of the student groups participating in this project over two semesters achieved each learning goal. Student perceptions of the project were evaluated using a survey. Nearly 90% of participating students felt they had learned a great deal in the areas of formulating a hypothesis, experimental design, and collecting and analyzing data; 72% of students felt this project had improved their scientific writing skills. In a separate survey, 84% of students who responded felt that peer review was valuable in improving their final poster submission. We designed this inquiry-based poster project to improve student scientific communication skills. This exercise is appropriate for any microbiology laboratory course whose learning outcomes include the development of scientific inquiry and literacy.

Poster Development and Presentation to Improve Scientific Inquiry and Broaden Effective Scientific Communication Skills †

PubMed Central

Rauschenbach, Ines; Keddis, Ramaydalis; Davis, Diane

2018-01-01

We have redesigned a tried-and-true laboratory exercise into an inquiry-based team activity exploring microbial growth control, and implemented this activity as the basis for preparing a scientific poster in a large, multi-section laboratory course. Spanning most of the semester, this project culminates in a poster presentation of data generated from a student-designed experiment. Students use and apply the scientific method and improve written and verbal communication skills. The guided inquiry format of this exercise provides the opportunity for student collaboration through cooperative learning. For each learning objective, a percentage score was tabulated (learning objective score = points awarded/total possible points). A score of 80% was our benchmark for achieving each objective. At least 76% of the student groups participating in this project over two semesters achieved each learning goal. Student perceptions of the project were evaluated using a survey. Nearly 90% of participating students felt they had learned a great deal in the areas of formulating a hypothesis, experimental design, and collecting and analyzing data; 72% of students felt this project had improved their scientific writing skills. In a separate survey, 84% of students who responded felt that peer review was valuable in improving their final poster submission. We designed this inquiry-based poster project to improve student scientific communication skills. This exercise is appropriate for any microbiology laboratory course whose learning outcomes include the development of scientific inquiry and literacy. PMID:29904518

Unobtrusive Multi-Static Serial LiDAR Imager (UMSLI) First Generation Shape-Matching Based Classifier for 2D Contours

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

Cao, Zheng; Ouyang, Bing; Principe, Jose

A multi-static serial LiDAR system prototype was developed under DE-EE0006787 to detect, classify, and record interactions of marine life with marine hydrokinetic generation equipment. This software implements a shape-matching based classifier algorithm for the underwater automated detection of marine life for that system. In addition to applying shape descriptors, the algorithm also adopts information theoretical learning based affine shape registration, improving point correspondences found by shape descriptors as well as the final similarity measure.

Semi-Supervised Multi-View Learning for Gene Network Reconstruction

PubMed Central

Ceci, Michelangelo; Pio, Gianvito; Kuzmanovski, Vladimir; Džeroski, Sašo

2015-01-01

The task of gene regulatory network reconstruction from high-throughput data is receiving increasing attention in recent years. As a consequence, many inference methods for solving this task have been proposed in the literature. It has been recently observed, however, that no single inference method performs optimally across all datasets. It has also been shown that the integration of predictions from multiple inference methods is more robust and shows high performance across diverse datasets. Inspired by this research, in this paper, we propose a machine learning solution which learns to combine predictions from multiple inference methods. While this approach adds additional complexity to the inference process, we expect it would also carry substantial benefits. These would come from the automatic adaptation to patterns on the outputs of individual inference methods, so that it is possible to identify regulatory interactions more reliably when these patterns occur. This article demonstrates the benefits (in terms of accuracy of the reconstructed networks) of the proposed method, which exploits an iterative, semi-supervised ensemble-based algorithm. The algorithm learns to combine the interactions predicted by many different inference methods in the multi-view learning setting. The empirical evaluation of the proposed algorithm on a prokaryotic model organism (E. coli) and on a eukaryotic model organism (S. cerevisiae) clearly shows improved performance over the state of the art methods. The results indicate that gene regulatory network reconstruction for the real datasets is more difficult for S. cerevisiae than for E. coli. The software, all the datasets used in the experiments and all the results are available for download at the following link: http://figshare.com/articles/Semi_supervised_Multi_View_Learning_for_Gene_Network_Reconstruction/1604827. PMID:26641091

Selection and ranking of patient video cases in paediatric neurology in relation to learner levels.

PubMed

Balslev, Thomas; Muijtjens, Arno M M; Maarbjerg, Sabine Frølich; de Grave, Willem

2018-05-01

Teaching and learning with patient video cases may add authenticity, enhance diagnostic accuracy and improve chances of early diagnosis. The aim of this study is firstly to identify selection criteria for key Patient video cases (PVCs), secondly to identify trends in relevance of PVCs for learner levels and thirdly, to rank PVCs for learner levels. Based on a literature review, we identified criteria for key PVCs for use in paediatric neurology. We then performed a multi-round Delphi analysis to obtain agreement between 28 expert clinician teachers concerning key PVCs for four learner levels. We identified two major criteria: key PVCs should demonstrate key movements, and these movements should be subtle and/or difficult to note. The expert clinician teachers subsequently assessed a list of 14 topics for key PVCs. We found a clear, increasing trend in relevance scores, from medical students to young residents to experienced residents and specialists. For medical students and residents, epileptic spasms, Down syndrome, developmental delay, cerebral palsy and absence epilepsy were highly ranked. For specialists, conditions like chorea, focal seizures or eye movement disorders topped the ranking list, although ranking was less clear for this group of advanced learners. Key PVCs should demonstrate movements that are difficult to note for learners. Ranked lists of key PVCs for teaching and learning at different learner levels are now available and may help institutions build validated local libraries of PVCs. Copyright © 2017 European Paediatric Neurology Society. Published by Elsevier Ltd. All rights reserved.

Improving High-Level Thinking Skills by Development of Learning PBL Approach on the Learning Mathematics for Senior High School Students

ERIC Educational Resources Information Center

Surya, Edy; Syahputra, Edi

2017-01-01

This study aims to improve the ability of high-level thinking by developing learning models based on problems in senior high school students. The type study is research development. The subject of dissemination consists in 3 district/city in North Sumatera, namely: SMK Negeri 6 Medan, MAN Deli Serdang Distric and SMA Yapim Taruna Langkat Distric,…

Clinical skills-related learning goals of senior medical students after performance feedback.

PubMed

Chang, Anna; Chou, Calvin L; Teherani, Arianne; Hauer, Karen E

2011-09-01

Lifelong learning is essential for doctors to maintain competence in clinical skills. With performance feedback, learners should be able to formulate specific and achievable learning goals in areas of need. We aimed to determine: (i) the type and specificity of medical student learning goals after a required clinical performance examination; (ii) differences in goal setting among low, average and high performers, and (iii) whether low performers articulate learning goals that are concordant with their learning needs. We conducted a single-site, multi-year, descriptive comparison study. Senior medical students were given performance benchmarks, individual feedback and guidelines on learning goals; each student was subsequently instructed to write two clinical skills learning goals. Investigators coded the learning goals for specificity, categorised the goals, and performed statistical analyses to determine their concordance with student performance level (low, average or high) in data gathering (history taking and physical examination) or communication skills. All 208 students each wrote two learning goals and most (n=200, 96%) wrote two specific learning goals. Nearly two-thirds of low performers in data gathering wrote at least one learning goal that referred to history taking or physical examination; one-third wrote learning goals pertaining to the organisation of the encounter. High performers in data gathering wrote significantly more patient education goals and significantly fewer history-taking goals than average or low performers. Only 50% of low performers in communication wrote learning goals related to communication skills. Low performers in communication were significantly more likely than average or high performers to identify learning goals related to improving performance in future examinations. The provision of performance benchmarking, individual feedback and brief written guidelines helped most senior medical students in our study to write specific clinical skills learning goals. Many low-performing students did not write learning goals concordant with their areas of weakness. Future work might focus on enhancing low performers' continued learning in areas of performance deficits. © Blackwell Publishing Ltd 2011.

Model-Based Comparison of Deep Brain Stimulation Array Functionality with Varying Number of Radial Electrodes and Machine Learning Feature Sets.

PubMed

Teplitzky, Benjamin A; Zitella, Laura M; Xiao, YiZi; Johnson, Matthew D

2016-01-01

Deep brain stimulation (DBS) leads with radially distributed electrodes have potential to improve clinical outcomes through more selective targeting of pathways and networks within the brain. However, increasing the number of electrodes on clinical DBS leads by replacing conventional cylindrical shell electrodes with radially distributed electrodes raises practical design and stimulation programming challenges. We used computational modeling to investigate: (1) how the number of radial electrodes impact the ability to steer, shift, and sculpt a region of neural activation (RoA), and (2) which RoA features are best used in combination with machine learning classifiers to predict programming settings to target a particular area near the lead. Stimulation configurations were modeled using 27 lead designs with one to nine radially distributed electrodes. The computational modeling framework consisted of a three-dimensional finite element tissue conductance model in combination with a multi-compartment biophysical axon model. For each lead design, two-dimensional threshold-dependent RoAs were calculated from the computational modeling results. The models showed more radial electrodes enabled finer resolution RoA steering; however, stimulation amplitude, and therefore spatial extent of the RoA, was limited by charge injection and charge storage capacity constraints due to the small electrode surface area for leads with more than four radially distributed electrodes. RoA shifting resolution was improved by the addition of radial electrodes when using uniform multi-cathode stimulation, but non-uniform multi-cathode stimulation produced equivalent or better resolution shifting without increasing the number of radial electrodes. Robust machine learning classification of 15 monopolar stimulation configurations was achieved using as few as three geometric features describing a RoA. The results of this study indicate that, for a clinical-scale DBS lead, more than four radial electrodes minimally improved in the ability to steer, shift, and sculpt axonal activation around a DBS lead and a simple feature set consisting of the RoA center of mass and orientation enabled robust machine learning classification. These results provide important design constraints for future development of high-density DBS arrays.

Model-Based Comparison of Deep Brain Stimulation Array Functionality with Varying Number of Radial Electrodes and Machine Learning Feature Sets

PubMed Central

Teplitzky, Benjamin A.; Zitella, Laura M.; Xiao, YiZi; Johnson, Matthew D.

2016-01-01

Deep brain stimulation (DBS) leads with radially distributed electrodes have potential to improve clinical outcomes through more selective targeting of pathways and networks within the brain. However, increasing the number of electrodes on clinical DBS leads by replacing conventional cylindrical shell electrodes with radially distributed electrodes raises practical design and stimulation programming challenges. We used computational modeling to investigate: (1) how the number of radial electrodes impact the ability to steer, shift, and sculpt a region of neural activation (RoA), and (2) which RoA features are best used in combination with machine learning classifiers to predict programming settings to target a particular area near the lead. Stimulation configurations were modeled using 27 lead designs with one to nine radially distributed electrodes. The computational modeling framework consisted of a three-dimensional finite element tissue conductance model in combination with a multi-compartment biophysical axon model. For each lead design, two-dimensional threshold-dependent RoAs were calculated from the computational modeling results. The models showed more radial electrodes enabled finer resolution RoA steering; however, stimulation amplitude, and therefore spatial extent of the RoA, was limited by charge injection and charge storage capacity constraints due to the small electrode surface area for leads with more than four radially distributed electrodes. RoA shifting resolution was improved by the addition of radial electrodes when using uniform multi-cathode stimulation, but non-uniform multi-cathode stimulation produced equivalent or better resolution shifting without increasing the number of radial electrodes. Robust machine learning classification of 15 monopolar stimulation configurations was achieved using as few as three geometric features describing a RoA. The results of this study indicate that, for a clinical-scale DBS lead, more than four radial electrodes minimally improved in the ability to steer, shift, and sculpt axonal activation around a DBS lead and a simple feature set consisting of the RoA center of mass and orientation enabled robust machine learning classification. These results provide important design constraints for future development of high-density DBS arrays. PMID:27375470

Evaluation Brief: Implementation and Outcomes of Kansas Multi-Tier System of Supports: 2011-2014

ERIC Educational Resources Information Center

Reedy, Kristen; Lacireno-Paquet, Natalie

2015-01-01

States, school districts, and schools across the country are increasingly implementing multi-tier systems of support (MTSS) to improve outcomes for all students. Kansas is no exception. The Kansas MTSS is designed to improve outcomes for all students by instituting system-level change across the classroom, school, district, and state. Such…

How can we further improve the LDL-cholesterol target level achievement rate based on the Hungarian MULTI GAP 2011 study results and considering the new European dyslipidemia guidelines?

PubMed

Mark, Laszlo; Paragh, György; Karadi, Istvan; Reiber, Istvan; Pados, Gyula; Kiss, Zoltan

2012-09-08

Despite the continuous improvement of the quality of lipid lowering therapy the achievement of target values is still not satisfactory, mainly in the very high cardiovascular risk category patients, where the goal of low density lipoprotein cholesterol (LDL-C) is 1.80 mmol/l. The trends in lipid lowering treatment of 17420 patients from different studies conducted between 2004 and 2010 were compared to that of 1626 patients of MULTI GAP (MULTI Goal Attainment Problem) 2011 treated by general practitioners (GPs) and specialists. In MULTI GAP 2011 the mean LDL-C level ± SD) of patients treated by GPs was found to be 2.87 ±1.01 mmol/l, the target value of 2.50 was achieved by 40% of them, in the specialists' patients the mean LDL-C level proved to be 2.77 ±1.10 mmol/l and the achievement rate was 45%. In the 2.50 mmol/l achievement rate of GPs' patients a satisfactory improvement was observed in the studied years, but the 1.80 mmol/l LDL-C goal in 2011 was attained only in 11% of very high risk cases. There was a linear correlation between the patient compliance estimated by the physicians and the LDL-C achievement rate. As the number of very high risk category patients has been increased according to the new European dyslipidemia guidelines, growing attention needs to be placed on attainment of the 1.80 mmol/l LDL-C level. Based on the results of the MULTI GAP studies, improving patients' adherence and the continuous training of physicians are necessary.

Chromatic Perceptual Learning but No Category Effects without Linguistic Input.

PubMed

Grandison, Alexandra; Sowden, Paul T; Drivonikou, Vicky G; Notman, Leslie A; Alexander, Iona; Davies, Ian R L

2016-01-01

Perceptual learning involves an improvement in perceptual judgment with practice, which is often specific to stimulus or task factors. Perceptual learning has been shown on a range of visual tasks but very little research has explored chromatic perceptual learning. Here, we use two low level perceptual threshold tasks and a supra-threshold target detection task to assess chromatic perceptual learning and category effects. Experiment 1 investigates whether chromatic thresholds reduce as a result of training and at what level of analysis learning effects occur. Experiment 2 explores the effect of category training on chromatic thresholds, whether training of this nature is category specific and whether it can induce categorical responding. Experiment 3 investigates the effect of category training on a higher level, lateralized target detection task, previously found to be sensitive to category effects. The findings indicate that performance on a perceptual threshold task improves following training but improvements do not transfer across retinal location or hue. Therefore, chromatic perceptual learning is category specific and can occur at relatively early stages of visual analysis. Additionally, category training does not induce category effects on a low level perceptual threshold task, as indicated by comparable discrimination thresholds at the newly learned hue boundary and adjacent test points. However, category training does induce emerging category effects on a supra-threshold target detection task. Whilst chromatic perceptual learning is possible, learnt category effects appear to be a product of left hemisphere processing, and may require the input of higher level linguistic coding processes in order to manifest.

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

PubMed Central

Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

2017-01-01

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization. PMID:28599282

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features.

PubMed

Zhang, Xin; Yan, Lin-Feng; Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

2017-07-18

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

Not just another multi-professional course! Part 1. Rationale for a transformative curriculum.

PubMed

Duncan, Madeleine; Alperstein, Melanie; Mayers, Pat; Olckers, Lorna; Gibbs, Trevor

2006-02-01

Undergraduate inter- and multi-professional education has traditionally aimed to develop health professionals who are able to collaborate effectively in comprehensive healthcare delivery. The respective professions learn from and about each other through comparisons of roles, responsibilities, powers, duties and perspectives in order to promote integrated service. Described here is the educational rationale of a multi-professional course with a difference; one that injects value to undergraduate health professional education through the development of critical cross-field knowledge, skills and attitudes that unite rather than differentiate professions. The aim of this course, offered at the Faculty of Health Sciences, University of Cape Town, is to lay an integrated, pan-professional foundation for the advancement of collective commitment to and understanding of national health and social development objectives such as primary health care, human rights and professionalism. Pan-professional refers to curriculum content that is core and of critical relevance to all participating professions. What is learned, how it is learned, how learning is facilitated and how it is applied, has been co-constructed by a multi-professional design team representing a range of health professions (audiology, medicine, occupational therapy, nursing, physiotherapy and speech therapy) and academic disciplines (anthropology, sociology, psychology, history, African studies and social development, information technology and language literacy). Education specialists facilitate the ongoing design process ensuring that the structure and content of the curriculum complies with contemporary adult learning principles and national higher education imperatives. Designing the original curriculum required the deconstruction of intra-professional and disciplinary canons of knowledge and ways of 'doing things' in order to identify and develop shared interpretations of critical epistemology and axiology for health professional practice in the South African context. This enabled the alignment of the learning objectives, at first year level, of all the represented professions. The educational rationale guiding the curriculum design process is discussed in Part 1 of two articles. Part 2 describes the 'nuts and bolts' or practicalities of the curriculum design process.

Evaluation of a multi-site program designed to strengthen relational bonds for siblings separated by foster care.

PubMed

Waid, Jeffrey; Wojciak, Armeda Stevenson

2017-10-01

Sibling relationships in foster care settings have received increased attention in recent years. Despite growing evidence regarding the protective potential of sibling relationships for youth in care, some sibling groups continue to experience foster care related separation, and few programs exist to address the needs of these youth. This study describes and evaluates Camp To Belong, a multi-site program designed to provide short-term reunification to separated sibling groups through a week-long summer camp experience. Using a pre-test post-test survey design, this paper examines changes in youth ratings of sibling conflict and sibling support across camps located in six geographically distinct regions of the United States. The effects of youth age, number of prior camp exposures, and camp location were tested using multilevel modeling procedures. Findings suggest that participation in Camp To Belong may reduce sibling conflict, and improvements in sibling support are noted for youth who have had prior exposure to the camp's programming. Camp-level variance in the sibling support outcome highlight the complex nature of relationships for siblings separated by foster care, and suggest the need for additional research. Lessons learned from this multi-site evaluation and future directions are discussed. Copyright © 2017 Elsevier Ltd. All rights reserved.

Leveraging Competency Framework to Improve Teaching and Learning: A Methodological Approach

ERIC Educational Resources Information Center

Shankararaman, Venky; Ducrot, Joelle

2016-01-01

A number of engineering education programs have defined learning outcomes and course-level competencies, and conducted assessments at the program level to determine areas for continuous improvement. However, many of these programs have not implemented a comprehensive competency framework to support the actual delivery and assessment of an…

A junction-tree based learning algorithm to optimize network wide traffic control: A coordinated multi-agent framework

DOE PAGES

Zhu, Feng; Aziz, H. M. Abdul; Qian, Xinwu; ...

2015-01-31

Our study develops a novel reinforcement learning algorithm for the challenging coordinated signal control problem. Traffic signals are modeled as intelligent agents interacting with the stochastic traffic environment. The model is built on the framework of coordinated reinforcement learning. The Junction Tree Algorithm (JTA) based reinforcement learning is proposed to obtain an exact inference of the best joint actions for all the coordinated intersections. Moreover, the algorithm is implemented and tested with a network containing 18 signalized intersections in VISSIM. Finally, our results show that the JTA based algorithm outperforms independent learning (Q-learning), real-time adaptive learning, and fixed timing plansmore » in terms of average delay, number of stops, and vehicular emissions at the network level.« less

Using Captioned Television To Improve the Reading Proficiency of Language Minority students. Research Study.

ERIC Educational Resources Information Center

National Captioning Inst., Inc., Falls Church, VA.

This study proposed that captioned television, as a multi-sensory, largely entertaining medium might be an important source of comprehensive input for bilingual students in learning language and literacy. To explore this issue, the study investigated the following questions: (1) can bilingual students acquire vocabulary incidentally through…

Knowing and Teaching Middle School Mathematics: A Professional Development Course for In-Service Teachers

ERIC Educational Resources Information Center

Anderson, Celia Rousseau; Hoffmeister, April M.

2007-01-01

This article describes a professional development course intended to improve the content understanding of middle school mathematics teachers. The design of the course included three professional learning strategies: problem solving, examination of student thinking, and discussion of research. The concepts studied in the course included multi-digit…

Routine Breakers for Emotionally Active Learning: "A Case Study"

ERIC Educational Resources Information Center

Munoz-Luna, Rosa; Jurado-Navas, Antonio

2016-01-01

The present paper aims to present a typology of classroom activities which may serve as group driving dynamics to improve student attention in class. Human attention skills may have been shortened now and traditional ways of imparting knowledge should be modified (Soslau, 2015). As a consequence, this implies multi-tasking behaviour as users…

College MOON Project Australia: Preservice Teachers Learning about the Moon's Phases

ERIC Educational Resources Information Center

Mulholland, Judith; Ginns, Ian

2008-01-01

This paper is a report of the Australian segment of an international multi-campus project centred on improving understanding of the Moon's phases for preservice teachers. Instructional strategies adopted for a science education subject enabled Australian participants to make extended observations of the Moon's phases and keep observational data…

Sounds and Sense-Abilities: Science for All

ERIC Educational Resources Information Center

Plourde, Lee A.; Klemm, E. Barbara

2004-01-01

Activities-oriented instruction offers multi modal opportunities for learning science. How do college students in elementary pre-service teacher preparation programs describe science lab activities in terms of visual, kinesthetic, auditory and motor characteristics? Research with elementary science methods students shows that the Levels of…

Teaching Cellular Automation Concepts through Interdisciplinary Collaborative Learning.

ERIC Educational Resources Information Center

Biernacki, Joseph J.; Ayers, Jerry B.

2000-01-01

Reports on the experiences of 12 students--three senior undergraduates majoring in chemical engineering, five master-level, and four doctoral students--in a course titled "Interdisciplinary Studies in Multi-Scale Simulation of Concrete Materials". Course objectives focused on incorporating team-oriented interdisciplinary experiences into the…

A decade of the Clinical Trials Transformation Initiative: What have we accomplished? What have we learned?

PubMed

Tenaerts, P; Madre, L; Landray, M

2018-02-01

The Clinical Trials Transformation Initiative reflects on 10 years of working to improve the quality and efficiency of clinical trials. This article highlights many of the Clinical Trials Transformation Initiative's accomplishments and offers examples of the impact that the Clinical Trials Transformation Initiative has had on the clinical trials enterprise. After conducting more than 25 projects and issuing recommendations for specific strategies to improve the design and execution of clinical trials, some common themes and lessons learned have emerged. Lessons include the importance of engaging many stakeholders, advanced planning to address critical issues, discontinuation of non-value added practices, and new opportunities presented by technology. Through its work, the Clinical Trials Transformation Initiative has also derived some operational best practices for conducting collaborative, multi-stakeholder projects covering project selection, project team dynamics and execution, and multi-stakeholder meetings and team discussions. Through these initiatives, the Clinical Trials Transformation Initiative has helped move the needle toward needed change in the clinical trials enterprise that has directly impacted stakeholders and patients alike.

How Residents Learn From Patient Feedback: A Multi-Institutional Qualitative Study of Pediatrics Residents' Perspectives.

PubMed

Bogetz, Alyssa L; Orlov, Nicola; Blankenburg, Rebecca; Bhavaraju, Vasudha; McQueen, Alisa; Rassbach, Caroline

2018-04-01

Residents may view feedback from patients and their families with greater skepticism than feedback from supervisors and peers. While discussing patient and family feedback with faculty may improve residents' acceptance of feedback and learning, specific strategies have not been identified. We explored pediatrics residents' perspectives of patient feedback and identified strategies that promote residents' reflection on and learning from feedback. In this multi-institutional, qualitative study conducted in June and July 2016, we conducted focus groups with a purposive sample of pediatrics residents after their participation in a randomized controlled trial in which they received written patient feedback and either discussed it with faculty or reviewed it independently. Focus group transcripts were audiorecorded, transcribed, and analyzed for themes using the constant comparative approach associated with grounded theory. Thirty-six of 92 (39%) residents participated in 7 focus groups. Four themes emerged: (1) residents valued patient feedback but felt it may lack the specificity they desire; (2) discussing feedback with a trusted faculty member was helpful for self-reflection; (3) residents identified 5 strategies faculty used to facilitate their openness to and acceptance of patient feedback (eg, help resident overcome emotional responses to feedback and situate feedback in the context of lifelong learning); and (4) residents' perceptions of feedback credibility improved when faculty observed patient encounters and solicited feedback on the resident's behalf prior to discussions. Discussing patient feedback with faculty provided important scaffolding to enhance residents' openness to and reflection on patient feedback.

Multi-Target Regression via Robust Low-Rank Learning.

PubMed

Zhen, Xiantong; Yu, Mengyang; He, Xiaofei; Li, Shuo

2018-02-01

Multi-target regression has recently regained great popularity due to its capability of simultaneously learning multiple relevant regression tasks and its wide applications in data mining, computer vision and medical image analysis, while great challenges arise from jointly handling inter-target correlations and input-output relationships. In this paper, we propose Multi-layer Multi-target Regression (MMR) which enables simultaneously modeling intrinsic inter-target correlations and nonlinear input-output relationships in a general framework via robust low-rank learning. Specifically, the MMR can explicitly encode inter-target correlations in a structure matrix by matrix elastic nets (MEN); the MMR can work in conjunction with the kernel trick to effectively disentangle highly complex nonlinear input-output relationships; the MMR can be efficiently solved by a new alternating optimization algorithm with guaranteed convergence. The MMR leverages the strength of kernel methods for nonlinear feature learning and the structural advantage of multi-layer learning architectures for inter-target correlation modeling. More importantly, it offers a new multi-layer learning paradigm for multi-target regression which is endowed with high generality, flexibility and expressive ability. Extensive experimental evaluation on 18 diverse real-world datasets demonstrates that our MMR can achieve consistently high performance and outperforms representative state-of-the-art algorithms, which shows its great effectiveness and generality for multivariate prediction.

Exploring Effects of Multi-Touch Tabletop on Collaborative Fraction Learning and the Relationship of Learning Behavior and Interaction with Learning Achievement

ERIC Educational Resources Information Center

Hwang, Wu-Yuin; Shadiev, Rustam; Tseng, Chi-Wei; Huang, Yueh-Min

2015-01-01

This study designed a learning system to facilitate elementary school students' fraction learning. An experiment was carried out to investigate how the system, which runs on multi-touch tabletop versus tablet PC, affects fraction learning. Two groups, a control and experimental, were assigned. Control students have learned fraction by using tablet…

The Study and Design of Adaptive Learning System Based on Fuzzy Set Theory

NASA Astrophysics Data System (ADS)

Jia, Bing; Zhong, Shaochun; Zheng, Tianyang; Liu, Zhiyong

Adaptive learning is an effective way to improve the learning outcomes, that is, the selection of learning content and presentation should be adapted to each learner's learning context, learning levels and learning ability. Adaptive Learning System (ALS) can provide effective support for adaptive learning. This paper proposes a new ALS based on fuzzy set theory. It can effectively estimate the learner's knowledge level by test according to learner's target. Then take the factors of learner's cognitive ability and preference into consideration to achieve self-organization and push plan of knowledge. This paper focuses on the design and implementation of domain model and user model in ALS. Experiments confirmed that the system providing adaptive content can effectively help learners to memory the content and improve their comprehension.

Goal-oriented robot navigation learning using a multi-scale space representation.

PubMed

Llofriu, M; Tejera, G; Contreras, M; Pelc, T; Fellous, J M; Weitzenfeld, A

2015-12-01

There has been extensive research in recent years on the multi-scale nature of hippocampal place cells and entorhinal grid cells encoding which led to many speculations on their role in spatial cognition. In this paper we focus on the multi-scale nature of place cells and how they contribute to faster learning during goal-oriented navigation when compared to a spatial cognition system composed of single scale place cells. The task consists of a circular arena with a fixed goal location, in which a robot is trained to find the shortest path to the goal after a number of learning trials. Synaptic connections are modified using a reinforcement learning paradigm adapted to the place cells multi-scale architecture. The model is evaluated in both simulation and physical robots. We find that larger scale and combined multi-scale representations favor goal-oriented navigation task learning. Copyright © 2015 Elsevier Ltd. All rights reserved.

Changing drug users' risk environments: peer health advocates as multi-level community change agents.

PubMed

Weeks, Margaret R; Convey, Mark; Dickson-Gomez, Julia; Li, Jianghong; Radda, Kim; Martinez, Maria; Robles, Eduardo

2009-06-01

Peer delivered, social oriented HIV prevention intervention designs are increasingly popular for addressing broader contexts of health risk beyond a focus on individual factors. Such interventions have the potential to affect multiple social levels of risk and change, including at the individual, network, and community levels, and reflect social ecological principles of interaction across social levels over time. The iterative and feedback dynamic generated by this multi-level effect increases the likelihood for sustained health improvement initiated by those trained to deliver the peer intervention. The Risk Avoidance Partnership (RAP), conducted with heroin and cocaine/crack users in Hartford, Connecticut, exemplified this intervention design and illustrated the multi-level effect on drug users' risk and harm reduction at the individual level, the social network level, and the larger community level. Implications of the RAP program for designing effective prevention programs and for analyzing long-term change to reduce HIV transmission among high-risk groups are discussed from this ecological and multi-level intervention perspective.

Gender and Acceptance of E-Learning: A Multi-Group Analysis Based on a Structural Equation Model among College Students in Chile and Spain.

PubMed

Ramírez-Correa, Patricio E; Arenas-Gaitán, Jorge; Rondán-Cataluña, F Javier

2015-01-01

The scope of this study was to evaluate whether the adoption of e-learning in two universities, and in particular, the relationship between the perception of external control and perceived ease of use, is different because of gender differences. The study was carried out with participating students in two different universities, one in Chile and one in Spain. The Technology Acceptance Model was used as a theoretical framework for the study. A multi-group analysis method in partial least squares was employed to relate differences between groups. The four main conclusions of the study are: (1) a version of the Technology Acceptance Model has been successfully used to explain the process of adoption of e-learning at an undergraduate level of study; (2) the finding of a strong and significant relationship between perception of external control and perception of ease of use of the e-learning platform; (3) a significant relationship between perceived enjoyment and perceived ease of use and between results demonstrability and perceived usefulness is found; (4) the study indicates a few statistically significant differences between males and females when adopting an e-learning platform, according to the tested model.

Web-based multi-channel analyzer

DOEpatents

Gritzo, Russ E.

2003-12-23

The present invention provides an improved multi-channel analyzer designed to conveniently gather, process, and distribute spectrographic pulse data. The multi-channel analyzer may operate on a computer system having memory, a processor, and the capability to connect to a network and to receive digitized spectrographic pulses. The multi-channel analyzer may have a software module integrated with a general-purpose operating system that may receive digitized spectrographic pulses for at least 10,000 pulses per second. The multi-channel analyzer may further have a user-level software module that may receive user-specified controls dictating the operation of the multi-channel analyzer, making the multi-channel analyzer customizable by the end-user. The user-level software may further categorize and conveniently distribute spectrographic pulse data employing non-proprietary, standard communication protocols and formats.

Surface EMG signals based motion intent recognition using multi-layer ELM

NASA Astrophysics Data System (ADS)

Wang, Jianhui; Qi, Lin; Wang, Xiao

2017-11-01

The upper-limb rehabilitation robot is regard as a useful tool to help patients with hemiplegic to do repetitive exercise. The surface electromyography (sEMG) contains motion information as the electric signals are generated and related to nerve-muscle motion. These sEMG signals, representing human's intentions of active motions, are introduced into the rehabilitation robot system to recognize upper-limb movements. Traditionally, the feature extraction is an indispensable part of drawing significant information from original signals, which is a tedious task requiring rich and related experience. This paper employs a deep learning scheme to extract the internal features of the sEMG signals using an advanced Extreme Learning Machine based auto-encoder (ELMAE). The mathematical information contained in the multi-layer structure of the ELM-AE is used as the high-level representation of the internal features of the sEMG signals, and thus a simple ELM can post-process the extracted features, formulating the entire multi-layer ELM (ML-ELM) algorithm. The method is employed for the sEMG based neural intentions recognition afterwards. The case studies show the adopted deep learning algorithm (ELM-AE) is capable of yielding higher classification accuracy compared to the Principle Component Analysis (PCA) scheme in 5 different types of upper-limb motions. This indicates the effectiveness and the learning capability of the ML-ELM in such motion intent recognition applications.

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.

Transfer learning improves supervised image segmentation across imaging protocols.

PubMed

van Opbroek, Annegreet; Ikram, M Arfan; Vernooij, Meike W; de Bruijne, Marleen

2015-05-01

The variation between images obtained with different scanners or different imaging protocols presents a major challenge in automatic segmentation of biomedical images. This variation especially hampers the application of otherwise successful supervised-learning techniques which, in order to perform well, often require a large amount of labeled training data that is exactly representative of the target data. We therefore propose to use transfer learning for image segmentation. Transfer-learning techniques can cope with differences in distributions between training and target data, and therefore may improve performance over supervised learning for segmentation across scanners and scan protocols. We present four transfer classifiers that can train a classification scheme with only a small amount of representative training data, in addition to a larger amount of other training data with slightly different characteristics. The performance of the four transfer classifiers was compared to that of standard supervised classification on two magnetic resonance imaging brain-segmentation tasks with multi-site data: white matter, gray matter, and cerebrospinal fluid segmentation; and white-matter-/MS-lesion segmentation. The experiments showed that when there is only a small amount of representative training data available, transfer learning can greatly outperform common supervised-learning approaches, minimizing classification errors by up to 60%.

Multi-Agent Framework for Virtual Learning Spaces.

ERIC Educational Resources Information Center

Sheremetov, Leonid; Nunez, Gustavo

1999-01-01

Discussion of computer-supported collaborative learning, distributed artificial intelligence, and intelligent tutoring systems focuses on the concept of agents, and describes a virtual learning environment that has a multi-agent system. Describes a model of interactions in collaborative learning and discusses agents for Web-based virtual…

E-learning and blended learning in textile engineering education: a closed feedback loop approach

NASA Astrophysics Data System (ADS)

Charitopoulos, A.; Vassiliadis, S.; Rangoussi, M.; Koulouriotis, D.

2017-10-01

E-learning has gained a significant role in typical education and in professional training, thanks to the flexibility it offers to the time and location parameters of the education event framework. Purely e-learning scenarios are mostly limited either to Open University-type higher education institutions or to graduate level or professional degrees; blended learning scenarios are progressively becoming popular thanks to their balanced approach. The aim of the present work is to propose approaches that exploit the e-learning and the blended-learning scenarios for Textile Engineering education programmes, especially for multi-institutional ones. The “E-Team” European MSc degree programme organized by AUTEX is used as a case study. The proposed solution is based on (i) a free and open-source e-learning platform (moodle) and (ii) blended learning educational scenarios. Educational challenges addressed include student engagement, student error / failure handling, as well as collaborative learning promotion and support.

Enhancing project-oriented learning by joining communities of practice and opening spaces for relatedness

NASA Astrophysics Data System (ADS)

Pascual, R.

2010-03-01

This article describes an extension to project-oriented learning to increase social construction of knowledge and learning. The focus is on: (a) maximising opportunities for students to share their knowledge with practitioners by joining communities of practice, and (b) increasing their intrinsic motivation by creating conditions for student's relatedness. The case study considers a last year capstone course in Mechanical Engineering. The work addresses innovative practices of active learning and beyond project-oriented learning through: (a) the development of a web-based decision support system, (b) meetings between the communities of students, maintenance engineers and academics, and (c) new off-campus group instances. The author hypothesises that this multi-modal approach increases deep learning and social impact of the educational process. Surveys to the actors support a successful achievement of the educational goals. The methodology can easily be extended to further improve the learning process.

Mapping Migratory Bird Prevalence Using Remote Sensing Data Fusion

PubMed Central

Swatantran, Anu; Dubayah, Ralph; Goetz, Scott; Hofton, Michelle; Betts, Matthew G.; Sun, Mindy; Simard, Marc; Holmes, Richard

2012-01-01

Background Improved maps of species distributions are important for effective management of wildlife under increasing anthropogenic pressures. Recent advances in lidar and radar remote sensing have shown considerable potential for mapping forest structure and habitat characteristics across landscapes. However, their relative efficacies and integrated use in habitat mapping remain largely unexplored. We evaluated the use of lidar, radar and multispectral remote sensing data in predicting multi-year bird detections or prevalence for 8 migratory songbird species in the unfragmented temperate deciduous forests of New Hampshire, USA. Methodology and Principal Findings A set of 104 predictor variables describing vegetation vertical structure and variability from lidar, phenology from multispectral data and backscatter properties from radar data were derived. We tested the accuracies of these variables in predicting prevalence using Random Forests regression models. All data sets showed more than 30% predictive power with radar models having the lowest and multi-sensor synergy (“fusion”) models having highest accuracies. Fusion explained between 54% and 75% variance in prevalence for all the birds considered. Stem density from discrete return lidar and phenology from multispectral data were among the best predictors. Further analysis revealed different relationships between the remote sensing metrics and bird prevalence. Spatial maps of prevalence were consistent with known habitat preferences for the bird species. Conclusion and Significance Our results highlight the potential of integrating multiple remote sensing data sets using machine-learning methods to improve habitat mapping. Multi-dimensional habitat structure maps such as those generated from this study can significantly advance forest management and ecological research by facilitating fine-scale studies at both stand and landscape level. PMID:22235254

Mapping migratory bird prevalence using remote sensing data fusion.

PubMed

Swatantran, Anu; Dubayah, Ralph; Goetz, Scott; Hofton, Michelle; Betts, Matthew G; Sun, Mindy; Simard, Marc; Holmes, Richard

2012-01-01

Improved maps of species distributions are important for effective management of wildlife under increasing anthropogenic pressures. Recent advances in lidar and radar remote sensing have shown considerable potential for mapping forest structure and habitat characteristics across landscapes. However, their relative efficacies and integrated use in habitat mapping remain largely unexplored. We evaluated the use of lidar, radar and multispectral remote sensing data in predicting multi-year bird detections or prevalence for 8 migratory songbird species in the unfragmented temperate deciduous forests of New Hampshire, USA. A set of 104 predictor variables describing vegetation vertical structure and variability from lidar, phenology from multispectral data and backscatter properties from radar data were derived. We tested the accuracies of these variables in predicting prevalence using Random Forests regression models. All data sets showed more than 30% predictive power with radar models having the lowest and multi-sensor synergy ("fusion") models having highest accuracies. Fusion explained between 54% and 75% variance in prevalence for all the birds considered. Stem density from discrete return lidar and phenology from multispectral data were among the best predictors. Further analysis revealed different relationships between the remote sensing metrics and bird prevalence. Spatial maps of prevalence were consistent with known habitat preferences for the bird species. Our results highlight the potential of integrating multiple remote sensing data sets using machine-learning methods to improve habitat mapping. Multi-dimensional habitat structure maps such as those generated from this study can significantly advance forest management and ecological research by facilitating fine-scale studies at both stand and landscape level.

A deep auto-encoder model for gene expression prediction.

PubMed

Xie, Rui; Wen, Jia; Quitadamo, Andrew; Cheng, Jianlin; Shi, Xinghua

2017-11-17

Gene expression is a key intermediate level that genotypes lead to a particular trait. Gene expression is affected by various factors including genotypes of genetic variants. With an aim of delineating the genetic impact on gene expression, we build a deep auto-encoder model to assess how good genetic variants will contribute to gene expression changes. This new deep learning model is a regression-based predictive model based on the MultiLayer Perceptron and Stacked Denoising Auto-encoder (MLP-SAE). The model is trained using a stacked denoising auto-encoder for feature selection and a multilayer perceptron framework for backpropagation. We further improve the model by introducing dropout to prevent overfitting and improve performance. To demonstrate the usage of this model, we apply MLP-SAE to a real genomic datasets with genotypes and gene expression profiles measured in yeast. Our results show that the MLP-SAE model with dropout outperforms other models including Lasso, Random Forests and the MLP-SAE model without dropout. Using the MLP-SAE model with dropout, we show that gene expression quantifications predicted by the model solely based on genotypes, align well with true gene expression patterns. We provide a deep auto-encoder model for predicting gene expression from SNP genotypes. This study demonstrates that deep learning is appropriate for tackling another genomic problem, i.e., building predictive models to understand genotypes' contribution to gene expression. With the emerging availability of richer genomic data, we anticipate that deep learning models play a bigger role in modeling and interpreting genomics.

Deep Multi-Task Learning for Tree Genera Classification

NASA Astrophysics Data System (ADS)

Ko, C.; Kang, J.; Sohn, G.

2018-05-01

The goal for our paper is to classify tree genera using airborne Light Detection and Ranging (LiDAR) data with Convolution Neural Network (CNN) - Multi-task Network (MTN) implementation. Unlike Single-task Network (STN) where only one task is assigned to the learning outcome, MTN is a deep learning architect for learning a main task (classification of tree genera) with other tasks (in our study, classification of coniferous and deciduous) simultaneously, with shared classification features. The main contribution of this paper is to improve classification accuracy from CNN-STN to CNN-MTN. This is achieved by introducing a concurrence loss (Lcd) to the designed MTN. This term regulates the overall network performance by minimizing the inconsistencies between the two tasks. Results show that we can increase the classification accuracy from 88.7 % to 91.0 % (from STN to MTN). The second goal of this paper is to solve the problem of small training sample size by multiple-view data generation. The motivation of this goal is to address one of the most common problems in implementing deep learning architecture, the insufficient number of training data. We address this problem by simulating training dataset with multiple-view approach. The promising results from this paper are providing a basis for classifying a larger number of dataset and number of classes in the future.

Distributed learning and multi-objectivity in traffic light control

NASA Astrophysics Data System (ADS)

Brys, Tim; Pham, Tong T.; Taylor, Matthew E.

2014-01-01

Traffic jams and suboptimal traffic flows are ubiquitous in modern societies, and they create enormous economic losses each year. Delays at traffic lights alone account for roughly 10% of all delays in US traffic. As most traffic light scheduling systems currently in use are static, set up by human experts rather than being adaptive, the interest in machine learning approaches to this problem has increased in recent years. Reinforcement learning (RL) approaches are often used in these studies, as they require little pre-existing knowledge about traffic flows. Distributed constraint optimisation approaches (DCOP) have also been shown to be successful, but are limited to cases where the traffic flows are known. The distributed coordination of exploration and exploitation (DCEE) framework was recently proposed to introduce learning in the DCOP framework. In this paper, we present a study of DCEE and RL techniques in a complex simulator, illustrating the particular advantages of each, comparing them against standard isolated traffic actuated signals. We analyse how learning and coordination behave under different traffic conditions, and discuss the multi-objective nature of the problem. Finally we evaluate several alternative reward signals in the best performing approach, some of these taking advantage of the correlation between the problem-inherent objectives to improve performance.

Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation.

PubMed

Bobo, Meg F; Bao, Shunxing; Huo, Yuankai; Yao, Yuang; Virostko, Jack; Plassard, Andrew J; Lyu, Ilwoo; Assad, Albert; Abramson, Richard G; Hilmes, Melissa A; Landman, Bennett A

2018-03-01

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities.

Fully convolutional neural networks improve abdominal organ segmentation

NASA Astrophysics Data System (ADS)

Bobo, Meg F.; Bao, Shunxing; Huo, Yuankai; Yao, Yuang; Virostko, Jack; Plassard, Andrew J.; Lyu, Ilwoo; Assad, Albert; Abramson, Richard G.; Hilmes, Melissa A.; Landman, Bennett A.

2018-03-01

Abdominal image segmentation is a challenging, yet important clinical problem. Variations in body size, position, and relative organ positions greatly complicate the segmentation process. Historically, multi-atlas methods have achieved leading results across imaging modalities and anatomical targets. However, deep learning is rapidly overtaking classical approaches for image segmentation. Recently, Zhou et al. showed that fully convolutional networks produce excellent results in abdominal organ segmentation of computed tomography (CT) scans. Yet, deep learning approaches have not been applied to whole abdomen magnetic resonance imaging (MRI) segmentation. Herein, we evaluate the applicability of an existing fully convolutional neural network (FCNN) designed for CT imaging to segment abdominal organs on T2 weighted (T2w) MRI's with two examples. In the primary example, we compare a classical multi-atlas approach with FCNN on forty-five T2w MRI's acquired from splenomegaly patients with five organs labeled (liver, spleen, left kidney, right kidney, and stomach). Thirty-six images were used for training while nine were used for testing. The FCNN resulted in a Dice similarity coefficient (DSC) of 0.930 in spleens, 0.730 in left kidneys, 0.780 in right kidneys, 0.913 in livers, and 0.556 in stomachs. The performance measures for livers, spleens, right kidneys, and stomachs were significantly better than multi-atlas (p < 0.05, Wilcoxon rank-sum test). In a secondary example, we compare the multi-atlas approach with FCNN on 138 distinct T2w MRI's with manually labeled pancreases (one label). On the pancreas dataset, the FCNN resulted in a median DSC of 0.691 in pancreases versus 0.287 for multi-atlas. The results are highly promising given relatively limited training data and without specific training of the FCNN model and illustrate the potential of deep learning approaches to transcend imaging modalities. 1

Creating a Culture of Continuous Assessment to Improve Student Learning through Curriculum Review

ERIC Educational Resources Information Center

Kalu, Frances; Dyjur, Patti

2018-01-01

This chapter describes a curriculum review framework that fosters continuous assessment through collaboration with multiple stakeholders, alignment with program level learning outcomes, evaluation based on multiple sources of evidence, and facilitated development of action plans to improve student learning.

Distributed Generation Planning using Peer Enhanced Multi-objective Teaching-Learning based Optimization in Distribution Networks

NASA Astrophysics Data System (ADS)

Selvam, Kayalvizhi; Vinod Kumar, D. M.; Siripuram, Ramakanth

2017-04-01

In this paper, an optimization technique called peer enhanced teaching learning based optimization (PeTLBO) algorithm is used in multi-objective problem domain. The PeTLBO algorithm is parameter less so it reduced the computational burden. The proposed peer enhanced multi-objective based TLBO (PeMOTLBO) algorithm has been utilized to find a set of non-dominated optimal solutions [distributed generation (DG) location and sizing in distribution network]. The objectives considered are: real power loss and the voltage deviation subjected to voltage limits and maximum penetration level of DG in distribution network. Since the DG considered is capable of injecting real and reactive power to the distribution network the power factor is considered as 0.85 lead. The proposed peer enhanced multi-objective optimization technique provides different trade-off solutions in order to find the best compromise solution a fuzzy set theory approach has been used. The effectiveness of this proposed PeMOTLBO is tested on IEEE 33-bus and Indian 85-bus distribution system. The performance is validated with Pareto fronts and two performance metrics (C-metric and S-metric) by comparing with robust multi-objective technique called non-dominated sorting genetic algorithm-II and also with the basic TLBO.

E-Learning Readiness in Medicine: Turkish Family Medicine (FM) Physicians Case

ERIC Educational Resources Information Center

Parlakkiliç, Alaattin

2015-01-01

This research investigates e-learning readiness level of family medicine physicians (FM) in Turkey. The study measures the level of e-learning readiness of Turkish FM physicians by an online e-learning readiness survey. According to results five areas are ready at Turkish FM physicians but need a few improvements:…

A Framework for Institutional Adoption and Implementation of Blended Learning in Higher Education

ERIC Educational Resources Information Center

Graham, Charles R.; Woodfield, Wendy; Harrison, J. Buckley

2013-01-01

There has been rapid growth in blended learning implementation and research focused on course-level issues such as improved learning outcomes, but very limited research focused on institutional policy and adoption issues. More institutional-level blended learning research is needed to guide institutions of higher education in strategically…

Reinforcement Learning with Orthonormal Basis Adaptation Based on Activity-Oriented Index Allocation

NASA Astrophysics Data System (ADS)

Satoh, Hideki

An orthonormal basis adaptation method for function approximation was developed and applied to reinforcement learning with multi-dimensional continuous state space. First, a basis used for linear function approximation of a control function is set to an orthonormal basis. Next, basis elements with small activities are replaced with other candidate elements as learning progresses. As this replacement is repeated, the number of basis elements with large activities increases. Example chaos control problems for multiple logistic maps were solved, demonstrating that the method for adapting an orthonormal basis can modify a basis while holding the orthonormality in accordance with changes in the environment to improve the performance of reinforcement learning and to eliminate the adverse effects of redundant noisy states.

Evaluating the predictive power of multivariate tensor-based morphometry in Alzheimer's disease progression via convex fused sparse group Lasso

NASA Astrophysics Data System (ADS)

Tsao, Sinchai; Gajawelli, Niharika; Zhou, Jiayu; Shi, Jie; Ye, Jieping; Wang, Yalin; Lepore, Natasha

2014-03-01

Prediction of Alzheimers disease (AD) progression based on baseline measures allows us to understand disease progression and has implications in decisions concerning treatment strategy. To this end we combine a predictive multi-task machine learning method1 with novel MR-based multivariate morphometric surface map of the hippocampus2 to predict future cognitive scores of patients. Previous work by Zhou et al.1 has shown that a multi-task learning framework that performs prediction of all future time points (or tasks) simultaneously can be used to encode both sparsity as well as temporal smoothness. They showed that this can be used in predicting cognitive outcomes of Alzheimers Disease Neuroimaging Initiative (ADNI) subjects based on FreeSurfer-based baseline MRI features, MMSE score demographic information and ApoE status. Whilst volumetric information may hold generalized information on brain status, we hypothesized that hippocampus specific information may be more useful in predictive modeling of AD. To this end, we applied Shi et al.2s recently developed multivariate tensor-based (mTBM) parametric surface analysis method to extract features from the hippocampal surface. We show that by combining the power of the multi-task framework with the sensitivity of mTBM features of the hippocampus surface, we are able to improve significantly improve predictive performance of ADAS cognitive scores 6, 12, 24, 36 and 48 months from baseline.

Learning from the Past as We Aim for the Future through Identifying Students' Learning Styles To Improve Teaching/Learning Experiences in College Students.

ERIC Educational Resources Information Center

Price, Elsa C.

Community college students arrive with a diversity of learning styles, study skills, and test anxiety levels. The study described here was conducted to determine whether activity grouping of students according to learning style (incorporating at least two different styles in each group) contributes to improved student performance. In the spring of…

Hardware Acceleration of Adaptive Neural Algorithms.

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

James, Conrad D.

As tradit ional numerical computing has faced challenges, researchers have turned towards alternative computing approaches to reduce power - per - computation metrics and improve algorithm performance. Here, we describe an approach towards non - conventional computing that strengthens the connection between machine learning and neuroscience concepts. The Hardware Acceleration of Adaptive Neural Algorithms (HAANA) project ha s develop ed neural machine learning algorithms and hardware for applications in image processing and cybersecurity. While machine learning methods are effective at extracting relevant features from many types of data, the effectiveness of these algorithms degrades when subjected to real - worldmore » conditions. Our team has generated novel neural - inspired approa ches to improve the resiliency and adaptability of machine learning algorithms. In addition, we have also designed and fabricated hardware architectures and microelectronic devices specifically tuned towards the training and inference operations of neural - inspired algorithms. Finally, our multi - scale simulation framework allows us to assess the impact of microelectronic device properties on algorithm performance.« less

Imaging and machine learning techniques for diagnosis of Alzheimer's disease.

PubMed

Mirzaei, Golrokh; Adeli, Anahita; Adeli, Hojjat

2016-12-01

Alzheimer's disease (AD) is a common health problem in elderly people. There has been considerable research toward the diagnosis and early detection of this disease in the past decade. The sensitivity of biomarkers and the accuracy of the detection techniques have been defined to be the key to an accurate diagnosis. This paper presents a state-of-the-art review of the research performed on the diagnosis of AD based on imaging and machine learning techniques. Different segmentation and machine learning techniques used for the diagnosis of AD are reviewed including thresholding, supervised and unsupervised learning, probabilistic techniques, Atlas-based approaches, and fusion of different image modalities. More recent and powerful classification techniques such as the enhanced probabilistic neural network of Ahmadlou and Adeli should be investigated with the goal of improving the diagnosis accuracy. A combination of different image modalities can help improve the diagnosis accuracy rate. Research is needed on the combination of modalities to discover multi-modal biomarkers.

Healthcare quality improvement -- policy implications and practicalities.

PubMed

Esain, Ann Elizabeth; Williams, Sharon J; Gakhal, Sandeep; Caley, Lynne; Cooke, Matthew W

2012-01-01

This article aims to explore quality improvement (QI) at individual, group and organisational level. It also aims to identify restraining forces using formative evaluation and discuss implications for current UK policy, particularly quality, innovation, productivity and prevention. Learning events combined with work-based projects, focusing on individual and group responses are evaluated. A total of 11 multi-disciplinary groups drawn from NHS England healthcare Trusts (self-governing operational groups) were sampled. These Trusts have different geographic locations and participants were drawn from primary, secondary and commissioning arms. Mixed methods: questionnaires, observations and reflective accounts were used. The paper finds that solution versus problem identification causes confusion and influences success. Time for problem solving to achieve QI was absent. Feedback and learning structures are often not in place or inflexible. Limited focus on patient-centred services may be related to past assumptions regarding organisational design, hence assumptions and models need to be understood and challenged. The authors revise the Plan, Do, Study; Act (PDSA) model by adding an explicit problem identification step and hence avoiding solution-focused habits; demonstrating the need for more formative evaluations to inform managers and policy makers about healthcare QI processes. - Although UK-centric, the quality agenda is a USA and European theme, findings may help those embarking on this journey or those struggling with QI.

Learning and innovative elements of strategy adoption rules expand cooperative network topologies.

PubMed

Wang, Shijun; Szalay, Máté S; Zhang, Changshui; Csermely, Peter

2008-04-09

Cooperation plays a key role in the evolution of complex systems. However, the level of cooperation extensively varies with the topology of agent networks in the widely used models of repeated games. Here we show that cooperation remains rather stable by applying the reinforcement learning strategy adoption rule, Q-learning on a variety of random, regular, small-word, scale-free and modular network models in repeated, multi-agent Prisoner's Dilemma and Hawk-Dove games. Furthermore, we found that using the above model systems other long-term learning strategy adoption rules also promote cooperation, while introducing a low level of noise (as a model of innovation) to the strategy adoption rules makes the level of cooperation less dependent on the actual network topology. Our results demonstrate that long-term learning and random elements in the strategy adoption rules, when acting together, extend the range of network topologies enabling the development of cooperation at a wider range of costs and temptations. These results suggest that a balanced duo of learning and innovation may help to preserve cooperation during the re-organization of real-world networks, and may play a prominent role in the evolution of self-organizing, complex systems.

[Case Study] CityCenter and Cosmopolitan Construction Projects, Las Vegas, Nevada: lessons learned from the use of multiple sources and mixed methods in a safety needs assessment.

PubMed

Gittleman, Janie L; Gardner, Paige C; Haile, Elizabeth; Sampson, Julie M; Cigularov, Konstantin P; Ermann, Erica D; Stafford, Pete; Chen, Peter Y

2010-06-01

The present study describes a response to eight tragic deaths over an eighteen month times span on a fast track construction project on the largest commercial development project in U.S. history. Four versions of a survey were distributed to workers, foremen, superintendents, and senior management. In addition to standard Likert-scale safety climate scale items, an open-ended item was included at the end of the survey. Safety climate perceptions differed by job level. Specifically, management perceived a more positive safety climate as compared to workers. Content analysis of the open-ended item was used to identify important safety and health concerns which might have been overlooked with the qualitative portion of the survey. The surveys were conducted to understand workforce issues of concern with the aim of improving site safety conditions. Such efforts can require minimal investment of resources and time and result in critical feedback for developing interventions affecting organizational structure, management processes, and communication. The most important lesson learned was that gauging differences in perception about site safety can provide critical feedback at all levels of a construction organization. Implementation of multi-level organizational perception surveys can identify major safety issues of concern. Feedback, if acted upon, can potentially result in fewer injuries and fatal events. (c) 2010 Elsevier Ltd. All rights reserved.

Use of focus groups in multi-site, multi-ethnic research projects for women's health: a Study of Women Across the Nation (swan) example.

PubMed

Kagawa-Singer, Marjorie; Adler, Shelley R; Mouton, Charles E; Ory, Marcia; Underwood, Lynne G

2009-01-01

To outline the lessons learned about the use of focus groups for the multisite, multi-ethnic longitudinal Study of Women Across the Nation (SWAN). Focus groups were designed to identify potential cultural differences in the incidence of symptoms and the meaning of transmenopause among women of diverse cultures, and to identify effective recruitment and retention strategies. Inductive and deductive focus groups for a multi-ethnic study. Seven community research sites across the United States conducted focus groups with six ethnic populations: African American, Chinese American, Japanese American, Mexican American, non-Hispanic white, and Puerto Rican. Community women from each ethnic group of color. A set of four/five focus groups in each ethnic group as the formative stage of the deductive, quantitative SWAN survey. Identification of methodological advantages and challenges to the successful implementation of formative focus groups in a multi-ethnic, multi-site population-based epidemiologic study. We provide recommendations from our lessons learned to improve the use of focus groups in future studies with multi-ethnic populations. Mixed methods using inductive and deductive approaches require the scientific integrity of both research paradigms. Adequate resources and time must be budgeted as essential parts of the overall strategy from the outset of study. Inductive cross-cultural researchers should be key team members, beginning with inception through each subsequent design phase to increase the scientific validity, generalizability, and comparability of the results across diverse ethnic groups, to assure the relevance, validity and applicability of the findings to the multicultural population of focus.

Improving self-regulated learning junior high school students through computer-based learning

NASA Astrophysics Data System (ADS)

Nurjanah; Dahlan, J. A.

2018-05-01

This study is back grounded by the importance of self-regulated learning as an affective aspect that determines the success of students in learning mathematics. The purpose of this research is to see how the improvement of junior high school students' self-regulated learning through computer based learning is reviewed in whole and school level. This research used a quasi-experimental research method. This is because individual sample subjects are not randomly selected. The research design used is Pretest-and-Posttest Control Group Design. Subjects in this study were students of grade VIII junior high school in Bandung taken from high school (A) and middle school (B). The results of this study showed that the increase of the students' self-regulated learning who obtain learning with computer-based learning is higher than students who obtain conventional learning. School-level factors have a significant effect on increasing of the students' self-regulated learning.

Chromatic Perceptual Learning but No Category Effects without Linguistic Input

PubMed Central

Grandison, Alexandra; Sowden, Paul T.; Drivonikou, Vicky G.; Notman, Leslie A.; Alexander, Iona; Davies, Ian R. L.

2016-01-01

Perceptual learning involves an improvement in perceptual judgment with practice, which is often specific to stimulus or task factors. Perceptual learning has been shown on a range of visual tasks but very little research has explored chromatic perceptual learning. Here, we use two low level perceptual threshold tasks and a supra-threshold target detection task to assess chromatic perceptual learning and category effects. Experiment 1 investigates whether chromatic thresholds reduce as a result of training and at what level of analysis learning effects occur. Experiment 2 explores the effect of category training on chromatic thresholds, whether training of this nature is category specific and whether it can induce categorical responding. Experiment 3 investigates the effect of category training on a higher level, lateralized target detection task, previously found to be sensitive to category effects. The findings indicate that performance on a perceptual threshold task improves following training but improvements do not transfer across retinal location or hue. Therefore, chromatic perceptual learning is category specific and can occur at relatively early stages of visual analysis. Additionally, category training does not induce category effects on a low level perceptual threshold task, as indicated by comparable discrimination thresholds at the newly learned hue boundary and adjacent test points. However, category training does induce emerging category effects on a supra-threshold target detection task. Whilst chromatic perceptual learning is possible, learnt category effects appear to be a product of left hemisphere processing, and may require the input of higher level linguistic coding processes in order to manifest. PMID:27252669

An improved multi-domain convolution tracking algorithm

NASA Astrophysics Data System (ADS)

Sun, Xin; Wang, Haiying; Zeng, Yingsen

2018-04-01

Along with the wide application of the Deep Learning in the field of Computer vision, Deep learning has become a mainstream direction in the field of object tracking. The tracking algorithm in this paper is based on the improved multidomain convolution neural network, and the VOT video set is pre-trained on the network by multi-domain training strategy. In the process of online tracking, the network evaluates candidate targets sampled from vicinity of the prediction target in the previous with Gaussian distribution, and the candidate target with the highest score is recognized as the prediction target of this frame. The Bounding Box Regression model is introduced to make the prediction target closer to the ground-truths target box of the test set. Grouping-update strategy is involved to extract and select useful update samples in each frame, which can effectively prevent over fitting. And adapt to changes in both target and environment. To improve the speed of the algorithm while maintaining the performance, the number of candidate target succeed in adjusting dynamically with the help of Self-adaption parameter Strategy. Finally, the algorithm is tested by OTB set, compared with other high-performance tracking algorithms, and the plot of success rate and the accuracy are drawn. which illustrates outstanding performance of the tracking algorithm in this paper.

Implementation and Perceived Effectiveness of Professional Learning Communities in the Kanawha County School District in West Virginia

ERIC Educational Resources Information Center

Brucker, Elizabeth L.

2013-01-01

The purpose of this study was to investigate teachers' perceptions of levels of implementation and levels of effectiveness in improving student learning of Professional Learning Communities (PLCs) in Kanawha County Schools. This study also sought to determine differences in levels of implementation and effectiveness for five selected independent…

What Did You Do in School Today? Transforming Classrooms through Social, Academic, and Intellectual Engagement. (First National Report)

ERIC Educational Resources Information Center

Willms, J. Douglas; Friesen, Sharon; Milton, Penny

2009-01-01

Across Canada there is increased attention to the important relationship between the quality of learning environments--particularly effective teaching--and student achievement. "What did you do in school today?" proposes a multi-dimensional framework of student engagement as a core idea for improving the quality of teaching and learning…

Probabilities and Predictions: Modeling the Development of Scientific Problem-Solving Skills

ERIC Educational Resources Information Center

Stevens, Ron; Johnson, David F.; Soller, Amy

2005-01-01

The IMMEX (Interactive Multi-Media Exercises) Web-based problem set platform enables the online delivery of complex, multimedia simulations, the rapid collection of student performance data, and has already been used in several genetic simulations. The next step is the use of these data to understand and improve student learning in a formative…

Small Boats in an Ocean of School Activities: Towards a European Vision on Education

ERIC Educational Resources Information Center

Villalba, Ernesto

2008-01-01

The paper discusses the concept of schools as "multi-purpose learning centres", proposed by the European Commission in the year 2000 as part of the Lisbon Strategy to improve competitiveness. This concept was arguably the "European vision" for school education and was meant to drive the modernization of school education.…

[INDENA SPA company's patent portfolio of Ginkgo biloba preparation].

PubMed

Wang, Nan; Guo, Kai; Cheng, Xin-min; Liu, Wei

2015-10-01

INDENA SPA Company in Italy is a multi-national company that produces and sells plant extracts. Based on its own re- search advantages in the field of Ginkgo biloba preparation, the company protects its own products market effectively through building patent portfolio around the patents of its opponent. Based on the multi-angle analysis for patent portfolio of G. biloba preparation from the aspects of application time, legal status, technical development route, and patent portfolio layout, this article provides technical reference on research and development of G. biloba preparation, and the author suggest that Chinese applicants learn techniques and layout experiences of other patents fully to enhance the level of research and patent protection level.

Expert meeting on Child Growth and Micronutrient Deficiencies--New Initiatives for Developing Countries to Achieve Millennium Development Goals: executive summary report.

PubMed

Usfar, Avita A; Achadi, Endang L; Martorell, Reynaldo; Hadi, Hamam; Thaha, Razak; Jus'at, Idrus; Atmarita; Martianto, Drajat; Ridwan, Hardinsyah; Soekirman

2009-01-01

Undernutrition in early childhood has long-term physical and intellectual consequences. Improving child growth should start before the age of two years and be an integrated effort between all sectors, covering all aspects such as diet and nutrient intake, disease reduction, optimum child care, and improved environmental sanitation. To discuss these issues, the Indonesian Danone Institute Foundation organized an expert meeting on Child Growth and Micronutrient Deficiencies: New Initiatives for Developing Countries to Achieve Millennium Development Goals. The objective of the meeting was to have a retrospective view on child growth: lessons learned from programs to overcome under-nutrition in the developed countries and to relate the situation to the Indonesian context, as well as to discuss implications for future programs. Recommendations derived from the meeting include focus intervention on the window of opportunity group, re-activation of the Integrated Health Post at the village level, improvement of infant and young child feeding, expand food fortification intervention programs, strengthen supplementation programs with multi-micronutrient, and strengthening public and private partnership on food related programs.

Consumer Education Resource Guide, K-12. A Multi-Disciplinary Approach.

ERIC Educational Resources Information Center

Calhoun, Calfrey C.; And Others

The guide suggests methods and resources for planning learning experiences in teaching consumer education to students at the K-12 levels. The major topics and related areas are: (1) financial planning (estimating income, estimating expenses, establishing goals, making decisions, and making the financial plan); (2) buying (importance of planned…

Collaboration Scripts for Enhancing Metacognitive Self-Regulation and Mathematics Literacy

ERIC Educational Resources Information Center

Chen, Cheng-Huan; Chiu, Chiung-Hui

2016-01-01

This study designed a set of computerized collaboration scripts for multi-touch supported collaborative design-based learning and evaluated its effects on multiple aspects of metacognitive self-regulation in terms of planning and controlling and mathematical literacy achievement at higher and lower levels. The computerized scripts provided a…

A Psycho-Pedagogical Framework for Multi-Adaptive Educational Games

ERIC Educational Resources Information Center

Kickmeier-Rust, Michael D.; Mattheiss, Elke; Steiner, Christina; Albert, Dietrich

2011-01-01

One of the trump cards of digital educational games is their enormous intrinsic motivational potential. Although learning game design is often understood on a one-fitsall level, the actual motivational strength of an educational game strongly depends on the individual learners, their very specific goals, preferences, abilities, strength and…

RTI Scheduling Processes for Middle Schools. Information Brief

ERIC Educational Resources Information Center

Prewett, Sara; Mellard, Daryl; Lieske-Lupo, Jessica

2011-01-01

Response to intervention integrates assessment and intervention within a multi-level prevention system to maximize student achievement and to reduce behavior problems. With RTI, schools identify students at risk for poor learning outcomes, monitor student progress, provide evidence-based interventions and adjust the intensity and nature of those…

Designing across Ages: Multi-Agent-Based Models and Learning Electricity

ERIC Educational Resources Information Center

Sengupta, Pratim

2009-01-01

Electricity is regarded as one of the most challenging topics for students at all levels--middle school--college (Cohen, Eylon, & Ganiel, 1983; Belcher & Olbert, 2003; Eylon & Ganiel, 1990; Steinberg et al., 1985). Several researchers have suggested that naive misconceptions about electricity stem from a deep incommensurability (Slotta & Chi,…

Exploding the Hierarchical Fallacy: The Significance of Foundation-Level Courses

ERIC Educational Resources Information Center

Maimon, Elaine P.

2017-01-01

Reform in American higher education depends on recognizing freshman courses as the foundation of higher-order thinking and learning. These courses must be recognized for their intellectual significance and their inherent possibilities for multi-disciplinary scholarship. The Maimon Hierarchical Fallacy is a phrase coined by Elaine Maimon to refer…

Learned filters for object detection in multi-object visual tracking

NASA Astrophysics Data System (ADS)

Stamatescu, Victor; Wong, Sebastien; McDonnell, Mark D.; Kearney, David

2016-05-01

We investigate the application of learned convolutional filters in multi-object visual tracking. The filters were learned in both a supervised and unsupervised manner from image data using artificial neural networks. This work follows recent results in the field of machine learning that demonstrate the use learned filters for enhanced object detection and classification. Here we employ a track-before-detect approach to multi-object tracking, where tracking guides the detection process. The object detection provides a probabilistic input image calculated by selecting from features obtained using banks of generative or discriminative learned filters. We present a systematic evaluation of these convolutional filters using a real-world data set that examines their performance as generic object detectors.

Multi-Sensor Optimal Data Fusion Based on the Adaptive Fading Unscented Kalman Filter

PubMed Central

Gao, Bingbing; Hu, Gaoge; Gao, Shesheng; Gu, Chengfan

2018-01-01

This paper presents a new optimal data fusion methodology based on the adaptive fading unscented Kalman filter for multi-sensor nonlinear stochastic systems. This methodology has a two-level fusion structure: at the bottom level, an adaptive fading unscented Kalman filter based on the Mahalanobis distance is developed and serves as local filters to improve the adaptability and robustness of local state estimations against process-modeling error; at the top level, an unscented transformation-based multi-sensor optimal data fusion for the case of N local filters is established according to the principle of linear minimum variance to calculate globally optimal state estimation by fusion of local estimations. The proposed methodology effectively refrains from the influence of process-modeling error on the fusion solution, leading to improved adaptability and robustness of data fusion for multi-sensor nonlinear stochastic systems. It also achieves globally optimal fusion results based on the principle of linear minimum variance. Simulation and experimental results demonstrate the efficacy of the proposed methodology for INS/GNSS/CNS (inertial navigation system/global navigation satellite system/celestial navigation system) integrated navigation. PMID:29415509

Multi-Sensor Optimal Data Fusion Based on the Adaptive Fading Unscented Kalman Filter.

PubMed

Gao, Bingbing; Hu, Gaoge; Gao, Shesheng; Zhong, Yongmin; Gu, Chengfan

2018-02-06

This paper presents a new optimal data fusion methodology based on the adaptive fading unscented Kalman filter for multi-sensor nonlinear stochastic systems. This methodology has a two-level fusion structure: at the bottom level, an adaptive fading unscented Kalman filter based on the Mahalanobis distance is developed and serves as local filters to improve the adaptability and robustness of local state estimations against process-modeling error; at the top level, an unscented transformation-based multi-sensor optimal data fusion for the case of N local filters is established according to the principle of linear minimum variance to calculate globally optimal state estimation by fusion of local estimations. The proposed methodology effectively refrains from the influence of process-modeling error on the fusion solution, leading to improved adaptability and robustness of data fusion for multi-sensor nonlinear stochastic systems. It also achieves globally optimal fusion results based on the principle of linear minimum variance. Simulation and experimental results demonstrate the efficacy of the proposed methodology for INS/GNSS/CNS (inertial navigation system/global navigation satellite system/celestial navigation system) integrated navigation.

GraphoGame – a catalyst for multi-level promotion of literacy in diverse contexts

PubMed Central

Ojanen, Emma; Ronimus, Miia; Ahonen, Timo; Chansa-Kabali, Tamara; February, Pamela; Jere-Folotiya, Jacqueline; Kauppinen, Karri-Pekka; Ketonen, Ritva; Ngorosho, Damaris; Pitkänen, Mikko; Puhakka, Suzanne; Sampa, Francis; Walubita, Gabriel; Yalukanda, Christopher; Pugh, Ken; Richardson, Ulla; Serpell, Robert; Lyytinen, Heikki

2015-01-01

GraphoGame (GG) is originally a technology-based intervention method for supporting children with reading difficulties. It is now known that children who face problems in reading acquisition have difficulties in learning to differentiate and manipulate speech sounds and consequently, in connecting these sounds to corresponding letters. GG was developed to provide intensive training in matching speech sounds and larger units of speech to their written counterparts. GG has been shown to benefit children with reading difficulties and the game is now available for all Finnish school children for literacy support. Presently millions of children in Africa fail to learn to read despite years of primary school education. As many African languages have transparent writing systems similar in structure to Finnish, it was hypothesized that GG-based training of letter-sound correspondences could also be effective in supporting children’s learning in African countries. In this article we will describe how GG has been developed from a Finnish dyslexia prevention game to an intervention method that can be used not only to improve children’s reading performance but also to raise teachers’ and parents’ awareness of the development of reading skill and effective reading instruction methods. We will also provide an overview of the GG activities in Zambia, Kenya, Tanzania, and Namibia, and the potential to promote education for all with a combination of scientific research and mobile learning. PMID:26113825

Facilitating Learning in SPI through Co-design

NASA Astrophysics Data System (ADS)

Seigerroth, Ulf; Lind, Mikael

Information system development (ISD) is not a stable discipline. On the contrary, ISD must constantly cope with rapidly changing and diversifying technologies, application domains, and organizational contexts [14]. ISD is a complex and a multi dimensional phenomenon [5, 15]. As a consequence of this. Software Process Improvement (SPI) can also be regarded as a complex and multi dimensional phenomenon [16]. Problems that are accentuated in relation to SPI are: SPI is in its current shape a quite young discipline [15], there is a sparse amount of SPI-theories that can guide SPI initiatives [19], SPI-initiatives often focus on the system development (SD)-process, methods and tools which is a narrow focus that leave out important aspects such as business orientation [6], organization and social factors [4, 5] and the learning process [19]. Arguments have therefore been raised that there is a need for both researchers and practitioners to better understand SD-organisations and their practice [5].

Waveform Optimization for Target Estimation by Cognitive Radar with Multiple Antennas.

PubMed

Yao, Yu; Zhao, Junhui; Wu, Lenan

2018-05-29

A new scheme based on Kalman filtering to optimize the waveforms of an adaptive multi-antenna radar system for target impulse response (TIR) estimation is presented. This work aims to improve the performance of TIR estimation by making use of the temporal correlation between successive received signals, and minimize the mean square error (MSE) of TIR estimation. The waveform design approach is based upon constant learning from the target feature at the receiver. Under the multiple antennas scenario, a dynamic feedback loop control system is established to real-time monitor the change in the target features extracted form received signals. The transmitter adapts its transmitted waveform to suit the time-invariant environment. Finally, the simulation results show that, as compared with the waveform design method based on the MAP criterion, the proposed waveform design algorithm is able to improve the performance of TIR estimation for extended targets with multiple iterations, and has a relatively lower level of complexity.

Web Image Search Re-ranking with Click-based Similarity and Typicality.

PubMed

Yang, Xiaopeng; Mei, Tao; Zhang, Yong Dong; Liu, Jie; Satoh, Shin'ichi

2016-07-20

In image search re-ranking, besides the well known semantic gap, intent gap, which is the gap between the representation of users' query/demand and the real intent of the users, is becoming a major problem restricting the development of image retrieval. To reduce human effects, in this paper, we use image click-through data, which can be viewed as the "implicit feedback" from users, to help overcome the intention gap, and further improve the image search performance. Generally, the hypothesis visually similar images should be close in a ranking list and the strategy images with higher relevance should be ranked higher than others are widely accepted. To obtain satisfying search results, thus, image similarity and the level of relevance typicality are determinate factors correspondingly. However, when measuring image similarity and typicality, conventional re-ranking approaches only consider visual information and initial ranks of images, while overlooking the influence of click-through data. This paper presents a novel re-ranking approach, named spectral clustering re-ranking with click-based similarity and typicality (SCCST). First, to learn an appropriate similarity measurement, we propose click-based multi-feature similarity learning algorithm (CMSL), which conducts metric learning based on clickbased triplets selection, and integrates multiple features into a unified similarity space via multiple kernel learning. Then based on the learnt click-based image similarity measure, we conduct spectral clustering to group visually and semantically similar images into same clusters, and get the final re-rank list by calculating click-based clusters typicality and withinclusters click-based image typicality in descending order. Our experiments conducted on two real-world query-image datasets with diverse representative queries show that our proposed reranking approach can significantly improve initial search results, and outperform several existing re-ranking approaches.

Multi-Resource Learning.

ERIC Educational Resources Information Center

Cuda, Rebecca A.

2001-01-01

Describes a multi-resource learning environment in which students can engage in their own learning with the teacher taking more of a facilitative role. This type of learning can occur as part of a unit of study and must be supplemented with more traditional types of instruction to ensure that the necessary content is given by the teacher. (SAH)

Multi-objective evolutionary algorithms for fuzzy classification in survival prediction.

PubMed

Jiménez, Fernando; Sánchez, Gracia; Juárez, José M

2014-03-01

This paper presents a novel rule-based fuzzy classification methodology for survival/mortality prediction in severe burnt patients. Due to the ethical aspects involved in this medical scenario, physicians tend not to accept a computer-based evaluation unless they understand why and how such a recommendation is given. Therefore, any fuzzy classifier model must be both accurate and interpretable. The proposed methodology is a three-step process: (1) multi-objective constrained optimization of a patient's data set, using Pareto-based elitist multi-objective evolutionary algorithms to maximize accuracy and minimize the complexity (number of rules) of classifiers, subject to interpretability constraints; this step produces a set of alternative (Pareto) classifiers; (2) linguistic labeling, which assigns a linguistic label to each fuzzy set of the classifiers; this step is essential to the interpretability of the classifiers; (3) decision making, whereby a classifier is chosen, if it is satisfactory, according to the preferences of the decision maker. If no classifier is satisfactory for the decision maker, the process starts again in step (1) with a different input parameter set. The performance of three multi-objective evolutionary algorithms, niched pre-selection multi-objective algorithm, elitist Pareto-based multi-objective evolutionary algorithm for diversity reinforcement (ENORA) and the non-dominated sorting genetic algorithm (NSGA-II), was tested using a patient's data set from an intensive care burn unit and a standard machine learning data set from an standard machine learning repository. The results are compared using the hypervolume multi-objective metric. Besides, the results have been compared with other non-evolutionary techniques and validated with a multi-objective cross-validation technique. Our proposal improves the classification rate obtained by other non-evolutionary techniques (decision trees, artificial neural networks, Naive Bayes, and case-based reasoning) obtaining with ENORA a classification rate of 0.9298, specificity of 0.9385, and sensitivity of 0.9364, with 14.2 interpretable fuzzy rules on average. Our proposal improves the accuracy and interpretability of the classifiers, compared with other non-evolutionary techniques. We also conclude that ENORA outperforms niched pre-selection and NSGA-II algorithms. Moreover, given that our multi-objective evolutionary methodology is non-combinational based on real parameter optimization, the time cost is significantly reduced compared with other evolutionary approaches existing in literature based on combinational optimization. Copyright © 2014 Elsevier B.V. All rights reserved.

A hierarchical anatomical classification schema for prediction of phenotypic side effects

PubMed Central

Kanji, Rakesh

2018-01-01

Prediction of adverse drug reactions is an important problem in drug discovery endeavors which can be addressed with data-driven strategies. SIDER is one of the most reliable and frequently used datasets for identification of key features as well as building machine learning models for side effects prediction. The inherently unbalanced nature of this data presents with a difficult multi-label multi-class problem towards prediction of drug side effects. We highlight the intrinsic issue with SIDER data and methodological flaws in relying on performance measures such as AUC while attempting to predict side effects.We argue for the use of metrics that are robust to class imbalance for evaluation of classifiers. Importantly, we present a ‘hierarchical anatomical classification schema’ which aggregates side effects into organs, sub-systems, and systems. With the help of a weighted performance measure, using 5-fold cross-validation we show that this strategy facilitates biologically meaningful side effects prediction at different levels of anatomical hierarchy. By implementing various machine learning classifiers we show that Random Forest model yields best classification accuracy at each level of coarse-graining. The manually curated, hierarchical schema for side effects can also serve as the basis of future studies towards prediction of adverse reactions and identification of key features linked to specific organ systems. Our study provides a strategy for hierarchical classification of side effects rooted in the anatomy and can pave the way for calibrated expert systems for multi-level prediction of side effects. PMID:29494708

A hierarchical anatomical classification schema for prediction of phenotypic side effects.

PubMed

Wadhwa, Somin; Gupta, Aishwarya; Dokania, Shubham; Kanji, Rakesh; Bagler, Ganesh

2018-01-01

Prediction of adverse drug reactions is an important problem in drug discovery endeavors which can be addressed with data-driven strategies. SIDER is one of the most reliable and frequently used datasets for identification of key features as well as building machine learning models for side effects prediction. The inherently unbalanced nature of this data presents with a difficult multi-label multi-class problem towards prediction of drug side effects. We highlight the intrinsic issue with SIDER data and methodological flaws in relying on performance measures such as AUC while attempting to predict side effects.We argue for the use of metrics that are robust to class imbalance for evaluation of classifiers. Importantly, we present a 'hierarchical anatomical classification schema' which aggregates side effects into organs, sub-systems, and systems. With the help of a weighted performance measure, using 5-fold cross-validation we show that this strategy facilitates biologically meaningful side effects prediction at different levels of anatomical hierarchy. By implementing various machine learning classifiers we show that Random Forest model yields best classification accuracy at each level of coarse-graining. The manually curated, hierarchical schema for side effects can also serve as the basis of future studies towards prediction of adverse reactions and identification of key features linked to specific organ systems. Our study provides a strategy for hierarchical classification of side effects rooted in the anatomy and can pave the way for calibrated expert systems for multi-level prediction of side effects.

Virtual patient instruction for dental students: can it improve dental care access for persons with special needs?

PubMed

Sanders, Carla; Kleinert, Harold L; Boyd, Sara E; Herren, Chris; Theiss, Lynn; Mink, John

2008-01-01

An interactive, virtual-patient module was produced on compact disc (CD-ROM) in response to the critical need to increase dental students' clinical exposure to patients with developmental disabilities. A content development team consisting of dental faculty members, parents of children with developmental disabilities, an individual with a developmental disability, and educational specialists developed the interactive, virtual-patient module. The module focused on a young man with congenital deafblindness presenting as a new patient with a painful molar. Students were required to make decisions regarding clinical interactions throughout the module. Differences in both comfort and knowledge level were measured pre- and post-module completion, as well as the dental students' overall satisfaction with the learning experience. Significant results were obtained in students' perceived comfort and knowledge base. Participants reported overall satisfaction using the modules. This study demonstrated that an interactive, multi-media (CD-ROM), virtual patient learning module for dental students could be an effective tool in providing students needed clinical exposure to patients with developmental disabilities.

Multi-task transfer learning deep convolutional neural network: application to computer-aided diagnosis of breast cancer on mammograms

NASA Astrophysics Data System (ADS)

Samala, Ravi K.; Chan, Heang-Ping; Hadjiiski, Lubomir M.; Helvie, Mark A.; Cha, Kenny H.; Richter, Caleb D.

2017-12-01

Transfer learning in deep convolutional neural networks (DCNNs) is an important step in its application to medical imaging tasks. We propose a multi-task transfer learning DCNN with the aim of translating the ‘knowledge’ learned from non-medical images to medical diagnostic tasks through supervised training and increasing the generalization capabilities of DCNNs by simultaneously learning auxiliary tasks. We studied this approach in an important application: classification of malignant and benign breast masses. With Institutional Review Board (IRB) approval, digitized screen-film mammograms (SFMs) and digital mammograms (DMs) were collected from our patient files and additional SFMs were obtained from the Digital Database for Screening Mammography. The data set consisted of 2242 views with 2454 masses (1057 malignant, 1397 benign). In single-task transfer learning, the DCNN was trained and tested on SFMs. In multi-task transfer learning, SFMs and DMs were used to train the DCNN, which was then tested on SFMs. N-fold cross-validation with the training set was used for training and parameter optimization. On the independent test set, the multi-task transfer learning DCNN was found to have significantly (p  =  0.007) higher performance compared to the single-task transfer learning DCNN. This study demonstrates that multi-task transfer learning may be an effective approach for training DCNN in medical imaging applications when training samples from a single modality are limited.

Stakeholders' views of shared learning models in general practice: a national survey.

PubMed

van de Mortel, Thea; Silberberg, Peter; Ahern, Christine; Pit, Sabrina

2014-09-01

The number of learners requiring general practice placements creates supervisory capacity constraints. This research examined how a shared learning model may affect training capacity. The number of learners requiring general practice placements creates supervisory capacity constraints. This research examined how a shared learning model may affect training capacity. A total of 1122 surveys were completed: 75% of learners had participated in shared learning; 25% of multi-level learner practices were not using shared learning. Learners were positive about shared learning (4.3-4.4/5), considering it an effective way to learn that created training capacity (4.1-4.2/5). 79-88% of learners preferred a mixture of one-to-one teaching and shared learning. Supervisors thought shared learning was more cost- and time-efficient, and created training capacity (4.3-4.4/5). Shared learning models have the potential to increase GP training capacity. Many practices are not utilising shared learning, representing capacity loss. Regional training providers should emphasise positive aspects of shared learning to facilitate uptake.

Music Students' Perception of the Use of Multi-Media Technology at the Graduate Level in Hong Kong Higher Education

ERIC Educational Resources Information Center

Ho, Wai-Chung

2007-01-01

The core purpose of this paper is to draw together research issues and concrete problems with the use of multimedia technology at the graduate level in higher music education by examining one university's responses to the challenges posed by the use of multimedia technology as a teaching and learning aid for music education. Between June and July…

The Greatest Learning Return on Your Pedagogical Investment: Alignment, Assessment or In-Class Instruction?

PubMed Central

Holt, Emily A.; Young, Craig; Keetch, Jared; Larsen, Skylar; Mollner, Brayden

2015-01-01

Critical thinking is often considered an essential learning outcome of institutions in higher education. Previous work has proposed three pedagogical strategies to address this goal: more active, student-centered in-class instruction, assessments which contain higher-order cognitive questions, and greater alignment within a classroom (i.e., high agreement of the cognitive level of learning objectives, assessments, and in-class instruction). Our goals were to determine which of these factors, individually or the interactions therein, contributed most to improvements in university students’ critical thinking. We assessed students’ higher-order cognitive skills in introductory non-majors biology courses the first and last week of instruction. For each of the fifteen sections observed, we also measured the cognitive level of assessments and learning objectives, evaluated the learner-centeredness of each classroom, and calculated an alignment score for each class. The best model to explain improvements in students’ high-order cognitive skills contained the measure of learner-centeredness of the class and pre-quiz scores as a covariate. The cognitive level of assessments, learning objectives, nor alignment explained improvements in students’ critical thinking. In accordance with much of the current literature, our findings support that more student-centered classes had greater improvements in student learning. However, more research is needed to clarify the role of assessment and alignment in student learning. PMID:26340659

The Greatest Learning Return on Your Pedagogical Investment: Alignment, Assessment or In-Class Instruction?

PubMed

Holt, Emily A; Young, Craig; Keetch, Jared; Larsen, Skylar; Mollner, Brayden

2015-01-01

Critical thinking is often considered an essential learning outcome of institutions in higher education. Previous work has proposed three pedagogical strategies to address this goal: more active, student-centered in-class instruction, assessments which contain higher-order cognitive questions, and greater alignment within a classroom (i.e., high agreement of the cognitive level of learning objectives, assessments, and in-class instruction). Our goals were to determine which of these factors, individually or the interactions therein, contributed most to improvements in university students' critical thinking. We assessed students' higher-order cognitive skills in introductory non-majors biology courses the first and last week of instruction. For each of the fifteen sections observed, we also measured the cognitive level of assessments and learning objectives, evaluated the learner-centeredness of each classroom, and calculated an alignment score for each class. The best model to explain improvements in students' high-order cognitive skills contained the measure of learner-centeredness of the class and pre-quiz scores as a covariate. The cognitive level of assessments, learning objectives, nor alignment explained improvements in students' critical thinking. In accordance with much of the current literature, our findings support that more student-centered classes had greater improvements in student learning. However, more research is needed to clarify the role of assessment and alignment in student learning.

Machine Learning for Big Data: A Study to Understand Limits at Scale

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

Sukumar, Sreenivas R.; Del-Castillo-Negrete, Carlos Emilio

This report aims to empirically understand the limits of machine learning when applied to Big Data. We observe that recent innovations in being able to collect, access, organize, integrate, and query massive amounts of data from a wide variety of data sources have brought statistical data mining and machine learning under more scrutiny, evaluation and application for gleaning insights from the data than ever before. Much is expected from algorithms without understanding their limitations at scale while dealing with massive datasets. In that context, we pose and address the following questions How does a machine learning algorithm perform on measuresmore » such as accuracy and execution time with increasing sample size and feature dimensionality? Does training with more samples guarantee better accuracy? How many features to compute for a given problem? Do more features guarantee better accuracy? Do efforts to derive and calculate more features and train on larger samples worth the effort? As problems become more complex and traditional binary classification algorithms are replaced with multi-task, multi-class categorization algorithms do parallel learners perform better? What happens to the accuracy of the learning algorithm when trained to categorize multiple classes within the same feature space? Towards finding answers to these questions, we describe the design of an empirical study and present the results. We conclude with the following observations (i) accuracy of the learning algorithm increases with increasing sample size but saturates at a point, beyond which more samples do not contribute to better accuracy/learning, (ii) the richness of the feature space dictates performance - both accuracy and training time, (iii) increased dimensionality often reflected in better performance (higher accuracy in spite of longer training times) but the improvements are not commensurate the efforts for feature computation and training and (iv) accuracy of the learning algorithms drop significantly with multi-class learners training on the same feature matrix and (v) learning algorithms perform well when categories in labeled data are independent (i.e., no relationship or hierarchy exists among categories).« less

The Use of Biosimulation in the Design of a Novel Multi-level Weight Loss Maintenance Program for Overweight Children

PubMed Central

Wilfley, Denise E.; Van Buren, Dorothy J.; Theim, Kelly R.; Stein, Richard I.; Saelens, Brian E.; Ezzet, Farkad; Russian, Angela C.; Perri, Michael G.; Epstein, Leonard H.

2011-01-01

Objective Weight loss outcomes achieved through conventional behavior change interventions are prone to deterioration over time. Basic learning laboratory studies in the area of behavioral extinction and renewal and multi-level models of weight control offer clues as to why newly acquired weight loss skills are prone to relapse. According to these models, current clinic-based interventions may not be of sufficient duration or scope to allow for the practice of new skills across the multiple community contexts necessary to promote sustainable weight loss. Although longer, more intensive interventions with greater reach may hold the key to improving weight loss outcomes, it is difficult to test these assumptions in a time efficient and cost-effective manner. A research design tool that has been increasingly utilized in other fields (e.g., pharmaceuticals) is the use of biosimulation analyses. The present paper describes our research team's use of computer simulation models to assist in designing a study to test a novel, comprehensive socio-environmental treatment approach to weight loss maintenance in children ages 7 to 12 years. Methods Weight outcome data from the weight loss, weight maintenance, and follow-up phases of a recently completed randomized controlled trial (RCT) were used to describe the time course of a proposed, extended multi-level treatment program. Simulations were then conducted to project the expected changes in child percent overweight trajectories in the proposed study. Results A 12.9% decrease in percent overweight at 30 months was estimated based upon the midway point between models of “best-case” and “worst-case” weight maintenance scenarios. Conclusions Preliminary data and further analyses, including biosimulation projections, suggest that our socio-environmental approach to weight loss maintenance treatment is promising and warrants evaluation in a large-scale RCT. Biosimulation techniques may have utility in the design of future community-level interventions for the treatment and prevention of childhood overweight. PMID:20107468

Instance annotation for multi-instance multi-label learning

Treesearch

F. Briggs; X.Z. Fern; R. Raich; Q. Lou

2013-01-01

Multi-instance multi-label learning (MIML) is a framework for supervised classification where the objects to be classified are bags of instances associated with multiple labels. For example, an image can be represented as a bag of segments and associated with a list of objects it contains. Prior work on MIML has focused on predicting label sets for previously unseen...

Assessment of the Orion-SLS Interface Management Process in Achieving the EIA 731.1 Systems Engineering Capability Model Generic Practices Level 3 Criteria

NASA Technical Reports Server (NTRS)

Jellicorse, John J.; Rahman, Shamin A.

2016-01-01

NASA is currently developing the next generation crewed spacecraft and launch vehicle for exploration beyond earth orbit including returning to the Moon and making the transit to Mars. Managing the design integration of major hardware elements of a space transportation system is critical for overcoming both the technical and programmatic challenges in taking a complex system from concept to space operations. An established method of accomplishing this is formal interface management. In this paper we set forth an argument that the interface management process implemented by NASA between the Orion Multi-Purpose Crew Vehicle (MPCV) and the Space Launch System (SLS) achieves the Level 3 tier of the EIA 731.1 System Engineering Capability Model (SECM) for Generic Practices. We describe the relevant NASA systems and associated organizations, and define the EIA SECM Level 3 Generic Practices. We then provide evidence for our compliance with those practices. This evidence includes discussions of: NASA Systems Engineering Interface (SE) Management standard process and best practices; the tailoring of that process for implementation on the Orion to SLS interface; changes made over time to improve the tailored process, and; the opportunities to take the resulting lessons learned and propose improvements to our institutional processes and best practices. We compare this evidence against the practices to form the rationale for the declared SECM maturity level.

[Gender-dependent effects of histone deacetylase inhibitor sodium valproate on early olfactory learning in 129Sv mice].

PubMed

Burenkova, O V; Aleksandrova, E A; Zaraĭskaia, I Iu

2013-02-01

In the brain, histone acetylation underlies both learning and the maintenance of long-term sustained effects of early experience which is further epigenetically inherited. However, the role of acetylation in learning previously has only been studied in adult animals: high level of learning could be dependent on high levels of histone H3 acetylation in the brain. The role of acetylation in the mechanisms of early learning has not been studied. In the present work, we were interested whether histone deacetylase inhibitor sodium valproate which increases the level of histone H3 acetylation will affect early olfactory discrimination learning in 8-day-old pups of 129Sv mice that are characterized by low efficiency of learning with imitation of maternal grooming. Multiple valproate injections from 3rd to 6th postnatal day had a gender-dependent effect: learning was selectively improved in male but not in female pups. In the female pups, learning improvement was observed after multiple injections of saline. Possible epigenetic mechanisms underlying these sex differences are discussed.

The Promise of Multimedia Technology for STI/HIV Prevention: Frameworks for Understanding Improved Facilitator Delivery and Participant Learning

PubMed Central

Epperson, Matthew W.; Gilbert, Louisa; Goddard, Dawn; Hunt, Timothy; Sarfo, Bright; El-Bassel, Nabila

2018-01-01

There is increasing excitement about multi-media sexually transmitted infection (STI) and HIV prevention interventions, yet there has been limited discussion of how use of multimedia technology may improve STI/HIV prevention efforts. The purpose of this paper is to describe the mechanisms through which multimedia technology may work to improve the delivery and uptake of intervention material. We present conceptual frameworks describing how multimedia technology may improve intervention delivery by increasing standardization and fidelity to the intervention material and the participant’s ability to learn by improving attention, cognition, emotional engagement, skills-building, and uptake of sensitive material about sexual and drug risks. In addition, we describe how the non-multimedia behavioral STI/HIV prevention intervention, Project WORTH, was adapted into a multimedia format for women involved in the criminal justice system and provide examples of how multimedia activities can more effectively target key mediators of behavioral change in this intervention. PMID:22223296

DeepFruits: A Fruit Detection System Using Deep Neural Networks

PubMed Central

Sa, Inkyu; Ge, Zongyuan; Dayoub, Feras; Upcroft, Ben; Perez, Tristan; McCool, Chris

2016-01-01

This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN). We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB) and Near-Infrared (NIR). Early and late fusion methods are explored for combining the multi-modal (RGB and NIR) information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0.807 to 0.838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform). The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit. PMID:27527168

DeepFruits: A Fruit Detection System Using Deep Neural Networks.

PubMed

Sa, Inkyu; Ge, Zongyuan; Dayoub, Feras; Upcroft, Ben; Perez, Tristan; McCool, Chris

2016-08-03

This paper presents a novel approach to fruit detection using deep convolutional neural networks. The aim is to build an accurate, fast and reliable fruit detection system, which is a vital element of an autonomous agricultural robotic platform; it is a key element for fruit yield estimation and automated harvesting. Recent work in deep neural networks has led to the development of a state-of-the-art object detector termed Faster Region-based CNN (Faster R-CNN). We adapt this model, through transfer learning, for the task of fruit detection using imagery obtained from two modalities: colour (RGB) and Near-Infrared (NIR). Early and late fusion methods are explored for combining the multi-modal (RGB and NIR) information. This leads to a novel multi-modal Faster R-CNN model, which achieves state-of-the-art results compared to prior work with the F1 score, which takes into account both precision and recall performances improving from 0 . 807 to 0 . 838 for the detection of sweet pepper. In addition to improved accuracy, this approach is also much quicker to deploy for new fruits, as it requires bounding box annotation rather than pixel-level annotation (annotating bounding boxes is approximately an order of magnitude quicker to perform). The model is retrained to perform the detection of seven fruits, with the entire process taking four hours to annotate and train the new model per fruit.

BN-FLEMOps pluvial - A probabilistic multi-variable loss estimation model for pluvial floods

NASA Astrophysics Data System (ADS)

Roezer, V.; Kreibich, H.; Schroeter, K.; Doss-Gollin, J.; Lall, U.; Merz, B.

2017-12-01

Pluvial flood events, such as in Copenhagen (Denmark) in 2011, Beijing (China) in 2012 or Houston (USA) in 2016, have caused severe losses to urban dwellings in recent years. These floods are caused by storm events with high rainfall rates well above the design levels of urban drainage systems, which lead to inundation of streets and buildings. A projected increase in frequency and intensity of heavy rainfall events in many areas and an ongoing urbanization may increase pluvial flood losses in the future. For an efficient risk assessment and adaptation to pluvial floods, a quantification of the flood risk is needed. Few loss models have been developed particularly for pluvial floods. These models usually use simple waterlevel- or rainfall-loss functions and come with very high uncertainties. To account for these uncertainties and improve the loss estimation, we present a probabilistic multi-variable loss estimation model for pluvial floods based on empirical data. The model was developed in a two-step process using a machine learning approach and a comprehensive database comprising 783 records of direct building and content damage of private households. The data was gathered through surveys after four different pluvial flood events in Germany between 2005 and 2014. In a first step, linear and non-linear machine learning algorithms, such as tree-based and penalized regression models were used to identify the most important loss influencing factors among a set of 55 candidate variables. These variables comprise hydrological and hydraulic aspects, early warning, precaution, building characteristics and the socio-economic status of the household. In a second step, the most important loss influencing variables were used to derive a probabilistic multi-variable pluvial flood loss estimation model based on Bayesian Networks. Two different networks were tested: a score-based network learned from the data and a network based on expert knowledge. Loss predictions are made through Bayesian inference using Markov chain Monte Carlo (MCMC) sampling. With the ability to cope with incomplete information and use expert knowledge, as well as inherently providing quantitative uncertainty information, it is shown that loss models based on BNs are superior to deterministic approaches for pluvial flood risk assessment.

Reinforcement learning in supply chains.

PubMed

Valluri, Annapurna; North, Michael J; Macal, Charles M

2009-10-01

Effective management of supply chains creates value and can strategically position companies. In practice, human beings have been found to be both surprisingly successful and disappointingly inept at managing supply chains. The related fields of cognitive psychology and artificial intelligence have postulated a variety of potential mechanisms to explain this behavior. One of the leading candidates is reinforcement learning. This paper applies agent-based modeling to investigate the comparative behavioral consequences of three simple reinforcement learning algorithms in a multi-stage supply chain. For the first time, our findings show that the specific algorithm that is employed can have dramatic effects on the results obtained. Reinforcement learning is found to be valuable in multi-stage supply chains with several learning agents, as independent agents can learn to coordinate their behavior. However, learning in multi-stage supply chains using these postulated approaches from cognitive psychology and artificial intelligence take extremely long time periods to achieve stability which raises questions about their ability to explain behavior in real supply chains. The fact that it takes thousands of periods for agents to learn in this simple multi-agent setting provides new evidence that real world decision makers are unlikely to be using strict reinforcement learning in practice.

Improving students' understanding of quantum mechanics

NASA Astrophysics Data System (ADS)

Zhu, Guangtian

2011-12-01

Learning physics is challenging at all levels. Students' difficulties in the introductory level physics courses have been widely studied and many instructional strategies have been developed to help students learn introductory physics. However, research shows that there is a large diversity in students' preparation and skills in the upper-level physics courses and it is necessary to provide scaffolding support to help students learn advanced physics. This thesis explores issues related to students' common difficulties in learning upper-level undergraduate quantum mechanics and how these difficulties can be reduced by research-based learning tutorials and peer instruction tools. We investigated students' difficulties in learning quantum mechanics by administering written tests and surveys to many classes and conducting individual interviews with a subset of students. Based on these investigations, we developed Quantum Interactive Learning Tutorials (QuILTs) and peer instruction tools to help students build a hierarchical knowledge structure of quantum mechanics through a guided approach. Preliminary assessments indicate that students' understanding of quantum mechanics is improved after using the research-based learning tools in the junior-senior level quantum mechanics courses. We also designed a standardized conceptual survey that can help instructors better probe students' understanding of quantum mechanics concepts in one spatial dimension. The validity and reliability of this quantum mechanics survey is discussed.

Perceptual Learning Improves Adult Amblyopic Vision Through Rule-Based Cognitive Compensation

PubMed Central

Zhang, Jun-Yun; Cong, Lin-Juan; Klein, Stanley A.; Levi, Dennis M.; Yu, Cong

2014-01-01

Purpose. We investigated whether perceptual learning in adults with amblyopia could be enabled to transfer completely to an orthogonal orientation, which would suggest that amblyopic perceptual learning results mainly from high-level cognitive compensation, rather than plasticity in the amblyopic early visual brain. Methods. Nineteen adults (mean age = 22.5 years) with anisometropic and/or strabismic amblyopia were trained following a training-plus-exposure (TPE) protocol. The amblyopic eyes practiced contrast, orientation, or Vernier discrimination at one orientation for six to eight sessions. Then the amblyopic or nonamblyopic eyes were exposed to an orthogonal orientation via practicing an irrelevant task. Training was first performed at a lower spatial frequency (SF), then at a higher SF near the cutoff frequency of the amblyopic eye. Results. Perceptual learning was initially orientation specific. However, after exposure to the orthogonal orientation, learning transferred to an orthogonal orientation completely. Reversing the exposure and training order failed to produce transfer. Initial lower SF training led to broad improvement of contrast sensitivity, and later higher SF training led to more specific improvement at high SFs. Training improved visual acuity by 1.5 to 1.6 lines (P < 0.001) in the amblyopic eyes with computerized tests and a clinical E acuity chart. It also improved stereoacuity by 53% (P < 0.001). Conclusions. The complete transfer of learning suggests that perceptual learning in amblyopia may reflect high-level learning of rules for performing a visual discrimination task. These rules are applicable to new orientations to enable learning transfer. Therefore, perceptual learning may improve amblyopic vision mainly through rule-based cognitive compensation. PMID:24550359

Perceptual learning improves adult amblyopic vision through rule-based cognitive compensation.

PubMed

Zhang, Jun-Yun; Cong, Lin-Juan; Klein, Stanley A; Levi, Dennis M; Yu, Cong

2014-04-01

We investigated whether perceptual learning in adults with amblyopia could be enabled to transfer completely to an orthogonal orientation, which would suggest that amblyopic perceptual learning results mainly from high-level cognitive compensation, rather than plasticity in the amblyopic early visual brain. Nineteen adults (mean age = 22.5 years) with anisometropic and/or strabismic amblyopia were trained following a training-plus-exposure (TPE) protocol. The amblyopic eyes practiced contrast, orientation, or Vernier discrimination at one orientation for six to eight sessions. Then the amblyopic or nonamblyopic eyes were exposed to an orthogonal orientation via practicing an irrelevant task. Training was first performed at a lower spatial frequency (SF), then at a higher SF near the cutoff frequency of the amblyopic eye. Perceptual learning was initially orientation specific. However, after exposure to the orthogonal orientation, learning transferred to an orthogonal orientation completely. Reversing the exposure and training order failed to produce transfer. Initial lower SF training led to broad improvement of contrast sensitivity, and later higher SF training led to more specific improvement at high SFs. Training improved visual acuity by 1.5 to 1.6 lines (P < 0.001) in the amblyopic eyes with computerized tests and a clinical E acuity chart. It also improved stereoacuity by 53% (P < 0.001). The complete transfer of learning suggests that perceptual learning in amblyopia may reflect high-level learning of rules for performing a visual discrimination task. These rules are applicable to new orientations to enable learning transfer. Therefore, perceptual learning may improve amblyopic vision mainly through rule-based cognitive compensation.

Training directionally selective motion pathways can significantly improve reading efficiency

NASA Astrophysics Data System (ADS)

Lawton, Teri

2004-06-01

This study examined whether perceptual learning at early levels of visual processing would facilitate learning at higher levels of processing. This was examined by determining whether training the motion pathways by practicing leftright movement discrimination, as found previously, would improve the reading skills of inefficient readers significantly more than another computer game, a word discrimination game, or the reading program offered by the school. This controlled validation study found that practicing left-right movement discrimination 5-10 minutes twice a week (rapidly) for 15 weeks doubled reading fluency, and significantly improved all reading skills by more than one grade level, whereas inefficient readers in the control groups barely improved on these reading skills. In contrast to previous studies of perceptual learning, these experiments show that perceptual learning of direction discrimination significantly improved reading skills determined at higher levels of cognitive processing, thereby being generalized to a new task. The deficits in reading performance and attentional focus experienced by the person who struggles when reading are suggested to result from an information overload, resulting from timing deficits in the direction-selectivity network proposed by Russell De Valois et al. (2000), that following practice on direction discrimination goes away. This study found that practicing direction discrimination rapidly transitions the inefficient 7-year-old reader to an efficient reader.

Automatic Association of Chats and Video Tracks for Activity Learning and Recognition in Aerial Video Surveillance

PubMed Central

Hammoud, Riad I.; Sahin, Cem S.; Blasch, Erik P.; Rhodes, Bradley J.; Wang, Tao

2014-01-01

We describe two advanced video analysis techniques, including video-indexed by voice annotations (VIVA) and multi-media indexing and explorer (MINER). VIVA utilizes analyst call-outs (ACOs) in the form of chat messages (voice-to-text) to associate labels with video target tracks, to designate spatial-temporal activity boundaries and to augment video tracking in challenging scenarios. Challenging scenarios include low-resolution sensors, moving targets and target trajectories obscured by natural and man-made clutter. MINER includes: (1) a fusion of graphical track and text data using probabilistic methods; (2) an activity pattern learning framework to support querying an index of activities of interest (AOIs) and targets of interest (TOIs) by movement type and geolocation; and (3) a user interface to support streaming multi-intelligence data processing. We also present an activity pattern learning framework that uses the multi-source associated data as training to index a large archive of full-motion videos (FMV). VIVA and MINER examples are demonstrated for wide aerial/overhead imagery over common data sets affording an improvement in tracking from video data alone, leading to 84% detection with modest misdetection/false alarm results due to the complexity of the scenario. The novel use of ACOs and chat messages in video tracking paves the way for user interaction, correction and preparation of situation awareness reports. PMID:25340453

Veterans Health Administration's Disaster Emergency Medical Personnel System (DEMPS) Training Evaluation: Potential Implications for Disaster Health Care Volunteers.

PubMed

Schmitz, Susan; Radcliff, Tiffany A; Chu, Karen; Smith, Robert E; Dobalian, Aram

2018-02-20

The US Veterans Health Administration's Disaster Emergency Medical Personnel System (DEMPS) is a team of employee disaster response volunteers who provide clinical and non-clinical staffing assistance when local systems are overwhelmed. This study evaluated attitudes and recommendations of the DEMPS program to understand the impact of multi-modal training on volunteer perceptions. DEMPS volunteers completed an electronic survey in 2012 (n=2120). Three training modes were evaluated: online, field exercise, and face-to-face. Measures included: "Training Satisfaction," "Attitudes about Training," "Continued Engagement in DEMPS." Data were analyzed using χ2 and logistic regression. Open-ended questions were evaluated in a manner consistent with grounded theory methodology. Most respondents participated in DEMPS training (80%). Volunteers with multi-modal training who completed all 3 modes (14%) were significantly more likely to have positive attitudes about training, plan to continue as volunteers, and would recommend DEMPS to others (P-value<0.001). Some respondents requested additional interactive activities and suggested increased availability of training may improve volunteer engagement. A blended learning environment using multi-modal training methods, could enhance satisfaction and attitudes and possibly encourage continued engagement in DEMPS or similar programs. DEMPS training program modifications in 2015 expanded this blended learning approach through new interactive online learning opportunities. (Disaster Med Public Health Preparedness. 2018; page 1 of 8).

Automatic association of chats and video tracks for activity learning and recognition in aerial video surveillance.

PubMed

Hammoud, Riad I; Sahin, Cem S; Blasch, Erik P; Rhodes, Bradley J; Wang, Tao

2014-10-22

We describe two advanced video analysis techniques, including video-indexed by voice annotations (VIVA) and multi-media indexing and explorer (MINER). VIVA utilizes analyst call-outs (ACOs) in the form of chat messages (voice-to-text) to associate labels with video target tracks, to designate spatial-temporal activity boundaries and to augment video tracking in challenging scenarios. Challenging scenarios include low-resolution sensors, moving targets and target trajectories obscured by natural and man-made clutter. MINER includes: (1) a fusion of graphical track and text data using probabilistic methods; (2) an activity pattern learning framework to support querying an index of activities of interest (AOIs) and targets of interest (TOIs) by movement type and geolocation; and (3) a user interface to support streaming multi-intelligence data processing. We also present an activity pattern learning framework that uses the multi-source associated data as training to index a large archive of full-motion videos (FMV). VIVA and MINER examples are demonstrated for wide aerial/overhead imagery over common data sets affording an improvement in tracking from video data alone, leading to 84% detection with modest misdetection/false alarm results due to the complexity of the scenario. The novel use of ACOs and chat Sensors 2014, 14 19844 messages in video tracking paves the way for user interaction, correction and preparation of situation awareness reports.

United states national land cover data base development? 1992-2001 and beyond

USGS Publications Warehouse

Yang, L.

2008-01-01

An accurate, up-to-date and spatially-explicate national land cover database is required for monitoring the status and trends of the nation's terrestrial ecosystem, and for managing and conserving land resources at the national scale. With all the challenges and resources required to develop such a database, an innovative and scientifically sound planning must be in place and a partnership be formed among users from government agencies, research institutes and private sectors. In this paper, we summarize major scientific and technical issues regarding the development of the NLCD 1992 and 2001. Experiences and lessons learned from the project are documented with regard to project design, technical approaches, accuracy assessment strategy, and projecti imiplementation.Future improvements in developing next generation NLCD beyond 2001 are suggested, including: 1) enhanced satellite data preprocessing in correction of atmospheric and adjacency effect and the topographic normalization; 2) improved classification accuracy through comprehensive and consistent training data and new algorithm development; 3) multi-resolution and multi-temporal database targeting major land cover changes and land cover database updates; 4) enriched database contents by including additional biophysical parameters and/or more detailed land cover classes through synergizing multi-sensor, multi-temporal, and multi-spectral satellite data and ancillary data, and 5) transform the NLCD project into a national land cover monitoring program. ?? 2008 IEEE.

Integrative Data Analysis of Multi-Platform Cancer Data with a Multimodal Deep Learning Approach.

PubMed

Liang, Muxuan; Li, Zhizhong; Chen, Ting; Zeng, Jianyang

2015-01-01

Identification of cancer subtypes plays an important role in revealing useful insights into disease pathogenesis and advancing personalized therapy. The recent development of high-throughput sequencing technologies has enabled the rapid collection of multi-platform genomic data (e.g., gene expression, miRNA expression, and DNA methylation) for the same set of tumor samples. Although numerous integrative clustering approaches have been developed to analyze cancer data, few of them are particularly designed to exploit both deep intrinsic statistical properties of each input modality and complex cross-modality correlations among multi-platform input data. In this paper, we propose a new machine learning model, called multimodal deep belief network (DBN), to cluster cancer patients from multi-platform observation data. In our integrative clustering framework, relationships among inherent features of each single modality are first encoded into multiple layers of hidden variables, and then a joint latent model is employed to fuse common features derived from multiple input modalities. A practical learning algorithm, called contrastive divergence (CD), is applied to infer the parameters of our multimodal DBN model in an unsupervised manner. Tests on two available cancer datasets show that our integrative data analysis approach can effectively extract a unified representation of latent features to capture both intra- and cross-modality correlations, and identify meaningful disease subtypes from multi-platform cancer data. In addition, our approach can identify key genes and miRNAs that may play distinct roles in the pathogenesis of different cancer subtypes. Among those key miRNAs, we found that the expression level of miR-29a is highly correlated with survival time in ovarian cancer patients. These results indicate that our multimodal DBN based data analysis approach may have practical applications in cancer pathogenesis studies and provide useful guidelines for personalized cancer therapy.

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.

Practice What You Teach: Connecting Curriculum & Professional Learning in Schools

ERIC Educational Resources Information Center

Wiener, Ross; Pimentel, Susan

2017-01-01

To improve teaching and advance student learning requires weaving together the curriculum that students engage with every day with the professional learning of teachers. This paper is designed as a resource for system leaders at the district, state, and charter-management organization (CMO) levels looking to improve instructional outcomes for…

A Statewide Collaborative Effort to Create School Leadership that Supports Learning

ERIC Educational Resources Information Center

Waddle, Jerry L.; Murphy, Carole H.

2007-01-01

With the evidence that improved leadership in schools produces increased student learning and with the accountability demands of No Child Left Behind and the Missouri School Improvement Program, it is imperative that school leaders in Missouri be prepared to support student learning at its highest level. Therefore, Missouri has made a substantial…

Crack Damage Detection Method via Multiple Visual Features and Efficient Multi-Task Learning Model.

PubMed

Wang, Baoxian; Zhao, Weigang; Gao, Po; Zhang, Yufeng; Wang, Zhe

2018-06-02

This paper proposes an effective and efficient model for concrete crack detection. The presented work consists of two modules: multi-view image feature extraction and multi-task crack region detection. Specifically, multiple visual features (such as texture, edge, etc.) of image regions are calculated, which can suppress various background noises (such as illumination, pockmark, stripe, blurring, etc.). With the computed multiple visual features, a novel crack region detector is advocated using a multi-task learning framework, which involves restraining the variability for different crack region features and emphasizing the separability between crack region features and complex background ones. Furthermore, the extreme learning machine is utilized to construct this multi-task learning model, thereby leading to high computing efficiency and good generalization. Experimental results of the practical concrete images demonstrate that the developed algorithm can achieve favorable crack detection performance compared with traditional crack detectors.

An interview study of how clinical teachers develop skills to attend to different level learners.

PubMed

Chen, H Carrie; Fogh, Shannon; Kobashi, Brent; Teherani, Arianne; Ten Cate, Olle; O'Sullivan, Patricia

2016-06-01

One clinical teaching challenge is the engagement of learners at different levels. Faculty development offerings mostly address general strategies applicable to all learners. This study examined how clinical faculty members develop the skills to work with different level learners. We conducted semi-structured interviews with medical school faculty members identified as excellent clinical teachers teaching multiple levels of learners. They discussed how they developed their approach to teaching different level learners and how their teaching evolved over time. We performed thematic analysis of the interview transcripts using open and axial coding. We interviewed 19 faculty members and identified three themes related to development of teaching practices: teacher agency and work-based learning of teaching strategies, developmental trajectory of clinical teachers, and interplay between clinical confidence and teaching skills. Faculty members were proactive in using on-the-job experiences to develop their teaching practices. Their teaching practices followed a developmental trajectory towards learner centeredness, and this evolution was associated with the development of clinical skills and confidence. Learning skills to teach multi-level learners requires workplace learning. Faculty development should include workplace learning opportunities and use a developmental approach that accounts for the trajectory of teaching as well as clinical skills attainment.

Review of the Status of Learning in Research on Sport Education: Future Research and Practice

PubMed Central

Araújo, Rui; Mesquita, Isabel; Hastie, Peter A.

2014-01-01

Research concerning Sport Education’s educational impact has shown unequivocal results according to students’ personal and social development. Nevertheless, research is still sparse with respect to the model’s impact on student learning outcomes. The goal of the present review is to therefore scrutinize what is currently known regarding students’ learning during their participation in Sport Education. This research spans a variety of studies, cross various countries, school grades, the sports studied, as well as the methods applied and dimensions of student learning analyzed. While research on the impact of Sport Education on students’ learning, as well as teachers’ and students’ perceptions about student learning has shown students’ improvements during the participation in Sport Education seasons, there is still considerable variance in these results. For example, some studies report superior learning opportunities to boys and higher skill-level students while other studies have identified superior learning opportunities for girls and lower skill-level students. These inconsistent results can be explained by factors not considered in the Sport Education research, such as the effect of time on students’ learning and the control of the teaching-learning process within Sport Education units. In this review directions for future research and practice are also described. Future research should define, implement, and evaluate protocols for student-coaches’ preparation in order to understand the influence of this issue on students’ learning as well as consider the implementation of hybrid approaches. Moreover, future studies should consider the interaction of gender and skill level and a retention test in the analysis of students’ learning improvements in order to obtain a more realist and complete portrait of the impact of Sport Education. Finally, in order to reach an entirely understanding of the teaching-learning process, it is necessary to use research designs that attend to the complexity of this process. Key Points Despite research regarding has showed students’ improvements during the participation in Sport Education seasons, it remains somewhat equivocal. The studies included in this review show students’ improvements on skill, knowledge and tactical development, as we as game play, during the participation in Sport Education units. Some studies report superior learning opportunities to boys and higher skill-level students while other studies exposed superior learning opportunities to girls and lower skill-level students. The effect of time on students’ learning and the control of the teaching-learning process within Sport Education units can explain these equivocal results. Future research is encouraged to consider the implementation of protocols for student-coaches’ preparation, hybrid models, a retention test, the interaction of gender and skill level, and use research designs that attend to the complexity of the teaching-learning process. PMID:25435778

Review of the status of learning in research on sport education: future research and practice.

PubMed

Araújo, Rui; Mesquita, Isabel; Hastie, Peter A

2014-12-01

Research concerning Sport Education's educational impact has shown unequivocal results according to students' personal and social development. Nevertheless, research is still sparse with respect to the model's impact on student learning outcomes. The goal of the present review is to therefore scrutinize what is currently known regarding students' learning during their participation in Sport Education. This research spans a variety of studies, cross various countries, school grades, the sports studied, as well as the methods applied and dimensions of student learning analyzed. While research on the impact of Sport Education on students' learning, as well as teachers' and students' perceptions about student learning has shown students' improvements during the participation in Sport Education seasons, there is still considerable variance in these results. For example, some studies report superior learning opportunities to boys and higher skill-level students while other studies have identified superior learning opportunities for girls and lower skill-level students. These inconsistent results can be explained by factors not considered in the Sport Education research, such as the effect of time on students' learning and the control of the teaching-learning process within Sport Education units. In this review directions for future research and practice are also described. Future research should define, implement, and evaluate protocols for student-coaches' preparation in order to understand the influence of this issue on students' learning as well as consider the implementation of hybrid approaches. Moreover, future studies should consider the interaction of gender and skill level and a retention test in the analysis of students' learning improvements in order to obtain a more realist and complete portrait of the impact of Sport Education. Finally, in order to reach an entirely understanding of the teaching-learning process, it is necessary to use research designs that attend to the complexity of this process. Key PointsDespite research regarding has showed students' improvements during the participation in Sport Education seasons, it remains somewhat equivocal.The studies included in this review show students' improvements on skill, knowledge and tactical development, as we as game play, during the participation in Sport Education units.Some studies report superior learning opportunities to boys and higher skill-level students while other studies exposed superior learning opportunities to girls and lower skill-level students.The effect of time on students' learning and the control of the teaching-learning process within Sport Education units can explain these equivocal results.Future research is encouraged to consider the implementation of protocols for student-coaches' preparation, hybrid models, a retention test, the interaction of gender and skill level, and use research designs that attend to the complexity of the teaching-learning process.

Predict Brain MR Image Registration via Sparse Learning of Appearance and Transformation

PubMed Central

Wang, Qian; Kim, Minjeong; Shi, Yonghong; Wu, Guorong; Shen, Dinggang

2014-01-01

We propose a new approach to register the subject image with the template by leveraging a set of intermediate images that are pre-aligned to the template. We argue that, if points in the subject and the intermediate images share similar local appearances, they may have common correspondence in the template. In this way, we learn the sparse representation of a certain subject point to reveal several similar candidate points in the intermediate images. Each selected intermediate candidate can bridge the correspondence from the subject point to the template space, thus predicting the transformation associated with the subject point at the confidence level that relates to the learned sparse coefficient. Following this strategy, we first predict transformations at selected key points, and retain multiple predictions on each key point, instead of allowing only a single correspondence. Then, by utilizing all key points and their predictions with varying confidences, we adaptively reconstruct the dense transformation field that warps the subject to the template. We further embed the prediction-reconstruction protocol above into a multi-resolution hierarchy. In the final, we refine our estimated transformation field via existing registration method in effective manners. We apply our method to registering brain MR images, and conclude that the proposed framework is competent to improve registration performances substantially. PMID:25476412

Use of machine learning to improve autism screening and diagnostic instruments: effectiveness, efficiency, and multi-instrument fusion

PubMed Central

Bone, Daniel; Bishop, Somer; Black, Matthew P.; Goodwin, Matthew S.; Lord, Catherine; Narayanan, Shrikanth S.

2016-01-01

Background Machine learning (ML) provides novel opportunities for human behavior research and clinical translation, yet its application can have noted pitfalls (Bone et al., 2015). In this work, we fastidiously utilize ML to derive autism spectrum disorder (ASD) instrument algorithms in an attempt to improve upon widely-used ASD screening and diagnostic tools. Methods The data consisted of Autism Diagnostic Interview-Revised (ADI-R) and Social Responsiveness Scale (SRS) scores for 1,264 verbal individuals with ASD and 462 verbal individuals with non-ASD developmental or psychiatric disorders (DD), split at age 10. Algorithms were created via a robust ML classifier, support vector machine (SVM), while targeting best-estimate clinical diagnosis of ASD vs. non-ASD. Parameter settings were tuned in multiple levels of cross-validation. Results The created algorithms were more effective (higher performing) than current algorithms, were tunable (sensitivity and specificity can be differentially weighted), and were more efficient (achieving near-peak performance with five or fewer codes). Results from ML-based fusion of ADI-R and SRS are reported. We present a screener algorithm for below (above) age 10 that reached 89.2% (86.7%) sensitivity and 59.0% (53.4%) specificity with only five behavioral codes. Conclusions ML is useful for creating robust, customizable instrument algorithms. In a unique dataset comprised of controls with other difficulties, our findings highlight limitations of current caregiver-report instruments and indicate possible avenues for improving ASD screening and diagnostic tools. PMID:27090613

Use of machine learning to improve autism screening and diagnostic instruments: effectiveness, efficiency, and multi-instrument fusion.

PubMed

Bone, Daniel; Bishop, Somer L; Black, Matthew P; Goodwin, Matthew S; Lord, Catherine; Narayanan, Shrikanth S

2016-08-01

Machine learning (ML) provides novel opportunities for human behavior research and clinical translation, yet its application can have noted pitfalls (Bone et al., 2015). In this work, we fastidiously utilize ML to derive autism spectrum disorder (ASD) instrument algorithms in an attempt to improve upon widely used ASD screening and diagnostic tools. The data consisted of Autism Diagnostic Interview-Revised (ADI-R) and Social Responsiveness Scale (SRS) scores for 1,264 verbal individuals with ASD and 462 verbal individuals with non-ASD developmental or psychiatric disorders, split at age 10. Algorithms were created via a robust ML classifier, support vector machine, while targeting best-estimate clinical diagnosis of ASD versus non-ASD. Parameter settings were tuned in multiple levels of cross-validation. The created algorithms were more effective (higher performing) than the current algorithms, were tunable (sensitivity and specificity can be differentially weighted), and were more efficient (achieving near-peak performance with five or fewer codes). Results from ML-based fusion of ADI-R and SRS are reported. We present a screener algorithm for below (above) age 10 that reached 89.2% (86.7%) sensitivity and 59.0% (53.4%) specificity with only five behavioral codes. ML is useful for creating robust, customizable instrument algorithms. In a unique dataset comprised of controls with other difficulties, our findings highlight the limitations of current caregiver-report instruments and indicate possible avenues for improving ASD screening and diagnostic tools. © 2016 Association for Child and Adolescent Mental Health.

Gender and Acceptance of E-Learning: A Multi-Group Analysis Based on a Structural Equation Model among College Students in Chile and Spain

PubMed Central

2015-01-01

The scope of this study was to evaluate whether the adoption of e-learning in two universities, and in particular, the relationship between the perception of external control and perceived ease of use, is different because of gender differences. The study was carried out with participating students in two different universities, one in Chile and one in Spain. The Technology Acceptance Model was used as a theoretical framework for the study. A multi-group analysis method in partial least squares was employed to relate differences between groups. The four main conclusions of the study are: (1) a version of the Technology Acceptance Model has been successfully used to explain the process of adoption of e-learning at an undergraduate level of study; (2) the finding of a strong and significant relationship between perception of external control and perception of ease of use of the e-learning platform; (3) a significant relationship between perceived enjoyment and perceived ease of use and between results demonstrability and perceived usefulness is found; (4) the study indicates a few statistically significant differences between males and females when adopting an e-learning platform, according to the tested model. PMID:26465895

Protein (multi-)location prediction: using location inter-dependencies in a probabilistic framework

PubMed Central

2014-01-01

Motivation Knowing the location of a protein within the cell is important for understanding its function, role in biological processes, and potential use as a drug target. Much progress has been made in developing computational methods that predict single locations for proteins. Most such methods are based on the over-simplifying assumption that proteins localize to a single location. However, it has been shown that proteins localize to multiple locations. While a few recent systems attempt to predict multiple locations of proteins, their performance leaves much room for improvement. Moreover, they typically treat locations as independent and do not attempt to utilize possible inter-dependencies among locations. Our hypothesis is that directly incorporating inter-dependencies among locations into both the classifier-learning and the prediction process can improve location prediction performance. Results We present a new method and a preliminary system we have developed that directly incorporates inter-dependencies among locations into the location-prediction process of multiply-localized proteins. Our method is based on a collection of Bayesian network classifiers, where each classifier is used to predict a single location. Learning the structure of each Bayesian network classifier takes into account inter-dependencies among locations, and the prediction process uses estimates involving multiple locations. We evaluate our system on a dataset of single- and multi-localized proteins (the most comprehensive protein multi-localization dataset currently available, derived from the DBMLoc dataset). Our results, obtained by incorporating inter-dependencies, are significantly higher than those obtained by classifiers that do not use inter-dependencies. The performance of our system on multi-localized proteins is comparable to a top performing system (YLoc+), without being restricted only to location-combinations present in the training set. PMID:24646119

Protein (multi-)location prediction: using location inter-dependencies in a probabilistic framework.

PubMed

Simha, Ramanuja; Shatkay, Hagit

2014-03-19

Knowing the location of a protein within the cell is important for understanding its function, role in biological processes, and potential use as a drug target. Much progress has been made in developing computational methods that predict single locations for proteins. Most such methods are based on the over-simplifying assumption that proteins localize to a single location. However, it has been shown that proteins localize to multiple locations. While a few recent systems attempt to predict multiple locations of proteins, their performance leaves much room for improvement. Moreover, they typically treat locations as independent and do not attempt to utilize possible inter-dependencies among locations. Our hypothesis is that directly incorporating inter-dependencies among locations into both the classifier-learning and the prediction process can improve location prediction performance. We present a new method and a preliminary system we have developed that directly incorporates inter-dependencies among locations into the location-prediction process of multiply-localized proteins. Our method is based on a collection of Bayesian network classifiers, where each classifier is used to predict a single location. Learning the structure of each Bayesian network classifier takes into account inter-dependencies among locations, and the prediction process uses estimates involving multiple locations. We evaluate our system on a dataset of single- and multi-localized proteins (the most comprehensive protein multi-localization dataset currently available, derived from the DBMLoc dataset). Our results, obtained by incorporating inter-dependencies, are significantly higher than those obtained by classifiers that do not use inter-dependencies. The performance of our system on multi-localized proteins is comparable to a top performing system (YLoc+), without being restricted only to location-combinations present in the training set.

Interdisciplinary: Cultural competency and culturally congruent education for millennials in health professions.

PubMed

Hawala-Druy, Souzan; Hill, Mary H

2012-10-01

The increasingly diverse multicultural and multigenerational student population in the United States requires that educators at all levels develop cultural knowledge, awareness, and sensitivity to help diverse learners fulfill their potential and to avoid cultural misunderstandings that can become obstacles or barriers to learning. The purpose of this study was to design and implement eclectic, creative, evidence-based interdisciplinary educational activities, along with culturally congruent teaching strategies, within a semester-long university course that promoted positive and culturally competent learning outcomes for culturally diverse, largely millennial students. The interdisciplinary course would prepare health professional students with the requisite knowledge and skills, through transformative learning that produces change agents, to provide culturally congruent and quality team-based care to diverse populations. This was a qualitative and quantitative study, which measured students' level of cultural awareness, competence, and proficiency pre and post the educational intervention. Instruments used for data collection included the Inventory for Assessing The Process of Cultural Competence-Student Version (IAPCC-SV) by Campinha-Bacote, course evaluations, students' feedback, and portfolio reflections. The study was conducted at a private academic institution located in the Mid-Atlantic region and the sample population included inter-professional students (N=106) from various health professions including nursing, pharmacy, and allied health sciences. Results from the pre- and post-test IAPCC-SV survey revealed that mean scores increased significantly from pre-test (60.8) to post-test (70.6). Thus, students' levels of cultural competency (awareness, knowledge, skills, desire, encounter) improved post-educational intervention, indicating that the teaching methods used in the course might be applied on a larger scale across the university system to cater to the nation's increasingly multi-cultural population. Copyright © 2012 Elsevier Ltd. All rights reserved.

Overcoming Hurdles Implementing Multi-skilling Policies

DTIC Science & Technology

2015-03-26

skilled workforce? Chapter II will communicate important concepts found in the literature on skill proficiency topics. These topics include skill...training methods that might improve learning and retention during the acquisition phase. 10 The active interlock modeling (AIM) protocol is a dyadic ...retention, as found in 43 Chapter 2. These techniques include dyadic training methods, overlearning, feedback, peer support, and managerial support

Evaluation of Title I Program, Community School Distrlct 31, New York City. 1978-79 School Year. Final Report, E.D.L. Reading Lab.

ERIC Educational Resources Information Center

Knight, Michael E.

This program was designed to improve reading skills and to provide intensive remediation for students in grades six through nine. Specialized materials and equipment were provided by Educational Development Laboratories (EDL). The EDL Reading Laboratory utilized the Learning 100 program, a multi-modality developmental and remedial program. Small…

Has the Bologna Process Been Worthwhile? An Analysis of the Learning Society-Adapted Outcome Index through Quantile Regression

ERIC Educational Resources Information Center

Fernandez-Sainz, A.; García-Merino, J. D.; Urionabarrenetxea, S.

2016-01-01

This paper seeks to discover whether the performance of university students has improved in the wake of the changes in higher education introduced by the Bologna Declaration of 1999 and the construction of the European Higher Education Area. A principal component analysis is used to construct a multi-dimensional performance variable called the…

Raising the Barre & Stretching the Canvas: Implementing High-Quality Arts Programming in a National Youth Serving Organization

ERIC Educational Resources Information Center

McClanahan, Wendy; Hartmann, Tracey A.

2017-01-01

As part of an ongoing, multi-million dollar Wallace Foundation initiative to improve and expand arts learning opportunities for young people, the Wallace Foundation, in partnership with the Boys & Girls Clubs of America (BGCA), developed the Youth Arts Initiative (YAI) to deliver otherwise inaccessible high-quality arts programs to low-income…

From Falling through the Cracks to Pulling Through: Moving from a Traditional Remediation Model toward a Multi-Layered Support Model for Basic Writing

ERIC Educational Resources Information Center

Ostergaard, Lori; Allan, Elizabeth G.

2016-01-01

This article examines two course redesigns undertaken to improve student support, learning, and retention in the basic writing program at Oakland University, a doctoral research university in southeast Michigan, where support for developmental writers has fluctuated dramatically between nurture and neglect over the past fifty years. However,…

Unpacking the "Value Added" Impact of Continuing Professional Education: A Multi-Method Case Study Approach.

ERIC Educational Resources Information Center

Smith, Jo; Topping, Annie

2001-01-01

A study of 14 nurses who completed a children's neuroscience course found evidence of improved knowledge and increased ability to care for neurology patients. Although the direct impact of continuing education on patient care is difficult to assess, participants' assessment of their learning and its potential to affect patient care is a valid…

Abuse of disabled parking: Reforming public's attitude through persuasive multimedia strategy

NASA Astrophysics Data System (ADS)

Yahaya, W. A. J. W.; Zain, M. Z. M.

2014-02-01

Attitude is one of the factors that contribute to the abuse of disabled parking. The attitude's components are affective, cognitive and behavioral and may be formed in various ways including learning and persuasion. Using learning and persuasion approach, this study has produced a persuasive multimedia aiming to form a positive attitude toward disabled persons in order to minimize the rate of disabled parking abuse. The persuasive multimedia was developed using Principle of Social Learning draws from Persuasive Technology as learning strategy at macro persuasion level, and modality and redundancy principles draw from Multimedia Learning Principles as design strategy at micro persuasion level. In order to measure the effectiveness of the persuasive multimedia, 93 respondents were selected in a 2 × 2 quasi experimental research design for experiment. Attitude components of affective, cognitive and behavioral were measured using adapted instrument from the Multi Dimensional Attitudes Scale toward Persons With Disabilities (MAS). Result of the study shows that the persuasive multimedia which designed based on Social Learning Theory at macro persuasion level is capable of forming positive attitude toward disabled person. The cognitive component of the attitude found to be the most responsive component. In term of design strategy at the micro persuasion level, modality found to be the most significant strategy compare to redundancy. While males are more responsive to the persuasive multimedia compare to females.

LINKS: learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images.

PubMed

Wang, Li; Gao, Yaozong; Shi, Feng; Li, Gang; Gilmore, John H; Lin, Weili; Shen, Dinggang

2015-03-01

Segmentation of infant brain MR images is challenging due to insufficient image quality, severe partial volume effect, and ongoing maturation and myelination processes. In the first year of life, the image contrast between white and gray matters of the infant brain undergoes dramatic changes. In particular, the image contrast is inverted around 6-8months of age, and the white and gray matter tissues are isointense in both T1- and T2-weighted MR images and thus exhibit the extremely low tissue contrast, which poses significant challenges for automated segmentation. Most previous studies used multi-atlas label fusion strategy, which has the limitation of equally treating the different available image modalities and is often computationally expensive. To cope with these limitations, in this paper, we propose a novel learning-based multi-source integration framework for segmentation of infant brain images. Specifically, we employ the random forest technique to effectively integrate features from multi-source images together for tissue segmentation. Here, the multi-source images include initially only the multi-modality (T1, T2 and FA) images and later also the iteratively estimated and refined tissue probability maps of gray matter, white matter, and cerebrospinal fluid. Experimental results on 119 infants show that the proposed method achieves better performance than other state-of-the-art automated segmentation methods. Further validation was performed on the MICCAI grand challenge and the proposed method was ranked top among all competing methods. Moreover, to alleviate the possible anatomical errors, our method can also be combined with an anatomically-constrained multi-atlas labeling approach for further improving the segmentation accuracy. Copyright © 2014 Elsevier Inc. All rights reserved.

LINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images

PubMed Central

Wang, Li; Gao, Yaozong; Shi, Feng; Li, Gang; Gilmore, John H.; Lin, Weili; Shen, Dinggang

2014-01-01

Segmentation of infant brain MR images is challenging due to insufficient image quality, severe partial volume effect, and ongoing maturation and myelination processes. In the first year of life, the image contrast between white and gray matters of the infant brain undergoes dramatic changes. In particular, the image contrast is inverted around 6-8 months of age, and the white and gray matter tissues are isointense in both T1- and T2-weighted MR images and thus exhibit the extremely low tissue contrast, which poses significant challenges for automated segmentation. Most previous studies used multi-atlas label fusion strategy, which has the limitation of equally treating the different available image modalities and is often computationally expensive. To cope with these limitations, in this paper, we propose a novel learning-based multi-source integration framework for segmentation of infant brain images. Specifically, we employ the random forest technique to effectively integrate features from multi-source images together for tissue segmentation. Here, the multi-source images include initially only the multi-modality (T1, T2 and FA) images and later also the iteratively estimated and refined tissue probability maps of gray matter, white matter, and cerebrospinal fluid. Experimental results on 119 infants show that the proposed method achieves better performance than other state-of-the-art automated segmentation methods. Further validation was performed on the MICCAI grand challenge and the proposed method was ranked top among all competing methods. Moreover, to alleviate the possible anatomical errors, our method can also be combined with an anatomically-constrained multi-atlas labeling approach for further improving the segmentation accuracy. PMID:25541188

RoboCup: Multi-disciplinary Senior Design Project.

ERIC Educational Resources Information Center

Elder, Kevin Lee

A cross-college team of educators has developed a collaborative, multi-disciplinary senior design course at Ohio University. This course offers an attractive opportunity for students from a variety of disciplines to work together in a learning community to accomplish a challenging task. It provides a novel multi-disciplinary learning environment…

Using Nonlinear Programming in International Trade Theory: The Factor-Proportions Model

ERIC Educational Resources Information Center

Gilbert, John

2004-01-01

Students at all levels benefit from a multi-faceted approach to learning abstract material. The most commonly used technique in teaching the pure theory of international trade is a combination of geometry and algebraic derivations. Numerical simulation can provide a valuable third support to these approaches. The author describes a simple…

Teaching All the Children: Stories from the Classroom.

ERIC Educational Resources Information Center

Leavitt, Midge, Ed.

This book presents personal narratives from New Brunswick teachers concerning their experiences in trying to meet the academic and social needs of children in multi-level classes. Topics include the first year of teaching, the process of adapting for students who have special needs, cooperative learning in the class, integration experiences,…

Social Work Education: Achieving Transformative Learning through a Cultural Competence Model for Transformative Education

ERIC Educational Resources Information Center

Blunt, Kesha

2007-01-01

Migration across national borders has resulted in demographic changes in the United States, causing the country to become more multi-ethnic. This presents considerable challenges for graduate level educators who need to be responsive to the unique academic needs of diverse populations by considering students' previous experiences, values, and…

Students Learning from Patients: Let's Get Real in Medical Education

ERIC Educational Resources Information Center

Bleakley, Alan; Bligh, John

2008-01-01

Medical students must be prepared for working in inter-professional and multi-disciplinary clinical teams centred on a patient's care pathway. While there has been a good deal of rhetoric surrounding patient-centred medical education, there has been little attempt to conceptualise such a practice beyond the level of describing education of…

Mathematics Undergraduates' Responses to Semantic Abbreviations, 'Geometric' Images and Multi-Level Abstractions in Group Theory.

ERIC Educational Resources Information Center

Nardi, Elena

2000-01-01

Identifies and explores the difficulties in the novice mathematician's encounter with mathematical abstraction. Observes 20 first-year mathematics undergraduates and extracts sets of episodes from the transcripts of the tutorials and interviews within five topics in pure mathematics. Discusses issues related to the learning of one mathematical…

The Impact of Response to Intervention on Learning Disability Identification: School Based Practices

ERIC Educational Resources Information Center

Smith, Tina B.

2017-01-01

The "Response to Intervention Guidance for New York State School Districts" (2010) document indicates Response to Intervention (RTI) is a mandated general education process intended to provide early interventions to struggling at-risk students. The multi-level RTI framework is structured to include targeted evidence-based interventions…

The 1971-72 Evaluation of the Connecticut Program for Migrant Children.

ERIC Educational Resources Information Center

Mosley, William; Scruggs, James A.

The program aimed to develop and implement educational activities for migrant children which would increase their achievement level in the public school classrooms and to deal with matters of self, their interaction with others, and survival. Two types of learning programs were emphasized: Multi-Purpose Resource Centers which supplemented the…

Students' Experience of Synchronous Learning in Distributed Environments

ERIC Educational Resources Information Center

Stewart, Anissa R.; Harlow, Danielle B.; DeBacco, Kim

2011-01-01

This article reports on a two-year ethnographic study of learners participating in multi-site, graduate-level education classes. Classes sometimes met face-to-face in the same physical location; at other times part of the class met physically elsewhere. Yet all were linked through the virtual space. Ethnographic analysis of four data types…

Arrowland v1.0

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

BIRKEL, GARRETT; GARCIA MARTIN, HECTOR; MORRELL, WILLIAM

"Arrowland" is a web-based software application primarily for mapping, integrating and visualizing a variety of metabolism data of living organisms, including but not limited to metabolomics, proteomics, transcriptomics and fluxomics. This software application makes multi-omics data analysis intuitive and interactive. It improves data sharing and communication by enabling users to visualize their omics data using a web browser (on a PC or mobile device). It increases user's productivity by simplifying multi-omics data analysis using well developed maps as a guide. Users using this tool can gain insights into their data sets that would be difficult or even impossible to teasemore » out by looking at raw number, or using their currently existing toolchains to generate static single-use maps. Arrowland helps users save time by visualizing relative changes in different conditions or over time, and helps users to produce more significant insights faster. Preexisting maps decrease the learning curve for beginners in the omics field. Sets of multi-omics data are presented in the browser, as a two-dimensional flowchart resembling a map, with varying levels of detail information, based on the scaling of the map. Users can pan and zoom to explore different maps, compare maps, upload their own research data sets onto desired maps, alter map appearance in ways that facilitate interpretation, visualization and analysis of the given data, and export data, reports and actionable items to help the user initiative.« less

Shaping Learning Cultures: A Strategic Challenge for Universities

NASA Astrophysics Data System (ADS)

Euler, Dieter

While there are strong stakeholders at universities arguing for increasing efforts to improve the research record, innovative actions for a corresponding commitment on teaching and learning are less frequent. In many cases, this issue is left to the discretion of individual teachers. In order to improve teaching and learning at universities, this approach does not seem to be appropriate. Rather, actions on different dimensions have to be organized, ranging from the individual, interactional, and institutional level of a university. The different perspectives on analysis and action are assembled in a construct called "learning cultures." This term covers the various dimensions impacting on student learning. The article provides a definition of "learning cultures," which will then be explained. Based on the explicated notion, a conceptual frame is put forward covering the key features of "learning cultures." Finally, some ideas are given providing some preliminary answers on how to shape learning cultures at the strategic level at universities.

Participating in a Community of Learners enhances resident perceptions of learning in an e-mentoring program: proof of concept

PubMed Central

2011-01-01

Background Community learning and e-mentoring, learning methods used in higher education, are not used to any extent in residency education. Yet both have the potential to enhance resident learning and, in the case of community learning, introduce residents to basic lifelong learning skills. We set out to determine whether residents participating in an Internet based e-mentoring program would, with appropriate facilitation, form a community of learners (CoL) and hold regular community meetings. We also determined resident and faculty perceptions of CoL and Internet sessions as effective learning experiences. Methods A six-month e-mentoring pilot was offered to 10 Radiology residents in the Aga Khan University Postgraduate Medical Education Program in Nairobi, Kenya (AKUHN) with a Professor of Radiology, located at University of Virginia, USA, acting as the e-mentor. Monthly Internet case-based teaching sessions were facilitated by the e-mentor. In addition, residents were coached by a community facilitator to form CoL and collectively work through clinical cases at weekly face-to-face CoL sessions. Event logs described observed resident activity at CoL sessions; exit survey and interviews were used to elicit perceptions of CoL and Internet sessions as effective learning experiences. Results Resident adoption of CoL behaviors was observed, including self-regulation, peer mentoring and collaborative problem solving. Analysis revealed high resident enthusiasm and value for CoL. Surveys and interviews indicated high levels of acceptance of Internet learning experiences, although there was room for improvement in audio-visual transmission technologies. Faculty indicated there was a need for a larger multi-specialty study. Conclusions The pilot demonstrated resident acceptance of community building and collaborative learning as valued learning experiences, addressing one barrier to its formal adoption in residency education curricula. It also highlighted the potential of e-mentoring as a means of expanding faculty and teaching materials in residency programs in developing countries. PMID:21266070

BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

PubMed

Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

2018-04-11

The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes by using deep learning on high-dimensional and small-scale biology data.

LapTrain: multi-modality training curriculum for laparoscopic cholecystectomy-results of a randomized controlled trial.

PubMed

Kowalewski, K F; Garrow, C R; Proctor, T; Preukschas, A A; Friedrich, M; Müller, P C; Kenngott, H G; Fischer, L; Müller-Stich, B P; Nickel, F

2018-02-12

Multiple training modalities for laparoscopy have different advantages, but little research has been conducted on the benefit of a training program that includes multiple different training methods compared to one method only. This study aimed to evaluate benefits of a combined multi-modality training program for surgical residents. Laparoscopic cholecystectomy (LC) was performed on a porcine liver as the pre-test. Randomization was stratified for experience to the multi-modality Training group (12 h of training on Virtual Reality (VR) and box trainer) or Control group (no training). The post-test consisted of a VR LC and porcine LC. Performance was rated with the Global Operative Assessment of Laparoscopic Skills (GOALS) score by blinded experts. Training (n = 33) and Control (n = 31) were similar in the pre-test (GOALS: 13.7 ± 3.4 vs. 14.7 ± 2.6; p = 0.198; operation time 57.0 ± 18.1 vs. 63.4 ± 17.5 min; p = 0.191). In the post-test porcine LC, Training had improved GOALS scores (+ 2.84 ± 2.85 points, p < 0.001), while Control did not (+ 0.55 ± 2.34 points, p = 0.154). Operation time in the post-test was shorter for Training vs. Control (40.0 ± 17.0 vs. 55.0 ± 22.2 min; p = 0.012). Junior residents improved GOALS scores to the level of senior residents (pre-test: 13.7 ± 2.7 vs. 18.3 ± 2.9; p = 0.010; post-test: 15.5 ± 3.4 vs. 18.8 ± 3.8; p = 0.120) but senior residents remained faster (50.1 ± 20.6 vs. 25.0 ± 1.9 min; p < 0.001). No differences were found between groups on the post-test VR trainer. Structured multi-modality training is beneficial for novices to improve basics and overcome the initial learning curve in laparoscopy as well as to decrease operation time for LCs in different stages of experience. Future studies should evaluate multi-modality training in comparison with single modalities. German Clinical Trials Register DRKS00011040.

Re-Interpreting Relevant Learning: An Evaluative Framework for Secondary Education in a Global Language

ERIC Educational Resources Information Center

Barrett, Angeline M.; Bainton, David

2016-01-01

The 2030 education goal privileges "relevant learning outcomes" as the evaluative space for quality improvement. Whilst the goal was designed for global level monitoring, its influence cuts across different scales. Implementation of the goal involves reinterpreting "relevant learning" at the local level. One way that small…

Student Motivations as Predictors of High-Level Cognitions in Project-Based Classrooms

ERIC Educational Resources Information Center

Stolk, Jonathan; Harari, Janie

2014-01-01

It is well established that active learning helps students engage in high-level thinking strategies and develop improved cognitive skills. Motivation and self-regulated learning research, however, illustrates that cognitive engagement is an effortful process that is related to students' valuing of the learning tasks, adoption of internalized goal…

Visual Imagery and Self-Questioning: Strategies to Improve Comprehension of Written Material.

ERIC Educational Resources Information Center

Clark, Frances L.; And Others

1984-01-01

Two learning strategies--visual imagery and self-questioning--designed to increase reading comprehension were taught to six learning disabled secondary students. Results indicate that LD students can learn the two strategies and can apply them in both reading ability level and grade level materials. Use of the strategies resulted in greater…

Efficient Resources Provisioning Based on Load Forecasting in Cloud

PubMed Central

Hu, Rongdong; Jiang, Jingfei; Liu, Guangming; Wang, Lixin

2014-01-01

Cloud providers should ensure QoS while maximizing resources utilization. One optimal strategy is to timely allocate resources in a fine-grained mode according to application's actual resources demand. The necessary precondition of this strategy is obtaining future load information in advance. We propose a multi-step-ahead load forecasting method, KSwSVR, based on statistical learning theory which is suitable for the complex and dynamic characteristics of the cloud computing environment. It integrates an improved support vector regression algorithm and Kalman smoother. Public trace data taken from multitypes of resources were used to verify its prediction accuracy, stability, and adaptability, comparing with AR, BPNN, and standard SVR. Subsequently, based on the predicted results, a simple and efficient strategy is proposed for resource provisioning. CPU allocation experiment indicated it can effectively reduce resources consumption while meeting service level agreements requirements. PMID:24701160

The utility of e-Learning to support training for a multicentre bladder online adaptive radiotherapy trial (TROG 10.01-BOLART).

PubMed

Foroudi, Farshad; Pham, Daniel; Bressel, Mathias; Tongs, David; Rolfo, Aldo; Styles, Colin; Gill, Suki; Kron, Tomas

2013-10-01

An e-Learning programme appeared useful for providing training and information regarding a multi-centre image guided radiotherapy trial. The aim of this study is to demonstrate the utility of this e-Learning programme. Modules were created on relevant pelvic anatomy, Cone Beam CT soft tissue recognition and trial details. Radiation therapist participants' knowledge and confidence were evaluated before, at the end of, and after at least 6 weeks of e-Learning (long term). One hundred and eighty-five participants were recruited from 12 centres, with 118 in the first, and 67 in the second cohort. One hundred and forty-six participants had two tests (pre and post e-Learning) and 39 of these had three tests (pre, post, and long term). There was an increase confidence after completion of modules (p<0.001). The first cohort pre scores increased from 67 ± 11 to 79 ± 8 (p<0.001) post. The long term same question score was 73 ± 14 (p=0.025, comparing to pre-test), and different questions' score was 77 ± 13 (p=0.014). In the second cohort, pre-test scores were 64 ± 10, post-test same question score 78 ± 9 (p<0.001) and different questions' score 81 ± 11 (p<0.001). e-Learning for a multi-centre clinical trial was feasible and improved confidence and knowledge. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Formation Learning Control of Multiple Autonomous Underwater Vehicles With Heterogeneous Nonlinear Uncertain Dynamics.

PubMed

Yuan, Chengzhi; Licht, Stephen; He, Haibo

2017-09-26

In this paper, a new concept of formation learning control is introduced to the field of formation control of multiple autonomous underwater vehicles (AUVs), which specifies a joint objective of distributed formation tracking control and learning/identification of nonlinear uncertain AUV dynamics. A novel two-layer distributed formation learning control scheme is proposed, which consists of an upper-layer distributed adaptive observer and a lower-layer decentralized deterministic learning controller. This new formation learning control scheme advances existing techniques in three important ways: 1) the multi-AUV system under consideration has heterogeneous nonlinear uncertain dynamics; 2) the formation learning control protocol can be designed and implemented by each local AUV agent in a fully distributed fashion without using any global information; and 3) in addition to the formation control performance, the distributed control protocol is also capable of accurately identifying the AUVs' heterogeneous nonlinear uncertain dynamics and utilizing experiences to improve formation control performance. Extensive simulations have been conducted to demonstrate the effectiveness of the proposed results.

SU-E-J-110: A Novel Level Set Active Contour Algorithm for Multimodality Joint Segmentation/Registration Using the Jensen-Rényi Divergence.

PubMed

Markel, D; Naqa, I El; Freeman, C; Vallières, M

2012-06-01

To present a novel joint segmentation/registration for multimodality image-guided and adaptive radiotherapy. A major challenge to this framework is the sensitivity of many segmentation or registration algorithms to noise. Presented is a level set active contour based on the Jensen-Renyi (JR) divergence to achieve improved noise robustness in a multi-modality imaging space. To present a novel joint segmentation/registration for multimodality image-guided and adaptive radiotherapy. A major challenge to this framework is the sensitivity of many segmentation or registration algorithms to noise. Presented is a level set active contour based on the Jensen-Renyi (JR) divergence to achieve improved noise robustness in a multi-modality imaging space. It was found that JR divergence when used for segmentation has an improved robustness to noise compared to using mutual information, or other entropy-based metrics. The MI metric failed at around 2/3 the noise power than the JR divergence. The JR divergence metric is useful for the task of joint segmentation/registration of multimodality images and shows improved results compared entropy based metric. The algorithm can be easily modified to incorporate non-intensity based images, which would allow applications into multi-modality and texture analysis. © 2012 American Association of Physicists in Medicine.

Washington State Guide to Planning, Implementing and Improving Work-based Learning. A Guide for Educators at All Levels.

ERIC Educational Resources Information Center

Highline Community Coll., Des Moines, WA.

This guide, which is intended primarily for school and college personnel interested in initiating or improving work-based learning, examines the development and implementation of work-based education programs in Washington. The following topics are discussed: the rationale for work-based learning (legislative and educational change information,…

Effects of Matching Teaching Strategy to Thinking Style on Learner's Quality of Reflection in an Online Learning Environment

ERIC Educational Resources Information Center

Chen, Nian-Shing; Kinshuk; Wei, Chun-Wang; Liu, Chia-Chi

2011-01-01

Reflection plays an important role in improving learning performance. This study, therefore, attempted to explore whether learners' reflection levels can be improved if teaching strategies are adapted to fit with learners' thinking styles in an online learning environment. Three teaching strategies, namely constructive, guiding, and inductive,…

Using Data to Improve Student Learning in Elementary Schools.

ERIC Educational Resources Information Center

Bernhardt, Victoria L.

2003-01-01

This book, part of a four-book series on using data to improve student learning, concentrates on elementary education. The book shows real analysis focused on the elementary education level. It provides templates on an accompanying CD-ROM for leaders to use in analyzing data in their own learning organizations. The chapters are: (1) Introduction;…

A New Automated Design Method Based on Machine Learning for CMOS Analog Circuits

NASA Astrophysics Data System (ADS)

Moradi, Behzad; Mirzaei, Abdolreza

2016-11-01

A new simulation based automated CMOS analog circuit design method which applies a multi-objective non-Darwinian-type evolutionary algorithm based on Learnable Evolution Model (LEM) is proposed in this article. The multi-objective property of this automated design of CMOS analog circuits is governed by a modified Strength Pareto Evolutionary Algorithm (SPEA) incorporated in the LEM algorithm presented here. LEM includes a machine learning method such as the decision trees that makes a distinction between high- and low-fitness areas in the design space. The learning process can detect the right directions of the evolution and lead to high steps in the evolution of the individuals. The learning phase shortens the evolution process and makes remarkable reduction in the number of individual evaluations. The expert designer's knowledge on circuit is applied in the design process in order to reduce the design space as well as the design time. The circuit evaluation is made by HSPICE simulator. In order to improve the design accuracy, bsim3v3 CMOS transistor model is adopted in this proposed design method. This proposed design method is tested on three different operational amplifier circuits. The performance of this proposed design method is verified by comparing it with the evolutionary strategy algorithm and other similar methods.

Time-Extended Policies in Mult-Agent Reinforcement Learning

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Agogino, Adrian K.

2004-01-01

Reinforcement learning methods perform well in many domains where a single agent needs to take a sequence of actions to perform a task. These methods use sequences of single-time-step rewards to create a policy that tries to maximize a time-extended utility, which is a (possibly discounted) sum of these rewards. In this paper we build on our previous work showing how these methods can be extended to a multi-agent environment where each agent creates its own policy that works towards maximizing a time-extended global utility over all agents actions. We show improved methods for creating time-extended utilities for the agents that are both "aligned" with the global utility and "learnable." We then show how to crate single-time-step rewards while avoiding the pi fall of having rewards aligned with the global reward leading to utilities not aligned with the global utility. Finally, we apply these reward functions to the multi-agent Gridworld problem. We explicitly quantify a utility's learnability and alignment, and show that reinforcement learning agents using the prescribed reward functions successfully tradeoff learnability and alignment. As a result they outperform both global (e.g., team games ) and local (e.g., "perfectly learnable" ) reinforcement learning solutions by as much as an order of magnitude.

Fuzzy Q-Learning for Generalization of Reinforcement Learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1996-01-01

Fuzzy Q-Learning, introduced earlier by the author, is an extension of Q-Learning into fuzzy environments. GARIC is a methodology for fuzzy reinforcement learning. In this paper, we introduce GARIC-Q, a new method for doing incremental Dynamic Programming using a society of intelligent agents which are controlled at the top level by Fuzzy Q-Learning and at the local level, each agent learns and operates based on GARIC. GARIC-Q improves the speed and applicability of Fuzzy Q-Learning through generalization of input space by using fuzzy rules and bridges the gap between Q-Learning and rule based intelligent systems.

Applying Neurological Learning Research to an Intro Astronomy Online Lab Course

NASA Astrophysics Data System (ADS)

Byrd, Gene G.; Byrd, Dana

2015-01-01

The neurological research used the 'Tower of London', a well-tested puzzle requiring multi-step planning toward a solution. Four and five year-olds are starting multistep reasoning and provide good puzzle subjects. Preschoolers who talked to themselves about future moves had greatly improved performance over those who did not. Adults given preplanning time prior to solving the same puzzle showed more neural activation during preplanning, especially in brain areas which serve higher level thinking. Applying these results to teaching astronomy, we modified an online introductory lab course in which students take a multiple choice final exam. We composed questions related to the learning objectives of the course modules (LOQs). Students could 'talk to themselves' by discursively answering these for extra credit prior to the final. Results were compared to an otherwise identical previous unmodified class. Modified classes showed statistically much better final exam average scores (78% vs. 66%). This modification helped those students who most need help. Students in the lower third of the class preferentially answered the LOQs to improve their scores and the class average on the exam. These results also show the effectiveness of relevant extra credit work. For more details plus an application to a lecture course, see Byrd and Byrd http://www.ncolr.org/issues/jiol/v12/n2/3 (Journal of Interactive Online Learning). The online lab course emphasized real photographic and quantitative astronomical observations. We also discuss and show equipment found to be most useful for the online lab course, including a 'pin-hole protractor', telescope kit and "AL-henge" telescope mount..