Networking K-12 Schools: Architecture Models and Evaluation of Costs and Benefits.

ERIC Educational Resources Information Center

Rothstein, Russell Isaac

This thesis examines the cost and benefits of communication networks in K-12 schools using cost analysis of five technology models with increasing levels of connectivity. Data indicate that the cost of the network hardware is only a small fraction of the overall networking costs. PC purchases, initial training, and retrofitting are the largest…

An Evaluation of the Feasibility of Using Hand-Held Computers for Training.

DTIC Science & Technology

1982-05-30

approved. I FRANK E. GIUNTI F. A. NERONE Chief, Instructuinal Colonel, Infantry Development Division Director, Training Developments Institute...on electronic networks (PLATO) were initiated, and HHCs were borrowed and programmed. A number of Battelle experts were also consulted. Devices Noted...of a network . as an book. aide-memoire, a calculator, a word For outdoor use there is no processor, a financial planner and comparable product. From on

Algebraic and adaptive learning in neural control systems

NASA Astrophysics Data System (ADS)

Ferrari, Silvia

A systematic approach is developed for designing adaptive and reconfigurable nonlinear control systems that are applicable to plants modeled by ordinary differential equations. The nonlinear controller comprising a network of neural networks is taught using a two-phase learning procedure realized through novel techniques for initialization, on-line training, and adaptive critic design. A critical observation is that the gradients of the functions defined by the neural networks must equal corresponding linear gain matrices at chosen operating points. On-line training is based on a dual heuristic adaptive critic architecture that improves control for large, coupled motions by accounting for actual plant dynamics and nonlinear effects. An action network computes the optimal control law; a critic network predicts the derivative of the cost-to-go with respect to the state. Both networks are algebraically initialized based on prior knowledge of satisfactory pointwise linear controllers and continue to adapt on line during full-scale simulations of the plant. On-line training takes place sequentially over discrete periods of time and involves several numerical procedures. A backpropagating algorithm called Resilient Backpropagation is modified and successfully implemented to meet these objectives, without excessive computational expense. This adaptive controller is as conservative as the linear designs and as effective as a global nonlinear controller. The method is successfully implemented for the full-envelope control of a six-degree-of-freedom aircraft simulation. The results show that the on-line adaptation brings about improved performance with respect to the initialization phase during aircraft maneuvers that involve large-angle and coupled dynamics, and parameter variations.

E3 Success Story - Whirlpool Trains Staff on Lean and Green Advantage

EPA Pesticide Factsheets

Whirlpool Corporation invited Green Suppliers Network representatives to its Monterrey facility to provide training on the Lean and Green Advantage. The project sought to expand E3 initiatives to every part of the company's operations.

Automatic Classification of volcano-seismic events based on Deep Neural Networks.

NASA Astrophysics Data System (ADS)

Titos Luzón, M.; Bueno Rodriguez, A.; Garcia Martinez, L.; Benitez, C.; Ibáñez, J. M.

2017-12-01

Seismic monitoring of active volcanoes is a popular remote sensing technique to detect seismic activity, often associated to energy exchanges between the volcano and the environment. As a result, seismographs register a wide range of volcano-seismic signals that reflect the nature and underlying physics of volcanic processes. Machine learning and signal processing techniques provide an appropriate framework to analyze such data. In this research, we propose a new classification framework for seismic events based on deep neural networks. Deep neural networks are composed by multiple processing layers, and can discover intrinsic patterns from the data itself. Internal parameters can be initialized using a greedy unsupervised pre-training stage, leading to an efficient training of fully connected architectures. We aim to determine the robustness of these architectures as classifiers of seven different types of seismic events recorded at "Volcán de Fuego" (Colima, Mexico). Two deep neural networks with different pre-training strategies are studied: stacked denoising autoencoder and deep belief networks. Results are compared to existing machine learning algorithms (SVM, Random Forest, Multilayer Perceptron). We used 5 LPC coefficients over three non-overlapping segments as training features in order to characterize temporal evolution, avoid redundancy and encode the signal, regardless of its duration. Experimental results show that deep architectures can classify seismic events with higher accuracy than classical algorithms, attaining up to 92% recognition accuracy. Pre-training initialization helps these models to detect events that occur simultaneously in time (such explosions and rockfalls), increase robustness against noisy inputs, and provide better generalization. These results demonstrate deep neural networks are robust classifiers, and can be deployed in real-environments to monitor the seismicity of restless volcanoes.

Effects of training strategies implemented in a complex videogame on functional connectivity of attentional networks.

PubMed

Voss, Michelle W; Prakash, Ruchika Shaurya; Erickson, Kirk I; Boot, Walter R; Basak, Chandramallika; Neider, Mark B; Simons, Daniel J; Fabiani, Monica; Gratton, Gabriele; Kramer, Arthur F

2012-01-02

We used the Space Fortress videogame, originally developed by cognitive psychologists to study skill acquisition, as a platform to examine learning-induced plasticity of interacting brain networks. Novice videogame players learned Space Fortress using one of two training strategies: (a) focus on all aspects of the game during learning (fixed priority), or (b) focus on improving separate game components in the context of the whole game (variable priority). Participants were scanned during game play using functional magnetic resonance imaging (fMRI), both before and after 20 h of training. As expected, variable priority training enhanced learning, particularly for individuals who initially performed poorly. Functional connectivity analysis revealed changes in brain network interaction reflective of more flexible skill learning and retrieval with variable priority training, compared to procedural learning and skill implementation with fixed priority training. These results provide the first evidence for differences in the interaction of large-scale brain networks when learning with different training strategies. Our approach and findings also provide a foundation for exploring the brain plasticity involved in transfer of trained abilities to novel real-world tasks such as driving, sport, or neurorehabilitation. Copyright © 2011 Elsevier Inc. All rights reserved.

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

PubMed

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

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

PREVENT: a program of the National Training Initiative on Injury and Violence Prevention.

PubMed

Runyan, Carol W; Gunther-Mohr, Carol; Orton, Stephen; Umble, Karl; Martin, Sandra L; Coyne-Beasley, Tamera

2005-12-01

Training practitioners to use evidence-based approaches to the primary prevention of violence is challenging as a result of the dearth of well-evaluated intervention programs and the lack of familiarity of some practitioners in drawing critically on existing literature. An element of the National Training Initiative in Injury and Violence Prevention, the PREVENT (Preventing Violence Through Education, Networking, and Technical Assistance) program began in late 2003 to train practitioners to address multiple types of violence by encouraging more widespread use of evidence-based approaches to primary prevention. It is intended to reach practitioners involved in addressing violence against women, sexual violence, child maltreatment, youth violence, and suicide in varied community settings. The program uses a combination of varied types of face-to-face training and distance learning coupled with opportunities for networking and technical assistance. Ultimately the program intends to stimulate and facilitate changes in individual, organizational, and cultural awareness and practices fostering primary prevention of violence. The project employs formative, process, and impact evaluation techniques aimed at improving delivery of the training as well as tracking changes in individual and organizations.

Modular representation of layered neural networks.

PubMed

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.

Network-Based Professional Development: A Comparison of Statewide Initiatives.

ERIC Educational Resources Information Center

Shotsberger, Paul G.; Stammen, Ronald; Vetter, Ronald; Blue, Gloria; Greer, Edrie

This paper addresses opportunities and issues related to the use of the World Wide Web and high-speed networks as a delivery vehicle for training educators who are geographically dispersed. The benefits and potential pitfalls of using networks as educational platforms are explored from the perspective of various systems specifically being…

Dissemination of public health information: key tools utilised by the NECOBELAC network in Europe and Latin America.

PubMed

De Castro, Paola; Marsili, Daniela; Poltronieri, Elisabetta; Calderón, Carlos Agudelo

2012-06-01

 Open Access (OA) to scientific information is an important step forward in communication patterns, yet we still need to reinforce OA principles to promote a cultural change of traditional publishing practices. The advantages of free access to scientific information are even more evident in public health where knowledge is directly associated with human wellbeing.  An OA 'consolidation' initiative in public health is presented to show how the involvement of people and institutions is fundamental to create awareness on OA and promote a cultural change. This initiative is developed within the project NEtwork of COllaboration Between Europe and Latin American Caribbean countries (NECOBELAC), financed by the European Commission.  Three actions are envisaged: Capacity building through a flexible and sustainable training programme on scientific writing and OA publishing; creation of training tools based on semantic web technologies; development of a network of supporting institutions.  In 2010-2011, 23 training initiatives were performed involving 856 participants from 15 countries; topic maps on scientific publication and OA were produced; 195 institutions are included in the network.  Cultural change in scientific dissemination practices is a long process requiring a flexible approach and strong commitment by all stakeholders. © 2012 The authors. Health Information and Libraries Journal © 2012 Health Libraries Group Health Information and Libraries Journal.

Improving Pattern Recognition and Neural Network Algorithms with Applications to Solar Panel Energy Optimization

NASA Astrophysics Data System (ADS)

Zamora Ramos, Ernesto

Artificial Intelligence is a big part of automation and with today's technological advances, artificial intelligence has taken great strides towards positioning itself as the technology of the future to control, enhance and perfect automation. Computer vision includes pattern recognition and classification and machine learning. Computer vision is at the core of decision making and it is a vast and fruitful branch of artificial intelligence. In this work, we expose novel algorithms and techniques built upon existing technologies to improve pattern recognition and neural network training, initially motivated by a multidisciplinary effort to build a robot that helps maintain and optimize solar panel energy production. Our contributions detail an improved non-linear pre-processing technique to enhance poorly illuminated images based on modifications to the standard histogram equalization for an image. While the original motivation was to improve nocturnal navigation, the results have applications in surveillance, search and rescue, medical imaging enhancing, and many others. We created a vision system for precise camera distance positioning motivated to correctly locate the robot for capture of solar panel images for classification. The classification algorithm marks solar panels as clean or dirty for later processing. Our algorithm extends past image classification and, based on historical and experimental data, it identifies the optimal moment in which to perform maintenance on marked solar panels as to minimize the energy and profit loss. In order to improve upon the classification algorithm, we delved into feedforward neural networks because of their recent advancements, proven universal approximation and classification capabilities, and excellent recognition rates. We explore state-of-the-art neural network training techniques offering pointers and insights, culminating on the implementation of a complete library with support for modern deep learning architectures, multilayer percepterons and convolutional neural networks. Our research with neural networks has encountered a great deal of difficulties regarding hyperparameter estimation for good training convergence rate and accuracy. Most hyperparameters, including architecture, learning rate, regularization, trainable parameters (or weights) initialization, and so on, are chosen via a trial and error process with some educated guesses. However, we developed the first quantitative method to compare weight initialization strategies, a critical hyperparameter choice during training, to estimate among a group of candidate strategies which would make the network converge to the highest classification accuracy faster with high probability. Our method provides a quick, objective measure to compare initialization strategies to select the best possible among them beforehand without having to complete multiple training sessions for each candidate strategy to compare final results.

A Computationally Inexpensive Optimal Guidance via Radial-Basis-Function Neural Network for Autonomous Soft Landing on Asteroids

PubMed Central

Zhang, Peng; Liu, Keping; Zhao, Bo; Li, Yuanchun

2015-01-01

Optimal guidance is essential for the soft landing task. However, due to its high computational complexities, it is hardly applied to the autonomous guidance. In this paper, a computationally inexpensive optimal guidance algorithm based on the radial basis function neural network (RBFNN) is proposed. The optimization problem of the trajectory for soft landing on asteroids is formulated and transformed into a two-point boundary value problem (TPBVP). Combining the database of initial states with the relative initial co-states, an RBFNN is trained offline. The optimal trajectory of the soft landing is determined rapidly by applying the trained network in the online guidance. The Monte Carlo simulations of soft landing on the Eros433 are performed to demonstrate the effectiveness of the proposed guidance algorithm. PMID:26367382

Evaluating a Training Intervention to Prepare Geriatric Case Managers to Assess for Suicide and Firearm Safety

ERIC Educational Resources Information Center

Pope, Natalie D.; Slovak, Karen L.; Giger, Jarod T.

2016-01-01

The purpose of this article is to report on the implementation and initial evaluation of a 1-day training intervention targeting direct care providers in the Ohio aging services network. A primary objective is to describe the training intervention that consisted of two parts: (a) a gatekeeper training for assessing suicide risk among older adults,…

Adaptive model predictive process control using neural networks

DOEpatents

Buescher, K.L.; Baum, C.C.; Jones, R.D.

1997-08-19

A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data. 46 figs.

Adaptive model predictive process control using neural networks

DOEpatents

Buescher, Kevin L.; Baum, Christopher C.; Jones, Roger D.

1997-01-01

A control system for controlling the output of at least one plant process output parameter is implemented by adaptive model predictive control using a neural network. An improved method and apparatus provides for sampling plant output and control input at a first sampling rate to provide control inputs at the fast rate. The MPC system is, however, provided with a network state vector that is constructed at a second, slower rate so that the input control values used by the MPC system are averaged over a gapped time period. Another improvement is a provision for on-line training that may include difference training, curvature training, and basis center adjustment to maintain the weights and basis centers of the neural in an updated state that can follow changes in the plant operation apart from initial off-line training data.

Training radial basis function networks for wind speed prediction using PSO enhanced differential search optimizer

PubMed Central

2018-01-01

This paper presents an integrated hybrid optimization algorithm for training the radial basis function neural network (RBF NN). Training of neural networks is still a challenging exercise in machine learning domain. Traditional training algorithms in general suffer and trap in local optima and lead to premature convergence, which makes them ineffective when applied for datasets with diverse features. Training algorithms based on evolutionary computations are becoming popular due to their robust nature in overcoming the drawbacks of the traditional algorithms. Accordingly, this paper proposes a hybrid training procedure with differential search (DS) algorithm functionally integrated with the particle swarm optimization (PSO). To surmount the local trapping of the search procedure, a new population initialization scheme is proposed using Logistic chaotic sequence, which enhances the population diversity and aid the search capability. To demonstrate the effectiveness of the proposed RBF hybrid training algorithm, experimental analysis on publicly available 7 benchmark datasets are performed. Subsequently, experiments were conducted on a practical application case for wind speed prediction to expound the superiority of the proposed RBF training algorithm in terms of prediction accuracy. PMID:29768463

Training radial basis function networks for wind speed prediction using PSO enhanced differential search optimizer.

PubMed

Rani R, Hannah Jessie; Victoire T, Aruldoss Albert

2018-01-01

This paper presents an integrated hybrid optimization algorithm for training the radial basis function neural network (RBF NN). Training of neural networks is still a challenging exercise in machine learning domain. Traditional training algorithms in general suffer and trap in local optima and lead to premature convergence, which makes them ineffective when applied for datasets with diverse features. Training algorithms based on evolutionary computations are becoming popular due to their robust nature in overcoming the drawbacks of the traditional algorithms. Accordingly, this paper proposes a hybrid training procedure with differential search (DS) algorithm functionally integrated with the particle swarm optimization (PSO). To surmount the local trapping of the search procedure, a new population initialization scheme is proposed using Logistic chaotic sequence, which enhances the population diversity and aid the search capability. To demonstrate the effectiveness of the proposed RBF hybrid training algorithm, experimental analysis on publicly available 7 benchmark datasets are performed. Subsequently, experiments were conducted on a practical application case for wind speed prediction to expound the superiority of the proposed RBF training algorithm in terms of prediction accuracy.

Neural networks for structural design - An integrated system implementation

NASA Technical Reports Server (NTRS)

Berke, Laszlo; Hafez, Wassim; Pao, Yoh-Han

1992-01-01

The development of powerful automated procedures to aid the creative designer is becoming increasingly critical for complex design tasks. In the work described here Artificial Neural Nets are applied to acquire structural analysis and optimization domain expertise. Based on initial instructions from the user an automated procedure generates random instances of structural analysis and/or optimization 'experiences' that cover a desired domain. It extracts training patterns from the created instances, constructs and trains an appropriate network architecture and checks the accuracy of net predictions. The final product is a trained neural net that can estimate analysis and/or optimization results instantaneously.

Major Programs | Division of Cancer Prevention

Cancer.gov

The Division of Cancer Prevention supports major scientific collaborations, research networks, investigator-initiated grants, postdoctoral training, and specialized resources across the United States. |

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method.

PubMed

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller's scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller's algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller's algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller's algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data.

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.

PubMed

Kang, Min-Joo; Kang, Je-Won

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security

PubMed Central

Kang, Min-Joo

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus. PMID:27271802

Coalition readiness management system preliminary interoperability experiment (CReaMS PIE)

NASA Astrophysics Data System (ADS)

Clark, Peter; Ryan, Peter; Zalcman, Lucien; Robbie, Andrew

2003-09-01

The United States Navy (USN) has initiated the Coalition Readiness Management System (CReaMS) Initiative to enhance coalition warfighting readiness through advancing development of a team interoperability training and combined mission rehearsal capability. It integrates evolving cognitive team learning principles and processes with advanced technology innovations to produce an effective and efficient team learning environment. The JOint Air Navy Networking Environment (JOANNE) forms the Australian component of CReaMS. The ultimate goal is to link Australian Defence simulation systems with the USN Battle Force Tactical Training (BFTT) system to demonstrate and achieve coalition level warfare training in a synthetic battlespace. This paper discusses the initial Preliminary Interoperability Experiment (PIE) involving USN and Australian Defence establishments.

Disseminating educational innovations in health care practice: training versus social networks.

PubMed

Jippes, Erik; Achterkamp, Marjolein C; Brand, Paul L P; Kiewiet, Derk Jan; Pols, Jan; van Engelen, Jo M L

2010-05-01

Improvements and innovation in health service organization and delivery have become more and more important due to the gap between knowledge and practice, rising costs, medical errors, and the organization of health care systems. Since training and education is widely used to convey and distribute innovative initiatives, we examined the effect that following an intensive Teach-the-Teacher training had on the dissemination of a new structured competency-based feedback technique of assessing clinical competencies among medical specialists in the Netherlands. We compared this with the effect of the structure of the social network of medical specialists, specifically the network tie strength (strong ties versus weak ties). We measured dissemination of the feedback technique by using a questionnaire filled in by Obstetrics & Gynecology and Pediatrics residents (n=63). Data on network tie strength was gathered with a structured questionnaire given to medical specialists (n=81). Social network analysis was used to compose the required network coefficients. We found a strong effect for network tie strength and no effect for the Teach-the-Teacher training course on the dissemination of the new structured feedback technique. This paper shows the potential that social networks have for disseminating innovations in health service delivery and organization. Further research is needed into the role and structure of social networks on the diffusion of innovations between departments and the various types of innovations involved. Copyright (c) 2010 Elsevier Ltd. All rights reserved.

Testing of information condensation in a model reverberating spiking neural network.

PubMed

Vidybida, Alexander

2011-06-01

Information about external world is delivered to the brain in the form of structured in time spike trains. During further processing in higher areas, information is subjected to a certain condensation process, which results in formation of abstract conceptual images of external world, apparently, represented as certain uniform spiking activity partially independent on the input spike trains details. Possible physical mechanism of condensation at the level of individual neuron was discussed recently. In a reverberating spiking neural network, due to this mechanism the dynamics should settle down to the same uniform/ periodic activity in response to a set of various inputs. Since the same periodic activity may correspond to different input spike trains, we interpret this as possible candidate for information condensation mechanism in a network. Our purpose is to test this possibility in a network model consisting of five fully connected neurons, particularly, the influence of geometric size of the network, on its ability to condense information. Dynamics of 20 spiking neural networks of different geometric sizes are modelled by means of computer simulation. Each network was propelled into reverberating dynamics by applying various initial input spike trains. We run the dynamics until it becomes periodic. The Shannon's formula is used to calculate the amount of information in any input spike train and in any periodic state found. As a result, we obtain explicit estimate of the degree of information condensation in the networks, and conclude that it depends strongly on the net's geometric size.

Modernising Education and Training: Mobilising Technology for Learning

ERIC Educational Resources Information Center

Attewell, Jill; Savill-Smith, Carol; Douch, Rebecca; Parker, Guy

2010-01-01

In recent years there have been amazing advances in consumer technology. The Mobile Learning Network (MoLeNET) initiative has enabled colleges and schools to harness some of this technology in order to modernise aspects of teaching, learning and training. The result has been improvements in learner engagement, retention, achievement and…

Wings: Women Entrepreneurs Take Flight.

ERIC Educational Resources Information Center

Baldwin, Fred D.

1997-01-01

Women's Initiative Networking Groups (WINGS) provides low- and moderate-income women in Appalachian Kentucky with training in business skills, contacts, and other resources they need to succeed as entrepreneurs. The women form informal networks to share business know-how and support for small business startup and operations. The program plans to…

10 CFR 73.56 - Personnel access authorization requirements for nuclear power plants.

Code of Federal Regulations, 2010 CFR

2010-01-01

... assessment. (2) The psychological assessment must be conducted in accordance with the applicable ethical...) Initial and refresher training may be delivered using a variety of media, including, but not limited to... communication systems and networks as identified in § 73.54, including— (i) Plant network systems administrators...

Cognitive and Neural Effects of Semantic Encoding Strategy Training in Older Adults

PubMed Central

Anderson, B. A.; Barch, D. M.; Jacoby, L. L.

2012-01-01

Prior research suggests that older adults are less likely than young adults to use effective learning strategies during intentional encoding. This functional magnetic resonance imaging (fMRI) study investigated whether training older adults to use semantic encoding strategies can increase their self-initiated use of these strategies and improve their recognition memory. The effects of training on older adults' brain activity during intentional encoding were also examined. Training increased older adults' self-initiated semantic encoding strategy use and eliminated pretraining age differences in recognition memory following intentional encoding. Training also increased older adults' brain activity in the medial superior frontal gyrus, right precentral gyrus, and left caudate during intentional encoding. In addition, older adults' training-related changes in recognition memory were strongly correlated with training-related changes in brain activity in prefrontal and left lateral temporal regions associated with semantic processing and self-initiated verbal encoding strategy use in young adults. These neuroimaging results demonstrate that semantic encoding strategy training can alter older adults' brain activity patterns during intentional encoding and suggest that young and older adults may use the same network of brain regions to support self-initiated use of verbal encoding strategies. PMID:21709173

Simple techniques for improving deep neural network outcomes on commodity hardware

NASA Astrophysics Data System (ADS)

Colina, Nicholas Christopher A.; Perez, Carlos E.; Paraan, Francis N. C.

2017-08-01

We benchmark improvements in the performance of deep neural networks (DNN) on the MNIST data test upon imple-menting two simple modifications to the algorithm that have little overhead computational cost. First is GPU parallelization on a commodity graphics card, and second is initializing the DNN with random orthogonal weight matrices prior to optimization. Eigenspectra analysis of the weight matrices reveal that the initially orthogonal matrices remain nearly orthogonal after training. The probability distributions from which these orthogonal matrices are drawn are also shown to significantly affect the performance of these deep neural networks.

Enhanced online convolutional neural networks for object tracking

NASA Astrophysics Data System (ADS)

Zhang, Dengzhuo; Gao, Yun; Zhou, Hao; Li, Tianwen

2018-04-01

In recent several years, object tracking based on convolution neural network has gained more and more attention. The initialization and update of convolution filters can directly affect the precision of object tracking effective. In this paper, a novel object tracking via an enhanced online convolution neural network without offline training is proposed, which initializes the convolution filters by a k-means++ algorithm and updates the filters by an error back-propagation. The comparative experiments of 7 trackers on 15 challenging sequences showed that our tracker can perform better than other trackers in terms of AUC and precision.

The “Picardie en Forme” Network: Federating Regional Health-enhancing Sports Resources

PubMed

Weissland, Thierry; Passavant, Éric; Allal, Aziz; Amiard, Valérie; Antczak, Boris; Manzo, Julie

2016-06-08

Initiated by the Regional Olympic and Sports Committee and the Regional Directorate of Youth, Sports and Social Cohesion, the “Picardie en Forme” network has been working since 2011 in favour of adults of all ages, with chronic noncommunicable or similar diseases, to encourage a gradual return to reassuring and perennial regular physical activity,. A first step consisted of organizing a care pathway based on two principles: inform general practitioners so that they can encourage their patients to be physically active by referring them to the network, develop a range of local sports by accrediting certain clubs with sports instructors who have been trained in the management of this specific population. In 2013, 121 users entered the network at the request of 61 doctors. 48 sports instructors were trained and 20 associations obtained the Picardie en Forme label. Comparison of the results of tests performed on entry in the network and then eight months later shows a general physical reconditioning of users, increasing their motivation and perceived physical value. However, despite these encouraging results, the network has difficulty retaining users, and maintaining the involvement of general practitioners and certain local partners. This article discusses the relevance of initial approaches and describes the changes made to sustain this regional network, which, for the first time, links sport, health and users.

Establishing a regional network of academic centers to support decision making for new vaccine introduction in Latin America and the Caribbean: the ProVac experience.

PubMed

Toscano, C M; Jauregui, B; Janusz, C B; Sinha, A; Clark, A D; Sanderson, C; Resch, S; Ruiz Matus, C; Andrus, J K

2013-07-02

The Pan American Health Organization's ProVac Initiative, designed to strengthen national decision making regarding the introduction of new vaccines, was initiated in 2004. Central to realizing ProVac's vision of regional capacity building, the ProVac Network of Centers of Excellence (CoEs) was established in 2010 to provide research support to the ProVac Initiative, leveraging existing capacity at Latin American and Caribbean (LAC) universities. We describe the process of establishing the ProVac Network of CoEs and its initial outcomes and challenges. A survey was sent to academic, not-for-profit institutions in LAC that had recently published work in the areas of clinical decision sciences and health economic analysis. Centers invited to join the Network were selected by an international committee on the basis of the survey results. Selection criteria included academic productivity in immunization-related work, team size and expertise, successful collaboration with governmental agencies and international organizations, and experience in training and education. The Network currently includes five academic institutions across LAC. Through open dialog and negotiation, specific projects were assigned to centers according to their areas of expertise. Collaboration among centers was highly encouraged. Faculty from ProVac's technical partners were assigned as focal points for each project. The resulting work led to the development and piloting of tools, methodological guides, and training materials that support countries in assessing existing evidence and generating new evidence on vaccine introduction. The evidence generated is shared with country-level decision makers and the scientific community. As the ProVac Initiative expands to other regions of the world with support from immunization and public health partners, the establishment of other regional and global networks of CoEs will be critical. The experience of LAC in creating the current network could benefit the formation of similar structures that support evidence-based decisions regarding new public health interventions. Copyright © 2013 Elsevier Ltd. All rights reserved.

An experimental study of interstitial lung tissue classification in HRCT images using ANN and role of cost functions

NASA Astrophysics Data System (ADS)

Dash, Jatindra K.; Kale, Mandar; Mukhopadhyay, Sudipta; Khandelwal, Niranjan; Prabhakar, Nidhi; Garg, Mandeep; Kalra, Naveen

2017-03-01

In this paper, we investigate the effect of the error criteria used during a training phase of the artificial neural network (ANN) on the accuracy of the classifier for classification of lung tissues affected with Interstitial Lung Diseases (ILD). Mean square error (MSE) and the cross-entropy (CE) criteria are chosen being most popular choice in state-of-the-art implementations. The classification experiment performed on the six interstitial lung disease (ILD) patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Micronodules, Fibrosis and Healthy from MedGIFT database. The texture features from an arbitrary region of interest (AROI) are extracted using Gabor filter. Two different neural networks are trained with the scaled conjugate gradient back propagation algorithm with MSE and CE error criteria function respectively for weight updation. Performance is evaluated in terms of average accuracy of these classifiers using 4 fold cross-validation. Each network is trained for five times for each fold with randomly initialized weight vectors and accuracies are computed. Significant improvement in classification accuracy is observed when ANN is trained by using CE (67.27%) as error function compared to MSE (63.60%). Moreover, standard deviation of the classification accuracy for the network trained with CE (6.69) error criteria is found less as compared to network trained with MSE (10.32) criteria.

Three learning phases for radial-basis-function networks.

PubMed

Schwenker, F; Kestler, H A; Palm, G

2001-05-01

In this paper, learning algorithms for radial basis function (RBF) networks are discussed. Whereas multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting the training procedure with a random initialization of the MLP's parameters, an RBF network may be trained in many different ways. We categorize these RBF training methods into one-, two-, and three-phase learning schemes. Two-phase RBF learning is a very common learning scheme. The two layers of an RBF network are learnt separately; first the RBF layer is trained, including the adaptation of centers and scaling parameters, and then the weights of the output layer are adapted. RBF centers may be trained by clustering, vector quantization and classification tree algorithms, and the output layer by supervised learning (through gradient descent or pseudo inverse solution). Results from numerical experiments of RBF classifiers trained by two-phase learning are presented in three completely different pattern recognition applications: (a) the classification of 3D visual objects; (b) the recognition hand-written digits (2D objects); and (c) the categorization of high-resolution electrocardiograms given as a time series (ID objects) and as a set of features extracted from these time series. In these applications, it can be observed that the performance of RBF classifiers trained with two-phase learning can be improved through a third backpropagation-like training phase of the RBF network, adapting the whole set of parameters (RBF centers, scaling parameters, and output layer weights) simultaneously. This, we call three-phase learning in RBF networks. A practical advantage of two- and three-phase learning in RBF networks is the possibility to use unlabeled training data for the first training phase. Support vector (SV) learning in RBF networks is a different learning approach. SV learning can be considered, in this context of learning, as a special type of one-phase learning, where only the output layer weights of the RBF network are calculated, and the RBF centers are restricted to be a subset of the training data. Numerical experiments with several classifier schemes including k-nearest-neighbor, learning vector quantization and RBF classifiers trained through two-phase, three-phase and support vector learning are given. The performance of the RBF classifiers trained through SV learning and three-phase learning are superior to the results of two-phase learning, but SV learning often leads to complex network structures, since the number of support vectors is not a small fraction of the total number of data points.

SAGRAD: A Program for Neural Network Training with Simulated Annealing and the Conjugate Gradient Method

PubMed Central

Bernal, Javier; Torres-Jimenez, Jose

2015-01-01

SAGRAD (Simulated Annealing GRADient), a Fortran 77 program for computing neural networks for classification using batch learning, is discussed. Neural network training in SAGRAD is based on a combination of simulated annealing and Møller’s scaled conjugate gradient algorithm, the latter a variation of the traditional conjugate gradient method, better suited for the nonquadratic nature of neural networks. Different aspects of the implementation of the training process in SAGRAD are discussed, such as the efficient computation of gradients and multiplication of vectors by Hessian matrices that are required by Møller’s algorithm; the (re)initialization of weights with simulated annealing required to (re)start Møller’s algorithm the first time and each time thereafter that it shows insufficient progress in reaching a possibly local minimum; and the use of simulated annealing when Møller’s algorithm, after possibly making considerable progress, becomes stuck at a local minimum or flat area of weight space. Outlines of the scaled conjugate gradient algorithm, the simulated annealing procedure and the training process used in SAGRAD are presented together with results from running SAGRAD on two examples of training data. PMID:26958442

Classification of conductance traces with recurrent neural networks

NASA Astrophysics Data System (ADS)

Lauritzen, Kasper P.; Magyarkuti, András; Balogh, Zoltán; Halbritter, András; Solomon, Gemma C.

2018-02-01

We present a new automated method for structural classification of the traces obtained in break junction experiments. Using recurrent neural networks trained on the traces of minimal cross-sectional area in molecular dynamics simulations, we successfully separate the traces into two classes: point contact or nanowire. This is done without any assumptions about the expected features of each class. The trained neural network is applied to experimental break junction conductance traces, and it separates the classes as well as the previously used experimental methods. The effect of using partial conductance traces is explored, and we show that the method performs equally well using full or partial traces (as long as the trace just prior to breaking is included). When only the initial part of the trace is included, the results are still better than random chance. Finally, we show that the neural network classification method can be used to classify experimental conductance traces without using simulated results for training, but instead training the network on a few representative experimental traces. This offers a tool to recognize some characteristic motifs of the traces, which can be hard to find by simple data selection algorithms.

Designing Corporate Training in Developing Economies Using Open Educational Resources

ERIC Educational Resources Information Center

Geith, Chris; Vignare, Karen; Bourquin, Leslie D.; Thiagarajan, Deepa

2010-01-01

The Food Safety Knowledge Network (FSKN) is a collaboration between Michigan State University, the Global Food Safety Initiative of the Consumer Goods Forum, and other food industry and public sector partners. FSKN's goal is to help strengthen the food industry's response to the complex food safety knowledge and training challenges that affect…

A Structure-Adaptive Hybrid RBF-BP Classifier with an Optimized Learning Strategy

PubMed Central

Wen, Hui; Xie, Weixin; Pei, Jihong

2016-01-01

This paper presents a structure-adaptive hybrid RBF-BP (SAHRBF-BP) classifier with an optimized learning strategy. SAHRBF-BP is composed of a structure-adaptive RBF network and a BP network of cascade, where the number of RBF hidden nodes is adjusted adaptively according to the distribution of sample space, the adaptive RBF network is used for nonlinear kernel mapping and the BP network is used for nonlinear classification. The optimized learning strategy is as follows: firstly, a potential function is introduced into training sample space to adaptively determine the number of initial RBF hidden nodes and node parameters, and a form of heterogeneous samples repulsive force is designed to further optimize each generated RBF hidden node parameters, the optimized structure-adaptive RBF network is used for adaptively nonlinear mapping the sample space; then, according to the number of adaptively generated RBF hidden nodes, the number of subsequent BP input nodes can be determined, and the overall SAHRBF-BP classifier is built up; finally, different training sample sets are used to train the BP network parameters in SAHRBF-BP. Compared with other algorithms applied to different data sets, experiments show the superiority of SAHRBF-BP. Especially on most low dimensional and large number of data sets, the classification performance of SAHRBF-BP outperforms other training SLFNs algorithms. PMID:27792737

Engine cylinder pressure reconstruction using crank kinematics and recurrently-trained neural networks

NASA Astrophysics Data System (ADS)

Bennett, C.; Dunne, J. F.; Trimby, S.; Richardson, D.

2017-02-01

A recurrent non-linear autoregressive with exogenous input (NARX) neural network is proposed, and a suitable fully-recurrent training methodology is adapted and tuned, for reconstructing cylinder pressure in multi-cylinder IC engines using measured crank kinematics. This type of indirect sensing is important for cost effective closed-loop combustion control and for On-Board Diagnostics. The challenge addressed is to accurately predict cylinder pressure traces within the cycle under generalisation conditions: i.e. using data not previously seen by the network during training. This involves direct construction and calibration of a suitable inverse crank dynamic model, which owing to singular behaviour at top-dead-centre (TDC), has proved difficult via physical model construction, calibration, and inversion. The NARX architecture is specialised and adapted to cylinder pressure reconstruction, using a fully-recurrent training methodology which is needed because the alternatives are too slow and unreliable for practical network training on production engines. The fully-recurrent Robust Adaptive Gradient Descent (RAGD) algorithm, is tuned initially using synthesised crank kinematics, and then tested on real engine data to assess the reconstruction capability. Real data is obtained from a 1.125 l, 3-cylinder, in-line, direct injection spark ignition (DISI) engine involving synchronised measurements of crank kinematics and cylinder pressure across a range of steady-state speed and load conditions. The paper shows that a RAGD-trained NARX network using both crank velocity and crank acceleration as input information, provides fast and robust training. By using the optimum epoch identified during RAGD training, acceptably accurate cylinder pressures, and especially accurate location-of-peak-pressure, can be reconstructed robustly under generalisation conditions, making it the most practical NARX configuration and recurrent training methodology for use on production engines.

Competitive Deep-Belief Networks for Underwater Acoustic Target Recognition

PubMed Central

Shen, Sheng; Yao, Xiaohui; Sheng, Meiping; Wang, Chen

2018-01-01

Underwater acoustic target recognition based on ship-radiated noise belongs to the small-sample-size recognition problems. A competitive deep-belief network is proposed to learn features with more discriminative information from labeled and unlabeled samples. The proposed model consists of four stages: (1) A standard restricted Boltzmann machine is pretrained using a large number of unlabeled data to initialize its parameters; (2) the hidden units are grouped according to categories, which provides an initial clustering model for competitive learning; (3) competitive training and back-propagation algorithms are used to update the parameters to accomplish the task of clustering; (4) by applying layer-wise training and supervised fine-tuning, a deep neural network is built to obtain features. Experimental results show that the proposed method can achieve classification accuracy of 90.89%, which is 8.95% higher than the accuracy obtained by the compared methods. In addition, the highest accuracy of our method is obtained with fewer features than other methods. PMID:29570642

Composability-Centered Convolutional Neural Network Pruning

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

Shen, Xipeng; Guan, Hui; Lim, Seung-Hwan

This work studies the composability of the building blocks ofstructural CNN models (e.g., GoogleLeNet and Residual Networks) in thecontext of network pruning. We empirically validate that a networkcomposed of pre-trained building blocks (e.g. residual blocks andInception modules) not only gives a better initial setting fortraining, but also allows the training process to converge at asignificantly higher accuracy in much less time. Based on thatinsight, we propose a {\\em composability-centered} design for CNNnetwork pruning. Experiments show that this new scheme shortens theconfiguration process in CNN network pruning by up to 186.8X forResNet-50 and up to 30.2X for Inception-V3, and meanwhile, themore » modelsit finds that meet the accuracy requirement are significantly morecompact than those found by default schemes.« less

On the use of harmony search algorithm in the training of wavelet neural networks

NASA Astrophysics Data System (ADS)

Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

2015-10-01

Wavelet neural networks (WNNs) are a class of feedforward neural networks that have been used in a wide range of industrial and engineering applications to model the complex relationships between the given inputs and outputs. The training of WNNs involves the configuration of the weight values between neurons. The backpropagation training algorithm, which is a gradient-descent method, can be used for this training purpose. Nonetheless, the solutions found by this algorithm often get trapped at local minima. In this paper, a harmony search-based algorithm is proposed for the training of WNNs. The training of WNNs, thus can be formulated as a continuous optimization problem, where the objective is to maximize the overall classification accuracy. Each candidate solution proposed by the harmony search algorithm represents a specific WNN architecture. In order to speed up the training process, the solution space is divided into disjoint partitions during the random initialization step of harmony search algorithm. The proposed training algorithm is tested onthree benchmark problems from the UCI machine learning repository, as well as one real life application, namely, the classification of electroencephalography signals in the task of epileptic seizure detection. The results obtained show that the proposed algorithm outperforms the traditional harmony search algorithm in terms of overall classification accuracy.

Virtual physiological human: training challenges.

PubMed

Lawford, Patricia V; Narracott, Andrew V; McCormack, Keith; Bisbal, Jesus; Martin, Carlos; Bijnens, Bart; Brook, Bindi; Zachariou, Margarita; Freixa, Jordi Villà I; Kohl, Peter; Fletcher, Katherine; Diaz-Zuccarini, Vanessa

2010-06-28

The virtual physiological human (VPH) initiative encompasses a wide range of activities, including structural and functional imaging, data mining, knowledge discovery tool and database development, biomedical modelling, simulation and visualization. The VPH community is developing from a multitude of relatively focused, but disparate, research endeavours into an integrated effort to bring together, develop and translate emerging technologies for application, from academia to industry and medicine. This process initially builds on the evolution of multi-disciplinary interactions and abilities, but addressing the challenges associated with the implementation of the VPH will require, in the very near future, a translation of quantitative changes into a new quality of highly trained multi-disciplinary personnel. Current strategies for undergraduate and on-the-job training may soon prove insufficient for this. The European Commission seventh framework VPH network of excellence is exploring this emerging need, and is developing a framework of novel training initiatives to address the predicted shortfall in suitably skilled VPH-aware professionals. This paper reports first steps in the implementation of a coherent VPH training portfolio.

The eBioKit, a stand-alone educational platform for bioinformatics.

PubMed

Hernández-de-Diego, Rafael; de Villiers, Etienne P; Klingström, Tomas; Gourlé, Hadrien; Conesa, Ana; Bongcam-Rudloff, Erik

2017-09-01

Bioinformatics skills have become essential for many research areas; however, the availability of qualified researchers is usually lower than the demand and training to increase the number of able bioinformaticians is an important task for the bioinformatics community. When conducting training or hands-on tutorials, the lack of control over the analysis tools and repositories often results in undesirable situations during training, as unavailable online tools or version conflicts may delay, complicate, or even prevent the successful completion of a training event. The eBioKit is a stand-alone educational platform that hosts numerous tools and databases for bioinformatics research and allows training to take place in a controlled environment. A key advantage of the eBioKit over other existing teaching solutions is that all the required software and databases are locally installed on the system, significantly reducing the dependence on the internet. Furthermore, the architecture of the eBioKit has demonstrated itself to be an excellent balance between portability and performance, not only making the eBioKit an exceptional educational tool but also providing small research groups with a platform to incorporate bioinformatics analysis in their research. As a result, the eBioKit has formed an integral part of training and research performed by a wide variety of universities and organizations such as the Pan African Bioinformatics Network (H3ABioNet) as part of the initiative Human Heredity and Health in Africa (H3Africa), the Southern Africa Network for Biosciences (SAnBio) initiative, the Biosciences eastern and central Africa (BecA) hub, and the International Glossina Genome Initiative.

The eBioKit, a stand-alone educational platform for bioinformatics

PubMed Central

Conesa, Ana; Bongcam-Rudloff, Erik

2017-01-01

Bioinformatics skills have become essential for many research areas; however, the availability of qualified researchers is usually lower than the demand and training to increase the number of able bioinformaticians is an important task for the bioinformatics community. When conducting training or hands-on tutorials, the lack of control over the analysis tools and repositories often results in undesirable situations during training, as unavailable online tools or version conflicts may delay, complicate, or even prevent the successful completion of a training event. The eBioKit is a stand-alone educational platform that hosts numerous tools and databases for bioinformatics research and allows training to take place in a controlled environment. A key advantage of the eBioKit over other existing teaching solutions is that all the required software and databases are locally installed on the system, significantly reducing the dependence on the internet. Furthermore, the architecture of the eBioKit has demonstrated itself to be an excellent balance between portability and performance, not only making the eBioKit an exceptional educational tool but also providing small research groups with a platform to incorporate bioinformatics analysis in their research. As a result, the eBioKit has formed an integral part of training and research performed by a wide variety of universities and organizations such as the Pan African Bioinformatics Network (H3ABioNet) as part of the initiative Human Heredity and Health in Africa (H3Africa), the Southern Africa Network for Biosciences (SAnBio) initiative, the Biosciences eastern and central Africa (BecA) hub, and the International Glossina Genome Initiative. PMID:28910280

[The Academy of Trauma Surgery (AUC). Service provider and management organization of the DGU].

PubMed

Sturm, J A; Hoffmann, R

2016-02-01

At the beginning of this century the German Trauma Society (DGU) became extensively active with an initiative on quality promotion, development of quality assurance and transparency regarding treatment of the severely injured. A white book on "Medical care of the severely injured" was published, focusing on the requirements on structural quality and especially procedural quality. The impact of the white book was immense and a trauma network with approved trauma centers, structured and graded for their individual trauma care performance, was developed. In order to monitor and document the required quality of care, a registry was needed. Furthermore, for cooperation within the trauma networks innovative methods for digital transfer of radiological images and patient documents became necessary. Finally, the auditing criteria for trauma centers had and still have to be completed with advanced medical education and training programs. In order to realize the implementation of such a broad spectrum of economically relevant and increasingly complex activities the Academy of Trauma Surgery (AUC) was established as a subsidiary of the DGU in 2004. The AUC currently has four divisions: 1) networks and health care structures, 2) registries and research management, 3) telemedicine, 4) medical education and training, all of which serve the goal of the initiative. The AUC is a full service provider and management organization in compliance with the statutes of the DGU. According to these statutes the business operations of the AUC also cover projects for numerous groups of patients, projects for the joint society the German Society for Orthopedics and Trauma (DGOU) as well as other medical institutions. This article describes the success stories of the trauma network (TraumaNetzwerk DGU®), the TraumaRegister DGU®, the telecooperation platform TKmed®, the new and fast-growing orthogeriatric center initiative (AltersTraumaZentrum DGU®) and the division of medical education and training, e.g. advanced trauma life support (ATLS®) and other training programs including the innovative interpersonal competence (IC) course.

Localization and identification of structural nonlinearities using cascaded optimization and neural networks

NASA Astrophysics Data System (ADS)

Koyuncu, A.; Cigeroglu, E.; Özgüven, H. N.

2017-10-01

In this study, a new approach is proposed for identification of structural nonlinearities by employing cascaded optimization and neural networks. Linear finite element model of the system and frequency response functions measured at arbitrary locations of the system are used in this approach. Using the finite element model, a training data set is created, which appropriately spans the possible nonlinear configurations space of the system. A classification neural network trained on these data sets then localizes and determines the types of all nonlinearities associated with the nonlinear degrees of freedom in the system. A new training data set spanning the parametric space associated with the determined nonlinearities is created to facilitate parametric identification. Utilizing this data set, initially, a feed forward regression neural network is trained, which parametrically identifies the classified nonlinearities. Then, the results obtained are further improved by carrying out an optimization which uses network identified values as starting points. Unlike identification methods available in literature, the proposed approach does not require data collection from the degrees of freedoms where nonlinear elements are attached, and furthermore, it is sufficiently accurate even in the presence of measurement noise. The application of the proposed approach is demonstrated on an example system with nonlinear elements and on a real life experimental setup with a local nonlinearity.

Sci-Thur AM: YIS – 05: Prediction of lung tumor motion using a generalized neural network optimized from the average prediction outcome of a group of patients

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

Teo, Troy; Alayoubi, Nadia; Bruce, Neil

Purpose: In image-guided adaptive radiotherapy systems, prediction of tumor motion is required to compensate for system latencies. However, due to the non-stationary nature of respiration, it is a challenge to predict the associated tumor motions. In this work, a systematic design of the neural network (NN) using a mixture of online data acquired during the initial period of the tumor trajectory, coupled with a generalized model optimized using a group of patient data (obtained offline) is presented. Methods: The average error surface obtained from seven patients was used to determine the input data size and number of hidden neurons formore » the generalized NN. To reduce training time, instead of using random weights to initialize learning (method 1), weights inherited from previous training batches (method 2) were used to predict tumor position for each sliding window. Results: The generalized network was established with 35 input data (∼4.66s) and 20 hidden nodes. For a prediction horizon of 650 ms, mean absolute errors of 0.73 mm and 0.59 mm were obtained for method 1 and 2 respectively. An average initial learning period of 8.82 s is obtained. Conclusions: A network with a relatively short initial learning time was achieved. Its accuracy is comparable to previous studies. This network could be used as a plug-and play predictor in which (a) tumor positions can be predicted as soon as treatment begins and (b) the need for pretreatment data and optimization for individual patients can be avoided.« less

Flight Test of an Intelligent Flight-Control System

NASA Technical Reports Server (NTRS)

Davidson, Ron; Bosworth, John T.; Jacobson, Steven R.; Thomson, Michael Pl; Jorgensen, Charles C.

2003-01-01

The F-15 Advanced Controls Technology for Integrated Vehicles (ACTIVE) airplane (see figure) was the test bed for a flight test of an intelligent flight control system (IFCS). This IFCS utilizes a neural network to determine critical stability and control derivatives for a control law, the real-time gains of which are computed by an algorithm that solves the Riccati equation. These derivatives are also used to identify the parameters of a dynamic model of the airplane. The model is used in a model-following portion of the control law, in order to provide specific vehicle handling characteristics. The flight test of the IFCS marks the initiation of the Intelligent Flight Control System Advanced Concept Program (IFCS ACP), which is a collaboration between NASA and Boeing Phantom Works. The goals of the IFCS ACP are to (1) develop the concept of a flight-control system that uses neural-network technology to identify aircraft characteristics to provide optimal aircraft performance, (2) develop a self-training neural network to update estimates of aircraft properties in flight, and (3) demonstrate the aforementioned concepts on the F-15 ACTIVE airplane in flight. The activities of the initial IFCS ACP were divided into three Phases, each devoted to the attainment of a different objective. The objective of Phase I was to develop a pre-trained neural network to store and recall the wind-tunnel-based stability and control derivatives of the vehicle. The objective of Phase II was to develop a neural network that can learn how to adjust the stability and control derivatives to account for failures or modeling deficiencies. The objective of Phase III was to develop a flight control system that uses the neural network outputs as a basis for controlling the aircraft. The flight test of the IFCS was performed in stages. In the first stage, the Phase I version of the pre-trained neural network was flown in a passive mode. The neural network software was running using flight data inputs with the outputs provided to instrumentation only. The IFCS was not used to control the airplane. In another stage of the flight test, the Phase I pre-trained neural network was integrated into a Phase III version of the flight control system. The Phase I pretrained neural network provided realtime stability and control derivatives to a Phase III controller that was based on a stochastic optimal feedforward and feedback technique (SOFFT). This combined Phase I/III system was operated together with the research flight-control system (RFCS) of the F-15 ACTIVE during the flight test. The RFCS enables the pilot to switch quickly from the experimental- research flight mode back to the safe conventional mode. These initial IFCS ACP flight tests were completed in April 1999. The Phase I/III flight test milestone was to demonstrate, across a range of subsonic and supersonic flight conditions, that the pre-trained neural network could be used to supply real-time aerodynamic stability and control derivatives to the closed-loop optimal SOFFT flight controller. Additional objectives attained in the flight test included (1) flight qualification of a neural-network-based control system; (2) the use of a combined neural-network/closed-loop optimal flight-control system to obtain level-one handling qualities; and (3) demonstration, through variation of control gains, that different handling qualities can be achieved by setting new target parameters. In addition, data for the Phase-II (on-line-learning) neural network were collected, during the use of stacked-frequency- sweep excitation, for post-flight analysis. Initial analysis of these data showed the potential for future flight tests that will incorporate the real-time identification and on-line learning aspects of the IFCS.

An application of artificial neural networks to experimental data approximation

NASA Technical Reports Server (NTRS)

Meade, Andrew J., Jr.

1993-01-01

As an initial step in the evaluation of networks, a feedforward architecture is trained to approximate experimental data by the backpropagation algorithm. Several drawbacks were detected and an alternative learning algorithm was then developed to partially address the drawbacks. This noniterative algorithm has a number of advantages over the backpropagation method and is easily implemented on existing hardware.

Disrupting the Implementation Gap with Digital Technology in Healthcare Distance Education: Critical Insights from an e-Mentoring Intensional Network Practitioner Research Project

ERIC Educational Resources Information Center

Singh, Gurmit

2013-01-01

Effective professional distance education is urgently needed to develop a well-trained workforce and improve impact on healthcare. However, distance education initiatives have had mixed results in improving practice. Often, successful implementation fails to leverage insights on the social and emergent nature of learning in networks. This paper…

Training set expansion: an approach to improving the reconstruction of biological networks from limited and uneven reliable interactions

PubMed Central

Yip, Kevin Y.; Gerstein, Mark

2009-01-01

Motivation: An important problem in systems biology is reconstructing complete networks of interactions between biological objects by extrapolating from a few known interactions as examples. While there are many computational techniques proposed for this network reconstruction task, their accuracy is consistently limited by the small number of high-confidence examples, and the uneven distribution of these examples across the potential interaction space, with some objects having many known interactions and others few. Results: To address this issue, we propose two computational methods based on the concept of training set expansion. They work particularly effectively in conjunction with kernel approaches, which are a popular class of approaches for fusing together many disparate types of features. Both our methods are based on semi-supervised learning and involve augmenting the limited number of gold-standard training instances with carefully chosen and highly confident auxiliary examples. The first method, prediction propagation, propagates highly confident predictions of one local model to another as the auxiliary examples, thus learning from information-rich regions of the training network to help predict the information-poor regions. The second method, kernel initialization, takes the most similar and most dissimilar objects of each object in a global kernel as the auxiliary examples. Using several sets of experimentally verified protein–protein interactions from yeast, we show that training set expansion gives a measurable performance gain over a number of representative, state-of-the-art network reconstruction methods, and it can correctly identify some interactions that are ranked low by other methods due to the lack of training examples of the involved proteins. Contact: mark.gerstein@yale.edu Availability: The datasets and additional materials can be found at http://networks.gersteinlab.org/tse. PMID:19015141

Accurate modeling of switched reluctance machine based on hybrid trained WNN

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

Song, Shoujun, E-mail: sunnyway@nwpu.edu.cn; Ge, Lefei; Ma, Shaojie

2014-04-15

According to the strong nonlinear electromagnetic characteristics of switched reluctance machine (SRM), a novel accurate modeling method is proposed based on hybrid trained wavelet neural network (WNN) which combines improved genetic algorithm (GA) with gradient descent (GD) method to train the network. In the novel method, WNN is trained by GD method based on the initial weights obtained per improved GA optimization, and the global parallel searching capability of stochastic algorithm and local convergence speed of deterministic algorithm are combined to enhance the training accuracy, stability and speed. Based on the measured electromagnetic characteristics of a 3-phase 12/8-pole SRM, themore » nonlinear simulation model is built by hybrid trained WNN in Matlab. The phase current and mechanical characteristics from simulation under different working conditions meet well with those from experiments, which indicates the accuracy of the model for dynamic and static performance evaluation of SRM and verifies the effectiveness of the proposed modeling method.« less

Cascade heterogeneous face sketch-photo synthesis via dual-scale Markov Network

NASA Astrophysics Data System (ADS)

Yao, Saisai; Chen, Zhenxue; Jia, Yunyi; Liu, Chengyun

2018-03-01

Heterogeneous face sketch-photo synthesis is an important and challenging task in computer vision, which has widely applied in law enforcement and digital entertainment. According to the different synthesis results based on different scales, this paper proposes a cascade sketch-photo synthesis method via dual-scale Markov Network. Firstly, Markov Network with larger scale is used to synthesise the initial sketches and the local vertical and horizontal neighbour search (LVHNS) method is used to search for the neighbour patches of test patches in training set. Then, the initial sketches and test photos are jointly entered into smaller scale Markov Network. Finally, the fine sketches are obtained after cascade synthesis process. Extensive experimental results on various databases demonstrate the superiority of the proposed method compared with several state-of-the-art methods.

The child and adolescent psychiatry trials network (CAPTN): infrastructure development and lessons learned

PubMed Central

Shapiro, Mark; Silva, Susan G; Compton, Scott; Chrisman, Allan; DeVeaugh-Geiss, Joseph; Breland-Noble, Alfiee; Kondo, Douglas; Kirchner, Jerry; March, John S

2009-01-01

Background In 2003, the National Institute of Mental Health funded the Child and Adolescent Psychiatry Trials Network (CAPTN) under the Advanced Center for Services and Intervention Research (ACSIR) mechanism. At the time, CAPTN was believed to be both a highly innovative undertaking and a highly speculative one. One reviewer even suggested that CAPTN was "unlikely to succeed, but would be a valuable learning experience for the field." Objective To describe valuable lessons learned in building a clinical research network in pediatric psychiatry, including innovations intended to decrease barriers to research participation. Methods The CAPTN Team has completed construction of the CAPTN network infrastructure, conducted a large, multi-center psychometric study of a novel adverse event reporting tool, and initiated a large antidepressant safety registry and linked pharmacogenomic study focused on severe adverse events. Specific challenges overcome included establishing structures for network organization and governance; recruiting over 150 active CAPTN participants and 15 child psychiatry training programs; developing and implementing procedures for site contracts, regulatory compliance, indemnification and malpractice coverage, human subjects protection training and IRB approval; and constructing an innovative electronic casa report form (eCRF) running on a web-based electronic data capture system; and, finally, establishing procedures for audit trail oversight requirements put forward by, among others, the Food and Drug Administration (FDA). Conclusion Given stable funding for network construction and maintenance, our experience demonstrates that judicious use of web-based technologies for profiling investigators, investigator training, and capturing clinical trials data, when coupled to innovative approaches to network governance, data management and site management, can reduce the costs and burden and improve the feasibility of incorporating clinical research into routine clinical practice. Having successfully achieved its initial aim of constructing a network infrastructure, CAPTN is now a capable platform for large safety registries, pharmacogenetic studies, and randomized practical clinical trials in pediatric psychiatry. PMID:19320979

Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV: structuring synaptic pathways among recurrent connections.

PubMed

Gilson, Matthieu; Burkitt, Anthony N; Grayden, David B; Thomas, Doreen A; van Hemmen, J Leo

2009-12-01

In neuronal networks, the changes of synaptic strength (or weight) performed by spike-timing-dependent plasticity (STDP) are hypothesized to give rise to functional network structure. This article investigates how this phenomenon occurs for the excitatory recurrent connections of a network with fixed input weights that is stimulated by external spike trains. We develop a theoretical framework based on the Poisson neuron model to analyze the interplay between the neuronal activity (firing rates and the spike-time correlations) and the learning dynamics, when the network is stimulated by correlated pools of homogeneous Poisson spike trains. STDP can lead to both a stabilization of all the neuron firing rates (homeostatic equilibrium) and a robust weight specialization. The pattern of specialization for the recurrent weights is determined by a relationship between the input firing-rate and correlation structures, the network topology, the STDP parameters and the synaptic response properties. We find conditions for feed-forward pathways or areas with strengthened self-feedback to emerge in an initially homogeneous recurrent network.

The Illinois Century Network: New Dimensions for Education in Illinois. A Vision for Communications and Computing Networking To Retain and Expand Illinois' Position as a World Leader by the Turn of the Century. Report and First-Phase Recommendations of the Higher Education Technology Task Force to the Illinois Board of Higher Education and the Illinois Community College Board.

ERIC Educational Resources Information Center

Illinois State Board of Higher Education, Springfield.

This proposal calls on the state of Illinois to initiate a statewide computing and telecommunications network that would give its residents access to higher education, advanced training, and electronic information resources. The proposed network, entitled Illinois Century Network, would link all higher education institutions in the state to…

The collaborative African genomics network training program: a trainee perspective on training the next generation of African scientists.

PubMed

Mlotshwa, Busisiwe C; Mwesigwa, Savannah; Mboowa, Gerald; Williams, Lesedi; Retshabile, Gaone; Kekitiinwa, Adeodata; Wayengera, Misaki; Kyobe, Samuel; Brown, Chester W; Hanchard, Neil A; Mardon, Graeme; Joloba, Moses; Anabwani, Gabriel; Mpoloka, Sununguko W

2017-07-01

The Collaborative African Genomics Network (CAfGEN) aims to establish sustainable genomics research programs in Botswana and Uganda through long-term training of PhD students from these countries at Baylor College of Medicine. Here, we present an overview of the CAfGEN PhD training program alongside trainees' perspectives on their involvement. Historically, collaborations between high-income countries (HICs) and low- and middle-income countries (LMICs), or North-South collaborations, have been criticized for the lack of a mutually beneficial distribution of resources and research findings, often undermining LMICs. CAfGEN plans to address this imbalance in the genomics field through a program of technology and expertise transfer to the participating LMICs. An overview of the training program is presented. Trainees from the CAfGEN project summarized their experiences, looking specifically at the training model, benefits of the program, challenges encountered relating to the cultural transition, and program outcomes after the first 2 years. Collaborative training programs like CAfGEN will not only help establish sustainable long-term research initiatives in LMICs but also foster stronger North-South and South-South networks. The CAfGEN model offers a framework for the development of training programs aimed at genomics education for those for whom genomics is not their "first language." Genet Med advance online publication 06 April 2017.

The collaborative African genomics network training program: a trainee perspective on training the next generation of African scientists

PubMed Central

Mlotshwa, Busisiwe C.; Mwesigwa, Savannah; Mboowa, Gerald; Williams, Lesedi; Retshabile, Gaone; Kekitiinwa, Adeodata; Wayengera, Misaki; Kyobe, Samuel; Brown, Chester W.; Hanchard, Neil A.; Mardon, Graeme; Joloba, Moses; Anabwani, Gabriel; Mpoloka, Sununguko W.

2017-01-01

Purpose: The Collaborative African Genomics Network (CAfGEN) aims to establish sustainable genomics research programs in Botswana and Uganda through long-term training of PhD students from these countries at Baylor College of Medicine. Here, we present an overview of the CAfGEN PhD training program alongside trainees’ perspectives on their involvement. Background: Historically, collaborations between high-income countries (HICs) and low- and middle-income countries (LMICs), or North–South collaborations, have been criticized for the lack of a mutually beneficial distribution of resources and research findings, often undermining LMICs. CAfGEN plans to address this imbalance in the genomics field through a program of technology and expertise transfer to the participating LMICs. Methods: An overview of the training program is presented. Trainees from the CAfGEN project summarized their experiences, looking specifically at the training model, benefits of the program, challenges encountered relating to the cultural transition, and program outcomes after the first 2 years. Conclusion: Collaborative training programs like CAfGEN will not only help establish sustainable long-term research initiatives in LMICs but also foster stronger North–South and South–South networks. The CAfGEN model offers a framework for the development of training programs aimed at genomics education for those for whom genomics is not their “first language.” Genet Med advance online publication 06 April 2017 PMID:28383545

Type 2 diabetes patient education in Reunion Island: perceptions and needs of professionals in advance of the initiation of a primary care management network.

PubMed

Balcou-Debussche, M; Debussche, X

2008-09-01

This study focused on issues in the education of type 2 diabetes patients in primary care on Reunion Island which, in a medical context, is broadly similar to metropolitan France, but with a much greater prevalence of diabetes. The aim was to assess the perceptions, training, reported practices and needs of health care providers in the field of patient education in advance of the initiation of a health care management network for diabetic patients. A total of 74 physicians and 63 nurses completed a detailed questionnaire comprising 52 items divided into six parts: professional activity, initial and postgraduate training, educational practices, objectives of patient education, perceived barriers and prospects for optimization. Educational activities for patients are almost nonexistent. Information and explanations given during a face-to-face encounter with the physician or nurse that combine technical and caring approaches are the main reasons reported for patient education. The obstacles reported by professionals that need to be overcome are limited available time, patient passivity and inadequate staff training. Practitioners and nurses are poorly taught as regards patient education and self-management of chronic diseases. The suggested improvements include professional acknowledgement, more convenient and available tools and improved postgraduate training. Patient education in primary care is still mostly an illusion, with many gaps that hinder education for both patients and professionals. The training of health professionals needs to meet the challenge of chronic diseases by integrating aspects from the fields of education and the social sciences.

"Does Knowing Stuff like PSHE and Citizenship Make Me a Better Teacher?": Student Teachers in the Teacher Training Figuration

ERIC Educational Resources Information Center

Velija, Philippa; Capel, Susan; Katene, Will; Hayes, Sid

2008-01-01

One of the key elements of figurational sociology is the emphasis on understanding complex networks of interdependencies in which people are involved. The focal point of this paper is the process of initial teacher training (ITT) and the relationships of which student teachers are part during their ITT course. The paper does not look at what…

Does Academic Apprenticeship Increase Networking Ties among Participants? A Case Study of an Energy Efficiency Training Program

ERIC Educational Resources Information Center

Hytönen, Kaisa; Palonen, Tuire; Lehtinen, Erno; Hakkarainen, Kai

2014-01-01

In order to address the requirements of future education in different fields of academic professional activity, a model called Academic Apprenticeship Education was initiated in Finland in 2009. The aim of this article is to analyse the development of expert networks in the context of a 1-year Academic Apprenticeship Education model in the field…

Long term care needs and personal care services under Medicaid: a survey of administrators.

PubMed

Palley, H A; Oktay, J S

1991-01-01

Home and community based care services constitute a public initiative in the development of a long term care service network. One such home based initiative is the personal care service program of Medicaid. The authors conducted a national survey of administrators of this program. They received a response from 16 administrators of such programs in 1987-1988. The responses raise significant issues regarding training, access to and equity of services, quality of services, administrative oversight and the coordination of home-based care in a network of available services. Based on administrator responses, the authors draw several conclusions.

High quality garbage: A neural network plastic sorter in hardware and software

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

Stanton, S.L.; Alam, M.K.; Hebner, G.A.

1993-09-01

In order to produce pure polymer streams from post-consumer waste plastics, a quick, accurate and relatively inexpensive method of sorting needs to be implemented. This technology has been demonstrated by using near-infrared spectroscopy reflectance data and neural network classification techniques. Backpropagation neural network routines have been developed to run real-time sortings in the lab, using a laboratory-grade spectrometer. In addition, a new reflectance spectrometer has been developed which is fast enough for commercial use. Initial training and test sets taken with the laboratory instrument show that a network is capable of learning 100% when classifying 5 groups of plastic (HDPEmore » and LDPE combined), and up to 100% when classifying 6 groups. Initial data sets from the new instrument have classified plastics into all seven groups with varying degrees of success. One of the initial networks has been implemented in hardware, for high speed computations, and thus rapid classification. Two neural accelerator systems have been evaluated, one based on the Intel 8017ONX chip, and another on the AT&T ANNA chip.« less

The Strengthening Families Initiative and Child Care Quality Improvement: How Strengthening Families Influenced Change in Child Care Programs in One State

ERIC Educational Resources Information Center

Douglass, Anne; Klerman, Lorraine

2012-01-01

Research Findings: This study investigated how the Strengthening Families through Early Care and Education initiative in Illinois (SFI) influenced change in 4 child care programs. Findings indicate that SFI influenced quality improvements through 4 primary pathways: (a) Learning Networks, (b) the quality of training, (c) the engagement of program…

A fuzzy neural network for intelligent data processing

NASA Astrophysics Data System (ADS)

Xie, Wei; Chu, Feng; Wang, Lipo; Lim, Eng Thiam

2005-03-01

In this paper, we describe an incrementally generated fuzzy neural network (FNN) for intelligent data processing. This FNN combines the features of initial fuzzy model self-generation, fast input selection, partition validation, parameter optimization and rule-base simplification. A small FNN is created from scratch -- there is no need to specify the initial network architecture, initial membership functions, or initial weights. Fuzzy IF-THEN rules are constantly combined and pruned to minimize the size of the network while maintaining accuracy; irrelevant inputs are detected and deleted, and membership functions and network weights are trained with a gradient descent algorithm, i.e., error backpropagation. Experimental studies on synthesized data sets demonstrate that the proposed Fuzzy Neural Network is able to achieve accuracy comparable to or higher than both a feedforward crisp neural network, i.e., NeuroRule, and a decision tree, i.e., C4.5, with more compact rule bases for most of the data sets used in our experiments. The FNN has achieved outstanding results for cancer classification based on microarray data. The excellent classification result for Small Round Blue Cell Tumors (SRBCTs) data set is shown. Compared with other published methods, we have used a much fewer number of genes for perfect classification, which will help researchers directly focus their attention on some specific genes and may lead to discovery of deep reasons of the development of cancers and discovery of drugs.

LAI inversion from optical reflectance using a neural network trained with a multiple scattering model

NASA Technical Reports Server (NTRS)

Smith, James A.

1992-01-01

The inversion of the leaf area index (LAI) canopy parameter from optical spectral reflectance measurements is obtained using a backpropagation artificial neural network trained using input-output pairs generated by a multiple scattering reflectance model. The problem of LAI estimation over sparse canopies (LAI < 1.0) with varying soil reflectance backgrounds is particularly difficult. Standard multiple regression methods applied to canopies within a single homogeneous soil type yield good results but perform unacceptably when applied across soil boundaries, resulting in absolute percentage errors of >1000 percent for low LAI. Minimization methods applied to merit functions constructed from differences between measured reflectances and predicted reflectances using multiple-scattering models are unacceptably sensitive to a good initial guess for the desired parameter. In contrast, the neural network reported generally yields absolute percentage errors of <30 percent when weighting coefficients trained on one soil type were applied to predicted canopy reflectance at a different soil background.

Daily iTBS worsens hand motor training--a combined TMS, fMRI and mirror training study.

PubMed

Läppchen, C H; Ringer, T; Blessin, J; Schulz, K; Seidel, G; Lange, R; Hamzei, F

2015-02-15

Repetitive transcranial magnetic stimulation (rTMS) is used to increase regional excitability to improve motor function in combination with training after neurological diseases or events such as stroke. We investigated whether a daily application of intermittent theta burst stimulation (iTBS; a short-duration rTMS that increases regional excitability) improves the training effect compared with sham stimulation in association with a four-day hand training program using a mirror (mirror training, MT). The right dorsal premotor cortex (dPMC right) was chosen as the target region for iTBS because this region has recently been emphasized as a node within a network related to MT. Healthy subjects were randomized into the iTBS group or sham group (control group CG). In the iTBS group, iTBS was applied daily over dPMC right, which was functionally determined in an initial fMRI session prior to starting MT. MT involved 20 min of hand training daily in a mirror over four days. The hand tests, the intracortical excitability and fMRI were evaluated prior to and at the end of MT. The results of the hand training tests of the iTBS group were surprisingly significantly poorer compared with those from the CG group. Both groups showed a different course of excitability in both M1 and a different course of fMRI activation within the supplementary motor area and M1 left. We suggest the inter-regional functional balance was affected by daily iTBS over dPMC right. Maybe an inter-regional connectivity within a network is differentially balanced. An excitability increase within an inhibitory-balanced network would therefore disturb the underlying network. Copyright © 2014 Elsevier Inc. All rights reserved.

Retrieval of ice thickness from polarimetric SAR data

NASA Technical Reports Server (NTRS)

Kwok, R.; Yueh, S. H.; Nghiem, S. V.; Huynh, D. D.

1993-01-01

We describe a potential procedure for retrieving ice thickness from multi-frequency polarimetric SAR data for thin ice. This procedure includes first masking out the thicker ice types with a simple classifier and then deriving the thickness of the remaining pixels using a model-inversion technique. The technique used to derive ice thickness from polarimetric observations is provided by a numerical estimator or neural network. A three-layer perceptron implemented with the backpropagation algorithm is used in this investigation with several improved aspects for a faster convergence rate and a better accuracy of the neural network. These improvements include weight initialization, normalization of the output range, the selection of offset constant, and a heuristic learning algorithm. The performance of the neural network is demonstrated by using training data generated by a theoretical scattering model for sea ice matched to the database of interest. The training data are comprised of the polarimetric backscattering coefficients of thin ice and the corresponding input ice parameters to the scattering model. The retrieved ice thickness from the theoretical backscattering coefficients is compare with the input ice thickness to the scattering model to illustrate the accuracy of the inversion method. Results indicate that the network convergence rate and accuracy are higher when multi-frequency training sets are presented. In addition, the dominant backscattering coefficients in retrieving ice thickness are found by comparing the behavior of the network trained backscattering data at various incidence angels. After the neural network is trained with the theoretical backscattering data at various incidence anges, the interconnection weights between nodes are saved and applied to the experimental data to be investigated. In this paper, we illustrate the effectiveness of this technique using polarimetric SAR data collected by the JPL DC-8 radar over a sea ice scene.

"It takes more than a fellowship program": reflections on capacity strengthening for health systems research in sub-Saharan Africa.

PubMed

Izugbara, Chimaraoke O; Kabiru, Caroline W; Amendah, Djesika; Dimbuene, Zacharie Tsala; Donfouet, Hermann Pythagore Pierre; Atake, Esso-Hanam; Ingabire, Marie-Gloriose; Maluka, Stephen; Mumah, Joyce N; Mwau, Matilu; Ndinya, Mollyne; Ngure, Kenneth; Sidze, Estelle M; Sossa, Charles; Soura, Abdramane; Ezeh, Alex C

2017-12-04

Sub-Saharan Africa (SSA) experiences an acute dearth of well-trained and skilled researchers. This dearth constrains the region's capacity to identify and address the root causes of its poor social, health, development, and other outcomes. Building sustainable research capacity in SSA requires, among other things, locally led and run initiatives that draw on existing regional capacities as well as mutually beneficial global collaborations. This paper describes a regional research capacity strengthening initiative-the African Doctoral Dissertation Research Fellowship (ADDRF) program. This Africa-based and African-led initiative has emerged as a practical and tested platform for producing and nurturing research leaders, strengthening university-wide systems for quality research training and productivity, and building a critical mass of highly-trained African scholars and researchers. The program deploys different interventions to ensure the success of fellows. These interventions include research methods and scientific writing workshops, research and reentry support grants, post-doctoral research support and placements, as well as grants for networking and scholarly conferences attendance. Across the region, ADDRF graduates are emerging as research leaders, showing signs of becoming the next generation of world-class researchers, and supporting the transformations of their home-institutions. While the contributions of the ADDRF program to research capacity strengthening in the region are significant, the sustainability of the initiative and other research and training fellowship programs on the continent requires significant investments from local sources and, especially, governments and the private sector in Africa. The ADDRF experience demonstrates that research capacity building in Africa is possible through innovative, multifaceted interventions that support graduate students to develop different critical capacities and transferable skills and build, expand, and maintain networks that can sustain them as scholars and researchers.

Improved STD Syndrome Management by a Network of Clinicians and Pharmacy Workers in Peru: The PREVEN Network

PubMed Central

García, Patricia J.; Carcamo, Cesar P.; Garnett, Geoff P.; Campos, Pablo E.; Holmes, King K.

2012-01-01

Background Sexually Transmitted diseases (STD) syndrome management has been one cornerstone of STD treatment. Persons with STD symptoms in many countries, especially those with limited resources, often initially seek care in pharmacies. The objective of the study was to develop and evaluate an integrated network of physicians, midwives and pharmacy workers trained in STD syndromic management (The PREVEN Network) as part of a national urban community-randomized trial of sexually transmitted infection prevention in Peru. Methods and Findings After a comprehensive census of physicians, midwives, and pharmacies in ten intervention and ten control cities, we introduced seminars and workshops for pharmacy workers, and continuing education for physicians and midwives in intervention cities and invited graduates to join the PREVEN Network. “Prevention Salespersons” visited pharmacies, boticas and clinicians regularly for educational support and collection of information on numbers of cases of STD syndromes seen at pharmacies and by clinicians in intervention cities. Simulated patients evaluated outcomes of training of pharmacy workers with respect to adequate STD syndrome management, recommendations for condom use and for treatment of partners. In intervention cities we trained, certified, and incorporated into the PREVEN Network the workers at 623 (80.6%) of 773 pharmacies and 701 (69.6%) of 1007 physicians and midwives in private practice. Extremely high clinician and pharmacy worker turnover, 13.4% and 44% respectively in the first year, dictated continued training of new pharmacy workers and clinicians. By the end of the intervention the Network included 792 pharmacies and 597 clinicians. Pharmacies reported more cases of STDs than did clinicians. Evaluations by simulated patients showed significant and substantial improvements in the management of STD syndromes at pharmacies in intervention cities but not in control cities. Conclusions Training pharmacy workers linked to a referral network of clinicians proved feasible and acceptable. High turn-over was challenging but over come. PMID:23082208

Improved STD syndrome management by a network of clinicians and pharmacy workers in Peru: The PREVEN Network.

PubMed

García, Patricia J; Carcamo, Cesar P; Garnett, Geoff P; Campos, Pablo E; Holmes, King K

2012-01-01

Sexually Transmitted diseases (STD) syndrome management has been one cornerstone of STD treatment. Persons with STD symptoms in many countries, especially those with limited resources, often initially seek care in pharmacies. The objective of the study was to develop and evaluate an integrated network of physicians, midwives and pharmacy workers trained in STD syndromic management (The PREVEN Network) as part of a national urban community-randomized trial of sexually transmitted infection prevention in Peru. After a comprehensive census of physicians, midwives, and pharmacies in ten intervention and ten control cities, we introduced seminars and workshops for pharmacy workers, and continuing education for physicians and midwives in intervention cities and invited graduates to join the PREVEN Network. "Prevention Salespersons" visited pharmacies, boticas and clinicians regularly for educational support and collection of information on numbers of cases of STD syndromes seen at pharmacies and by clinicians in intervention cities. Simulated patients evaluated outcomes of training of pharmacy workers with respect to adequate STD syndrome management, recommendations for condom use and for treatment of partners. In intervention cities we trained, certified, and incorporated into the PREVEN Network the workers at 623 (80.6%) of 773 pharmacies and 701 (69.6%) of 1007 physicians and midwives in private practice. Extremely high clinician and pharmacy worker turnover, 13.4% and 44% respectively in the first year, dictated continued training of new pharmacy workers and clinicians. By the end of the intervention the Network included 792 pharmacies and 597 clinicians. Pharmacies reported more cases of STDs than did clinicians. Evaluations by simulated patients showed significant and substantial improvements in the management of STD syndromes at pharmacies in intervention cities but not in control cities. Training pharmacy workers linked to a referral network of clinicians proved feasible and acceptable. High turn-over was challenging but over come.

High-Throughput Classification of Radiographs Using Deep Convolutional Neural Networks.

PubMed

Rajkomar, Alvin; Lingam, Sneha; Taylor, Andrew G; Blum, Michael; Mongan, John

2017-02-01

The study aimed to determine if computer vision techniques rooted in deep learning can use a small set of radiographs to perform clinically relevant image classification with high fidelity. One thousand eight hundred eighty-five chest radiographs on 909 patients obtained between January 2013 and July 2015 at our institution were retrieved and anonymized. The source images were manually annotated as frontal or lateral and randomly divided into training, validation, and test sets. Training and validation sets were augmented to over 150,000 images using standard image manipulations. We then pre-trained a series of deep convolutional networks based on the open-source GoogLeNet with various transformations of the open-source ImageNet (non-radiology) images. These trained networks were then fine-tuned using the original and augmented radiology images. The model with highest validation accuracy was applied to our institutional test set and a publicly available set. Accuracy was assessed by using the Youden Index to set a binary cutoff for frontal or lateral classification. This retrospective study was IRB approved prior to initiation. A network pre-trained on 1.2 million greyscale ImageNet images and fine-tuned on augmented radiographs was chosen. The binary classification method correctly classified 100 % (95 % CI 99.73-100 %) of both our test set and the publicly available images. Classification was rapid, at 38 images per second. A deep convolutional neural network created using non-radiological images, and an augmented set of radiographs is effective in highly accurate classification of chest radiograph view type and is a feasible, rapid method for high-throughput annotation.

Probabilistic estimation of dune retreat on the Gold Coast, Australia

USGS Publications Warehouse

Palmsten, Margaret L.; Splinter, Kristen D.; Plant, Nathaniel G.; Stockdon, Hilary F.

2014-01-01

Sand dunes are an important natural buffer between storm impacts and development backing the beach on the Gold Coast of Queensland, Australia. The ability to forecast dune erosion at a prediction horizon of days to a week would allow efficient and timely response to dune erosion in this highly populated area. Towards this goal, we modified an existing probabilistic dune erosion model for use on the Gold Coast. The original model was trained using observations of dune response from Hurricane Ivan on Santa Rosa Island, Florida, USA (Plant and Stockdon 2012. Probabilistic prediction of barrier-island response to hurricanes, Journal of Geophysical Research, 117(F3), F03015). The model relates dune position change to pre-storm dune elevations, dune widths, and beach widths, along with storm surge and run-up using a Bayesian network. The Bayesian approach captures the uncertainty of inputs and predictions through the conditional probabilities between variables. Three versions of the barrier island response Bayesian network were tested for use on the Gold Coast. One network has the same structure as the original and was trained with the Santa Rosa Island data. The second network has a modified design and was trained using only pre- and post-storm data from 1988-2009 for the Gold Coast. The third version of the network has the same design as the second version of the network and was trained with the combined data from the Gold Coast and Santa Rosa Island. The two networks modified for use on the Gold Coast hindcast dune retreat with equal accuracy. Both networks explained 60% of the observed dune retreat variance, which is comparable to the skill observed by Plant and Stockdon (2012) in the initial Bayesian network application at Santa Rosa Island. The new networks improved predictions relative to application of the original network on the Gold Coast. Dune width was the most important morphologic variable in hindcasting dune retreat, while hydrodynamic variables, surge and run-up elevation, were also important

Implementation of Integrated Service Networks under the Quebec Mental Health Reform: Facilitators and Barriers associated with Different Territorial Profiles.

PubMed

Fleury, Marie-Josée; Grenier, Guy; Vallée, Catherine; Aubé, Denise; Farand, Lambert

2017-03-10

This study evaluates implementation of the Quebec Mental Health Reform (2005-2015), which promoted the development of integrated service networks, in 11 local service networks organized into four territorial groups according to socio-demographic characteristics and mental health services offered. Data were collected from documents concerning networks; structured questionnaires completed by 90 managers and by 16 respondent-psychiatrists; and semi-structured interviews with 102 network stakeholders. Factors associated with implementation and integration were organized according to: 1) reform characteristics; 2) implementation context; 3) organizational characteristics; and 4) integration strategies. While local networks were in a process of development and expansion, none were fully integrated at the time of the study. Facilitators and barriers to implementation and integration were primarily associated with organizational characteristics. Integration was best achieved in larger networks including a general hospital with a psychiatric department, followed by networks with a psychiatric hospital. Formalized integration strategies such as service agreements, liaison officers, and joint training reduced some barriers to implementation in networks experiencing less favourable conditions. Strategies for the implementation of healthcare reform and integrated service networks should include sustained support and training in best-practices, adequate performance indicators and resources, formalized integration strategies to improve network coordination and suitable initiatives to promote staff retention.

Just-in-Time Training: A Novel Approach to Quality Improvement Education.

PubMed

Knutson, Allison; Park, Nesha D; Smith, Denise; Tracy, Kelly; Reed, Danielle J W; Olsen, Steven L

2015-01-01

Just-in-time training (JITT) is accepted in medical education as a training method for newer concepts or seldom-performed procedures. Providing JITT to a large nursing staff may be an effective method to teach quality improvement (QI) initiatives. We sought to determine if JITT could increase knowledge of a specific nutrition QI initiative. Members of the nutrition QI team interviewed staff using the Frontline Contextual Inquiry to assess knowledge regarding the specific QI project. The inquiry was completed pre- and post-JITT. A JITT educational cart was created, which allowed trainers to bring the educational information to the bedside for a short, small group educational session. The results demonstrated a marked improvement in the knowledge of the frontline staff regarding our Vermont Oxford Network involvement and the specifics of the nutrition QI project. Just-in-time training can be a valuable and effective method to disseminate QI principles to a large audience of staff members.

High-Lift Optimization Design Using Neural Networks on a Multi-Element Airfoil

NASA Technical Reports Server (NTRS)

Greenman, Roxana M.; Roth, Karlin R.; Smith, Charles A. (Technical Monitor)

1998-01-01

The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag, and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural networks were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 83% compared with traditional gradient-based optimization procedures for multiple optimization runs.

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.

Identifying Important Attributes for Prognostic Prediction in Traumatic Brain Injury Patients. A Hybrid Method of Decision Tree and Neural Network.

PubMed

Pourahmad, Saeedeh; Hafizi-Rastani, Iman; Khalili, Hosseinali; Paydar, Shahram

2016-10-17

Generally, traumatic brain injury (TBI) patients do not have a stable condition, particularly after the first week of TBI. Hence, indicating the attributes in prognosis through a prediction model is of utmost importance since it helps caregivers with treatment-decision options, or prepares the relatives for the most-likely outcome. This study attempted to determine and order the attributes in prognostic prediction in TBI patients, based on early clinical findings. A hybrid method was employed, which combines a decision tree (DT) and an artificial neural network (ANN) in order to improve the modeling process. The DT approach was applied as the initial analysis of the network architecture to increase accuracy in prediction. Afterwards, the ANN structure was mapped from the initial DT based on a part of the data. Subsequently, the designed network was trained and validated by the remaining data. 5-fold cross-validation method was applied to train the network. The area under the receiver operating characteristic (ROC) curve, sensitivity, specificity, and accuracy rate were utilized as performance measures. The important attributes were then determined from the trained network using two methods: change of mean squared error (MSE), and sensitivity analysis (SA). The hybrid method offered better results compared to the DT method. The accuracy rate of 86.3 % vs. 82.2 %, sensitivity value of 55.1 % vs. 47.6 %, specificity value of 93.6 % vs. 91.1 %, and the area under the ROC curve of 0.705 vs. 0.695 were achieved for the hybrid method and DT, respectively. However, the attributes' order by DT method was more consistent with the clinical literature. The combination of different modeling methods can enhance their performance. However, it may create some complexities in computations and interpretations. The outcome of the present study could deliver some useful hints in prognostic prediction on the basis of early clinical findings for TBI patients.

Prediction of Welded Joint Strength in Plasma Arc Welding: A Comparative Study Using Back-Propagation and Radial Basis Neural Networks

NASA Astrophysics Data System (ADS)

Srinivas, Kadivendi; Vundavilli, Pandu R.; Manzoor Hussain, M.; Saiteja, M.

2016-09-01

Welding input parameters such as current, gas flow rate and torch angle play a significant role in determination of qualitative mechanical properties of weld joint. Traditionally, it is necessary to determine the weld input parameters for every new welded product to obtain a quality weld joint which is time consuming. In the present work, the effect of plasma arc welding parameters on mild steel was studied using a neural network approach. To obtain a response equation that governs the input-output relationships, conventional regression analysis was also performed. The experimental data was constructed based on Taguchi design and the training data required for neural networks were randomly generated, by varying the input variables within their respective ranges. The responses were calculated for each combination of input variables by using the response equations obtained through the conventional regression analysis. The performances in Levenberg-Marquardt back propagation neural network and radial basis neural network (RBNN) were compared on various randomly generated test cases, which are different from the training cases. From the results, it is interesting to note that for the above said test cases RBNN analysis gave improved training results compared to that of feed forward back propagation neural network analysis. Also, RBNN analysis proved a pattern of increasing performance as the data points moved away from the initial input values.

A training network for introducing telemedicine, telecare and hospital informatics in the Adriatic-Danube-Black Sea region.

PubMed

Anogeianaki, Antonia; Ilonidis, George; Anogianakis, George; Lianguris, John; Katsaros, Kyriakos; Pseftogianni, Dimitra; Klisarova, Anelia; Negrev, Negrin

2004-01-01

DIMNET is a training mechanism for a region of central Europe. The aim is to upgrade the information technology skills of local hospital personnel and preserve their employability following the introduction of medical informatics. DIMNET uses Internet-based virtual classrooms to provide a 200-hour training course in medical informatics. Training takes place in the cities of Drama, Kavala, Xanthi and Varna. So far, more than 600 people have benefited from the programme. Initial results are encouraging. DIMNET promotes a new vocational training culture in the Balkans and is supported by local governments that perceive health-care as a fulcrum for economic development.

Global teaching and training initiatives for emerging cohort studies

PubMed Central

Paulus, Jessica K.; Santoyo-Vistrain, Rocío; Havelick, David; Cohen, Amy; Kalyesubula, Robert; Ajayi, Ikeoluwapo O.; Mattsson, Jens G.; Adami, Hans-Olov; Dalal, Shona

2015-01-01

A striking disparity exists across the globe, with essentially no large-scale longitudinal studies ongoing in regions that will be significantly affected by the oncoming non-communicable disease epidemic. The successful implementation of cohort studies in most low-resource research environments presents unique challenges that may be aided by coordinated training programs. Leaders of emerging cohort studies attending the First World Cohort Integration Workshop were surveyed about training priorities, unmet needs and potential cross-cohort solutions to these barriers through an electronic pre-workshop questionnaire and focus groups. Cohort studies representing India, Mexico, Nigeria, South Africa, Sweden, Tanzania and Uganda described similar training needs, including on-the-job training, data analysis software instruction, and database and bio-bank management. A lack of funding and protected time for training activities were commonly identified constraints. Proposed solutions include a collaborative cross-cohort teaching platform with web-based content and interactive teaching methods for a range of research personnel. An international network for research mentorship and idea exchange, and modifying the graduate thesis structure were also identified as key initiatives. Cross-cohort integrated educational initiatives will efficiently meet shared needs, catalyze the development of emerging cohorts, speed closure of the global disparity in cohort research, and may fortify scientific capacity development in low-resource settings. PMID:23856451

A novel constructive-optimizer neural network for the traveling salesman problem.

PubMed

Saadatmand-Tarzjan, Mahdi; Khademi, Morteza; Akbarzadeh-T, Mohammad-R; Moghaddam, Hamid Abrishami

2007-08-01

In this paper, a novel constructive-optimizer neural network (CONN) is proposed for the traveling salesman problem (TSP). CONN uses a feedback structure similar to Hopfield-type neural networks and a competitive training algorithm similar to the Kohonen-type self-organizing maps (K-SOMs). Consequently, CONN is composed of a constructive part, which grows the tour and an optimizer part to optimize it. In the training algorithm, an initial tour is created first and introduced to CONN. Then, it is trained in the constructive phase for adding a number of cities to the tour. Next, the training algorithm switches to the optimizer phase for optimizing the current tour by displacing the tour cities. After convergence in this phase, the training algorithm switches to the constructive phase anew and is continued until all cities are added to the tour. Furthermore, we investigate a relationship between the number of TSP cities and the number of cities to be added in each constructive phase. CONN was tested on nine sets of benchmark TSPs from TSPLIB to demonstrate its performance and efficiency. It performed better than several typical Neural networks (NNs), including KNIES_TSP_Local, KNIES_TSP_Global, Budinich's SOM, Co-Adaptive Net, and multivalued Hopfield network as wall as computationally comparable variants of the simulated annealing algorithm, in terms of both CPU time and accuracy. Furthermore, CONN converged considerably faster than expanding SOM and evolved integrated SOM and generated shorter tours compared to KNIES_DECOMPOSE. Although CONN is not yet comparable in terms of accuracy with some sophisticated computationally intensive algorithms, it converges significantly faster than they do. Generally speaking, CONN provides the best compromise between CPU time and accuracy among currently reported NNs for TSP.

Robust visual tracking via multiscale deep sparse networks

NASA Astrophysics Data System (ADS)

Wang, Xin; Hou, Zhiqiang; Yu, Wangsheng; Xue, Yang; Jin, Zefenfen; Dai, Bo

2017-04-01

In visual tracking, deep learning with offline pretraining can extract more intrinsic and robust features. It has significant success solving the tracking drift in a complicated environment. However, offline pretraining requires numerous auxiliary training datasets and is considerably time-consuming for tracking tasks. To solve these problems, a multiscale sparse networks-based tracker (MSNT) under the particle filter framework is proposed. Based on the stacked sparse autoencoders and rectifier linear unit, the tracker has a flexible and adjustable architecture without the offline pretraining process and exploits the robust and powerful features effectively only through online training of limited labeled data. Meanwhile, the tracker builds four deep sparse networks of different scales, according to the target's profile type. During tracking, the tracker selects the matched tracking network adaptively in accordance with the initial target's profile type. It preserves the inherent structural information more efficiently than the single-scale networks. Additionally, a corresponding update strategy is proposed to improve the robustness of the tracker. Extensive experimental results on a large scale benchmark dataset show that the proposed method performs favorably against state-of-the-art methods in challenging environments.

Training pediatric clinical pharmacology and therapeutics specialists of the future: the needs, the reality, and opportunities for international networking.

PubMed

Gazarian, Madlen

2009-01-01

In recent years there has been a rapid and marked increase in global recognition of the need for better medicines for children, with various initiatives being implemented at global and regional levels. These exciting developments are matched by recognition of the need to build greater capacity in the field of pediatric clinical pharmacology and therapeutics to help deliver on the promise of better medicines for children. A range of pediatric medicines researchers, educators, clinical therapeutics practitioners, and experts in drug evaluation, regulation, and broader medicines policy are needed on a larger scale, in both developed and developing world settings. The current and likely future training needs to meet these diverse challenges, the current realities of trying to meet such needs, and the opportunities for international networking to help meet future training needs are discussed from a global perspective.

Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap S.

1992-01-01

Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.

Research training program: Duke University and Brazilian Society of Cardiology.

PubMed

Pellanda, Lucia Campos; Cesa, Claudia Ciceri; Belli, Karlyse Claudino; David, Vinicius Frayze; Rodrigues, Clarissa Garcia; Vissoci, João Ricardo Nickenig; Bacal, Fernando; Kalil, Renato A K; Pietrobon, Ricardo

2012-12-01

Research coaching program focuses on the development of abilities and scientific reasoning. For health professionals, it may be useful to increase both the number and quality of projects and manuscripts. To evaluate the initial results and implementation methodology of the Research and Innovation Coaching Program of the Research on Research group of Duke University in the Brazilian Society of Cardiology. The program works on two bases: training and coaching. Training is done online and addresses contents on research ideas, literature search, scientific writing and statistics. After training, coaching favors the establishment of a collaboration between researchers and centers by means of a network of contacts. The present study describes the implementation and initial results in reference to the years 2011-2012. In 2011, 24 centers received training, which consisted of online meetings, study and practice of the contents addressed. In January 2012, a new format was implemented with the objective of reaching more researchers. In six months, 52 researchers were allocated. In all, 20 manuscripts were published and 49 more were written and await submission and/or publication. Additionally, five research funding proposals have been elaborated. The number of manuscripts and funding proposals achieved the objectives initially proposed. However, the main results of this type of initiative should be measured in the long term, because the consolidation of the national production of high-quality research is a virtuous cycle that feeds itself back and expands over time.

Character Recognition Using Genetically Trained Neural Networks

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

Diniz, C.; Stantz, K.M.; Trahan, M.W.

1998-10-01

Computationally intelligent recognition of characters and symbols addresses a wide range of applications including foreign language translation and chemical formula identification. The combination of intelligent learning and optimization algorithms with layered neural structures offers powerful techniques for character recognition. These techniques were originally developed by Sandia National Laboratories for pattern and spectral analysis; however, their ability to optimize vast amounts of data make them ideal for character recognition. An adaptation of the Neural Network Designer soflsvare allows the user to create a neural network (NN_) trained by a genetic algorithm (GA) that correctly identifies multiple distinct characters. The initial successfidmore » recognition of standard capital letters can be expanded to include chemical and mathematical symbols and alphabets of foreign languages, especially Arabic and Chinese. The FIN model constructed for this project uses a three layer feed-forward architecture. To facilitate the input of characters and symbols, a graphic user interface (GUI) has been developed to convert the traditional representation of each character or symbol to a bitmap. The 8 x 8 bitmap representations used for these tests are mapped onto the input nodes of the feed-forward neural network (FFNN) in a one-to-one correspondence. The input nodes feed forward into a hidden layer, and the hidden layer feeds into five output nodes correlated to possible character outcomes. During the training period the GA optimizes the weights of the NN until it can successfully recognize distinct characters. Systematic deviations from the base design test the network's range of applicability. Increasing capacity, the number of letters to be recognized, requires a nonlinear increase in the number of hidden layer neurodes. Optimal character recognition performance necessitates a minimum threshold for the number of cases when genetically training the net. And, the amount of noise significantly degrades character recognition efficiency, some of which can be overcome by adding noise during training and optimizing the form of the network's activation fimction.« less

California Basic Skills Initiative (BSI) Regional Networks as Self-Sustaining Communities of Practice

ERIC Educational Resources Information Center

Mullen, Adrienne Ann

2011-01-01

The Basic Skills Report for California Community Colleges (2007) stresses the importance of comprehensive training and development opportunities for all faculty (tenured and part-time), administrators and staff members who work with underprepared students. With such a large number of academically underprepared students entering the community…

An Innovative Community College Program and Partnership in Information Security.

ERIC Educational Resources Information Center

Howard, Barbara C; Morneau, Keith A.

This report describes an innovative network security program initiated by Northern Virginia Community College and funded with a grant from the Northern Virginia Regional Partnership. The program educates and trains students in the instillation, configuration, and troubleshooting of the hardware and software infrastructure of information security.…

The Story of Crownpoint Institute of Technology and Its Alternative Livestock Program.

ERIC Educational Resources Information Center

VanAlstine, Matthew; Ramalho, Elizabeth Murakami; Sanchez, Timothy

2002-01-01

To foster economic growth in the Navajo communities served by Crownpoint Institute of Technology, an initiative developed networks among educational, industrial, and nonprofit organizations. By promoting the sharing of knowledge between Navajo medicine men and veterinarians, Crownpoint has developed high quality training, employment, and small…

A heuristic neural network initialization scheme for modeling nonlinear functions in engineering mechanics: continuous development

NASA Astrophysics Data System (ADS)

Pei, Jin-Song; Mai, Eric C.

2007-04-01

This paper introduces a continuous effort towards the development of a heuristic initialization methodology for constructing multilayer feedforward neural networks to model nonlinear functions. In this and previous studies that this work is built upon, including the one presented at SPIE 2006, the authors do not presume to provide a universal method to approximate arbitrary functions, rather the focus is given to the development of a rational and unambiguous initialization procedure that applies to the approximation of nonlinear functions in the specific domain of engineering mechanics. The applications of this exploratory work can be numerous including those associated with potential correlation and interpretation of the inner workings of neural networks, such as damage detection. The goal of this study is fulfilled by utilizing the governing physics and mathematics of nonlinear functions and the strength of the sigmoidal basis function. A step-by-step graphical procedure utilizing a few neural network prototypes as "templates" to approximate commonly seen memoryless nonlinear functions of one or two variables is further developed in this study. Decomposition of complex nonlinear functions into a summation of some simpler nonlinear functions is utilized to exploit this prototype-based initialization methodology. Training examples are presented to demonstrate the rationality and effciency of the proposed methodology when compared with the popular Nguyen-Widrow initialization algorithm. Future work is also identfied.

Grassroots inter-professional networks: the case of organizing care for older cancer patients.

PubMed

Bagayogo, Fatou Farima; Lepage, Annick; Denis, Jean-Louis; Lamothe, Lise; Lapointe, Liette; Vedel, Isabelle

2016-09-19

Purpose The purpose of this paper of inter-professional networks is to analyze the evolution of relationships between professional groups enacting new forms of collaboration to address clinical imperatives. Design/methodology/approach This paper uses a case study based on semi-structured interviews with physicians and nurses, document analysis and informal discussions. Findings This study documents how two inter-professional networks were developed through professional agency. The findings show that the means by which networks are developed influence the form of collaboration therein. One of the networks developed from day-to-day, immediately relevant, exchange, for patient care. The other one developed from more formal and infrequent research and training exchanges that were seen as less decisive in facilitating patient care. The latter resulted in a loosely knit network based on a small number of ad hoc referrals while the other resulted in a tightly knit network based on frequent referrals and advice seeking. Practical implications Developing inter-professional networks likely require a sustained phase of interpersonal contacts characterized by persuasion, knowledge sharing, skill demonstration and trust building from less powerful professional groups to obtain buy-in from more powerful professional groups. The nature of the collaboration in any resulting network depends largely on the nature of these initial contacts. Originality/value The literature on inter-professional healthcare networks focusses on mandated networks such as NHS managed care networks. There is a lack of research on inter-professional networks that emerged from the bottom up at the initiative of healthcare professionals in response to clinical imperatives. This study looks at some forms of collaboration that these "grass-root" initiatives engender and how they are consolidated.

The Ne3LS Network, Québec's initiative to evaluate the impact and promote a responsible and sustainable development of nanotechnology

NASA Astrophysics Data System (ADS)

Endo, Charles-Anica; Emond, Claude; Battista, Renaldo; Parizeau, Marie-Hélène; Beaudry, Catherine

2011-07-01

The spectacular progress made by nanosciences and nanotechnologies elicits as much hope and fear. Consequently, a great number of research and training initiatives on the ethical, environmental, economic, legal and social issues regarding nanotechnology development (Ne3LS) are emerging worldwide. In Québec, Canada, a Task Force was mandated by NanoQuébec to conceive a Ne3LS research and training strategy to assess those issues. This Task Force brought together experts from universities, governments or industry working in nanosciences and nanotechnologies or in Ne3LS. Their resulting action plan, made public in November 2006, contained several recommendations, including the creation of a knowledge network (Ne3LS Network). In the following years, after consulting with numerous key players concerned with the possible impacts of nanosciences and nanotechnologies in Québec, the Ne3LS Network was launched in January 2010 in partnership with the Fonds québécois de la recherche sur la nature et les technologies, the Fonds québécois de la recherche sur la société et la culture and the Fonds de la recherche en santé du Québec, NanoQuébec, the Institut de recherche Robert-Sauvé en santé et en sécurité du travail as well as the University of Montreal. Its objectives are to 1) Foster the development of Ne3LS research activities (grants and fellowships); 2) Spearhead the Canadian and international Ne3LS network; 3) Take part in the training of researchers and experts; 4) Encourage the creation of interactive tools for the general public; 5) Facilitate collaboration between decision-makers and experts; 6) Involve the scientific community through a host of activities (symposium, conferences, thematic events); 7) Build multidisciplinary research teams to evaluate the impact of nanotechnology.

Integrating TeamSTEPPS® into ambulatory reproductive health care: Early successes and lessons learned.

PubMed

Paul, Maureen E; Dodge, Laura E; Intondi, Evelyn; Ozcelik, Guzey; Plitt, Ken; Hacker, Michele R

2017-04-01

Most medical teamwork improvement interventions have occurred in hospitals, and more efforts are needed to integrate them into ambulatory care settings. In 2014, Affiliates Risk Management Services, Inc. (ARMS), the risk management services organization for a large network of reproductive health care organizations in the United States, launched a voluntary 5-year initiative to implement a medical teamwork system in this network using the TeamSTEPPS model. This article describes the ARMS initiative and progress made during the first 2 years, including lessons learned. The ARMS TeamSTEPPS program consists of the following components: preparation of participating organizations, TeamSTEPPS master training, implementation of teamwork improvement programs, and evaluation. We used self-administered questionnaires to assess satisfaction with the ARMS program and with the master training course. In the first 2 years, 20 organizations enrolled. Participants found the preparation phase valuable and were highly satisfied with the master training course. Although most attendees felt that the course imparted the knowledge and tools critical for TeamSTEPPS implementation, they identified time restraints and competing initiatives as potential barriers. The project team has learned valuable lessons about obtaining buy-in, consolidating the change teams, making the curriculum relevant, and evaluation. Ambulatory care settings require innovative approaches to integration of teamwork improvement systems. Evaluating and sharing lessons learned will help to hone best practices as we navigate this new frontier in the field of patient safety. © 2017 American Society for Healthcare Risk Management of the American Hospital Association.

Locomotion training of legged robots using hybrid machine learning techniques

NASA Technical Reports Server (NTRS)

Simon, William E.; Doerschuk, Peggy I.; Zhang, Wen-Ran; Li, Andrew L.

1995-01-01

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Using a neural network to proximity correct patterns written with a Cambridge electron beam microfabricator 10.5 lithography system

NASA Astrophysics Data System (ADS)

Cummings, K. D.; Frye, R. C.; Rietman, E. A.

1990-10-01

This letter describes the initial results of using a theoretical determination of the proximity function and an adaptively trained neural network to proximity-correct patterns written on a Cambridge electron beam lithography system. The methods described are complete and may be applied to any electron beam exposure system that can modify the dose during exposure. The patterns produced in resist show the effects of proximity correction versus noncorrected patterns.

Functional brain networks for learning predictive statistics.

PubMed

Giorgio, Joseph; Karlaftis, Vasilis M; Wang, Rui; Shen, Yuan; Tino, Peter; Welchman, Andrew; Kourtzi, Zoe

2017-08-18

Making predictions about future events relies on interpreting streams of information that may initially appear incomprehensible. This skill relies on extracting regular patterns in space and time by mere exposure to the environment (i.e., without explicit feedback). Yet, we know little about the functional brain networks that mediate this type of statistical learning. Here, we test whether changes in the processing and connectivity of functional brain networks due to training relate to our ability to learn temporal regularities. By combining behavioral training and functional brain connectivity analysis, we demonstrate that individuals adapt to the environment's statistics as they change over time from simple repetition to probabilistic combinations. Further, we show that individual learning of temporal structures relates to decision strategy. Our fMRI results demonstrate that learning-dependent changes in fMRI activation within and functional connectivity between brain networks relate to individual variability in strategy. In particular, extracting the exact sequence statistics (i.e., matching) relates to changes in brain networks known to be involved in memory and stimulus-response associations, while selecting the most probable outcomes in a given context (i.e., maximizing) relates to changes in frontal and striatal networks. Thus, our findings provide evidence that dissociable brain networks mediate individual ability in learning behaviorally-relevant statistics. Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.

Neural initialization of audiovisual integration in prereaders at varying risk for developmental dyslexia.

PubMed

I Karipidis, Iliana; Pleisch, Georgette; Röthlisberger, Martina; Hofstetter, Christoph; Dornbierer, Dario; Stämpfli, Philipp; Brem, Silvia

2017-02-01

Learning letter-speech sound correspondences is a major step in reading acquisition and is severely impaired in children with dyslexia. Up to now, it remains largely unknown how quickly neural networks adopt specific functions during audiovisual integration of linguistic information when prereading children learn letter-speech sound correspondences. Here, we simulated the process of learning letter-speech sound correspondences in 20 prereading children (6.13-7.17 years) at varying risk for dyslexia by training artificial letter-speech sound correspondences within a single experimental session. Subsequently, we acquired simultaneously event-related potentials (ERP) and functional magnetic resonance imaging (fMRI) scans during implicit audiovisual presentation of trained and untrained pairs. Audiovisual integration of trained pairs correlated with individual learning rates in right superior temporal, left inferior temporal, and bilateral parietal areas and with phonological awareness in left temporal areas. In correspondence, a differential left-lateralized parietooccipitotemporal ERP at 400 ms for trained pairs correlated with learning achievement and familial risk. Finally, a late (650 ms) posterior negativity indicating audiovisual congruency of trained pairs was associated with increased fMRI activation in the left occipital cortex. Taken together, a short (<30 min) letter-speech sound training initializes audiovisual integration in neural systems that are responsible for processing linguistic information in proficient readers. To conclude, the ability to learn grapheme-phoneme correspondences, the familial history of reading disability, and phonological awareness of prereading children account for the degree of audiovisual integration in a distributed brain network. Such findings on emerging linguistic audiovisual integration could allow for distinguishing between children with typical and atypical reading development. Hum Brain Mapp 38:1038-1055, 2017. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

Spontaneous brain activity predicts learning ability of foreign sounds.

PubMed

Ventura-Campos, Noelia; Sanjuán, Ana; González, Julio; Palomar-García, María-Ángeles; Rodríguez-Pujadas, Aina; Sebastián-Gallés, Núria; Deco, Gustavo; Ávila, César

2013-05-29

Can learning capacity of the human brain be predicted from initial spontaneous functional connectivity (FC) between brain areas involved in a task? We combined task-related functional magnetic resonance imaging (fMRI) and resting-state fMRI (rs-fMRI) before and after training with a Hindi dental-retroflex nonnative contrast. Previous fMRI results were replicated, demonstrating that this learning recruited the left insula/frontal operculum and the left superior parietal lobe, among other areas of the brain. Crucially, resting-state FC (rs-FC) between these two areas at pretraining predicted individual differences in learning outcomes after distributed (Experiment 1) and intensive training (Experiment 2). Furthermore, this rs-FC was reduced at posttraining, a change that may also account for learning. Finally, resting-state network analyses showed that the mechanism underlying this reduction of rs-FC was mainly a transfer in intrinsic activity of the left frontal operculum/anterior insula from the left frontoparietal network to the salience network. Thus, rs-FC may contribute to predict learning ability and to understand how learning modifies the functioning of the brain. The discovery of this correspondence between initial spontaneous brain activity in task-related areas and posttraining performance opens new avenues to find predictors of learning capacities in the brain using task-related fMRI and rs-fMRI combined.

ENLIGHT: European network for Light ion hadron therapy.

PubMed

Dosanjh, Manjit; Amaldi, Ugo; Mayer, Ramona; Poetter, Richard

2018-04-03

The European Network for Light Ion Hadron Therapy (ENLIGHT) was established in 2002 following various European particle therapy network initiatives during the 1980s and 1990s (e.g. EORTC task group, EULIMA/PIMMS accelerator design). ENLIGHT started its work on major topics related to hadron therapy (HT), such as patient selection, clinical trials, technology, radiobiology, imaging and health economics. It was initiated through CERN and ESTRO and dealt with various disciplines such as (medical) physics and engineering, radiation biology and radiation oncology. ENLIGHT was funded until 2005 through the EC FP5 programme. A regular annual meeting structure was started in 2002 and continues until today bringing together the various disciplines and projects and institutions in the field of HT at different European places for regular exchange of information on best practices and research and development. Starting in 2006 ENLIGHT coordination was continued through CERN in collaboration with ESTRO and other partners involved in HT. Major projects within the EC FP7 programme (2008-2014) were launched for R&D and transnational access (ULICE, ENVISION) and education and training networks (Marie Curie ITNs: PARTNER, ENTERVISION). These projects were instrumental for the strengthening of the field of hadron therapy. With the start of 4 European carbon ion and proton centres and the upcoming numerous European proton therapy centres, the future scope of ENLIGHT will focus on strengthening current and developing European particle therapy research, multidisciplinary education and training and general R&D in technology and biology with annual meetings and a continuously strong CERN support. Collaboration with the European Particle Therapy Network (EPTN) and other similar networks will be pursued. Copyright © 2018 CERN. Published by Elsevier B.V. All rights reserved.

Effects of Long-term Diving Training on Cortical Gyrification.

PubMed

Zhang, Yuanchao; Zhao, Lu; Bi, Wenwei; Wang, Yue; Wei, Gaoxia; Evans, Alan; Jiang, Tianzi

2016-06-20

During human brain development, cortical gyrification, which is believed to facilitate compact wiring of neural circuits, has been shown to follow an inverted U-shaped curve, coinciding with the two-stage neurodevelopmental process of initial synaptic overproduction with subsequent pruning. This trajectory allows postnatal experiences to refine the wiring, which may manifest as endophenotypic changes in cortical gyrification. Diving experts, typical elite athletes who commence intensive motor training at a very young age in their early childhood, serve ideal models for examining the gyrification changes related to long-term intensive diving training. Using local gyrification index (LGI), we compared the cortical gyrification between 12 diving experts and 12 controls. Compared with controls, diving experts showed widespread LGI reductions in regions relevant to diving performance. Negative correlations between LGIs and years of diving training were also observed in diving experts. Further exploratory network efficiency analysis of structural cortical networks, inferred from interregional correlation of LGIs, revealed comparable global and local efficiency in diving experts relative to controls. These findings suggest that gyrification reductions in diving experts may be the result of long-term diving training which could refine the neural circuitry (via synaptic pruning) and might be the anatomical substrate underlying their extraordinary diving performance.

Partnerships and Pathways of Dissemination: The NIDA-SAMHSA Blending Initiative in the Clinical Trials Network

PubMed Central

Martino, Steve; Brigham, Gregory S.; Higgins, Christine; Gallon, Steve; Freese, Thomas E.; Albright, Lonnetta M.; Hulsey, Eric G.; Krom, Laurie; Storti, Susan A.; Perl, Harold; Nugent, Cathrine D.; Pintello, Denise; Condon, Timothy P.

2010-01-01

Since 2001, the National Drug Abuse Treatment Clinical Trials Network (CTN) has worked to put the results of its trials into the hands of community treatment programs, in large part through its participation in the National Institute on Drug Abuse - Substance Abuse and Mental Health Services Administration Blending Initiative and its close involvement with the Center for Substance Abuse Treatment’s Addiction Technology Transfer Centers. This article describes 1) the CTN’s integral role in the Blending Initiative, 2) key partnerships and dissemination pathways through which the results of CTN trials are developed into blending products and then transferred to community treatment programs, and 3) three blending initiatives involving buprenorphine, motivational incentives, and motivational interviewing. The Blending Initiative has resulted in high utilization of its products, preparation of over 200 regional trainers, widespread training of service providers in most U.S. States, Puerto Rico, and the U.S. Virgin Islands, and movement toward the development of web-based implementation supports and technical assistance. Implications for future directions of the Blending Initiative and opportunities for research are discussed. PMID:20307793

CIAN - Cell Imaging and Analysis Network at the Biology Department of McGill University

PubMed Central

Lacoste, J.; Lesage, G.; Bunnell, S.; Han, H.; Küster-Schöck, E.

2010-01-01

CF-31 The Cell Imaging and Analysis Network (CIAN) provides services and tools to researchers in the field of cell biology from within or outside Montreal's McGill University community. CIAN is composed of six scientific platforms: Cell Imaging (confocal and fluorescence microscopy), Proteomics (2-D protein gel electrophoresis and DiGE, fluorescent protein analysis), Automation and High throughput screening (Pinning robot and liquid handler), Protein Expression for Antibody Production, Genomics (real-time PCR), and Data storage and analysis (cluster, server, and workstations). Users submit project proposals, and can obtain training and consultation in any aspect of the facility, or initiate projects with the full-service platforms. CIAN is designed to facilitate training, enhance interactions, as well as share and maintain resources and expertise.

Efficient airport detection using region-based fully convolutional neural networks

NASA Astrophysics Data System (ADS)

Xin, Peng; Xu, Yuelei; Zhang, Xulei; Ma, Shiping; Li, Shuai; Lv, Chao

2018-04-01

This paper presents a model for airport detection using region-based fully convolutional neural networks. To achieve fast detection with high accuracy, we shared the conv layers between the region proposal procedure and the airport detection procedure and used graphics processing units (GPUs) to speed up the training and testing time. For lack of labeled data, we transferred the convolutional layers of ZF net pretrained by ImageNet to initialize the shared convolutional layers, then we retrained the model using the alternating optimization training strategy. The proposed model has been tested on an airport dataset consisting of 600 images. Experiments show that the proposed method can distinguish airports in our dataset from similar background scenes almost real-time with high accuracy, which is much better than traditional methods.

Teaching Public Health Networks in England: an innovative approach to building public health capacity and capability.

PubMed

Orme, J; Pilkington, P; Gray, S; Rao, M

2009-12-01

This paper examines the development and achievements of the Teaching Public Health Networks (TPHNs) in England; an initiative that aimed to catalyse collaborative working between the public health workforce and further and higher education, to enhance public health knowledge in the wider workforce with a view to enhancing capacity to tackle inequalities and meeting public health targets. This paper highlights activities under three outcomes: mobilizing resources, people, money and materials; building capacity through training and infrastructure development; and raising public and political awareness. The TPHN approach is shown to have led to innovative developments in public health education and training, including engagement with professionals that have not previously had exposure to public health. This paper aims to disseminate the learning from this complex public health initiative, now in its third year of development, and to share examples of good practice. It is hoped that other countries can use the TPHN approach as a model to address the various common and country-specific challenges in public health workforce development.

Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control

NASA Technical Reports Server (NTRS)

Hageman, Jacob J.; Smith, Mark S.; Stachowiak, Susan

2003-01-01

An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.

Path selection rules for droplet trains in single-lane microfluidic networks

NASA Astrophysics Data System (ADS)

Amon, A.; Schmit, A.; Salkin, L.; Courbin, L.; Panizza, P.

2013-07-01

We investigate the transport of periodic trains of droplets through microfluidic networks having one inlet, one outlet, and nodes consisting of T junctions. Variations of the dilution of the trains, i.e., the distance between drops, reveal the existence of various hydrodynamic regimes characterized by the number of preferential paths taken by the drops. As the dilution increases, this number continuously decreases until only one path remains explored. Building on a continuous approach used to treat droplet traffic through a single asymmetric loop, we determine selection rules for the paths taken by the drops and we predict the variations of the fraction of droplets taking these paths with the parameters at play including the dilution. Our results show that as dilution decreases, the paths are selected according to the ascending order of their hydrodynamic resistance in the absence of droplets. The dynamics of these systems controlled by time-delayed feedback is complex: We observe a succession of periodic regimes separated by a wealth of bifurcations as the dilution is varied. In contrast to droplet traffic in single asymmetric loops, the dynamical behavior in networks of loops is sensitive to initial conditions because of extra degrees of freedom.

Harnessing Online Peer Education (HOPE): integrating C-POL and social media to train peer leaders in HIV prevention.

PubMed

Jaganath, Devan; Gill, Harkiran K; Cohen, Adam Carl; Young, Sean D

2012-01-01

Novel methods, such as Internet-based interventions, are needed to combat the spread of HIV. While past initiatives have used the Internet to promote HIV prevention, the growing popularity, decreasing digital divide, and multi-functionality of social networking sites, such as Facebook, make this an ideal time to develop innovative ways to use online social networking sites to scale HIV prevention interventions among high-risk groups. The UCLA Harnessing Online Peer Education study is a longitudinal experimental study to evaluate the feasibility, acceptability, and preliminary effectiveness of using social media for peer-led HIV prevention, specifically among African American and Latino Men who have Sex with Men (MSM). No curriculum currently exists to train peer leaders in delivering culturally aware HIV prevention messages using social media. Training was created that adapted the Community Popular Opinion Leader (C-POL) model, for use on social networking sites. Peer leaders are recruited who represent the target population and have experience with both social media and community outreach. The curriculum contains the following elements: discussion and role playing exercises to integrate basic knowledge of HIV/AIDS, awareness of sociocultural HIV/AIDS issues in the age of technology, and communication methods for training peer leaders in effective, interactive social media-based HIV prevention. Ethical issues related to Facebook and health interventions are integrated throughout the sessions. Training outcomes have been developed for long-term assessment of retention and efficacy. This is the first C-POL curriculum that has been adapted for use on social networking websites. Although this curriculum has been used to target African-American and Latino MSM, it has been created to allow generalization to other high-risk groups.

Harnessing Online Peer Education (HOPE): Integrating C-POL and Social Media to Train Peer Leaders in HIV Prevention

PubMed Central

Jaganath, Devan; Gill, Harkiran K.; Cohen, Adam Carl; Young, Sean D.

2011-01-01

Novel methods, such as Internet-based interventions, are needed to combat the spread of HIV. While past initiatives have used the Internet to promote HIV prevention, the growing popularity, decreasing digital divide, and multi-functionality of social networking sites, such as Facebook, make this an ideal time to develop innovative ways to use online social networking sites to scale HIV prevention interventions among high-risk groups. The UCLA HOPE [Harnessing Online Peer Education] study is a longitudinal experimental study to evaluate the feasibility, acceptability, and preliminary effectiveness of using social media for peer-led HIV prevention, specifically among African American and Latino Men who have Sex with Men (MSM). No curriculum currently exists to train peer leaders in delivering culturally aware HIV prevention messages using social media. Training was created that adapted the Community Popular Opinion Leader (C-POL) model, for use on social networking sites. Peer leaders are recruited who represent the target population and have experience with both social media and community outreach. The curriculum contains the following elements: discussion and role playing exercises to integrate basic knowledge of HIV/AIDS, awareness of sociocultural HIV/AIDS issues in the age of technology, and communication methods for training peer leaders in effective, interactive social media-based HIV prevention. Ethical issues related to Facebook and health interventions are integrated throughout the sessions. Training outcomes have been developed for long-term assessment of retention and efficacy. This is the first C-POL curriculum that has been adapted for use on social networking websites. Although this curriculum has been used to target African American and Latino MSM, it has been created to allow generalization to other high-risk groups. PMID:22149081

Acoustic target detection and classification using neural networks

NASA Technical Reports Server (NTRS)

Robertson, James A.; Conlon, Mark

1993-01-01

A neural network approach to the classification of acoustic emissions of ground vehicles and helicopters is demonstrated. Data collected during the Joint Acoustic Propagation Experiment conducted in July of l991 at White Sands Missile Range, New Mexico was used to train a classifier to distinguish between the spectrums of a UH-1, M60, M1 and M114. An output node was also included that would recognize background (i.e. no target) data. Analysis revealed specific hidden nodes responding to the features input into the classifier. Initial results using the neural network were encouraging with high correct identification rates accompanied by high levels of confidence.

Deep multi-scale location-aware 3D convolutional neural networks for automated detection of lacunes of presumed vascular origin.

PubMed

Ghafoorian, Mohsen; Karssemeijer, Nico; Heskes, Tom; Bergkamp, Mayra; Wissink, Joost; Obels, Jiri; Keizer, Karlijn; de Leeuw, Frank-Erik; Ginneken, Bram van; Marchiori, Elena; Platel, Bram

2017-01-01

Lacunes of presumed vascular origin (lacunes) are associated with an increased risk of stroke, gait impairment, and dementia and are a primary imaging feature of the small vessel disease. Quantification of lacunes may be of great importance to elucidate the mechanisms behind neuro-degenerative disorders and is recommended as part of study standards for small vessel disease research. However, due to the different appearance of lacunes in various brain regions and the existence of other similar-looking structures, such as perivascular spaces, manual annotation is a difficult, elaborative and subjective task, which can potentially be greatly improved by reliable and consistent computer-aided detection (CAD) routines. In this paper, we propose an automated two-stage method using deep convolutional neural networks (CNN). We show that this method has good performance and can considerably benefit readers. We first use a fully convolutional neural network to detect initial candidates. In the second step, we employ a 3D CNN as a false positive reduction tool. As the location information is important to the analysis of candidate structures, we further equip the network with contextual information using multi-scale analysis and integration of explicit location features. We trained, validated and tested our networks on a large dataset of 1075 cases obtained from two different studies. Subsequently, we conducted an observer study with four trained observers and compared our method with them using a free-response operating characteristic analysis. Shown on a test set of 111 cases, the resulting CAD system exhibits performance similar to the trained human observers and achieves a sensitivity of 0.974 with 0.13 false positives per slice. A feasibility study also showed that a trained human observer would considerably benefit once aided by the CAD system.

Neural networks for self-learning control systems

NASA Technical Reports Server (NTRS)

Nguyen, Derrick H.; Widrow, Bernard

1990-01-01

It is shown how a neural network can learn of its own accord to control a nonlinear dynamic system. An emulator, a multilayered neural network, learns to identify the system's dynamic characteristics. The controller, another multilayered neural network, next learns to control the emulator. The self-trained controller is then used to control the actual dynamic system. The learning process continues as the emulator and controller improve and track the physical process. An example is given to illustrate these ideas. The 'truck backer-upper,' a neural network controller that steers a trailer truck while the truck is backing up to a loading dock, is demonstrated. The controller is able to guide the truck to the dock from almost any initial position. The technique explored should be applicable to a wide variety of nonlinear control problems.

Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks.

PubMed

Kim, D H; MacKinnon, T

2018-05-01

To identify the extent to which transfer learning from deep convolutional neural networks (CNNs), pre-trained on non-medical images, can be used for automated fracture detection on plain radiographs. The top layer of the Inception v3 network was re-trained using lateral wrist radiographs to produce a model for the classification of new studies as either "fracture" or "no fracture". The model was trained on a total of 11,112 images, after an eightfold data augmentation technique, from an initial set of 1,389 radiographs (695 "fracture" and 694 "no fracture"). The training data set was split 80:10:10 into training, validation, and test groups, respectively. An additional 100 wrist radiographs, comprising 50 "fracture" and 50 "no fracture" images, were used for final testing and statistical analysis. The area under the receiver operator characteristic curve (AUC) for this test was 0.954. Setting the diagnostic cut-off at a threshold designed to maximise both sensitivity and specificity resulted in values of 0.9 and 0.88, respectively. The AUC scores for this test were comparable to state-of-the-art providing proof of concept for transfer learning from CNNs in fracture detection on plain radiographs. This was achieved using only a moderate sample size. This technique is largely transferable, and therefore, has many potential applications in medical imaging, which may lead to significant improvements in workflow productivity and in clinical risk reduction. Copyright © 2017 The Royal College of Radiologists. Published by Elsevier Ltd. All rights reserved.

Intermittent θ burst stimulation modulates resting-state functional connectivity in the attention network and promotes behavioral recovery in patients with visual spatial neglect.

PubMed

Cao, Lei; Fu, Wei; Zhang, Yanming; Huo, Su; Du, JuBao; Zhu, Lin; Song, Weiqun

2016-12-07

Functional connectivity changes in the attention network are viewed as a physiological signature of visual spatial neglect (VSN). The left dorsal lateral prefrontal cortex (LDLPFC) is known to initiate and monitor top-down attentional control and dynamically adjust behavioral performance. This study aimed to investigate whether increasing the activity of the LDLPFC through intermittent θ burst stimulation (iTBS) could modulate the resting-state functional connectivity in the attention network and facilitate recovery from VSN. Patients with right hemisphere stroke and VSN were randomly assigned to two groups matched for clinical characteristics and given a 10-day treatment. On each day, all patients underwent visual scanning training and motor function training and received iTBS over the LDLPFC either at 80% resting motor threshold (RMT) or at 40% RMT before the trainings. MRI, the line bisection test, and the star cancelation test were performed before and after treatment. Patients who received iTBS at 80% RMT showed a large-scale reduction in the resting-state functional connectivity extent, largely in the right attention network, and more significant improvement of behavioral performance compared with patients who received iTBS at 40% RMT. These results support that the LDLPFC potentially plays a key role in the modulation of attention networks in neglect. Increasing the activity of the LDPLPFC through iTBS can facilitate recovery from VSN in patients with stroke.

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment.

PubMed

Li, Yongcheng; Sun, Rong; Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot's performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment

PubMed Central

Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot’s performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks. PMID:27806074

A-Train Education Activities: Partnerships to Engage Citizens with Atmospheric Science

NASA Astrophysics Data System (ADS)

Ellis, T. D.; Taylor, J.; Chambers, L. H.; Graham, S.; Butcher, G. J.

2016-12-01

Since the launch of Aqua in 2002, the A-Train satellites have been at the forefront of observing Earth's atmosphere using the wide variety of instruments on the spacecraft in the formation. Similarly, the A-Train missions have also taken a variety of perspectives on engaging the general public with NASA science. These approaches have included a range of formal education partnerships featuring the GLOBE program (including a cloud observation network through CloudSat, several initiatives to understand and measure aerosols, and development of a new elementary story book), unique citizen-science activities such as Students' Cloud Observations On Line (S'COOL), connections with the PBS Kids SciGirls program, and much more. An education component was also featured at the first A-Train symposium in New Orleans, engaging local educators to learn about the many education resources available from the A-Train missions. Increasingly, the mission education teams have been working together to drive home thematic science content, such as the roles of clouds in our climate system and regular measurements of Earth's radiant energy balance. This paper describes the evolution of A-Train education efforts over the past decade, highlights key achievements, and presents information on new initiatives to continue to engage the public with A-Train science.

Egg production forecasting: Determining efficient modeling approaches.

PubMed

Ahmad, H A

2011-12-01

Several mathematical or statistical and artificial intelligence models were developed to compare egg production forecasts in commercial layers. Initial data for these models were collected from a comparative layer trial on commercial strains conducted at the Poultry Research Farms, Auburn University. Simulated data were produced to represent new scenarios by using means and SD of egg production of the 22 commercial strains. From the simulated data, random examples were generated for neural network training and testing for the weekly egg production prediction from wk 22 to 36. Three neural network architectures-back-propagation-3, Ward-5, and the general regression neural network-were compared for their efficiency to forecast egg production, along with other traditional models. The general regression neural network gave the best-fitting line, which almost overlapped with the commercial egg production data, with an R(2) of 0.71. The general regression neural network-predicted curve was compared with original egg production data, the average curves of white-shelled and brown-shelled strains, linear regression predictions, and the Gompertz nonlinear model. The general regression neural network was superior in all these comparisons and may be the model of choice if the initial overprediction is managed efficiently. In general, neural network models are efficient, are easy to use, require fewer data, and are practical under farm management conditions to forecast egg production.

Development of an Efficient Identifier for Nuclear Power Plant Transients Based on Latest Advances of Error Back-Propagation Learning Algorithm

NASA Astrophysics Data System (ADS)

Moshkbar-Bakhshayesh, Khalil; Ghofrani, Mohammad B.

2014-02-01

This study aims to improve the performance of nuclear power plants (NPPs) transients training and identification using the latest advances of error back-propagation (EBP) learning algorithm. To this end, elements of EBP, including input data, initial weights, learning rate, cost function, activation function, and weights updating procedure are investigated and an efficient neural network is developed. Usefulness of modular networks is also examined and appropriate identifiers, one for each transient, are employed. Furthermore, the effect of transient type on transient identifier performance is illustrated. Subsequently, the developed transient identifier is applied to Bushehr nuclear power plant (BNPP). Seven types of the plant events are probed to analyze the ability of the proposed identifier. The results reveal that identification occurs very early with only five plant variables, whilst in the previous studies a larger number of variables (typically 15 to 20) were required. Modular networks facilitated identification due to its sole dependency on the sign of each network output signal. Fast training of input patterns, extendibility for identification of more transients and reduction of false identification are other advantageous of the proposed identifier. Finally, the balance between the correct answer to the trained transients (memorization) and reasonable response to the test transients (generalization) is improved, meeting one of the primary design criteria of identifiers.

The African Field Epidemiology Network-Networking for effective field epidemiology capacity building and service delivery

PubMed Central

Gitta, Sheba Nakacubo; Mukanga, David; Babirye, Rebecca; Dahlke, Melissa; Tshimanga, Mufuta; Nsubuga, Peter

2011-01-01

Networks are a catalyst for promoting common goals and objectives of their membership. Public Health networks in Africa are crucial, because of the severe resource limitations that nations face in dealing with priority public health problems. For a long time, networks have existed on the continent and globally, but many of these are disease-specific with a narrow scope. The African Field Epidemiology Network (AFENET) is a public health network established in 2005 as a non-profit networking alliance of Field Epidemiology and Laboratory Training Programs (FELTPs) and Field Epidemiology Training Programs (FETPs) in Africa. AFENET is dedicated to helping ministries of health in Africa build strong, effective and sustainable programs and capacity to improve public health systems by partnering with global public health experts. The Network's goal is to strengthen field epidemiology and public health laboratory capacity to contribute effectively to addressing epidemics and other major public health problems in Africa. AFENET currently networks 12 FELTPs and FETPs in sub-Saharan Africa with operations in 20 countries. AFENET has a unique tripartite working relationship with government technocrats from human health and animal sectors, academicians from partner universities, and development partners, presenting the Network with a distinct vantage point. Through the Network, African nations are making strides in strengthening their health systems. Members are able to: leverage resources to support field epidemiology and public health laboratory training and service delivery notably in the area of outbreak investigation and response as well as disease surveillance; by-pass government bureaucracies that often hinder and frustrate development partners; and consolidate efforts of different partners channelled through the FELTPs by networking graduates through alumni associations and calling on them to offer technical support in various public health capacities as the need arises. AFENET presents a bridging platform between governments and the private sector, allowing for continuity of health interventions at the national and regional level while offering free exit and entry for existing and new partners respectively. AFENET has established itself as a versatile networking model that is highly responsive to members’ needs. Based on the successes recorded in AFENET's first 5 years, we envision that the Network's membership will continue to expand as new training programs are established. The lessons learned will be useful in initiating new programs and building sustainability frameworks for FETPs and FELTPs in Africa. AFENET will continue to play a role in coordinating, advocacy, and building capacity for epidemic disease preparedness and response. PMID:22359691

Mixed-Initiative Information System for Computer-Aided Training and Decision Making. Final Report.

ERIC Educational Resources Information Center

Grignetti, Mario C.; Warnock, Eleanor H.

A description of the NET-SCHOLAR system, an on-line aid for naive users of the Advanced Research Projects Administration (ARPA) Computer Network, is provided. The discussion focuses upon the system's representation and handling of functional and procedural information and its ability to deal with action verbs, all within the context of the ARPA…

Effects of Cognitive Training on Resting-State Functional Connectivity of Default Mode, Salience, and Central Executive Networks.

PubMed

Cao, Weifang; Cao, Xinyi; Hou, Changyue; Li, Ting; Cheng, Yan; Jiang, Lijuan; Luo, Cheng; Li, Chunbo; Yao, Dezhong

2016-01-01

Neuroimaging studies have documented that aging can disrupt certain higher cognitive systems such as the default mode network (DMN), the salience network and the central executive network (CEN). The effect of cognitive training on higher cognitive systems remains unclear. This study used a 1-year longitudinal design to explore the cognitive training effect on three higher cognitive networks in healthy older adults. The community-living healthy older adults were divided into two groups: the multi-domain cognitive training group (24 sessions of cognitive training over a 3-months period) and the wait-list control group. All subjects underwent cognitive measurements and resting-state functional magnetic resonance imaging scanning at baseline and at 1 year after the training ended. We examined training-related changes in functional connectivity (FC) within and between three networks. Compared with the baseline, we observed maintained or increased FC within all three networks after training. The scans after training also showed maintained anti-correlation of FC between the DMN and CEN compared to the baseline. These findings demonstrated that cognitive training maintained or improved the functional integration within networks and the coupling between the DMN and CEN in older adults. Our findings suggested that multi-domain cognitive training can mitigate the aging-related dysfunction of higher cognitive networks.

Effects of Cognitive Training on Resting-State Functional Connectivity of Default Mode, Salience, and Central Executive Networks

PubMed Central

Cao, Weifang; Cao, Xinyi; Hou, Changyue; Li, Ting; Cheng, Yan; Jiang, Lijuan; Luo, Cheng; Li, Chunbo; Yao, Dezhong

2016-01-01

Neuroimaging studies have documented that aging can disrupt certain higher cognitive systems such as the default mode network (DMN), the salience network and the central executive network (CEN). The effect of cognitive training on higher cognitive systems remains unclear. This study used a 1-year longitudinal design to explore the cognitive training effect on three higher cognitive networks in healthy older adults. The community-living healthy older adults were divided into two groups: the multi-domain cognitive training group (24 sessions of cognitive training over a 3-months period) and the wait-list control group. All subjects underwent cognitive measurements and resting-state functional magnetic resonance imaging scanning at baseline and at 1 year after the training ended. We examined training-related changes in functional connectivity (FC) within and between three networks. Compared with the baseline, we observed maintained or increased FC within all three networks after training. The scans after training also showed maintained anti-correlation of FC between the DMN and CEN compared to the baseline. These findings demonstrated that cognitive training maintained or improved the functional integration within networks and the coupling between the DMN and CEN in older adults. Our findings suggested that multi-domain cognitive training can mitigate the aging-related dysfunction of higher cognitive networks. PMID:27148042

Practice-based research networks, part II: a descriptive analysis of the athletic training practice-based research network in the secondary school setting.

PubMed

Valovich McLeod, Tamara C; Lam, Kenneth C; Bay, R Curtis; Sauers, Eric L; Snyder Valier, Alison R

2012-01-01

Analysis of health care service models requires the collection and evaluation of basic practice characterization data. Practice-based research networks (PBRNs) provide a framework for gathering data useful in characterizing clinical practice. To describe preliminary secondary school setting practice data from the Athletic Training Practice-Based Research Network (AT-PBRN). Descriptive study. Secondary school athletic training facilities within the AT-PBRN. Clinicians (n = 22) and their patients (n = 2523) from the AT-PBRN. A Web-based survey was used to obtain data on clinical practice site and clinician characteristics. Patient and practice characteristics were obtained via deidentified electronic medical record data collected between September 1, 2009, and April 1, 2011. Descriptive data regarding the clinician and CPS practice characteristics are reported as percentages and frequencies. Descriptive analysis of patient encounters and practice characteristic data was performed, with the percentages and frequencies of the type of injuries recorded at initial evaluation, type of treatment received at initial evaluation, daily treatment, and daily sign-in procedures. The AT-PBRN had secondary school sites in 7 states, and most athletic trainers at those sites (78.2%) had less than 5 years of experience. The secondary school sites within the AT-PBRN documented 2523 patients treated across 3140 encounters. Patients most frequently sought care for a current injury (61.3%), followed by preventive services (24.0%), and new injuries (14.7%). The most common diagnoses were ankle sprain/strain (17.9%), hip sprain/strain (12.5%), concussion (12.0%), and knee pain (2.5%). The most frequent procedures were athletic trainer evaluation (53.9%), hot- or cold-pack application (26.0%), strapping (10.3%), and therapeutic exercise (5.7%). The median number of treatments per injury was 3 (interquartile range = 2, 4; range = 2-19). These preliminary data describe services provided by clinicians within the AT-PBRN and demonstrate the usefulness of the PBRN model for obtaining such data.

Promoting Diversity Through Polar Interdisciplinary Coordinated Education (Polar ICE)

NASA Astrophysics Data System (ADS)

McDonnell, J. D.; Hotaling, L. A.; Garza, C.; Van Dyk, P. B.; Hunter-thomson, K. I.; Middendorf, J.; Daniel, A.; Matsumoto, G. I.; Schofield, O.

2017-12-01

Polar Interdisciplinary Coordinated Education (ICE) is an education and outreach program designed to provide public access to the Antarctic and Arctic regions through polar data and interactions with the scientists. The program provides multi-faceted science communication training for early career scientists that consist of a face-to face workshop and opportunities to apply these skills. The key components of the scientist training workshop include cultural competency training, deconstructing/decoding science for non-expert audiences, the art of telling science stories, and networking with members of the education and outreach community and reflecting on communication skills. Scientists partner with educators to provide professional development for K-12 educators and support for student research symposia. Polar ICE has initiated a Polar Literacy initiative that provides both a grounding in big ideas in polar science and science communication training designed to underscore the importance of the Polar Regions to the public while promoting interdisciplinary collaborations between scientists and educators. Our ultimate objective is to promote STEM identity through professional development of scientists and educators while developing career awareness of STEM pathways in Polar science.

Initial results on fault diagnosis of DSN antenna control assemblies using pattern recognition techniques

NASA Technical Reports Server (NTRS)

Smyth, P.; Mellstrom, J.

1990-01-01

Initial results obtained from an investigation using pattern recognition techniques for identifying fault modes in the Deep Space Network (DSN) 70 m antenna control loops are described. The overall background to the problem is described, the motivation and potential benefits of this approach are outlined. In particular, an experiment is described in which fault modes were introduced into a state-space simulation of the antenna control loops. By training a multilayer feed-forward neural network on the simulated sensor output, classification rates of over 95 percent were achieved with a false alarm rate of zero on unseen tests data. It concludes that although the neural classifier has certain practical limitations at present, it also has considerable potential for problems of this nature.

Developing scientists in Hispanic substance use and health disparities research through the creation of a national mentoring network.

PubMed

Bazzi, Angela R; Mogro-Wilson, Cristina; Negi, Nalini Junko; Gonzalez, Jennifer M Reingle; Cano, Miguel Ángel; Castro, Yessenia; Cepeda, Alice

2017-01-01

Hispanics are disproportionately affected by substance use and related health harms yet remain underrepresented across scientific disciplines focused on researching and addressing these issues. An interdisciplinary network of scientists committed to fostering the development of social and biomedical researchers focused on Hispanic substance use and health disparities developed innovative mentoring and career development activities. We conducted a formative evaluation study using anonymous membership and conference feedback data to describe specific mentoring and career development activities developed within the national network. Successful mentoring initiatives and career development activities were infused with cultural and community values supportive of professional integration and persistence. Mentoring initially occurred within an annual national conference and was then sustained throughout the year through formal training programs and informal mentoring networks. Although rigorous evaluation is needed to determine the success of these strategies in fostering long-term career development among scientists conducting Hispanic health and substance use research, this innovative model may hold promise for other groups committed to promoting career development and professional integration and persistence for minority (and non-minority) scientists committed to addressing health disparities.

Empowering health personnel for decentralized health planning in India: The Public Health Resource Network.

PubMed

Kalita, Anuska; Zaidi, Sarover; Prasad, Vandana; Raman, V R

2009-07-20

The Public Health Resource Network is an innovative distance-learning course in training, motivating, empowering and building a network of health personnel from government and civil society groups. Its aim is to build human resource capacity for strengthening decentralized health planning, especially at the district level, to improve accountability of health systems, elicit community participation for health, ensure equitable and accessible health facilities and to bring about convergence in programmes and services. The question confronting health systems in India is how best to reform, revitalize and resource primary health systems to deliver different levels of service aligned to local realities, ensuring universal coverage, equitable access, efficiency and effectiveness, through an empowered cadre of health personnel. To achieve these outcomes it is essential that health planning be decentralized. Districts vary widely according to the specific needs of their population, and even more so in terms of existing interventions and available resources. Strategies, therefore, have to be district-specific, not only because health needs vary, but also because people's perceptions and capacities to intervene and implement programmes vary. In centrally designed plans there is little scope for such adaptation and contextualization, and hence decentralized planning becomes crucial. To undertake these initiatives, there is a strong need for trained, motivated, empowered and networked health personnel. It is precisely at this level that a lack of technical knowledge and skills and the absence of a supportive network or adequate educational opportunities impede personnel from making improvements. The absence of in-service training and of training curricula that reflect field realities also adds to this, discouraging health workers from pursuing effective strategies. The Public Health Resource Network is thus an attempt to reach out to motivated though often isolated health workers. It interacts with, and works to empower, health personnel within the government health system as well as civil society, to meaningfully participate in and strengthen decentralized planning processes and outcomes. Structured as an innovative distance-learning course spread over 12 to 18 months of coursework and contact programmes, the Public Health Resource Network comprises 14 core modules and five optional courses. The technical content and contact programmes have been specifically developed to build perspectives and technical knowledge of participants and provide them with a variety of options that can be immediately put into practice within their work environments and everyday roles. The thematic areas of the course modules range from technical knowledge related to maternal and child health and communicable and noncommunicable diseases; programmatic and systemic knowledge related to health planning, convergence, health management and public-private partnerships; to perspective-building knowledge related to mainstreaming gender issues and community participation. Currently the Public Health Resource Network has been launched in four states of India--Chhattisgarh, Jharkhand, Bihar and Orissa--in its first phase, and reaches out to more than 500 participants with diverse backgrounds. The initiative has received valuable support from central and state government departments of health, state training institutes, the National Rural Health Mission--the current comprehensive health policy in the country--and leading civil society organizations.

Empowering health personnel for decentralized health planning in India: The Public Health Resource Network

PubMed Central

Kalita, Anuska; Zaidi, Sarover; Prasad, Vandana; Raman, VR

2009-01-01

The Public Health Resource Network is an innovative distance-learning course in training, motivating, empowering and building a network of health personnel from government and civil society groups. Its aim is to build human resource capacity for strengthening decentralized health planning, especially at the district level, to improve accountability of health systems, elicit community participation for health, ensure equitable and accessible health facilities and to bring about convergence in programmes and services. The question confronting health systems in India is how best to reform, revitalize and resource primary health systems to deliver different levels of service aligned to local realities, ensuring universal coverage, equitable access, efficiency and effectiveness, through an empowered cadre of health personnel. To achieve these outcomes it is essential that health planning be decentralized. Districts vary widely according to the specific needs of their population, and even more so in terms of existing interventions and available resources. Strategies, therefore, have to be district-specific, not only because health needs vary, but also because people's perceptions and capacities to intervene and implement programmes vary. In centrally designed plans there is little scope for such adaptation and contextualization, and hence decentralized planning becomes crucial. To undertake these initiatives, there is a strong need for trained, motivated, empowered and networked health personnel. It is precisely at this level that a lack of technical knowledge and skills and the absence of a supportive network or adequate educational opportunities impede personnel from making improvements. The absence of in-service training and of training curricula that reflect field realities also adds to this, discouraging health workers from pursuing effective strategies. The Public Health Resource Network is thus an attempt to reach out to motivated though often isolated health workers. It interacts with, and works to empower, health personnel within the government health system as well as civil society, to meaningfully participate in and strengthen decentralized planning processes and outcomes. Structured as an innovative distance-learning course spread over 12 to 18 months of coursework and contact programmes, the Public Health Resource Network comprises 14 core modules and five optional courses. The technical content and contact programmes have been specifically developed to build perspectives and technical knowledge of participants and provide them with a variety of options that can be immediately put into practice within their work environments and everyday roles. The thematic areas of the course modules range from technical knowledge related to maternal and child health and communicable and noncommunicable diseases; programmatic and systemic knowledge related to health planning, convergence, health management and public-private partnerships; to perspective-building knowledge related to mainstreaming gender issues and community participation. Currently the Public Health Resource Network has been launched in four states of India – Chhattisgarh, Jharkhand, Bihar and Orissa – in its first phase, and reaches out to more than 500 participants with diverse backgrounds. The initiative has received valuable support from central and state government departments of health, state training institutes, the National Rural Health Mission – the current comprehensive health policy in the country – and leading civil society organizations. PMID:19615106

Creating Weather System Ensembles Through Synergistic Process Modeling and Machine Learning

NASA Astrophysics Data System (ADS)

Chen, B.; Posselt, D. J.; Nguyen, H.; Wu, L.; Su, H.; Braverman, A. J.

2017-12-01

Earth's weather and climate are sensitive to a variety of control factors (e.g., initial state, forcing functions, etc). Characterizing the response of the atmosphere to a change in initial conditions or model forcing is critical for weather forecasting (ensemble prediction) and climate change assessment. Input - response relationships can be quantified by generating an ensemble of multiple (100s to 1000s) realistic realizations of weather and climate states. Atmospheric numerical models generate simulated data through discretized numerical approximation of the partial differential equations (PDEs) governing the underlying physics. However, the computational expense of running high resolution atmospheric state models makes generation of more than a few simulations infeasible. Here, we discuss an experiment wherein we approximate the numerical PDE solver within the Weather Research and Forecasting (WRF) Model using neural networks trained on a subset of model run outputs. Once trained, these neural nets can produce large number of realization of weather states from a small number of deterministic simulations with speeds that are orders of magnitude faster than the underlying PDE solver. Our neural network architecture is inspired by the governing partial differential equations. These equations are location-invariant, and consist of first and second derivations. As such, we use a 3x3 lon-lat grid of atmospheric profiles as the predictor in the neural net to provide the network the information necessary to compute the first and second moments. Results indicate that the neural network algorithm can approximate the PDE outputs with high degree of accuracy (less than 1% error), and that this error increases as a function of the prediction time lag.

A novel and generalized approach in the inversion of geoelectrical resistivity data using Artificial Neural Networks (ANN)

NASA Astrophysics Data System (ADS)

Raj, A. Stanley; Srinivas, Y.; Oliver, D. Hudson; Muthuraj, D.

2014-03-01

The non-linear apparent resistivity problem in the subsurface study of the earth takes into account the model parameters in terms of resistivity and thickness of individual subsurface layers using the trained synthetic data by means of Artificial Neural Networks (ANN). Here we used a single layer feed-forward neural network with fast back propagation learning algorithm. So on proper training of back propagation networks it tends to give the resistivity and thickness of the subsurface layer model of the field resistivity data with reference to the synthetic data trained in the appropriate network. During training, the weights and biases of the network are iteratively adjusted to make network performance function level more efficient. On adequate training, errors are minimized and the best result is obtained using the artificial neural networks. The network is trained with more number of VES data and this trained network is demonstrated by the field data. The accuracy of inversion depends upon the number of data trained. In this novel and specially designed algorithm, the interpretation of the vertical electrical sounding has been done successfully with the more accurate layer model.

Training in reproductive endocrinology and infertility and assisted reproductive technologies: options and worldwide needs.

PubMed

de Ziegler, Dominique; de Ziegler, Nathalie; Sean, Sokteang; Bajouh, Osama; Meldrum, David R

2015-07-01

Standardized, high-quality training in reproductive endocrinology, infertility, and assisted reproductive technologies (REI-ART) faces challenges owing to the high-tech nature of ART and the important country-to-country differences in clinical practice and regulations overseeing training. Moreover, while the training capacity of the classical by-fellowship training platforms is shrinking, an increasing demand for REI-ART specialists is coming from emerging countries. To meet this expanding need for REI-ART specialists, we propose a novel by-network model linking a reference training center to satellite practical training sites. Simulation should be used more extensively to achieve competency before initiating live clinical experience, analogous to the highly effective training systems that have been used in aviation for decades. Large ART databases that exist because of obligations to report ART activity and results constitute unique yet so far untapped sources for developing by-scenario simulation training models. Online training materials incorporating these state-of-the-art information technology tools could be developed as a means of fulfilling training needs worldwide. Copyright © 2015. Published by Elsevier Inc.

Partnerships and pathways of dissemination: the National Institute on Drug Abuse-Substance Abuse and Mental Health Services Administration Blending Initiative in the Clinical Trials Network.

PubMed

Martino, Steve; Brigham, Gregory S; Higgins, Christine; Gallon, Steve; Freese, Thomas E; Albright, Lonnetta M; Hulsey, Eric G; Krom, Laurie; Storti, Susan A; Perl, Harold; Nugent, Cathrine D; Pintello, Denise; Condon, Timothy P

2010-06-01

Since 2001, the National Drug Abuse Treatment Clinical Trials Network (CTN) has worked to put the results of its trials into the hands of community treatment programs, in large part through its participation in the National Institute on Drug Abuse-Substance Abuse and Mental Health Services Administration Blending Initiative and its close involvement with the Center for Substance Abuse Treatment's Addiction Technology Transfer Centers. This article describes (a) the CTN's integral role in the Blending Initiative, (b) key partnerships and dissemination pathways through which the results of CTN trials are developed into blending products and then transferred to community treatment programs, and (c) three blending initiatives involving buprenorphine, motivational incentives, and motivational interviewing. The Blending Initiative has resulted in high utilization of its products, preparation of more than 200 regional trainers, widespread training of service providers in most U.S. States, Puerto Rico, and the U.S. Virgin Islands and movement toward the development of Web-based implementation supports and technical assistance. Implications for future directions of the Blending Initiative and opportunities for research are discussed.

Guiding the development of family medicine training in Africa through collaboration with the Medical Education Partnership Initiative.

PubMed

Mash, Robert J; de Villiers, Marietjie R; Moodley, Kalay; Nachega, Jean B

2014-08-01

Africa's health care challenges include a high burden of disease, low life expectancy, health workforce shortages, and varying degrees of commitment to primary health care on the part of policy makers and government officials. One overarching goal of the Medical Education Partnership Initiative (MEPI) is to develop models of medical education in Sub-Saharan Africa. To do this, MEPI has created a network of universities and other institutions that, among other things, recognizes the importance of supporting training programs in family medicine. This article provides a framework for assessing the stage of the development of family medicine training in Africa, including the challenges that were encountered and how educational organizations can help to address them. A modified "stages of change" model (precontemplation, contemplation, action, maintenance, and relapse) was used as a conceptual framework to understand the various phases that countries go through in developing family medicine in the public sector and to determine the type of assistance that is useful at each phase.

High pressure air compressor valve fault diagnosis using feedforward neural networks

NASA Astrophysics Data System (ADS)

James Li, C.; Yu, Xueli

1995-09-01

Feedforward neural networks (FNNs) are developed and implemented to classify a four-stage high pressure air compressor into one of the following conditions: baseline, suction or exhaust valve faults. These FNNs are used for the compressor's automatic condition monitoring and fault diagnosis. Measurements of 39 variables are obtained under different baseline conditions and third-stage suction and exhaust valve faults. These variables include pressures and temperatures at all stages, voltage between phase aand phase b, voltage between phase band phase c, total three-phase real power, cooling water flow rate, etc. To reduce the number of variables, the amount of their discriminatory information is quantified by scattering matrices to identify statistical significant ones. Measurements of the selected variables are then used by a fully automatic structural and weight learning algorithm to construct three-layer FNNs to classify the compressor's condition. This learning algorithm requires neither guesses of initial weight values nor number of neurons in the hidden layer of an FNN. It takes an incremental approach in which a hidden neuron is trained by exemplars and then augmented to the existing network. These exemplars are then made orthogonal to the newly identified hidden neuron. They are subsequently used for the training of the next hidden neuron. The betterment continues until a desired accuracy is reached. After the neural networks are established, novel measurements from various conditions that haven't been previously seen by the FNNs are then used to evaluate their ability in fault diagnosis. The trained neural networks provide very accurate diagnosis for suction and discharge valve defects.

Neural network pattern recognition of lingual-palatal pressure for automated detection of swallow.

PubMed

Hadley, Aaron J; Krival, Kate R; Ridgel, Angela L; Hahn, Elizabeth C; Tyler, Dustin J

2015-04-01

We describe a novel device and method for real-time measurement of lingual-palatal pressure and automatic identification of the oral transfer phase of deglutition. Clinical measurement of the oral transport phase of swallowing is a complicated process requiring either placement of obstructive sensors or sitting within a fluoroscope or articulograph for recording. Existing detection algorithms distinguish oral events with EMG, sound, and pressure signals from the head and neck, but are imprecise and frequently result in false detection. We placed seven pressure sensors on a molded mouthpiece fitting over the upper teeth and hard palate and recorded pressure during a variety of swallow and non-swallow activities. Pressure measures and swallow times from 12 healthy and 7 Parkinson's subjects provided training data for a time-delay artificial neural network to categorize the recordings as swallow or non-swallow events. User-specific neural networks properly categorized 96 % of swallow and non-swallow events, while a generalized population-trained network was able to properly categorize 93 % of swallow and non-swallow events across all recordings. Lingual-palatal pressure signals are sufficient to selectively and specifically recognize the initiation of swallowing in healthy and dysphagic patients.

Networking grassroots efforts to improve safety and health in informal economy workplaces in Asia.

PubMed

Kawakami, Tsuyoshi

2006-01-01

Many workers in Asia are in the informal economy. They often work in substandard conditions, exposed to hazards in the workplace. Learning from the recent successes of participatory training programmes to improve safety and health in Asia, the ILO has strengthened its partnership efforts with local people to improve safety and health of informal economy workplaces. The target groups were: (1) home workplaces in Cambodia and Thailand, (2) salt fields and fishing villages in Cambodia where many young workers are working, and (3) small construction sites in Cambodia, Laos, Mongolia, Thailand and Vietnam. The walk-through survey results showed that the workers and owners in the target informal economy workplaces had the strong will to improve safety and health at their own initiatives and needed practical support. In the participatory, action-oriented training workshops carried out, the participated workers and owners were able to identify their priority safety and health actions. Commonly identified were clear and safe transport ways, safer handling of hazardous substances, basic welfare needs such as drinking water and sanitary toilets, and work posture. The follow-up visits confirmed that many of the proposed actions were actually taken by using low-cost available materials. These positive changes were possible by applying the participatory training tools such as illustrated checklists and extensive use of photographs showing local good examples and placing emphasis on facilitator roles of trainers. In conclusion, the target informal economy workplaces in Asia made positive changes in safety and health through the participatory, action-oriented training focusing on local initiative and low-cost improvement measures. Local network support mechanisms to share lessons from good practices played essential roles in encouraging the voluntary implementation of practical improvement actions. It is important to increase our joint efforts to reach more informal economy workplaces in industrially developing countries and provide practical support measures focusing on local self-help initiatives.

Effective Multifocus Image Fusion Based on HVS and BP Neural Network

PubMed Central

Yang, Yong

2014-01-01

The aim of multifocus image fusion is to fuse the images taken from the same scene with different focuses to obtain a resultant image with all objects in focus. In this paper, a novel multifocus image fusion method based on human visual system (HVS) and back propagation (BP) neural network is presented. Three features which reflect the clarity of a pixel are firstly extracted and used to train a BP neural network to determine which pixel is clearer. The clearer pixels are then used to construct the initial fused image. Thirdly, the focused regions are detected by measuring the similarity between the source images and the initial fused image followed by morphological opening and closing operations. Finally, the final fused image is obtained by a fusion rule for those focused regions. Experimental results show that the proposed method can provide better performance and outperform several existing popular fusion methods in terms of both objective and subjective evaluations. PMID:24683327

Neural networks involved in learning lexical-semantic and syntactic information in a second language.

PubMed

Mueller, Jutta L; Rueschemeyer, Shirley-Ann; Ono, Kentaro; Sugiura, Motoaki; Sadato, Norihiro; Nakamura, Akinori

2014-01-01

The present study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of language acquisition in a realistic learning environment. Japanese native speakers were trained in a miniature version of German prior to fMRI scanning. During scanning they listened to (1) familiar sentences, (2) sentences including a novel sentence structure, and (3) sentences containing a novel word while visual context provided referential information. Learning-related decreases of brain activation over time were found in a mainly left-hemispheric network comprising classical frontal and temporal language areas as well as parietal and subcortical regions and were largely overlapping for novel words and the novel sentence structure in initial stages of learning. Differences occurred at later stages of learning during which content-specific activation patterns in prefrontal, parietal and temporal cortices emerged. The results are taken as evidence for a domain-general network supporting the initial stages of language learning which dynamically adapts as learners become proficient.

Culturally Aware Agents for Training Environments (CAATE): Phase I Final Report

DTIC Science & Technology

2009-01-01

attitudes, relationships , personality, personal traits, state, social roles, physical context. The initial set of potentially important cultural... relationships that affect culturally situated behavior. For instance, we will want to be able to model interconnections such as familial... relationships , group membership, and attitudes (e.g., trust, dislike). To accomplish this, our design leverages social network modeling technologies provided by

Predicting concrete corrosion of sewers using artificial neural network.

PubMed

Jiang, Guangming; Keller, Jurg; Bond, Philip L; Yuan, Zhiguo

2016-04-01

Corrosion is often a major failure mechanism for concrete sewers and under such circumstances the sewer service life is largely determined by the progression of microbially induced concrete corrosion. The modelling of sewer processes has become possible due to the improved understanding of in-sewer transformation. Recent systematic studies about the correlation between the corrosion processes and sewer environment factors should be utilized to improve the prediction capability of service life by sewer models. This paper presents an artificial neural network (ANN)-based approach for modelling the concrete corrosion processes in sewers. The approach included predicting the time for the corrosion to initiate and then predicting the corrosion rate after the initiation period. The ANN model was trained and validated with long-term (4.5 years) corrosion data obtained in laboratory corrosion chambers, and further verified with field measurements in real sewers across Australia. The trained model estimated the corrosion initiation time and corrosion rates very close to those measured in Australian sewers. The ANN model performed better than a multiple regression model also developed on the same dataset. Additionally, the ANN model can serve as a prediction framework for sewer service life, which can be progressively improved and expanded by including corrosion rates measured in different sewer conditions. Furthermore, the proposed methodology holds promise to facilitate the construction of analytical models associated with corrosion processes of concrete sewers. Copyright © 2016 Elsevier Ltd. All rights reserved.

MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling.

PubMed

Mutasa, Simukayi; Chang, Peter D; Ruzal-Shapiro, Carrie; Ayyala, Rama

2018-02-05

Bone age assessment (BAA) is a commonly performed diagnostic study in pediatric radiology to assess skeletal maturity. The most commonly utilized method for assessment of BAA is the Greulich and Pyle method (Pediatr Radiol 46.9:1269-1274, 2016; Arch Dis Child 81.2:172-173, 1999) atlas. The evaluation of BAA can be a tedious and time-consuming process for the radiologist. As such, several computer-assisted detection/diagnosis (CAD) methods have been proposed for automation of BAA. Classical CAD tools have traditionally relied on hard-coded algorithmic features for BAA which suffer from a variety of drawbacks. Recently, the advent and proliferation of convolutional neural networks (CNNs) has shown promise in a variety of medical imaging applications. There have been at least two published applications of using deep learning for evaluation of bone age (Med Image Anal 36:41-51, 2017; JDI 1-5, 2017). However, current implementations are limited by a combination of both architecture design and relatively small datasets. The purpose of this study is to demonstrate the benefits of a customized neural network algorithm carefully calibrated to the evaluation of bone age utilizing a relatively large institutional dataset. In doing so, this study will aim to show that advanced architectures can be successfully trained from scratch in the medical imaging domain and can generate results that outperform any existing proposed algorithm. The training data consisted of 10,289 images of different skeletal age examinations, 8909 from the hospital Picture Archiving and Communication System at our institution and 1383 from the public Digital Hand Atlas Database. The data was separated into four cohorts, one each for male and female children above the age of 8, and one each for male and female children below the age of 10. The testing set consisted of 20 radiographs of each 1-year-age cohort from 0 to 1 years to 14-15+ years, half male and half female. The testing set included left-hand radiographs done for bone age assessment, trauma evaluation without significant findings, and skeletal surveys. A 14 hidden layer-customized neural network was designed for this study. The network included several state of the art techniques including residual-style connections, inception layers, and spatial transformer layers. Data augmentation was applied to the network inputs to prevent overfitting. A linear regression output was utilized. Mean square error was used as the network loss function and mean absolute error (MAE) was utilized as the primary performance metric. MAE accuracies on the validation and test sets for young females were 0.654 and 0.561 respectively. For older females, validation and test accuracies were 0.662 and 0.497 respectively. For young males, validation and test accuracies were 0.649 and 0.585 respectively. Finally, for older males, validation and test set accuracies were 0.581 and 0.501 respectively. The female cohorts were trained for 900 epochs each and the male cohorts were trained for 600 epochs. An eightfold cross-validation set was employed for hyperparameter tuning. Test error was obtained after training on a full data set with the selected hyperparameters. Using our proposed customized neural network architecture on our large available data, we achieved an aggregate validation and test set mean absolute errors of 0.637 and 0.536 respectively. To date, this is the best published performance on utilizing deep learning for bone age assessment. Our results support our initial hypothesis that customized, purpose-built neural networks provide improved performance over networks derived from pre-trained imaging data sets. We build on that initial work by showing that the addition of state-of-the-art techniques such as residual connections and inception architecture further improves prediction accuracy. This is important because the current assumption for use of residual and/or inception architectures is that a large pre-trained network is required for successful implementation given the relatively small datasets in medical imaging. Instead we show that a small, customized architecture incorporating advanced CNN strategies can indeed be trained from scratch, yielding significant improvements in algorithm accuracy. It should be noted that for all four cohorts, testing error outperformed validation error. One reason for this is that our ground truth for our test set was obtained by averaging two pediatric radiologist reads compared to our training data for which only a single read was used. This suggests that despite relatively noisy training data, the algorithm could successfully model the variation between observers and generate estimates that are close to the expected ground truth.

Increasing Use of Postpartum Family Planning and the Postpartum IUD: Early Experiences in West and Central Africa.

PubMed

Pleah, Tsigue; Hyjazi, Yolande; Austin, Suzanne; Diallo, Abdoulaye; Dao, Blami; Waxman, Rachel; Karna, Priya

2016-08-11

A global resurgence of interest in the intrauterine device (IUD) as an effective long-acting reversible contraceptive and in improving access to a wide range of contraceptive methods, as well as an emphasis on encouraging women to give birth in health care facilities, has led programs to introduce postpartum IUD (PPIUD) services into postpartum family planning (PPFP) programs. We describe strategic, organizational, and technical elements that contributed to early successes of a regional initiative in West and Central Africa to train antenatal, maternity, and postnatal care providers in PPFP counseling for the full range of available methods and in PPIUD service delivery. In November 2013, the initiative provided competency-based training in Guinea for providers from the main public teaching hospital in 5 selected countries (Benin, Chad, Côte d'Ivoire, Niger, and Senegal) with no prior PPFP counseling or PPIUD capacity. The training was followed by a transfer-of-learning visit and monitoring to support the trained providers. One additional country, Togo, replicated the initiative's model in 2014. Although nascent, this initiative has introduced high-quality PPFP and PPIUD services to the region, where less than 1% of married women of reproductive age use the IUD. In total, 21 providers were trained in PPFP counseling, 18 of whom were also trained in PPIUD insertion. From 2014 to 2015, more than 15,000 women were counseled about PPFP, and 2,269 women chose and received the PPIUD in Benin, Côte d'Ivoire, Niger, Senegal, and Togo. (Introduction of PPIUD services in Chad has been delayed.) South-South collaboration has been central to the initiative's accomplishments: Guinea's clinical centers of excellence and qualified trainers provided a culturally resonant example of a PPFP/PPIUD program, and trainings are creating a network of regional trainers to facilitate expansion. Two of the selected countries (Benin and Niger) have expanded their PPFP/PPUID training programs to additional sites. Inspired after learning about the initiative at a regional meeting, Togo has outperformed the original countries involved in the initiative by training more providers than the other countries. Challenges to scale-up include a lack of formal channels for reporting PPFP and PPIUD service delivery outcomes, inconsistent coordination of services across the reproductive health continuum of care, and slow uptake in some countries. Continued success will rely on careful recordkeeping, regular monitoring and feedback, and strategic data use to advocate scale-up. © Pleah et al.

Neural-network-directed alignment of optical systems using the laser-beam spatial filter as an example

NASA Technical Reports Server (NTRS)

Decker, Arthur J.; Krasowski, Michael J.; Weiland, Kenneth E.

1993-01-01

This report describes an effort at NASA Lewis Research Center to use artificial neural networks to automate the alignment and control of optical measurement systems. Specifically, it addresses the use of commercially available neural network software and hardware to direct alignments of the common laser-beam-smoothing spatial filter. The report presents a general approach for designing alignment records and combining these into training sets to teach optical alignment functions to neural networks and discusses the use of these training sets to train several types of neural networks. Neural network configurations used include the adaptive resonance network, the back-propagation-trained network, and the counter-propagation network. This work shows that neural networks can be used to produce robust sequencers. These sequencers can learn by example to execute the step-by-step procedures of optical alignment and also can learn adaptively to correct for environmentally induced misalignment. The long-range objective is to use neural networks to automate the alignment and operation of optical measurement systems in remote, harsh, or dangerous aerospace environments. This work also shows that when neural networks are trained by a human operator, training sets should be recorded, training should be executed, and testing should be done in a manner that does not depend on intellectual judgments of the human operator.

Two-Dimensional High-Lift Aerodynamic Optimization Using Neural Networks

NASA Technical Reports Server (NTRS)

Greenman, Roxana M.

1998-01-01

The high-lift performance of a multi-element airfoil was optimized by using neural-net predictions that were trained using a computational data set. The numerical data was generated using a two-dimensional, incompressible, Navier-Stokes algorithm with the Spalart-Allmaras turbulence model. Because it is difficult to predict maximum lift for high-lift systems, an empirically-based maximum lift criteria was used in this study to determine both the maximum lift and the angle at which it occurs. The 'pressure difference rule,' which states that the maximum lift condition corresponds to a certain pressure difference between the peak suction pressure and the pressure at the trailing edge of the element, was applied and verified with experimental observations for this configuration. Multiple input, single output networks were trained using the NASA Ames variation of the Levenberg-Marquardt algorithm for each of the aerodynamic coefficients (lift, drag and moment). The artificial neural networks were integrated with a gradient-based optimizer. Using independent numerical simulations and experimental data for this high-lift configuration, it was shown that this design process successfully optimized flap deflection, gap, overlap, and angle of attack to maximize lift. Once the neural nets were trained and integrated with the optimizer, minimal additional computer resources were required to perform optimization runs with different initial conditions and parameters. Applying the neural networks within the high-lift rigging optimization process reduced the amount of computational time and resources by 44% compared with traditional gradient-based optimization procedures for multiple optimization runs.

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

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

Ortiz-Rodriguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetrymore » with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural net approach it is possible to reduce the rate counts used to unfold the neutron spectrum. To evaluate these codes a computer tool called Neutron Spectrometry and dosimetry computer tool was designed. The results obtained with this package are showed. The codes here mentioned are freely available upon request to the authors.« less

Evaluating the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks

NASA Astrophysics Data System (ADS)

Ortiz-Rodríguez, J. M.; Reyes Alfaro, A.; Reyes Haro, A.; Solís Sánches, L. O.; Miranda, R. Castañeda; Cervantes Viramontes, J. M.; Vega-Carrillo, H. R.

2013-07-01

In this work the performance of two neutron spectrum unfolding codes based on iterative procedures and artificial neural networks is evaluated. The first one code based on traditional iterative procedures and called Neutron spectrometry and dosimetry from the Universidad Autonoma de Zacatecas (NSDUAZ) use the SPUNIT iterative algorithm and was designed to unfold neutron spectrum and calculate 15 dosimetric quantities and 7 IAEA survey meters. The main feature of this code is the automated selection of the initial guess spectrum trough a compendium of neutron spectrum compiled by the IAEA. The second one code known as Neutron spectrometry and dosimetry with artificial neural networks (NDSann) is a code designed using neural nets technology. The artificial intelligence approach of neural net does not solve mathematical equations. By using the knowledge stored at synaptic weights on a neural net properly trained, the code is capable to unfold neutron spectrum and to simultaneously calculate 15 dosimetric quantities, needing as entrance data, only the rate counts measured with a Bonner spheres system. Similarities of both NSDUAZ and NSDann codes are: they follow the same easy and intuitive user's philosophy and were designed in a graphical interface under the LabVIEW programming environment. Both codes unfold the neutron spectrum expressed in 60 energy bins, calculate 15 dosimetric quantities and generate a full report in HTML format. Differences of these codes are: NSDUAZ code was designed using classical iterative approaches and needs an initial guess spectrum in order to initiate the iterative procedure. In NSDUAZ, a programming routine was designed to calculate 7 IAEA instrument survey meters using the fluence-dose conversion coefficients. NSDann code use artificial neural networks for solving the ill-conditioned equation system of neutron spectrometry problem through synaptic weights of a properly trained neural network. Contrary to iterative procedures, in neural net approach it is possible to reduce the rate counts used to unfold the neutron spectrum. To evaluate these codes a computer tool called Neutron Spectrometry and dosimetry computer tool was designed. The results obtained with this package are showed. The codes here mentioned are freely available upon request to the authors.

Friendship Network and Dental Brushing Behavior among Middle School Students: An Agent Based Modeling Approach.

PubMed

Sadeghipour, Maryam; Khoshnevisan, Mohammad Hossein; Jafari, Afshin; Shariatpanahi, Seyed Peyman

2017-01-01

By using a standard questionnaire, the level of dental brushing frequency was assessed among 201 adolescent female middle school students in Tehran. The initial assessment was repeated after 5 months, in order to observe the dynamics in dental health behavior level. Logistic Regression model was used to evaluate the correlation among individuals' dental health behavior in their social network. A significant correlation on dental brushing habits was detected among groups of friends. This correlation was further spread over the network within the 5 months period. Moreover, it was identified that the average brushing level was improved within the 5 months period. Given that there was a significant correlation between social network's nodes' in-degree value, and brushing level, it was suggested that the observed improvement was partially due to more popularity of individuals with better tooth brushing habit. Agent Based Modeling (ABM) was used to demonstrate the dynamics of dental brushing frequency within a sample of friendship network. Two models with static and dynamic assumptions for the network structure were proposed. The model with dynamic network structure successfully described the dynamics of dental health behavior. Based on this model, on average, every 43 weeks a student changes her brushing habit due to learning from her friends. Finally, three training scenarios were tested by these models in order to evaluate their effectiveness. When training more popular students, considerable improvement in total students' brushing frequency was demonstrated by simulation results.

Resource constrained design of artificial neural networks using comparator neural network

NASA Technical Reports Server (NTRS)

Wah, Benjamin W.; Karnik, Tanay S.

1992-01-01

We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.

Development of the Global Measles Laboratory Network.

PubMed

Featherstone, David; Brown, David; Sanders, Ray

2003-05-15

The routine reporting of suspected measles cases and laboratory testing of samples from these cases is the backbone of measles surveillance. The Global Measles Laboratory Network (GMLN) has developed standards for laboratory confirmation of measles and provides training resources for staff of network laboratories, reference materials and expertise for the development and quality control of testing procedures, and accurate information for the Measles Mortality Reduction and Regional Elimination Initiative. The GMLN was developed along the lines of the successful Global Polio Laboratory Network, and much of the polio laboratory infrastructure was utilized for measles. The GMLN has developed as countries focus on measles control activities following successful eradication of polio. Currently more than 100 laboratories are part of the global network and follow standardized testing and reporting procedures. A comprehensive laboratory accreditation process will be introduced in 2002 with six quality assurance and performance indicators.

GOFC-GOLD/LCLUC/START Regional Networking: building capacity for science and decision-making.

NASA Astrophysics Data System (ADS)

Justice, C. O.; Vadrevu, K.; Gutman, G.

2016-12-01

Over the past 20 years, the international GOFC-GOLD Program and START, with core funding from the NASA LCLUC program and ESA have been developing regional networks of scientists and data users for scientific capacity building and sharing experience in the use and application of Earth Observation data. Regional networks connect scientists from countries with similar environmental and social issues and often with shared water and airsheds. Through periodic regional workshops, regional and national projects are showcased and national priorities and policy drivers are articulated. The workshops encourage both north-south and south-south exchange and collaboration. The workshops are multi-sponsored and each include a training component, targeting early career scientists and data users from the region. The workshops provide an opportunity for regional scientists to publish in peer-reviewed special editions focused on regional issues. Currently, the NASA LCLUC program funded "South and Southeast Asia Regional Initiative (SARI)" team is working closely with the USAID/NASA SERVIR program to implement some capacity building and training activities jointly in south/southeast Asian countries to achieve maximum benefit.

LVQ and backpropagation neural networks applied to NASA SSME data

NASA Technical Reports Server (NTRS)

Doniere, Timothy F.; Dhawan, Atam P.

1993-01-01

Feedfoward neural networks with backpropagation learning have been used as function approximators for modeling the space shuttle main engine (SSME) sensor signals. The modeling of these sensor signals is aimed at the development of a sensor fault detection system that can be used during ground test firings. The generalization capability of a neural network based function approximator depends on the training vectors which in this application may be derived from a number of SSME ground test-firings. This yields a large number of training vectors. Large training sets can cause the time required to train the network to be very large. Also, the network may not be able to generalize for large training sets. To reduce the size of the training sets, the SSME test-firing data is reduced using the learning vector quantization (LVQ) based technique. Different compression ratios were used to obtain compressed data in training the neural network model. The performance of the neural model trained using reduced sets of training patterns is presented and compared with the performance of the model trained using complete data. The LVQ can also be used as a function approximator. The performance of the LVQ as a function approximator using reduced training sets is presented and compared with the performance of the backpropagation network.

Cloud Classification in Polar and Desert Regions and Smoke Classification from Biomass Burning Using a Hierarchical Neural Network

NASA Technical Reports Server (NTRS)

Alexander, June; Corwin, Edward; Lloyd, David; Logar, Antonette; Welch, Ronald

1996-01-01

This research focuses on a new neural network scene classification technique. The task is to identify scene elements in Advanced Very High Resolution Radiometry (AVHRR) data from three scene types: polar, desert and smoke from biomass burning in South America (smoke). The ultimate goal of this research is to design and implement a computer system which will identify the clouds present on a whole-Earth satellite view as a means of tracking global climate changes. Previous research has reported results for rule-based systems (Tovinkere et at 1992, 1993) for standard back propagation (Watters et at. 1993) and for a hierarchical approach (Corwin et al 1994) for polar data. This research uses a hierarchical neural network with don't care conditions and applies this technique to complex scenes. A hierarchical neural network consists of a switching network and a collection of leaf networks. The idea of the hierarchical neural network is that it is a simpler task to classify a certain pattern from a subset of patterns than it is to classify a pattern from the entire set. Therefore, the first task is to cluster the classes into groups. The switching, or decision network, performs an initial classification by selecting a leaf network. The leaf networks contain a reduced set of similar classes, and it is in the various leaf networks that the actual classification takes place. The grouping of classes in the various leaf networks is determined by applying an iterative clustering algorithm. Several clustering algorithms were investigated, but due to the size of the data sets, the exhaustive search algorithms were eliminated. A heuristic approach using a confusion matrix from a lightly trained neural network provided the basis for the clustering algorithm. Once the clusters have been identified, the hierarchical network can be trained. The approach of using don't care nodes results from the difficulty in generating extremely complex surfaces in order to separate one class from all of the others. This approach finds pairwise separating surfaces and forms the more complex separating surface from combinations of simpler surfaces. This technique both reduces training time and improves accuracy over the previously reported results. Accuracies of 97.47%, 95.70%, and 99.05% were achieved for the polar, desert and smoke data sets.

Developing a Community of Practice for HIV Care: Supporting Knowledge Translation in a Regional Training Initiative.

PubMed

Gallagher, Donna M; Hirschhorn, Lisa R; Lorenz, Laura S; Piya, Priyatam

2017-01-01

Ensuring knowledgeable, skilled HIV providers is challenged by rapid advances in the field, diversity of patients and providers, and the need to retain experienced providers while training new providers. These challenges highlight the need for education strategies, including training and clinical consultation to support translation of new knowledge to practice. New England AIDS Education and Training Center (NEAETC) provides a range of educational modalities including academic peer detailing and distance support to HIV providers in six states. We describe the interprofessional perspectives of HIV providers who participated in this regional program to understand success and areas for strengthening pedagogical modality, content, and impact on clinical practice. This 2013 to 2014 mixed-methods study analyzed quantitative programmatic data to understand changes in training participants and modalities and used semistructured interviews with 30 HIV providers and coded for preidentified and emerging themes. Since 2010, NEAETC evolved modalities to a greater focus on active learning (case discussion, clinical consultation), decreasing didactic training by half (18-9%). This shift was designed to move from knowledge transfer to translation, and qualitative findings supported the value of active learning approaches. Providers valued interactive trainings and presentation of cases supporting knowledge translation. On-site training encouraged peer networking and sharing of lessons learned. Diversity in learning priorities across providers and sites validated NEAETC's approach of tailoring topics to local needs and encouraging regional networking. Tailored approaches resulted in improved provider-reported capacity, peer learning, and support. Future evaluations should explore the impact of this multipronged approach on supporting a community of practice and empowerment of provider teams.

Design of microstrip patch antennas using knowledge insertion through retraining

NASA Astrophysics Data System (ADS)

Divakar, T. V. S.; Sudhakar, A.

2018-04-01

The traditional way of analyzing/designing neural network is to collect experimental data and train neural network. Then, the trained neural network acts as global approximate function. The network is then used to calculate parameters for unknown configurations. The main drawback of this method is one does not have enough experimental data, cost of prototypes being a major factor [1-4]. Therefore, in this method the author collected training data from available approximate formulas with in full design range and trained the network with it. After successful training, the network is retrained with available measured results. This simple way inserts experimental knowledge into the network [5]. This method is tested for rectangular microstrip antenna and circular microstrip antenna.

Design of Neural Networks for Fast Convergence and Accuracy

NASA Technical Reports Server (NTRS)

Maghami, Peiman G.; Sparks, Dean W., Jr.

1998-01-01

A novel procedure for the design and training of artificial neural networks, used for rapid and efficient controls and dynamics design and analysis for flexible space systems, has been developed. Artificial neural networks are employed to provide a means of evaluating the impact of design changes rapidly. Specifically, two-layer feedforward neural networks are designed to approximate the functional relationship between the component spacecraft design changes and measures of its performance. A training algorithm, based on statistical sampling theory, is presented, which guarantees that the trained networks provide a designer-specified degree of accuracy in mapping the functional relationship. Within each iteration of this statistical-based algorithm, a sequential design algorithm is used for the design and training of the feedforward network to provide rapid convergence to the network goals. Here, at each sequence a new network is trained to minimize the error of previous network. The design algorithm attempts to avoid the local minima phenomenon that hampers the traditional network training. A numerical example is performed on a spacecraft application in order to demonstrate the feasibility of the proposed approach.

Supervised Learning Based on Temporal Coding in Spiking Neural Networks.

PubMed

Mostafa, Hesham

2017-08-01

Gradient descent training techniques are remarkably successful in training analog-valued artificial neural networks (ANNs). Such training techniques, however, do not transfer easily to spiking networks due to the spike generation hard nonlinearity and the discrete nature of spike communication. We show that in a feedforward spiking network that uses a temporal coding scheme where information is encoded in spike times instead of spike rates, the network input-output relation is differentiable almost everywhere. Moreover, this relation is piecewise linear after a transformation of variables. Methods for training ANNs thus carry directly to the training of such spiking networks as we show when training on the permutation invariant MNIST task. In contrast to rate-based spiking networks that are often used to approximate the behavior of ANNs, the networks we present spike much more sparsely and their behavior cannot be directly approximated by conventional ANNs. Our results highlight a new approach for controlling the behavior of spiking networks with realistic temporal dynamics, opening up the potential for using these networks to process spike patterns with complex temporal information.

Reformulated Neural Network (ReNN): a New Alternative for Data-driven Modelling in Hydrology and Water Resources Engineering

NASA Astrophysics Data System (ADS)

Razavi, S.; Tolson, B.; Burn, D.; Seglenieks, F.

2012-04-01

Reformulated Neural Network (ReNN) has been recently developed as an efficient and more effective alternative to feedforward multi-layer perceptron (MLP) neural networks [Razavi, S., and Tolson, B. A. (2011). "A new formulation for feedforward neural networks." IEEE Transactions on Neural Networks, 22(10), 1588-1598, DOI: 1510.1109/TNN.2011.2163169]. This presentation initially aims to introduce the ReNN to the water resources community and then demonstrates ReNN applications to water resources related problems. ReNN is essentially equivalent to a single-hidden-layer MLP neural network but defined on a new set of network variables which is more effective than the traditional set of network weights and biases. The main features of the new network variables are that they are geometrically interpretable and each variable has a distinct role in forming the network response. ReNN is more efficiently trained as it has a less complex error response surface. In addition to the ReNN training efficiency, the interpretability of the ReNN variables enables the users to monitor and understand the internal behaviour of the network while training. Regularization in the ReNN response can be also directly measured and controlled. This feature improves the generalization ability of the network. The appeal of the ReNN is demonstrated with two ReNN applications to water resources engineering problems. In the first application, the ReNN is used to model the rainfall-runoff relationships in multiple watersheds in the Great Lakes basin located in northeastern North America. Modelling inflows to the Great Lakes are of great importance to the management of the Great Lakes system. Due to the lack of some detailed physical data about existing control structures in many subwatersheds of this huge basin, the data-driven approach to modelling such as the ReNN are required to replace predictions from a physically-based rainfall runoff model. Unlike traditional MLPs, the ReNN does not necessarily require an independent set of data for validation as the ReNN has the capability to control and verify the network degree of regularization. As such, the ReNN can be very beneficial in this case study as the data available in this case study is limited. In the second application, ReNN is fitted on the response function of the SWAT hydrologic model to act as a fast-to-run response surface surrogate (i.e., metamodel) of the original computationally intensive SWAT model. Besides the training efficiency gains, the ReNN applications demonstrate how the ReNN interpretability could help users develop more reliable networks which perform predictably better in terms of generalization.

Design of Neural Networks for Fast Convergence and Accuracy: Dynamics and Control

NASA Technical Reports Server (NTRS)

Maghami, Peiman G.; Sparks, Dean W., Jr.

1997-01-01

A procedure for the design and training of artificial neural networks, used for rapid and efficient controls and dynamics design and analysis for flexible space systems, has been developed. Artificial neural networks are employed, such that once properly trained, they provide a means of evaluating the impact of design changes rapidly. Specifically, two-layer feedforward neural networks are designed to approximate the functional relationship between the component/spacecraft design changes and measures of its performance or nonlinear dynamics of the system/components. A training algorithm, based on statistical sampling theory, is presented, which guarantees that the trained networks provide a designer-specified degree of accuracy in mapping the functional relationship. Within each iteration of this statistical-based algorithm, a sequential design algorithm is used for the design and training of the feedforward network to provide rapid convergence to the network goals. Here, at each sequence a new network is trained to minimize the error of previous network. The proposed method should work for applications wherein an arbitrary large source of training data can be generated. Two numerical examples are performed on a spacecraft application in order to demonstrate the feasibility of the proposed approach.

Design of neural networks for fast convergence and accuracy: dynamics and control.

PubMed

Maghami, P G; Sparks, D R

2000-01-01

A procedure for the design and training of artificial neural networks, used for rapid and efficient controls and dynamics design and analysis for flexible space systems, has been developed. Artificial neural networks are employed, such that once properly trained, they provide a means of evaluating the impact of design changes rapidly. Specifically, two-layer feedforward neural networks are designed to approximate the functional relationship between the component/spacecraft design changes and measures of its performance or nonlinear dynamics of the system/components. A training algorithm, based on statistical sampling theory, is presented, which guarantees that the trained networks provide a designer-specified degree of accuracy in mapping the functional relationship. Within each iteration of this statistical-based algorithm, a sequential design algorithm is used for the design and training of the feedforward network to provide rapid convergence to the network goals. Here, at each sequence a new network is trained to minimize the error of previous network. The proposed method should work for applications wherein an arbitrary large source of training data can be generated. Two numerical examples are performed on a spacecraft application in order to demonstrate the feasibility of the proposed approach.

Deep convolutional networks for pancreas segmentation in CT imaging

NASA Astrophysics Data System (ADS)

Roth, Holger R.; Farag, Amal; Lu, Le; Turkbey, Evrim B.; Summers, Ronald M.

2015-03-01

Automatic organ segmentation is an important prerequisite for many computer-aided diagnosis systems. The high anatomical variability of organs in the abdomen, such as the pancreas, prevents many segmentation methods from achieving high accuracies when compared to state-of-the-art segmentation of organs like the liver, heart or kidneys. Recently, the availability of large annotated training sets and the accessibility of affordable parallel computing resources via GPUs have made it feasible for "deep learning" methods such as convolutional networks (ConvNets) to succeed in image classification tasks. These methods have the advantage that used classification features are trained directly from the imaging data. We present a fully-automated bottom-up method for pancreas segmentation in computed tomography (CT) images of the abdomen. The method is based on hierarchical coarse-to-fine classification of local image regions (superpixels). Superpixels are extracted from the abdominal region using Simple Linear Iterative Clustering (SLIC). An initial probability response map is generated, using patch-level confidences and a two-level cascade of random forest classifiers, from which superpixel regions with probabilities larger 0.5 are retained. These retained superpixels serve as a highly sensitive initial input of the pancreas and its surroundings to a ConvNet that samples a bounding box around each superpixel at different scales (and random non-rigid deformations at training time) in order to assign a more distinct probability of each superpixel region being pancreas or not. We evaluate our method on CT images of 82 patients (60 for training, 2 for validation, and 20 for testing). Using ConvNets we achieve maximum Dice scores of an average 68% +/- 10% (range, 43-80%) in testing. This shows promise for accurate pancreas segmentation, using a deep learning approach and compares favorably to state-of-the-art methods.

A neural network construction method for surrogate modeling of physics-based analysis

NASA Astrophysics Data System (ADS)

Sung, Woong Je

In this thesis existing methodologies related to the developmental methods of neural networks have been surveyed and their approaches to network sizing and structuring are carefully observed. This literature review covers the constructive methods, the pruning methods, and the evolutionary methods and questions about the basic assumption intrinsic to the conventional neural network learning paradigm, which is primarily devoted to optimization of connection weights (or synaptic strengths) for the pre-determined connection structure of the network. The main research hypothesis governing this thesis is that, without breaking a prevailing dichotomy between weights and connectivity of the network during learning phase, the efficient design of a task-specific neural network is hard to achieve because, as long as connectivity and weights are searched by separate means, a structural optimization of the neural network requires either repetitive re-training procedures or computationally expensive topological meta-search cycles. The main contribution of this thesis is designing and testing a novel learning mechanism which efficiently learns not only weight parameters but also connection structure from a given training data set, and positioning this learning mechanism within the surrogate modeling practice. In this work, a simple and straightforward extension to the conventional error Back-Propagation (BP) algorithm has been formulated to enable a simultaneous learning for both connectivity and weights of the Generalized Multilayer Perceptron (GMLP) in supervised learning tasks. A particular objective is to achieve a task-specific network having reasonable generalization performance with a minimal training time. The dichotomy between architectural design and weight optimization is reconciled by a mechanism establishing a new connection for a neuron pair which has potentially higher error-gradient than one of the existing connections. Interpreting an instance of the absence of connection as a zero-weight connection, the potential contribution to training error reduction of any present or absent connection can readily be evaluated using the BP algorithm. Instead of being broken, the connections that contribute less remain frozen with constant weight values optimized to that point but they are excluded from further weight optimization until reselected. In this way, a selective weight optimization is executed only for the dynamically maintained pool of high gradient connections. By searching the rapidly changing weights and concentrating optimization resources on them, the learning process is accelerated without either a significant increase in computational cost or a need for re-training. This results in a more task-adapted network connection structure. Combined with another important criterion for the division of a neuron which adds a new computational unit to a network, a highly fitted network can be grown out of the minimal random structure. This particular learning strategy can belong to a more broad class of the variable connectivity learning scheme and the devised algorithm has been named Optimal Brain Growth (OBG). The OBG algorithm has been tested on two canonical problems; a regression analysis using the Complicated Interaction Regression Function and a classification of the Two-Spiral Problem. A comparative study with conventional Multilayer Perceptrons (MLPs) consisting of single- and double-hidden layers shows that OBG is less sensitive to random initial conditions and generalizes better with only a minimal increase in computational time. This partially proves that a variable connectivity learning scheme has great potential to enhance computational efficiency and reduce efforts to select proper network architecture. To investigate the applicability of the OBG to more practical surrogate modeling tasks, the geometry-to-pressure mapping of a particular class of airfoils in the transonic flow regime has been sought using both the conventional MLP networks with pre-defined architecture and the OBG-developed networks started from the same initial MLP networks. Considering wide variety in airfoil geometry and diversity of flow conditions distributed over a range of flow Mach numbers and angles of attack, the new method shows a great potential to capture fundamentally nonlinear flow phenomena especially related to the occurrence of shock waves on airfoil surfaces in transonic flow regime. (Abstract shortened by UMI.).

Parametric motion control of robotic arms: A biologically based approach using neural networks

NASA Technical Reports Server (NTRS)

Bock, O.; D'Eleuterio, G. M. T.; Lipitkas, J.; Grodski, J. J.

1993-01-01

A neural network based system is presented which is able to generate point-to-point movements of robotic manipulators. The foundation of this approach is the use of prototypical control torque signals which are defined by a set of parameters. The parameter set is used for scaling and shaping of these prototypical torque signals to effect a desired outcome of the system. This approach is based on neurophysiological findings that the central nervous system stores generalized cognitive representations of movements called synergies, schemas, or motor programs. It has been proposed that these motor programs may be stored as torque-time functions in central pattern generators which can be scaled with appropriate time and magnitude parameters. The central pattern generators use these parameters to generate stereotypical torque-time profiles, which are then sent to the joint actuators. Hence, only a small number of parameters need to be determined for each point-to-point movement instead of the entire torque-time trajectory. This same principle is implemented for controlling the joint torques of robotic manipulators where a neural network is used to identify the relationship between the task requirements and the torque parameters. Movements are specified by the initial robot position in joint coordinates and the desired final end-effector position in Cartesian coordinates. This information is provided to the neural network which calculates six torque parameters for a two-link system. The prototypical torque profiles (one per joint) are then scaled by those parameters. After appropriate training of the network, our parametric control design allowed the reproduction of a trained set of movements with relatively high accuracy, and the production of previously untrained movements with comparable accuracy. We conclude that our approach was successful in discriminating between trained movements and in generalizing to untrained movements.

Developing scientists in Hispanic substance use and health disparities research through the creation of a national mentoring network

PubMed Central

Bazzi, Angela R.; Mogro-Wilson, Cristina; Negi, Nalini Junko; Gonzalez, Jennifer M. Reingle; Cano, Miguel Ángel; Castro, Yessenia; Cepeda, Alice

2017-01-01

Hispanics are disproportionately affected by substance use and related health harms yet remain underrepresented across scientific disciplines focused on researching and addressing these issues. An interdisciplinary network of scientists committed to fostering the development of social and biomedical researchers focused on Hispanic substance use and health disparities developed innovative mentoring and career development activities. We conducted a formative evaluation study using anonymous membership and conference feedback data to describe specific mentoring and career development activities developed within the national network. Successful mentoring initiatives and career development activities were infused with cultural and community values supportive of professional integration and persistence. Mentoring initially occurred within an annual national conference and was then sustained throughout the year through formal training programs and informal mentoring networks. Although rigorous evaluation is needed to determine the success of these strategies in fostering long-term career development among scientists conducting Hispanic health and substance use research, this innovative model may hold promise for other groups committed to promoting career development and professional integration and persistence for minority (and non-minority) scientists committed to addressing health disparities. PMID:28804254

Striatal and Hippocampal Involvement in Motor Sequence Chunking Depends on the Learning Strategy

PubMed Central

Lungu, Ovidiu; Monchi, Oury; Albouy, Geneviève; Jubault, Thomas; Ballarin, Emanuelle; Burnod, Yves; Doyon, Julien

2014-01-01

Motor sequences can be learned using an incremental approach by starting with a few elements and then adding more as training evolves (e.g., learning a piano piece); conversely, one can use a global approach and practice the whole sequence in every training session (e.g., shifting gears in an automobile). Yet, the neural correlates associated with such learning strategies in motor sequence learning remain largely unexplored to date. Here we used functional magnetic resonance imaging to measure the cerebral activity of individuals executing the same 8-element sequence after they completed a 4-days training regimen (2 sessions each day) following either a global or incremental strategy. A network comprised of striatal and fronto-parietal regions was engaged significantly regardless of the learning strategy, whereas the global training regimen led to additional cerebellar and temporal lobe recruitment. Analysis of chunking/grouping of sequence elements revealed a common prefrontal network in both conditions during the chunk initiation phase, whereas execution of chunk cores led to higher mediotemporal activity (involving the hippocampus) after global than incremental training. The novelty of our results relate to the recruitment of mediotemporal regions conditional of the learning strategy. Thus, the present findings may have clinical implications suggesting that the ability of patients with lesions to the medial temporal lobe to learn and consolidate new motor sequences may benefit from using an incremental strategy. PMID:25148078

Striatal and hippocampal involvement in motor sequence chunking depends on the learning strategy.

PubMed

Lungu, Ovidiu; Monchi, Oury; Albouy, Geneviève; Jubault, Thomas; Ballarin, Emanuelle; Burnod, Yves; Doyon, Julien

2014-01-01

Motor sequences can be learned using an incremental approach by starting with a few elements and then adding more as training evolves (e.g., learning a piano piece); conversely, one can use a global approach and practice the whole sequence in every training session (e.g., shifting gears in an automobile). Yet, the neural correlates associated with such learning strategies in motor sequence learning remain largely unexplored to date. Here we used functional magnetic resonance imaging to measure the cerebral activity of individuals executing the same 8-element sequence after they completed a 4-days training regimen (2 sessions each day) following either a global or incremental strategy. A network comprised of striatal and fronto-parietal regions was engaged significantly regardless of the learning strategy, whereas the global training regimen led to additional cerebellar and temporal lobe recruitment. Analysis of chunking/grouping of sequence elements revealed a common prefrontal network in both conditions during the chunk initiation phase, whereas execution of chunk cores led to higher mediotemporal activity (involving the hippocampus) after global than incremental training. The novelty of our results relate to the recruitment of mediotemporal regions conditional of the learning strategy. Thus, the present findings may have clinical implications suggesting that the ability of patients with lesions to the medial temporal lobe to learn and consolidate new motor sequences may benefit from using an incremental strategy.

Grounding the Meanings in Sensorimotor Behavior using Reinforcement Learning

PubMed Central

Farkaš, Igor; Malík, Tomáš; Rebrová, Kristína

2012-01-01

The recent outburst of interest in cognitive developmental robotics is fueled by the ambition to propose ecologically plausible mechanisms of how, among other things, a learning agent/robot could ground linguistic meanings in its sensorimotor behavior. Along this stream, we propose a model that allows the simulated iCub robot to learn the meanings of actions (point, touch, and push) oriented toward objects in robot’s peripersonal space. In our experiments, the iCub learns to execute motor actions and comment on them. Architecturally, the model is composed of three neural-network-based modules that are trained in different ways. The first module, a two-layer perceptron, is trained by back-propagation to attend to the target position in the visual scene, given the low-level visual information and the feature-based target information. The second module, having the form of an actor-critic architecture, is the most distinguishing part of our model, and is trained by a continuous version of reinforcement learning to execute actions as sequences, based on a linguistic command. The third module, an echo-state network, is trained to provide the linguistic description of the executed actions. The trained model generalizes well in case of novel action-target combinations with randomized initial arm positions. It can also promptly adapt its behavior if the action/target suddenly changes during motor execution. PMID:22393319

Hypersonic Vehicle Trajectory Optimization and Control

NASA Technical Reports Server (NTRS)

Balakrishnan, S. N.; Shen, J.; Grohs, J. R.

1997-01-01

Two classes of neural networks have been developed for the study of hypersonic vehicle trajectory optimization and control. The first one is called an 'adaptive critic'. The uniqueness and main features of this approach are that: (1) they need no external training; (2) they allow variability of initial conditions; and (3) they can serve as feedback control. This is used to solve a 'free final time' two-point boundary value problem that maximizes the mass at the rocket burn-out while satisfying the pre-specified burn-out conditions in velocity, flightpath angle, and altitude. The second neural network is a recurrent network. An interesting feature of this network formulation is that when its inputs are the coefficients of the dynamics and control matrices, the network outputs are the Kalman sequences (with a quadratic cost function); the same network is also used for identifying the coefficients of the dynamics and control matrices. Consequently, we can use it to control a system whose parameters are uncertain. Numerical results are presented which illustrate the potential of these methods.

RENEB - Running the European Network of biological dosimetry and physical retrospective dosimetry.

PubMed

Kulka, Ulrike; Abend, Michael; Ainsbury, Elizabeth; Badie, Christophe; Barquinero, Joan Francesc; Barrios, Lleonard; Beinke, Christina; Bortolin, Emanuela; Cucu, Alexandra; De Amicis, Andrea; Domínguez, Inmaculada; Fattibene, Paola; Frøvig, Anne Marie; Gregoire, Eric; Guogyte, Kamile; Hadjidekova, Valeria; Jaworska, Alicja; Kriehuber, Ralf; Lindholm, Carita; Lloyd, David; Lumniczky, Katalin; Lyng, Fiona; Meschini, Roberta; Mörtl, Simone; Della Monaca, Sara; Monteiro Gil, Octávia; Montoro, Alegria; Moquet, Jayne; Moreno, Mercedes; Oestreicher, Ursula; Palitti, Fabrizio; Pantelias, Gabriel; Patrono, Clarice; Piqueret-Stephan, Laure; Port, Matthias; Prieto, María Jesus; Quintens, Roel; Ricoul, Michelle; Romm, Horst; Roy, Laurence; Sáfrány, Géza; Sabatier, Laure; Sebastià, Natividad; Sommer, Sylwester; Terzoudi, Georgia; Testa, Antonella; Thierens, Hubert; Turai, Istvan; Trompier, François; Valente, Marco; Vaz, Pedro; Voisin, Philippe; Vral, Anne; Woda, Clemens; Zafiropoulos, Demetre; Wojcik, Andrzej

2017-01-01

A European network was initiated in 2012 by 23 partners from 16 European countries with the aim to significantly increase individualized dose reconstruction in case of large-scale radiological emergency scenarios. The network was built on three complementary pillars: (1) an operational basis with seven biological and physical dosimetric assays in ready-to-use mode, (2) a basis for education, training and quality assurance, and (3) a basis for further network development regarding new techniques and members. Techniques for individual dose estimation based on biological samples and/or inert personalized devices as mobile phones or smart phones were optimized to support rapid categorization of many potential victims according to the received dose to the blood or personal devices. Communication and cross-border collaboration were also standardized. To assure long-term sustainability of the network, cooperation with national and international emergency preparedness organizations was initiated and links to radiation protection and research platforms have been developed. A legal framework, based on a Memorandum of Understanding, was established and signed by 27 organizations by the end of 2015. RENEB is a European Network of biological and physical-retrospective dosimetry, with the capacity and capability to perform large-scale rapid individualized dose estimation. Specialized to handle large numbers of samples, RENEB is able to contribute to radiological emergency preparedness and wider large-scale research projects.

A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing.

PubMed

Sillin, Henry O; Aguilera, Renato; Shieh, Hsien-Hang; Avizienis, Audrius V; Aono, Masakazu; Stieg, Adam Z; Gimzewski, James K

2013-09-27

Atomic switch networks (ASNs) have been shown to generate network level dynamics that resemble those observed in biological neural networks. To facilitate understanding and control of these behaviors, we developed a numerical model based on the synapse-like properties of individual atomic switches and the random nature of the network wiring. We validated the model against various experimental results highlighting the possibility to functionalize the network plasticity and the differences between an atomic switch in isolation and its behaviors in a network. The effects of changing connectivity density on the nonlinear dynamics were examined as characterized by higher harmonic generation in response to AC inputs. To demonstrate their utility for computation, we subjected the simulated network to training within the framework of reservoir computing and showed initial evidence of the ASN acting as a reservoir which may be optimized for specific tasks by adjusting the input gain. The work presented represents steps in a unified approach to experimentation and theory of complex systems to make ASNs a uniquely scalable platform for neuromorphic computing.

A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing

NASA Astrophysics Data System (ADS)

Sillin, Henry O.; Aguilera, Renato; Shieh, Hsien-Hang; Avizienis, Audrius V.; Aono, Masakazu; Stieg, Adam Z.; Gimzewski, James K.

2013-09-01

Atomic switch networks (ASNs) have been shown to generate network level dynamics that resemble those observed in biological neural networks. To facilitate understanding and control of these behaviors, we developed a numerical model based on the synapse-like properties of individual atomic switches and the random nature of the network wiring. We validated the model against various experimental results highlighting the possibility to functionalize the network plasticity and the differences between an atomic switch in isolation and its behaviors in a network. The effects of changing connectivity density on the nonlinear dynamics were examined as characterized by higher harmonic generation in response to AC inputs. To demonstrate their utility for computation, we subjected the simulated network to training within the framework of reservoir computing and showed initial evidence of the ASN acting as a reservoir which may be optimized for specific tasks by adjusting the input gain. The work presented represents steps in a unified approach to experimentation and theory of complex systems to make ASNs a uniquely scalable platform for neuromorphic computing.

Research on particle swarm optimization algorithm based on optimal movement probability

NASA Astrophysics Data System (ADS)

Ma, Jianhong; Zhang, Han; He, Baofeng

2017-01-01

The particle swarm optimization algorithm to improve the control precision, and has great application value training neural network and fuzzy system control fields etc.The traditional particle swarm algorithm is used for the training of feed forward neural networks,the search efficiency is low, and easy to fall into local convergence.An improved particle swarm optimization algorithm is proposed based on error back propagation gradient descent. Particle swarm optimization for Solving Least Squares Problems to meme group, the particles in the fitness ranking, optimization problem of the overall consideration, the error back propagation gradient descent training BP neural network, particle to update the velocity and position according to their individual optimal and global optimization, make the particles more to the social optimal learning and less to its optimal learning, it can avoid the particles fall into local optimum, by using gradient information can accelerate the PSO local search ability, improve the multi beam particle swarm depth zero less trajectory information search efficiency, the realization of improved particle swarm optimization algorithm. Simulation results show that the algorithm in the initial stage of rapid convergence to the global optimal solution can be near to the global optimal solution and keep close to the trend, the algorithm has faster convergence speed and search performance in the same running time, it can improve the convergence speed of the algorithm, especially the later search efficiency.

Strengthening the Tuberculosis Specimen Referral Network in Uganda: The Role of Public-Private Partnerships.

PubMed

Joloba, Moses; Mwangi, Christina; Alexander, Heather; Nadunga, Diana; Bwanga, Freddie; Modi, Nelson; Downing, Robert; Nabasirye, Agnes; Adatu, Francis E; Shrivastava, Ritu; Gadde, Renuka; Nkengasong, John N

2016-04-15

Diagnosis of multidrug-resistant tuberculosis and prompt initiation of effective treatment rely on access to rapid and reliable drug-susceptibility testing. Efficient specimen transport systems and appropriate training on specimen referral contribute to optimal and timely access to tuberculosis diagnostic services. With support and technical assistance from a public-private partnership (PPP) between Becton Dickinson and the US President's Emergency Plan for AIDS Relief, the Uganda National TB Reference Laboratory (NTRL) and National TB and Leprosy Program redesigned the tuberculosis specimen transport network and trained healthcare workers with the goal of improving multidrug-resistant tuberculosis detection. Between 2008 and 2011, the PPP mapped 93% of health facilities and trained 724 healthcare and postal staff members covering 72% of districts. Strengthening the tuberculosis specimen referral system increased referrals from presumptive multidrug-resistant tuberculosis cases by >10-fold, with 94% of specimens reaching the NTRL within the established target transport time. This study demonstrates the potential of PPP collaborations with ministries of health to positively influence patient care by strengthening laboratory systems through increased access to drug-susceptibility testing in Uganda. Ongoing efforts to integrate specimen transport networks will maximize resources and improve patient management. © The Author 2016. Published by Oxford University Press for the Infectious Diseases Society of America. All rights reserved. For permissions, e-mail journals.permissions@oup.com.

Maryland's Special Populations Network. A model for cancer disparities research, education, and training.

PubMed

Baquet, Claudia R; Mack, Kelly M; Mishra, Shiraz I; Bramble, Joy; Deshields, Mary; Datcher, Delores; Savoy, Mervin; Brooks, Sandra E; Boykin-Brown, Stephanie; Hummel, Kery

2006-10-15

The unequal burden of cancer in minority and underserved communities nationally and in Maryland is a compelling crisis. The Maryland Special Populations Cancer Research Network (MSPN) developed an infrastructure covering Maryland's 23 jurisdictions and Baltimore City through formal partnerships between the University of Maryland School of Medicine, University of Maryland Statewide Health Network, University of Maryland Eastern Shore, and community partners in Baltimore City, rural Eastern Shore, rural Western Maryland, rural Southern Maryland, and Piscataway Conoy Tribe and statewide American Indians. Guided by the community-based participatory framework, the MSPN undertook a comprehensive assessment (of needs, strengths, and resources available) that laid the foundation for programmatic efforts in community-initiated cancer awareness and education, research, and training. The MSPN infrastructure was used to implement successful and innovative community-based cancer education interventions and technological solutions; conduct education and promotion of clinical trials, cancer health disparities research, and minority faculty cancer research career development; and leverage additional resources for sustainability. MSPN engaged in informed advocacy among decision- and policymakers at state and national levels, and its community-based clinical trials program was recognized by the U.S. Department of Health and Human Services as a Best Practice Award. The solutions to reduce and eliminate cancer health disparities are complex and require comprehensive and focused multidisciplinary cancer health disparities research, training, and education strategies implemented through robust community-academic partnerships. Cancer 2006. (c) American Cancer Society.

Clouds, airplanes, trucks and people: carrying radioisotopes to and across Mexico.

PubMed

Mateos, Gisela; Suárez-Díaz, Edna

2015-01-01

The aim of this paper is to describe the early stages of Mexican nuclearization that took place in contact with radioisotopes. This history requires a multilayered narrative with an emphasis in North-South asymmetric relations, and in the value of education and training in the creation of international asymmetrical networks. Radioisotopes were involved in exchanges with the United States since the late 1940s, but also with Canada. We also describe the context of implementation of Eisenhower's Atoms for Peace initiative in Mexico that opened the door to training programs at both the Comisión Nacional de Energía Nuclear and the Universidad Nacional Autónoma de México. Radioisotopes became the best example of the peaceful applications of atomic energy, and as such they fitted the Mexican nuclearization process that was and still is defined by its commitment to pacifism. In 1955 Mexico became one of the 16 members of the atomic fallout network established by the United Nations. As part of this network, the first generation of Mexican (women) radio-chemists was trained. By the end of the 1960s, radioisotopes and biological markers were being produced in a research reactor, prepared and distributed by the CNEN within Mexico. We end up this paper with a brief reflection on North-South nuclear exchanges and the particularities of the Mexican case.

Interaction of multiple networks modulated by the working memory training based on real-time fMRI

NASA Astrophysics Data System (ADS)

Shen, Jiahui; Zhang, Gaoyan; Zhu, Chaozhe; Yao, Li; Zhao, Xiaojie

2015-03-01

Neuroimaging studies of working memory training have identified the alteration of brain activity as well as the regional interactions within the functional networks such as central executive network (CEN) and default mode network (DMN). However, how the interaction within and between these multiple networks is modulated by the training remains unclear. In this paper, we examined the interaction of three training-induced brain networks during working memory training based on real-time functional magnetic resonance imaging (rtfMRI). Thirty subjects assigned to the experimental and control group respectively participated in two times training separated by seven days. Three networks including silence network (SN), CEN and DMN were identified by the training data with the calculated function connections within each network. Structural equation modeling (SEM) approach was used to construct the directional connectivity patterns. The results showed that the causal influences from the percent signal changes of target ROI to the SN were positively changed in both two groups, as well as the causal influence from the SN to CEN was positively changed in experimental group but negatively changed in control group from the SN to DMN. Further correlation analysis of the changes in each network with the behavioral improvements showed that the changes in SN were stronger positively correlated with the behavioral improvement of letter memory task. These findings indicated that the SN was not only a switch between the target ROI and the other networks in the feedback training but also an essential factor to the behavioral improvement.

A Comprehensive and Cost-Effective Computer Infrastructure for K-12 Schools

NASA Technical Reports Server (NTRS)

Warren, G. P.; Seaton, J. M.

1996-01-01

Since 1993, NASA Langley Research Center has been developing and implementing a low-cost Internet connection model, including system architecture, training, and support, to provide Internet access for an entire network of computers. This infrastructure allows local area networks which exceed 50 machines per school to independently access the complete functionality of the Internet by connecting to a central site, using state-of-the-art commercial modem technology, through a single standard telephone line. By locating high-cost resources at this central site and sharing these resources and their costs among the school districts throughout a region, a practical, efficient, and affordable infrastructure for providing scale-able Internet connectivity has been developed. As the demand for faster Internet access grows, the model has a simple expansion path that eliminates the need to replace major system components and re-train personnel. Observations of optical Internet usage within an environment, particularly school classrooms, have shown that after an initial period of 'surfing,' the Internet traffic becomes repetitive. By automatically storing requested Internet information on a high-capacity networked disk drive at the local site (network based disk caching), then updating this information only when it changes, well over 80 percent of the Internet traffic that leaves a location can be eliminated by retrieving the information from the local disk cache.

Bringing New Ph.D.s Together for Interdisciplinary Climate Change Research

NASA Astrophysics Data System (ADS)

Phelan, Liam; Jones, Holly; Marlon, Jennifer R.

2013-01-01

Climate change is complex and thus requires interdisciplinary research, and new scholars are rising to that challenge. The Dissertations Initiative for the Advancement of Climate Change Research (DISCCRS (pronounced "discourse"); see http://www.disccrs.org) brings together select groups of recent PhD graduates to encourage interdisciplinary work on climate change. The DISCCRS Symposium VII held just outside of Colorado Springs, Colo., brought together 33 graduates from fields as diverse as climatology, ecology, anthropology, and political science for an intensive week of cross-disciplinary engagement in activities like facilitation and leadership training, collaborative research development, peer networking, communication training, and analysis of working group processes.

Three-Dimensional Reconstruction from Single Image Base on Combination of CNN and Multi-Spectral Photometric Stereo.

PubMed

Lu, Liang; Qi, Lin; Luo, Yisong; Jiao, Hengchao; Dong, Junyu

2018-03-02

Multi-spectral photometric stereo can recover pixel-wise surface normal from a single RGB image. The difficulty lies in that the intensity in each channel is the tangle of illumination, albedo and camera response; thus, an initial estimate of the normal is required in optimization-based solutions. In this paper, we propose to make a rough depth estimation using the deep convolutional neural network (CNN) instead of using depth sensors or binocular stereo devices. Since high-resolution ground-truth data is expensive to obtain, we designed a network and trained it with rendered images of synthetic 3D objects. We use the model to predict initial normal of real-world objects and iteratively optimize the fine-scale geometry in the multi-spectral photometric stereo framework. The experimental results illustrate the improvement of the proposed method compared with existing methods.

Three-Dimensional Reconstruction from Single Image Base on Combination of CNN and Multi-Spectral Photometric Stereo

PubMed Central

Lu, Liang; Qi, Lin; Luo, Yisong; Jiao, Hengchao; Dong, Junyu

2018-01-01

Multi-spectral photometric stereo can recover pixel-wise surface normal from a single RGB image. The difficulty lies in that the intensity in each channel is the tangle of illumination, albedo and camera response; thus, an initial estimate of the normal is required in optimization-based solutions. In this paper, we propose to make a rough depth estimation using the deep convolutional neural network (CNN) instead of using depth sensors or binocular stereo devices. Since high-resolution ground-truth data is expensive to obtain, we designed a network and trained it with rendered images of synthetic 3D objects. We use the model to predict initial normal of real-world objects and iteratively optimize the fine-scale geometry in the multi-spectral photometric stereo framework. The experimental results illustrate the improvement of the proposed method compared with existing methods. PMID:29498703

Practice-Based Research Networks, Part II: A Descriptive Analysis of the Athletic Training Practice-Based Research Network in the Secondary School Setting

PubMed Central

McLeod, Tamara C. Valovich; Lam, Kenneth C.; Bay, R. Curtis; Sauers, Eric L.; Valier, Alison R. Snyder

2012-01-01

Context Analysis of health care service models requires the collection and evaluation of basic practice characterization data. Practice-based research networks (PBRNs) provide a framework for gathering data useful in characterizing clinical practice. Objective To describe preliminary secondary school setting practice data from the Athletic Training Practice-Based Research Network (AT-PBRN). Design Descriptive study. Setting Secondary school athletic training facilities within the AT-PBRN. Patients or Other Participants Clinicians (n = 22) and their patients (n = 2523) from the AT-PBRN. Main Outcome Measure(s) A Web-based survey was used to obtain data on clinical practice site and clinician characteristics. Patient and practice characteristics were obtained via deidentified electronic medical record data collected between September 1, 2009, and April 1, 2011. Descriptive data regarding the clinician and CPS practice characteristics are reported as percentages and frequencies. Descriptive analysis of patient encounters and practice characteristic data was performed, with the percentages and frequencies of the type of injuries recorded at initial evaluation, type of treatment received at initial evaluation, daily treatment, and daily sign-in procedures. Results The AT-PBRN had secondary school sites in 7 states, and most athletic trainers at those sites (78.2%) had less than 5 years of experience. The secondary school sites within the AT-PBRN documented 2523 patients treated across 3140 encounters. Patients most frequently sought care for a current injury (61.3%), followed by preventive services (24.0%), and new injuries (14.7%). The most common diagnoses were ankle sprain/strain (17.9%), hip sprain/strain (12.5%), concussion (12.0%), and knee pain (2.5%). The most frequent procedures were athletic trainer evaluation (53.9%), hot- or cold-pack application (26.0%), strapping (10.3%), and therapeutic exercise (5.7%). The median number of treatments per injury was 3 (interquartile range = 2, 4; range = 2–19). Conclusions These preliminary data describe services provided by clinicians within the AT-PBRN and demonstrate the usefulness of the PBRN model for obtaining such data. PMID:23068594

Fostering Earth Observation Regional Networks - Integrative and iterative approaches to capacity building

NASA Astrophysics Data System (ADS)

Habtezion, S.

2015-12-01

Fostering Earth Observation Regional Networks - Integrative and iterative approaches to capacity building Fostering Earth Observation Regional Networks - Integrative and iterative approaches to capacity building Senay Habtezion (shabtezion@start.org) / Hassan Virji (hvirji@start.org)Global Change SySTem for Analysis, Training and Research (START) (www.start.org) 2000 Florida Avenue NW, Suite 200 Washington, DC 20009 USA As part of the Global Observation of Forest and Land Cover Dynamics (GOFC-GOLD) project partnership effort to promote use of earth observations in advancing scientific knowledge, START works to bridge capacity needs related to earth observations (EOs) and their applications in the developing world. GOFC-GOLD regional networks, fostered through the support of regional and thematic workshops, have been successful in (1) enabling participation of scientists for developing countries and from the US to collaborate on key GOFC-GOLD and Land Cover and Land Use Change (LCLUC) issues, including NASA Global Data Set validation and (2) training young developing country scientists to gain key skills in EOs data management and analysis. Members of the regional networks are also engaged and reengaged in other EOs programs (e.g. visiting scientists program; data initiative fellowship programs at the USGS EROS Center and Boston University), which has helped strengthen these networks. The presentation draws from these experiences in advocating for integrative and iterative approaches to capacity building through the lens of the GOFC-GOLD partnership effort. Specifically, this presentation describes the role of the GODC-GOLD partnership in nurturing organic networks of scientists and EOs practitioners in Asia, Africa, Eastern Europe and Latin America.

Fast, Distributed Algorithms in Deep Networks

DTIC Science & Technology

2016-05-11

may not have realized how vital she was in making this project a reality is Professor Crainiceanu. Without knowing who you were, you invited me into...objective function. Training is complete when (2) converges, or stated alternatively , when the difference between t and φL can no longer be...the state-of-the art approaches simply rely on random initialization. We propose an alternative 10 (a) Features in 1-dimensional space (b) Features

Collaborative field research and training in occupational health and ergonomics.

PubMed

Kogi, K

1998-01-01

Networking collaborative research and training in Asian developing countries includes three types of joint activities: field studies of workplace potentials for better safety and health, intensive action training for improvement of working conditions in small enterprises, and action-oriented workshops on low-cost improvements for managers, workers, and farmers. These activities were aimed at identifying workable strategies for making locally adjusted improvements in occupational health and ergonomics. Many improvements have resulted as direct outcomes. Most these improvements were multifaceted, low-cost, and practicable using local skills. Three common features of these interactive processes seem important in facilitating realistic improvements: 1) voluntary approaches building on local achievements; 2) the use of practical methods for identifying multiple improvements; and 3) participatory steps for achieving low-cost results first. The effective use of group work tools is crucial. Stepwise training packages have thus proven useful for promoting local problem-solving interventions based on voluntary initiatives.

Prediction of phycoremediation of As(III) and As(V) from synthetic wastewater by Chlorella pyrenoidosa using artificial neural network

NASA Astrophysics Data System (ADS)

Podder, M. S.; Majumder, C. B.

2017-11-01

An artificial neural network (ANN) model was developed to predict the phycoremediation efficiency of Chlorella pyrenoidosa for the removal of both As(III) and As(V) from synthetic wastewater based on 49 data-sets obtained from experimental study and increased the data using CSCF technique. The data were divided into training (60%) validation (20%) and testing (20%) sets. The data collected was used for training a three-layer feed-forward back propagation (BP) learning algorithm having 4-5-1 architecture. The model used tangent sigmoid transfer function at input to hidden layer ( tansing) while a linear transfer function ( purelin) was used at output layer. Comparison between experimental results and model results gave a high correlation coefficient (R allANN 2 equal to 0.99987 for both ions and exhibited that the model was able to predict the phycoremediation of As(III) and As(V) from wastewater. Experimental parameters influencing phycoremediation process like pH, inoculum size, contact time and initial arsenic concentration [either As(III) or As(V)] were investigated. A contact time of 168 h was mainly required for achieving equilibrium at pH 9.0 with an inoculum size of 10% (v/v). At optimum conditions, metal ion uptake enhanced with increasing initial metal ion concentration.

Impact of real-time fMRI working memory feedback training on the interactions between three core brain networks.

PubMed

Zhang, Qiushi; Zhang, Gaoyan; Yao, Li; Zhao, Xiaojie

2015-01-01

Working memory (WM) refers to the temporary holding and manipulation of information during the performance of a range of cognitive tasks, and WM training is a promising method for improving an individual's cognitive functions. Our previous work demonstrated that WM performance can be improved through self-regulation of dorsal lateral prefrontal cortex (PFC) activation using real-time functional magnetic resonance imaging (rtfMRI), which enables individuals to control local brain activities volitionally according to the neurofeedback. Furthermore, research concerning large-scale brain networks has demonstrated that WM training requires the engagement of several networks, including the central executive network (CEN), the default mode network (DMN) and the salience network (SN), and functional connectivity within the CEN and DMN can be changed by WM training. Although a switching role of the SN between the CEN and DMN has been demonstrated, it remains unclear whether WM training can affect the interactions between the three networks and whether a similar mechanism also exists during the training process. In this study, we investigated the dynamic functional connectivity between the three networks during the rtfMRI feedback training using independent component analysis (ICA) and correlation analysis. The results indicated that functional connectivity within and between the three networks were significantly enhanced by feedback training, and most of the changes were associated with the insula and correlated with behavioral improvements. These findings suggest that the insula plays a critical role in the reorganization of functional connectivity among the three networks induced by rtfMRI training and in WM performance, thus providing new insights into the mechanisms of high-level functions and the clinical treatment of related functional impairments.

Radiology education: a glimpse into the future.

PubMed

Scarsbrook, A F; Graham, R N J; Perriss, R W

2006-08-01

The digital revolution in radiology continues to advance rapidly. There are a number of interesting developments within radiology informatics which may have a significant impact on education and training of radiologists in the near future. These include extended functionality of handheld computers, web-based skill and knowledge assessment, standardization of radiological procedural training using simulated or virtual patients, worldwide videoconferencing via high-quality health networks such as Internet2 and global collaboration of radiological educational resources via comprehensive, multi-national databases such as the medical imaging resource centre initiative of the Radiological Society of North America. This article will explore the role of e-learning in radiology, highlight a number of useful web-based applications in this area, and explain how the current and future technological advances might best be incorporated into radiological training.

Networking for rare diseases: a necessity for Europe.

PubMed

Aymé, S; Schmidtke, J

2007-12-01

Most rare diseases are life-threatening and chronically debilitating conditions, and the vast majority of them are genetically determined. Their individually low prevalence requires special combined efforts to address them so as to improve diagnosis, care and prevention. Though it is difficult to develop a public health policy specific to each rare disease, it is possible to have a global rather than a piecemeal approach in the areas of scientific and biomedical research, drug research and development, industry policy, information and training, social benefits, hospitalisation and outpatient care. In the recent past, several initiatives at EU and Member States levels have been taken and proved efficient in developing suitable solutions which are now having a positive impact on the quality of life of patients. These initiatives are presented here. They include the establishment of Orphanet, a database of rare diseases and orphan drugs providing an encyclopedia of rare diseases and a directory of associated expert services, the funding of research networks to boost the collaboration between research teams, as well as the funding of networks of clinical centres of reference to better serve the patients and contribute to developing clinical research.

The DSFPN, a new neural network for optical character recognition.

PubMed

Morns, L P; Dlay, S S

1999-01-01

A new type of neural network for recognition tasks is presented in this paper. The network, called the dynamic supervised forward-propagation network (DSFPN), is based on the forward only version of the counterpropagation network (CPN). The DSFPN, trains using a supervised algorithm and can grow dynamically during training, allowing subclasses in the training data to be learnt in an unsupervised manner. It is shown to train in times comparable to the CPN while giving better classification accuracies than the popular backpropagation network. Both Fourier descriptors and wavelet descriptors are used for image preprocessing and the wavelets are proven to give a far better performance.

Stochastic associative memory

NASA Astrophysics Data System (ADS)

Baumann, Erwin W.; Williams, David L.

1993-08-01

Artificial neural networks capable of learning and recalling stochastic associations between non-deterministic quantities have received relatively little attention to date. One potential application of such stochastic associative networks is the generation of sensory 'expectations' based on arbitrary subsets of sensor inputs to support anticipatory and investigate behavior in sensor-based robots. Another application of this type of associative memory is the prediction of how a scene will look in one spectral band, including noise, based upon its appearance in several other wavebands. This paper describes a semi-supervised neural network architecture composed of self-organizing maps associated through stochastic inter-layer connections. This 'Stochastic Associative Memory' (SAM) can learn and recall non-deterministic associations between multi-dimensional probability density functions. The stochastic nature of the network also enables it to represent noise distributions that are inherent in any true sensing process. The SAM architecture, training process, and initial application to sensor image prediction are described. Relationships to Fuzzy Associative Memory (FAM) are discussed.

Artificial neural network predictions of lengths of stay on a post-coronary care unit.

PubMed

Mobley, B A; Leasure, R; Davidson, L

1995-01-01

To create and validate a model that predicts length of hospital unit stay. Ex post facto. Seventy-four independent admission variables in 15 general categories were utilized to predict possible stays of 1 to 20 days. Laboratory. Records of patients discharged from a post-coronary care unit in early 1993. An artificial neural network was trained on 629 records and tested on an additional 127 records of patients. The absolute disparity between the actual lengths of stays in the test records and the predictions of the network averaged 1.4 days per record, and the actual length of stay was predicted within 1 day 72% of the time. The artificial neural network demonstrated the capacity to utilize common patient admission characteristics to predict lengths of stay. This technology shows promise in aiding timely initiation of treatment and effective resource planning and cost control.

Cascade Back-Propagation Learning in Neural Networks

NASA Technical Reports Server (NTRS)

Duong, Tuan A.

2003-01-01

The cascade back-propagation (CBP) algorithm is the basis of a conceptual design for accelerating learning in artificial neural networks. The neural networks would be implemented as analog very-large-scale integrated (VLSI) circuits, and circuits to implement the CBP algorithm would be fabricated on the same VLSI circuit chips with the neural networks. Heretofore, artificial neural networks have learned slowly because it has been necessary to train them via software, for lack of a good on-chip learning technique. The CBP algorithm is an on-chip technique that provides for continuous learning in real time. Artificial neural networks are trained by example: A network is presented with training inputs for which the correct outputs are known, and the algorithm strives to adjust the weights of synaptic connections in the network to make the actual outputs approach the correct outputs. The input data are generally divided into three parts. Two of the parts, called the "training" and "cross-validation" sets, respectively, must be such that the corresponding input/output pairs are known. During training, the cross-validation set enables verification of the status of the input-to-output transformation learned by the network to avoid over-learning. The third part of the data, termed the "test" set, consists of the inputs that are required to be transformed into outputs; this set may or may not include the training set and/or the cross-validation set. Proposed neural-network circuitry for on-chip learning would be divided into two distinct networks; one for training and one for validation. Both networks would share the same synaptic weights.

Training product unit neural networks with genetic algorithms

NASA Technical Reports Server (NTRS)

Janson, D. J.; Frenzel, J. F.; Thelen, D. C.

1991-01-01

The training of product neural networks using genetic algorithms is discussed. Two unusual neural network techniques are combined; product units are employed instead of the traditional summing units and genetic algorithms train the network rather than backpropagation. As an example, a neural netork is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima affect the performance of a genetic algorithm, and one method of overcoming this is presented.

The effects of working memory training on functional brain network efficiency.

PubMed

Langer, Nicolas; von Bastian, Claudia C; Wirz, Helen; Oberauer, Klaus; Jäncke, Lutz

2013-10-01

The human brain is a highly interconnected network. Recent studies have shown that the functional and anatomical features of this network are organized in an efficient small-world manner that confers high efficiency of information processing at relatively low connection cost. However, it has been unclear how the architecture of functional brain networks is related to performance in working memory (WM) tasks and if these networks can be modified by WM training. Therefore, we conducted a double-blind training study enrolling 66 young adults. Half of the subjects practiced three WM tasks and were compared to an active control group practicing three tasks with low WM demand. High-density resting-state electroencephalography (EEG) was recorded before and after training to analyze graph-theoretical functional network characteristics at an intracortical level. WM performance was uniquely correlated with power in the theta frequency, and theta power was increased by WM training. Moreover, the better a person's WM performance, the more their network exhibited small-world topology. WM training shifted network characteristics in the direction of high performers, showing increased small-worldness within a distributed fronto-parietal network. Taken together, this is the first longitudinal study that provides evidence for the plasticity of the functional brain network underlying WM. Copyright © 2013 Elsevier Ltd. All rights reserved.

Network Training for a Boy with Learning Disabilities and Behaviours That Challenge

ERIC Educational Resources Information Center

Cooper, Kate; McElwee, Jennifer

2016-01-01

Background: Network Training is an intervention that draws upon systemic ideas and behavioural principles to promote positive change in networks of support for people defined as having a learning disability. To date, there are no published case studies looking at the outcomes of Network Training. Materials and Methods: This study aimed to…

Prediction of β-turns in proteins from multiple alignment using neural network

PubMed Central

Kaur, Harpreet; Raghava, Gajendra Pal Singh

2003-01-01

A neural network-based method has been developed for the prediction of β-turns in proteins by using multiple sequence alignment. Two feed-forward back-propagation networks with a single hidden layer are used where the first-sequence structure network is trained with the multiple sequence alignment in the form of PSI-BLAST–generated position-specific scoring matrices. The initial predictions from the first network and PSIPRED-predicted secondary structure are used as input to the second structure-structure network to refine the predictions obtained from the first net. A significant improvement in prediction accuracy has been achieved by using evolutionary information contained in the multiple sequence alignment. The final network yields an overall prediction accuracy of 75.5% when tested by sevenfold cross-validation on a set of 426 nonhomologous protein chains. The corresponding Qpred, Qobs, and Matthews correlation coefficient values are 49.8%, 72.3%, and 0.43, respectively, and are the best among all the previously published β-turn prediction methods. The Web server BetaTPred2 (http://www.imtech.res.in/raghava/betatpred2/) has been developed based on this approach. PMID:12592033

Adapting and Bending the Portal to the Public: Evaluation of an NSF-Funded Science Communication Model for UNAVCO's Geoscience Summer Internships

NASA Astrophysics Data System (ADS)

Dutilly, E.; Charlevoix, D. J.; Bartel, B. A.

2017-12-01

UNAVCO is a National Science Foundation (NSF) facility specializing in geodesy. As part of its education and outreach work, it operates annual summer internships. In 2016, UNAVCO joined the Portal to the Public (PoP) network and the PoP model was adapted and bent to provide science communication professional development for summer interns. PoP is one way that UNAVCO invests in and trains future generations of geoscientists. The NSF-funded PoP initiative and its network, PoPNet, is a premier outreach framework connecting scientists and public audiences for over a decade. PoPNet is a network of sixty organizations committed to using the PoP method to engage the public in face-to-face interactions with practicing scientists. The PoP initiative provides professional development to scientists focused on best practices in science communication, helps them to develop an interactive exhibit consistent with their current research, and offers them a venue for interacting with the public. No other evaluation work to date has examined how summer internships can uptake the PoP model. This presentation focuses on evaluation findings from two cohorts of summer interns across two years. Three primary domains were assessed: how demographic composition across cohorts required changes to the original PoP framework, which of the PoP professional development trainings were valued (or not) by interns, and changes to intern knowledge, attitudes, and abilities to communicate science. Analyses via surveys and interviews revealed that level of intern geoscience knowledge was a major factor in deciding the focus of the work, specifically whether to create new hands-on exhibits or use existing ones. Regarding the use of PoP trainings, there was no obvious pattern in what interns preferred. Most growth and learning for interns occurred during and after the outreach activity. Results of this evaluation can be used to inform other applications of the PoP approach in summer internships.

Weight-elimination neural networks applied to coronary surgery mortality prediction.

PubMed

Ennett, Colleen M; Frize, Monique

2003-06-01

The objective was to assess the effectiveness of the weight-elimination cost function in improving classification performance of artificial neural networks (ANNs) and to observe how changing the a priori distribution of the training set affects network performance. Backpropagation feedforward ANNs with and without weight-elimination estimated mortality for coronary artery surgery patients. The ANNs were trained and tested on cases with 32 input variables describing the patient's medical history; the output variable was in-hospital mortality (mortality rates: training 3.7%, test 3.8%). Artificial training sets with mortality rates of 20%, 50%, and 80% were created to observe the impact of training with a higher-than-normal prevalence. When the results were averaged, weight-elimination networks achieved higher sensitivity rates than those without weight-elimination. Networks trained on higher-than-normal prevalence achieved higher sensitivity rates at the cost of lower specificity and correct classification. The weight-elimination cost function can improve the classification performance when the network is trained with a higher-than-normal prevalence. A network trained with a moderately high artificial mortality rate (artificial mortality rate of 20%) can improve the sensitivity of the model without significantly affecting other aspects of the model's performance. The ANN mortality model achieved comparable performance as additive and statistical models for coronary surgery mortality estimation in the literature.

Musical training induces functional and structural auditory-motor network plasticity in young adults.

PubMed

Li, Qiongling; Wang, Xuetong; Wang, Shaoyi; Xie, Yongqi; Li, Xinwei; Xie, Yachao; Li, Shuyu

2018-05-01

Playing music requires a strong coupling of perception and action mediated by multimodal integration of brain regions, which can be described as network connections measured by anatomical and functional correlations between regions. However, the structural and functional connectivities within and between the auditory and sensorimotor networks after long-term musical training remain largely uninvestigated. Here, we compared the structural connectivity (SC) and resting-state functional connectivity (rs-FC) within and between the two networks in 29 novice healthy young adults before and after musical training (piano) with those of another 27 novice participants who were evaluated longitudinally but with no intervention. In addition, a correlation analysis was performed between the changes in FC or SC with practice time in the training group. As expected, participants in the training group showed increased FC within the sensorimotor network and increased FC and SC of the auditory-motor network after musical training. Interestingly, we further found that the changes in FC within the sensorimotor network and SC of the auditory-motor network were positively correlated with practice time. Our results indicate that musical training could induce enhanced local interaction and global integration between musical performance-related regions, which provides insights into the mechanism of brain plasticity in young adults. © 2018 Wiley Periodicals, Inc.

Training for the challenges of sexual violence against children and adolescents in four Brazilian capitals.

PubMed

Vieira, Luiza Jane Eyre de Souza; Silva, Raimunda Magalhães da; Cavalcanti, Ludmila Fontenele; Deslandes, Suely Ferreira

2015-11-01

This article analyzes the training offered to municipal public employees to confront sexual violence against children and adolescents in four Brazilian capitals. Based on a multiple case study, it focuses on the training programs offered in the 2010-2011 biennium by the municipal government for professionals and managers in the public health network. We analyzed 66 semi-structured interviews and written documents pertaining to the training actions. We observed an unequal investment among the capitals and a lack of specificity in the treatment of the themes. There is a considerable lack of institutional memory which complicates the analysis of professional training strategies. Healthcare was the field which trained their professionals the most, including the subject of notification in training content. We noted little investment in training oriented toward the prevention of violence and the promotion of protective relationships and links. We emphasized the inductive role of federal and state programs in the areas of Tourism and Education. Few initiatives included the participation of more than one public sector. We suggest the creation of a training plan about violence and the sexual rights of children and adolescents, and in particular about sexual violence.

Reorganization of functional brain networks mediates the improvement of cognitive performance following real-time neurofeedback training of working memory.

PubMed

Zhang, Gaoyan; Yao, Li; Shen, Jiahui; Yang, Yihong; Zhao, Xiaojie

2015-05-01

Working memory (WM) is essential for individuals' cognitive functions. Neuroimaging studies indicated that WM fundamentally relied on a frontoparietal working memory network (WMN) and a cinguloparietal default mode network (DMN). Behavioral training studies demonstrated that the two networks can be modulated by WM training. Different from the behavioral training, our recent study used a real-time functional MRI (rtfMRI)-based neurofeedback method to conduct WM training, demonstrating that WM performance can be significantly improved after successfully upregulating the activity of the target region of interest (ROI) in the left dorsolateral prefrontal cortex (Zhang et al., [2013]: PloS One 8:e73735); however, the neural substrate of rtfMRI-based WM training remains unclear. In this work, we assessed the intranetwork and internetwork connectivity changes of WMN and DMN during the training, and their correlations with the change of brain activity in the target ROI as well as with the improvement of post-training behavior. Our analysis revealed an "ROI-network-behavior" correlation relationship underlying the rtfMRI training. Further mediation analysis indicated that the reorganization of functional brain networks mediated the effect of self-regulation of the target brain activity on the improvement of cognitive performance following the neurofeedback training. The results of this study enhance our understanding of the neural basis of real-time neurofeedback and suggest a new direction to improve WM performance by regulating the functional connectivity in the WM related networks. © 2014 Wiley Periodicals, Inc.

Process Control Strategies for Dual-Phase Steel Manufacturing Using ANN and ANFIS

NASA Astrophysics Data System (ADS)

Vafaeenezhad, H.; Ghanei, S.; Seyedein, S. H.; Beygi, H.; Mazinani, M.

2014-11-01

In this research, a comprehensive soft computational approach is presented for the analysis of the influencing parameters on manufacturing of dual-phase steels. A set of experimental data have been gathered to obtain the initial database used for the training and testing of both artificial neural networks (ANN) and adaptive neuro-fuzzy inference system (ANFIS). The parameters used in the strategy were intercritical annealing temperature, carbon content, and holding time which gives off martensite percentage as an output. A fraction of the data set was chosen to train both ANN and ANFIS, and the rest was put into practice to authenticate the act of the trained networks while seeing unseen data. To compare the obtained results, coefficient of determination and root mean squared error indexes were chosen. Using artificial intelligence methods, it is not necessary to consider and establish a preliminary mathematical model and formulate its affecting parameters on its definition. In conclusion, the martensite percentages corresponding to the manufacturing parameters can be determined prior to a production using these controlling algorithms. Although the results acquired from both ANN and ANFIS are very encouraging, the proposed ANFIS has enhanced performance over the ANN and takes better effect on cost-reduction profit.

Astronomy Landscape in Africa

NASA Astrophysics Data System (ADS)

Nemaungani, Takalani

2015-01-01

The vision for astronomy in Africa is embedded in the African Space Policy of the African Union in early 2014. The vision is about positioning Africa as an emerging hub for astronomy sciences and facilities. Africa recognized the need to take advantage of its natural resource, the geographical advantage of the clear southern skies and pristine sites for astronomy. The Pan African University (PAU) initiative also presents an opportunity as a post-graduate training and research network of university nodes in five regions of Africa and supported by the African Union. The Southern African node based in South Africa concentrates on space sciences which also includes astronomy. The PAU aims to provide the opportunity for advanced graduate training and postgraduate research to high-performing African students. Objectives also include promoting mobility of students and teachers and harmonizing programs and degrees.A number of astronomy initiatives have burgeoned in the Southern African region and these include the Southern Africa Largest Optical Telescope (SALT), HESS (High Energy Stereoscopic System), the SKA (Square Kilometre Array) and the AVN (African Very Long Baseline Interferometer Network). There is a growing appetite for astronomy sciences in Africa. In East Africa, the astronomy community is well organized and is growing - the East African Astronomical society (EAAS) held its successful fourth annual conference since 2010 on 30 June to 04 July 2014 at the University of Rwanda. Centred around the 'Role of Astronomy in Socio-Economic Transformation,' this conference aimed at strengthening capacity building in Astronomy, Astrophysics and Space Science in general, while providing a forum for astronomers from the region to train young and upcoming scientists.

Distributed computing methodology for training neural networks in an image-guided diagnostic application.

PubMed

Plagianakos, V P; Magoulas, G D; Vrahatis, M N

2006-03-01

Distributed computing is a process through which a set of computers connected by a network is used collectively to solve a single problem. In this paper, we propose a distributed computing methodology for training neural networks for the detection of lesions in colonoscopy. Our approach is based on partitioning the training set across multiple processors using a parallel virtual machine. In this way, interconnected computers of varied architectures can be used for the distributed evaluation of the error function and gradient values, and, thus, training neural networks utilizing various learning methods. The proposed methodology has large granularity and low synchronization, and has been implemented and tested. Our results indicate that the parallel virtual machine implementation of the training algorithms developed leads to considerable speedup, especially when large network architectures and training sets are used.

Modeling Self-Healing of Concrete Using Hybrid Genetic Algorithm–Artificial Neural Network

PubMed Central

Ramadan Suleiman, Ahmed; Nehdi, Moncef L.

2017-01-01

This paper presents an approach to predicting the intrinsic self-healing in concrete using a hybrid genetic algorithm–artificial neural network (GA–ANN). A genetic algorithm was implemented in the network as a stochastic optimizing tool for the initial optimal weights and biases. This approach can assist the network in achieving a global optimum and avoid the possibility of the network getting trapped at local optima. The proposed model was trained and validated using an especially built database using various experimental studies retrieved from the open literature. The model inputs include the cement content, water-to-cement ratio (w/c), type and dosage of supplementary cementitious materials, bio-healing materials, and both expansive and crystalline additives. Self-healing indicated by means of crack width is the model output. The results showed that the proposed GA–ANN model is capable of capturing the complex effects of various self-healing agents (e.g., biochemical material, silica-based additive, expansive and crystalline components) on the self-healing performance in cement-based materials. PMID:28772495

Combined neural network/Phillips-Tikhonov approach to aerosol retrievals over land from the NASA Research Scanning Polarimeter

NASA Astrophysics Data System (ADS)

Di Noia, Antonio; Hasekamp, Otto P.; Wu, Lianghai; van Diedenhoven, Bastiaan; Cairns, Brian; Yorks, John E.

2017-11-01

In this paper, an algorithm for the retrieval of aerosol and land surface properties from airborne spectropolarimetric measurements - combining neural networks and an iterative scheme based on Phillips-Tikhonov regularization - is described. The algorithm - which is an extension of a scheme previously designed for ground-based retrievals - is applied to measurements from the Research Scanning Polarimeter (RSP) on board the NASA ER-2 aircraft. A neural network, trained on a large data set of synthetic measurements, is applied to perform aerosol retrievals from real RSP data, and the neural network retrievals are subsequently used as a first guess for the Phillips-Tikhonov retrieval. The resulting algorithm appears capable of accurately retrieving aerosol optical thickness, fine-mode effective radius and aerosol layer height from RSP data. Among the advantages of using a neural network as initial guess for an iterative algorithm are a decrease in processing time and an increase in the number of converging retrievals.

Modeling Self-Healing of Concrete Using Hybrid Genetic Algorithm-Artificial Neural Network.

PubMed

Ramadan Suleiman, Ahmed; Nehdi, Moncef L

2017-02-07

This paper presents an approach to predicting the intrinsic self-healing in concrete using a hybrid genetic algorithm-artificial neural network (GA-ANN). A genetic algorithm was implemented in the network as a stochastic optimizing tool for the initial optimal weights and biases. This approach can assist the network in achieving a global optimum and avoid the possibility of the network getting trapped at local optima. The proposed model was trained and validated using an especially built database using various experimental studies retrieved from the open literature. The model inputs include the cement content, water-to-cement ratio (w/c), type and dosage of supplementary cementitious materials, bio-healing materials, and both expansive and crystalline additives. Self-healing indicated by means of crack width is the model output. The results showed that the proposed GA-ANN model is capable of capturing the complex effects of various self-healing agents (e.g., biochemical material, silica-based additive, expansive and crystalline components) on the self-healing performance in cement-based materials.

Meeting information needs in health policy and public health: priorities for the National Library of Medicine and The National Network of Libraries of Medicine.

PubMed

Humphreys, B L

1998-12-01

Those seeking information in health policy and public health are not as well served as those seeking clinical information. Problems inhibiting access to health policy and public health information include the heterogeneity of professionals seeking the information, the distribution of relevant information across disciplines and information sources, scarcity of synthesized information useful to practitioners, lack of awareness of available services or training in their use, and lack of access to information technology or to knowledgeable librarians and information specialists. Since 1990, the National Library of Medicine and the National Network of Libraries of Medicine have been working to enhance information services in health policy and public health through expanding the coverage of the NLM collection, building new databases, and engaging in targeted outreach and training initiatives directed toward segments of the health policy and public health communities. Progress has been made, but more remains to be done. Recommendations arising from the meeting, Accessing Useful Information: Challenges in Health Policy and Public Health, will help NLM and the National Network of Libraries of Medicine to establish priorities and action plans for the next several years.

Humane Education in Brazil: Organisation, Challenges and Opportunities.

PubMed

Bachinski, Róber; Tréz, Thales; Alves, Gutemberg G; de C M Garcia, Rita; Oliveira, Simone T; da S Alonso, Luciano; Heck, Júlio X; Dias, Claudia M C; Costa Neto, João M; Rocha, Alexandro A; Ruiz, Valeska R R; Paixão, Rita L

2015-11-01

Humane education and the debate on alternatives to harmful animal use for training is a relatively recent issue in Brazil. While animal use in secondary education has been illegal since the late 1970s, animal use in higher science education is widespread. However, alternatives to animal experiments in research and testing have recently received attention from the Government, especially after the first legislation on animal experiments was passed, in 2008. This article proposes that higher science education should be based on a critical and humane approach. It outlines the recent establishment of the Brazilian Network for Humane Education (RedEH), as a result of the project, Mapping Animal Use for Undergraduate Education in Brazil, which was recognised by the 2014 Lush Prize. The network aims to create a platform to promote change in science education in Brazil, starting by quantitatively and qualitatively understanding animal use, developing new approaches adapted to the current needs in Brazil and Latin America, and communicating these initiatives nationally. This paper explores the trajectory of alternatives and replacement methods to harmful animal use in training and education, as well as the status of humane education in Brazil, from the point of view of educators and researchers engaged with the network.

An analysis of image storage systems for scalable training of deep neural networks

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

Lim, Seung-Hwan; Young, Steven R; Patton, Robert M

This study presents a principled empirical evaluation of image storage systems for training deep neural networks. We employ the Caffe deep learning framework to train neural network models for three different data sets, MNIST, CIFAR-10, and ImageNet. While training the models, we evaluate five different options to retrieve training image data: (1) PNG-formatted image files on local file system; (2) pushing pixel arrays from image files into a single HDF5 file on local file system; (3) in-memory arrays to hold the pixel arrays in Python and C++; (4) loading the training data into LevelDB, a log-structured merge tree based key-valuemore » storage; and (5) loading the training data into LMDB, a B+tree based key-value storage. The experimental results quantitatively highlight the disadvantage of using normal image files on local file systems to train deep neural networks and demonstrate reliable performance with key-value storage based storage systems. When training a model on the ImageNet dataset, the image file option was more than 17 times slower than the key-value storage option. Along with measurements on training time, this study provides in-depth analysis on the cause of performance advantages/disadvantages of each back-end to train deep neural networks. We envision the provided measurements and analysis will shed light on the optimal way to architect systems for training neural networks in a scalable manner.« less

Prediction and Optimization of Key Performance Indicators in the Production of Stator Core Using a GA-NN Approach

NASA Astrophysics Data System (ADS)

Rajora, M.; Zou, P.; Xu, W.; Jin, L.; Chen, W.; Liang, S. Y.

2017-12-01

With the rapidly changing demands of the manufacturing market, intelligent techniques are being used to solve engineering problems due to their ability to handle nonlinear complex problems. For example, in the conventional production of stator cores, it is relied upon experienced engineers to make an initial plan on the number of compensation sheets to be added to achieve uniform pressure distribution throughout the laminations. Additionally, these engineers must use their experience to revise the initial plans based upon the measurements made during the production of stator core. However, this method yields inconsistent results as humans are incapable of storing and analysing large amounts of data. In this article, first, a Neural Network (NN), trained using a hybrid Levenberg-Marquardt (LM) - Genetic Algorithm (GA), is developed to assist the engineers with the decision-making process. Next, the trained NN is used as a fitness function in an optimization algorithm to find the optimal values of the initial compensation sheet plan with the aim of minimizing the required revisions during the production of the stator core.

Public health initiatives in South Africa in the 1940s and 1950s: lessons for a post-apartheid era.

PubMed

Yach, D; Tollman, S M

1993-07-01

Inspiration drawn from South African public health initiatives in the 1940s played an important role in the development of the network of community and migrant health centers in the United States. The first such center at Pholela in Natal emphasized the need for a comprehensive (preventive and curative) service that based its practices on empirical data derived from epidemiological and anthropological research. In addition, community consultation preceded the introduction of new service or research initiatives. The Institute of Family and Community Health in Durban pioneered community-based multidisciplinary training and developed Pholela and other sites as centers for service, teaching, and research. Several important lessons for South African health professionals emerge from the Pholela experience. First, public health models of the past need to be reintroduced locally; second, the training of public health professionals needs to be upgraded and reoriented; third, appropriate research programs need to respond to community needs and address service demands; fourth, community involvement strategies need to be implemented early on; and fifth, funding sources for innovation in health service provision should be sought.

Learning and diagnosing faults using neural networks

NASA Technical Reports Server (NTRS)

Whitehead, Bruce A.; Kiech, Earl L.; Ali, Moonis

1990-01-01

Neural networks have been employed for learning fault behavior from rocket engine simulator parameters and for diagnosing faults on the basis of the learned behavior. Two problems in applying neural networks to learning and diagnosing faults are (1) the complexity of the sensor data to fault mapping to be modeled by the neural network, which implies difficult and lengthy training procedures; and (2) the lack of sufficient training data to adequately represent the very large number of different types of faults which might occur. Methods are derived and tested in an architecture which addresses these two problems. First, the sensor data to fault mapping is decomposed into three simpler mappings which perform sensor data compression, hypothesis generation, and sensor fusion. Efficient training is performed for each mapping separately. Secondly, the neural network which performs sensor fusion is structured to detect new unknown faults for which training examples were not presented during training. These methods were tested on a task of fault diagnosis by employing rocket engine simulator data. Results indicate that the decomposed neural network architecture can be trained efficiently, can identify faults for which it has been trained, and can detect the occurrence of faults for which it has not been trained.

Airway reopening through catastrophic events in a hierarchical network

PubMed Central

Baudoin, Michael; Song, Yu; Manneville, Paul; Baroud, Charles N.

2013-01-01

When you reach with your straw for the final drops of a milkshake, the liquid forms a train of plugs that flow slowly initially because of the high viscosity. They then suddenly rupture and are replaced with a rapid airflow with the characteristic slurping sound. Trains of liquid plugs also are observed in complex geometries, such as porous media during petroleum extraction, in microfluidic two-phase flows, or in flows in the pulmonary airway tree under pathological conditions. The dynamics of rupture events in these geometries play the dominant role in the spatial distribution of the flow and in determining how much of the medium remains occluded. Here we show that the flow of a train of plugs in a straight channel is always unstable to breaking through a cascade of ruptures. Collective effects considerably modify the rupture dynamics of plug trains: Interactions among nearest neighbors take place through the wetting films and slow down the cascade, whereas global interactions, through the total resistance to flow of the train, accelerate the dynamics after each plug rupture. In a branching tree of microchannels, similar cascades occur along paths that connect the input to a particular output. This divides the initial tree into several independent subnetworks, which then evolve independently of one another. The spatiotemporal distribution of the cascades is random, owing to strong sensitivity to the plug divisions at the bifurcations. PMID:23277557

Improving the peer review skills of young rheumatologists and researchers in rheumatology: the EMEUNET Peer Review Mentoring Program.

PubMed

Rodríguez-Carrio, Javier; Putrik, Polina; Sepriano, Alexandre; Moltó, Anna; Nikiphorou, Elena; Gossec, Laure; Kvien, Tore K; Ramiro, Sofia

2018-01-01

Although peer review plays a central role in the maintenance of high standards in scientific research, training of reviewing skills is not included in the common education programmes. The Emerging EULAR (European League Against Rheumatism) Network (EMEUNET) developed a programme to address this unmet need. The EMEUNET Peer Review Mentoring Program for Rheumatology Journals promotes a systematic training of reviewing skills by engaging mentees in a 'real world' peer review experience supervised by experienced mentors with support from rheumatology journals. This viewpoint provides an overview of this initiative and its outcomes, and discusses its potential limitations. Over 4 years, 18 mentors and 86 mentees have participated. Among the 33 participants who have completed the programme, 13 (39.3%) have become independent reviewers for Annals of the Rheumatic Diseases after the training. This programme has been recently evaluated by a survey and qualitative interviews, revealing a high interest in this initiative. The main strengths (involvement of a top journal and learning opportunities) and weaknesses of the programme (limited number of places and insufficient dissemination) were identified. Overall, this programme represents an innovative and successful approach to peer review training. Continuous evaluation and improvement are key to its functioning. The EMEUNET Peer Review Mentoring Program may be used as a reference for peer review training in areas outside rheumatology.

Regional approach to building operational level capacity for disaster planning: the case of the Eastern Africa region.

PubMed

Bazeyo, W; Mayega, R W; Orach, G C; Kiguli, J; Mamuya, S; Tabu, J S; Sena, L; Rugigana, E; Mapatano, M; Lewy, D; Mock, N; Burnham, G; Keim, M; Killewo, J

2013-06-01

The Eastern Africa region is regularly affected by a variety of disasters ranging from drought, to human conflict and population displacement. The magnitude of emergencies and response capacities is similar across the region. In order to strengthen public health disaster management capacities at the operational level in six countries of the Eastern Africa region, the USAID-funded leadership project worked through the HEALTH Alliance, a network of seven schools of public health from six countries in the region to train district-level teams. To develop a sustainable regional approach to building operational level capacity for disaster planning. This project was implemented through a higher education leadership initiative. Project activities were spear-headed by a network of Deans and Directors of public health schools within local universities in the Eastern Africa region. The leadership team envisioned a district-oriented systems change strategy. Pre-service and in-service curricula were developed regionally and district teams were formed to attend short training courses. Project activities began with a situational analysis of the disaster management capacity at national and operational levels. The next steps were chronologically the formation of country training teams and training of trainers, the development of a regional disaster management training curriculum and training materials, the cascading of training activities in the region, and the incorporation of emerging issues into the training curriculum. An evaluation model included the analysis of preparedness impact of the training program. The output from the district teams was the creation of individual district-level disaster plans and their implementation. This 4-year project focused on building operational level public health emergency response capacity, which had not previously been part of any national program. Use of the all-hazard approach rather than a scenario-based contingency planning led to the development of a standardized curriculum for training both in-service and pre-service personnel. Materials developed during the implementation phases of the project have been incorporated into public health graduate curricula in the seven schools. This systems-based strategy resulted in demonstrable outcomes related to district preparedness and university engagement in disaster management. University partnerships are an effective method to build district-level disaster planning capacity. Use of a regional network created a standardized approach across six countries.

Application of Particle Swarm Optimization Algorithm for Optimizing ANN Model in Recognizing Ripeness of Citrus

NASA Astrophysics Data System (ADS)

Diyana Rosli, Anis; Adenan, Nur Sabrina; Hashim, Hadzli; Ezan Abdullah, Noor; Sulaiman, Suhaimi; Baharudin, Rohaiza

2018-03-01

This paper shows findings of the application of Particle Swarm Optimization (PSO) algorithm in optimizing an Artificial Neural Network that could categorize between ripeness and unripeness stage of citrus suhuensis. The algorithm would adjust the network connections weights and adapt its values during training for best results at the output. Initially, citrus suhuensis fruit’s skin is measured using optically non-destructive method via spectrometer. The spectrometer would transmit VIS (visible spectrum) photonic light radiation to the surface (skin of citrus) of the sample. The reflected light from the sample’s surface would be received and measured by the same spectrometer in terms of reflectance percentage based on VIS range. These measured data are used to train and test the best optimized ANN model. The accuracy is based on receiver operating characteristic (ROC) performance. The result outcomes from this investigation have shown that the achieved accuracy for the optimized is 70.5% with a sensitivity and specificity of 60.1% and 80.0% respectively.

Plastic Surgery Response in Natural Disasters.

PubMed

Chung, Susan; Zimmerman, Amanda; Gaviria, Andres; Dayicioglu, Deniz

2015-06-01

Disasters cause untold damage and are often unpredictable; however, with proper preparation, these events can be better managed. The initial response has the greatest impact on the overall success of the relief effort. A well-trained multidisciplinary network of providers is necessary to ensure coordinated care for the victims of these mass casualty disasters. As members of this network of providers, plastic surgeons have the ability to efficiently address injuries sustained in mass casualty disasters and are a valuable member of the relief effort. The skill set of plastic surgeons includes techniques that can address injuries sustained in large-scale emergencies, such as the management of soft-tissue injury, tissue viability, facial fractures, and extremity salvage. An approach to disaster relief, the types of disasters encountered, the management of injuries related to mass casualty disasters, the role of plastic surgeons in the relief effort, and resource management are discussed. In order to improve preparedness in future mass casualty disasters, plastic surgeons should receive training during residency regarding the utilization of plastic surgery knowledge in the disaster setting.

Neurofeedback and networks of depression

PubMed Central

Linden, David E. J.

2014-01-01

Recent advances in imaging technology and in the understanding of neural circuits relevant to emotion, motivation, and depression have boosted interest and experimental work in neuromodulation for affective disorders. Real-time functional magnetic resonance imaging (fMRI) can be used to train patients in the self regulation of these circuits, and thus complement existing neurofeedback technologies based on electroencephalography (EEG). EEG neurofeedback for depression has mainly been based on models of altered hemispheric asymmetry. fMRI-based neurofeedback (fMRI-NF) can utilize functional localizer scans that allow the dynamic adjustment of the target areas or networks for self-regulation training to individual patterns of emotion processing. An initial application of fMRI-NF in depression has produced promising clinical results, and further clinical trials are under way. Challenges lie in the design of appropriate control conditions for rigorous clinical trials, and in the transfer of neurofeedback protocols from the laboratory to mobile devices to enhance the sustainability of any clinical benefits. PMID:24733975

Increasing Use of Postpartum Family Planning and the Postpartum IUD: Early Experiences in West and Central Africa

PubMed Central

Pleah, Tsigue; Hyjazi, Yolande; Austin, Suzanne; Diallo, Abdoulaye; Dao, Blami; Waxman, Rachel; Karna, Priya

2016-01-01

ABSTRACT A global resurgence of interest in the intrauterine device (IUD) as an effective long-acting reversible contraceptive and in improving access to a wide range of contraceptive methods, as well as an emphasis on encouraging women to give birth in health care facilities, has led programs to introduce postpartum IUD (PPIUD) services into postpartum family planning (PPFP) programs. We describe strategic, organizational, and technical elements that contributed to early successes of a regional initiative in West and Central Africa to train antenatal, maternity, and postnatal care providers in PPFP counseling for the full range of available methods and in PPIUD service delivery. In November 2013, the initiative provided competency-based training in Guinea for providers from the main public teaching hospital in 5 selected countries (Benin, Chad, Côte d’Ivoire, Niger, and Senegal) with no prior PPFP counseling or PPIUD capacity. The training was followed by a transfer-of-learning visit and monitoring to support the trained providers. One additional country, Togo, replicated the initiative’s model in 2014. Although nascent, this initiative has introduced high-quality PPFP and PPIUD services to the region, where less than 1% of married women of reproductive age use the IUD. In total, 21 providers were trained in PPFP counseling, 18 of whom were also trained in PPIUD insertion. From 2014 to 2015, more than 15,000 women were counseled about PPFP, and 2,269 women chose and received the PPIUD in Benin, Côte d’Ivoire, Niger, Senegal, and Togo. (Introduction of PPIUD services in Chad has been delayed.) South–South collaboration has been central to the initiative’s accomplishments: Guinea’s clinical centers of excellence and qualified trainers provided a culturally resonant example of a PPFP/PPIUD program, and trainings are creating a network of regional trainers to facilitate expansion. Two of the selected countries (Benin and Niger) have expanded their PPFP/PPUID training programs to additional sites. Inspired after learning about the initiative at a regional meeting, Togo has outperformed the original countries involved in the initiative by training more providers than the other countries. Challenges to scale-up include a lack of formal channels for reporting PPFP and PPIUD service delivery outcomes, inconsistent coordination of services across the reproductive health continuum of care, and slow uptake in some countries. Continued success will rely on careful recordkeeping, regular monitoring and feedback, and strategic data use to advocate scale-up. PMID:27540120

Classification of E-Nose Aroma Data of Four Fruit Types by ABC-Based Neural Network

PubMed Central

Adak, M. Fatih; Yumusak, Nejat

2016-01-01

Electronic nose technology is used in many areas, and frequently in the beverage industry for classification and quality-control purposes. In this study, four different aroma data (strawberry, lemon, cherry, and melon) were obtained using a MOSES II electronic nose for the purpose of fruit classification. To improve the performance of the classification, the training phase of the neural network with two hidden layers was optimized using artificial bee colony algorithm (ABC), which is known to be successful in exploration. Test data were given to two different neural networks, each of which were trained separately with backpropagation (BP) and ABC, and average test performances were measured as 60% for the artificial neural network trained with BP and 76.39% for the artificial neural network trained with ABC. Training and test phases were repeated 30 times to obtain these average performance measurements. This level of performance shows that the artificial neural network trained with ABC is successful in classifying aroma data. PMID:26927124

Classification of E-Nose Aroma Data of Four Fruit Types by ABC-Based Neural Network.

PubMed

Adak, M Fatih; Yumusak, Nejat

2016-02-27

Electronic nose technology is used in many areas, and frequently in the beverage industry for classification and quality-control purposes. In this study, four different aroma data (strawberry, lemon, cherry, and melon) were obtained using a MOSES II electronic nose for the purpose of fruit classification. To improve the performance of the classification, the training phase of the neural network with two hidden layers was optimized using artificial bee colony algorithm (ABC), which is known to be successful in exploration. Test data were given to two different neural networks, each of which were trained separately with backpropagation (BP) and ABC, and average test performances were measured as 60% for the artificial neural network trained with BP and 76.39% for the artificial neural network trained with ABC. Training and test phases were repeated 30 times to obtain these average performance measurements. This level of performance shows that the artificial neural network trained with ABC is successful in classifying aroma data.

Workshop: Western hemisphere network of bird banding programs

USGS Publications Warehouse

Celis-Murillo, A.

2007-01-01

Purpose: To promote collaboration among banding programs in the Americas. Introduction: Bird banding and marking provide indispensable tools for ornithological research, management, and conservation of migratory birds on migratory routes, breeding and non-breeding grounds. Many countries and organizations in Latin America and the Caribbean are in the process of developing or have expressed interest in developing national banding schemes and databases to support their research and management programs. Coordination of developing and existing banding programs is essential for effective data management, reporting, archiving and security, and most importantly, for gaining a fuller understanding of migratory bird conservation issues and how the banding data can help. Currently, there is a well established bird-banding program in the U.S.A. and Canada, and programs in other countries are being developed as well. Ornithologists in many Latin American countries and the Caribbean are interested in using banding and marking in their research programs. Many in the ornithological community are interested in establishing banding schemes and some countries have recently initiated independent banding programs. With the number of long term collaborative and international initiatives increasing, the time is ripe to discuss and explore opportunities for international collaboration, coordination, and administration of bird banding programs in the Western Hemisphere. We propose the second ?Western Hemisphere Network of Bird Banding Programs? workshop, in association with the SCSCB, to be an essential step in the progress to strengthen international partnerships and support migratory bird conservation in the Americas and beyond. This will be the second multi-national meeting to promote collaboration among banding programs in the Americas (the first meeting was held in October 8-9, 2006 in La Mancha, Veracruz, Mexico). The Second ?Western Hemisphere Network of Bird Banding Programs? workshop will continue addressing issues surrounding the coordination of an Americas? approach to bird banding and will review in detail the advances made on the first workshop such as, coordination of bands and markers, coordination in recovery reporting, permit issues, data management and data sharing and archiving, data security, training, etc. Workshop Goals: Build on accomplishments of the network?s first workshop (Oct 8-9, 2006). Identify and explore new opportunities for data sharing, data archiving, data access, training, etc. Initiate strategies to support international collaboration and coordination amongst bird banding programs in the Western Hemisphere. Workshop structure: One day workshop of guided discussions. Participants: Representatives of government agencies, program managers and NGOs.

A Network Flow Approach to the Initial Skills Training Scheduling Problem

DTIC Science & Technology

2007-12-01

include (but are not limited to) queuing theory, stochastic analysis and simulation. After the demand schedule has been estimated, it can be ...software package has already been purchased and is in use by AFPC, AFPC has requested that the new algorithm be programmed in this language as well ...the discussed outputs from those schedules. Required Inputs A single input file details the students to be scheduled as well as the courses

A generalized LSTM-like training algorithm for second-order recurrent neural networks

PubMed Central

Monner, Derek; Reggia, James A.

2011-01-01

The Long Short Term Memory (LSTM) is a second-order recurrent neural network architecture that excels at storing sequential short-term memories and retrieving them many time-steps later. LSTM’s original training algorithm provides the important properties of spatial and temporal locality, which are missing from other training approaches, at the cost of limiting it’s applicability to a small set of network architectures. Here we introduce the Generalized Long Short-Term Memory (LSTM-g) training algorithm, which provides LSTM-like locality while being applicable without modification to a much wider range of second-order network architectures. With LSTM-g, all units have an identical set of operating instructions for both activation and learning, subject only to the configuration of their local environment in the network; this is in contrast to the original LSTM training algorithm, where each type of unit has its own activation and training instructions. When applied to LSTM architectures with peephole connections, LSTM-g takes advantage of an additional source of back-propagated error which can enable better performance than the original algorithm. Enabled by the broad architectural applicability of LSTM-g, we demonstrate that training recurrent networks engineered for specific tasks can produce better results than single-layer networks. We conclude that LSTM-g has the potential to both improve the performance and broaden the applicability of spatially and temporally local gradient-based training algorithms for recurrent neural networks. PMID:21803542

PSFGAN: a generative adversarial network system for separating quasar point sources and host galaxy light

NASA Astrophysics Data System (ADS)

Stark, Dominic; Launet, Barthelemy; Schawinski, Kevin; Zhang, Ce; Koss, Michael; Turp, M. Dennis; Sartori, Lia F.; Zhang, Hantian; Chen, Yiru; Weigel, Anna K.

2018-06-01

The study of unobscured active galactic nuclei (AGN) and quasars depends on the reliable decomposition of the light from the AGN point source and the extended host galaxy light. The problem is typically approached using parametric fitting routines using separate models for the host galaxy and the point spread function (PSF). We present a new approach using a Generative Adversarial Network (GAN) trained on galaxy images. We test the method using Sloan Digital Sky Survey r-band images with artificial AGN point sources added that are then removed using the GAN and with parametric methods using GALFIT. When the AGN point source is more than twice as bright as the host galaxy, we find that our method, PSFGAN, can recover point source and host galaxy magnitudes with smaller systematic error and a lower average scatter (49 per cent). PSFGAN is more tolerant to poor knowledge of the PSF than parametric methods. Our tests show that PSFGAN is robust against a broadening in the PSF width of ± 50 per cent if it is trained on multiple PSFs. We demonstrate that while a matched training set does improve performance, we can still subtract point sources using a PSFGAN trained on non-astronomical images. While initial training is computationally expensive, evaluating PSFGAN on data is more than 40 times faster than GALFIT fitting two components. Finally, PSFGAN is more robust and easy to use than parametric methods as it requires no input parameters.

NASA's Indigenous Capacity Building Initiative: Balancing Traditional Knowledge and Existing Remote Sensing Training to Inform Management Decisions

NASA Astrophysics Data System (ADS)

McCullum, A. J. K.; Schmidt, C.; Palacios, S. L.; Ly, V.

2017-12-01

NASA's Indigenous Capacity Building Initiative is aimed to provide remote sensing training, mentoring, and research opportunities to the indigenous community. A key programmatic goal is the co-production of place-based trainings where participants have the opportunity to address specific natural resource research and management issues facing their tribal lands. Three primary strategies have been adopted to engage with our tribal partners, these include: (1) the use of existing tribal networks and conferences such as the National Tribal GIS Conference, (2) coordination with other federal agencies such as the Bureau of Indian Affairs (BIA) and tribal liaisons at regional Climate Science Centers, and (3) connecting with tribes directly. Regional partner visits with tribes, such as meetings with the Samish Indian Nation, are integral to cultivate trusting, collaborative, and sustained partnerships and an understanding of how Earth Observations can be applied to the unique set of challenges and goals each tribe faces. As the program continues to grow, we aim to increase our incorporation of Traditional Ecological Knowledge (TEK) into technical methods and to develop trainings tailored to thematic areas of interest to specific tribes. Engagement and feedback are encouraged to refine our approaches to increase capacity within the indigenous community to utilize NASA Earth Observations.

Initiation of bladder voiding with epidural stimulation in paralyzed, step trained rats.

PubMed

Gad, Parag N; Roy, Roland R; Zhong, Hui; Lu, Daniel C; Gerasimenko, Yury P; Edgerton, V Reggie

2014-01-01

The inability to control timely bladder emptying is one of the most serious challenges among the several functional deficits that occur after a complete spinal cord injury. Having demonstrated that electrodes placed epidurally on the dorsum of the spinal cord can be used in animals and humans to recover postural and locomotor function after complete paralysis, we hypothesized that a similar approach could be used to recover bladder function after paralysis. Also knowing that posture and locomotion can be initiated immediately with a specific frequency-dependent stimulation pattern and that with repeated stimulation-training sessions these functions can improve even further, we reasoned that the same two strategies could be used to regain bladder function. Recent evidence suggests that rats with severe paralysis can be rehabilitated with a multisystem neuroprosthetic training regime that counteracts the development of neurogenic bladder dysfunction. No data regarding the acute effects of locomotion on bladder function, however, were reported. In this study we show that enabling of locomotor-related spinal neuronal circuits by epidural stimulation also influences neural networks controlling bladder function and can play a vital role in recovering bladder function after complete paralysis. We have identified specific spinal cord stimulation parameters that initiate bladder emptying within seconds of the initiation of epidural stimulation. The clinical implications of these results are substantial in that this strategy could have a major impact in improving the quality of life and longevity of patients while simultaneously dramatically reducing ongoing health maintenance after a spinal cord injury.

Initiation of Bladder Voiding with Epidural Stimulation in Paralyzed, Step Trained Rats

PubMed Central

Gad, Parag N.; Roy, Roland R.; Zhong, Hui; Lu, Daniel C.; Gerasimenko, Yury P.; Edgerton, V. Reggie

2014-01-01

The inability to control timely bladder emptying is one of the most serious challenges among the several functional deficits that occur after a complete spinal cord injury. Having demonstrated that electrodes placed epidurally on the dorsum of the spinal cord can be used in animals and humans to recover postural and locomotor function after complete paralysis, we hypothesized that a similar approach could be used to recover bladder function after paralysis. Also knowing that posture and locomotion can be initiated immediately with a specific frequency-dependent stimulation pattern and that with repeated stimulation-training sessions these functions can improve even further, we reasoned that the same two strategies could be used to regain bladder function. Recent evidence suggests that rats with severe paralysis can be rehabilitated with a multisystem neuroprosthetic training regime that counteracts the development of neurogenic bladder dysfunction. No data regarding the acute effects of locomotion on bladder function, however, were reported. In this study we show that enabling of locomotor-related spinal neuronal circuits by epidural stimulation also influences neural networks controlling bladder function and can play a vital role in recovering bladder function after complete paralysis. We have identified specific spinal cord stimulation parameters that initiate bladder emptying within seconds of the initiation of epidural stimulation. The clinical implications of these results are substantial in that this strategy could have a major impact in improving the quality of life and longevity of patients while simultaneously dramatically reducing ongoing health maintenance after a spinal cord injury. PMID:25264607

Estimation of effective connectivity using multi-layer perceptron artificial neural network.

PubMed

Talebi, Nasibeh; Nasrabadi, Ali Motie; Mohammad-Rezazadeh, Iman

2018-02-01

Studies on interactions between brain regions estimate effective connectivity, (usually) based on the causality inferences made on the basis of temporal precedence. In this study, the causal relationship is modeled by a multi-layer perceptron feed-forward artificial neural network, because of the ANN's ability to generate appropriate input-output mapping and to learn from training examples without the need of detailed knowledge of the underlying system. At any time instant, the past samples of data are placed in the network input, and the subsequent values are predicted at its output. To estimate the strength of interactions, the measure of " Causality coefficient " is defined based on the network structure, the connecting weights and the parameters of hidden layer activation function. Simulation analysis demonstrates that the method, called "CREANN" (Causal Relationship Estimation by Artificial Neural Network), can estimate time-invariant and time-varying effective connectivity in terms of MVAR coefficients. The method shows robustness with respect to noise level of data. Furthermore, the estimations are not significantly influenced by the model order (considered time-lag), and the different initial conditions (initial random weights and parameters of the network). CREANN is also applied to EEG data collected during a memory recognition task. The results implicate that it can show changes in the information flow between brain regions, involving in the episodic memory retrieval process. These convincing results emphasize that CREANN can be used as an appropriate method to estimate the causal relationship among brain signals.

The effect of learning on bursting.

PubMed

Stegenga, Jan; Le Feber, Joost; Marani, Enrico; Rutten, Wim L C

2009-04-01

We have studied the effect that learning a new stimulus-response (SR) relationship had within a neuronal network cultured on a multielectrode array. For training, we applied repetitive focal electrical stimulation delivered at a low rate (<1/s). Stimulation was withdrawn when a desired SR success ratio was achieved. It has been shown elsewhere, and we verified that this training algorithm, named conditional repetitive stimulation (CRS), can be used to strengthen an initially weak SR. So far, it remained unclear what the role of the rest of the network during learning was. We therefore studied the effect of CRS on spontaneously occurring network bursts. To this end, we made profiles of the firing rates within network bursts. We have earlier shown that these profiles change shape on a time base of several hours during spontaneous development. We show here that profiles of summed activity, called burst profiles, changed shape at an increased rate during CRS. This suggests that the whole network was involved in making the changes necessary to incorporate the desired SR relationship. However, a local (path-specific) component to learning was also found by analyzing profiles of single-electrode-activity phase profiles. Phase profiles that were not part of the SR relationship changed far less during CRS than the phase profiles of the electrodes that were part of the SR relationship. Finally, the manner in which phase profiles changed shape varied and could not be linked to the SR relationship.

Improving chronic care delivery and outcomes: the impact of the cystic fibrosis Care Center Network.

PubMed

Mogayzel, Peter J; Dunitz, Jordan; Marrow, Laura C; Hazle, Leslie A

2014-04-01

Cystic fibrosis (CF) is a multisystem, life-shortening genetic disease that requires complex care. To facilitate this expert, multidisciplinary care, the CF Foundation established a Care Center Network and accredited the first care centres in 1961. This model of care brings together physicians and specialists from other disciplines to provide care, facilitate basic and clinical research, and educate the next generation of providers. Although the Care Center Network has been invaluable in achieving substantial gains in survival and quality of life, additional opportunities for improvements in CF care exist. In 1999, analysis of data from the CF Foundation's Patient Registry detected variation in care practices and outcomes across centres, identifying opportunities for improvement. In 2002, the CF Foundation launched a comprehensive quality improvement (QI) initiative to enhance care by assembling national experts to develop a strategic plan to disseminate QI training and processes throughout the Care Center Network. The QI strategies included developing leadership (nationally and within each care centre), identifying best CF care practices, and incorporating people with CF and their families into improvement efforts. The goal was to improve the care for every person with CF in the USA. Multiple tactics were undertaken to implement the strategic plan and disseminate QI training and tools throughout the Care Center Network. In addition, strategies to foster collaboration between care centre staff and individuals with CF and their families became a cornerstone of QI efforts. Today it is clear that the application of QI principles within the CF Care Center Network has improved adherence to clinical guidelines and achievement of important health outcomes.

Direct modulation of aberrant brain network connectivity through real-time NeuroFeedback.

PubMed

Ramot, Michal; Kimmich, Sara; Gonzalez-Castillo, Javier; Roopchansingh, Vinai; Popal, Haroon; White, Emily; Gotts, Stephen J; Martin, Alex

2017-09-16

The existence of abnormal connectivity patterns between resting state networks in neuropsychiatric disorders, including Autism Spectrum Disorder (ASD), has been well established. Traditional treatment methods in ASD are limited, and do not address the aberrant network structure. Using real-time fMRI neurofeedback, we directly trained three brain nodes in participants with ASD, in which the aberrant connectivity has been shown to correlate with symptom severity. Desired network connectivity patterns were reinforced in real-time, without participants' awareness of the training taking place. This training regimen produced large, significant long-term changes in correlations at the network level, and whole brain analysis revealed that the greatest changes were focused on the areas being trained. These changes were not found in the control group. Moreover, changes in ASD resting state connectivity following the training were correlated to changes in behavior, suggesting that neurofeedback can be used to directly alter complex, clinically relevant network connectivity patterns.

Neural network approach to the inverse problem of the crack-depth determination from ultrasonic backscattering data

NASA Astrophysics Data System (ADS)

Takadoya, M.; Notake, M.; Kitahara, M.; Achenbach, J. D.; Guo, Q. C.; Peterson, M. L.

A neural network approach has been developed to determine the depth of a surface breaking crack in a steel plate from ultrasonic backscattering data. The network is trained by the use of a feedforward three-layered network together with a back-propagation algorithm for error corrections. Synthetic data are employed for network training. The signal used for crack isonification is a mode converted 45 deg transverse wave. The plate with a surface breaking crack is immersed in water, and the crack is insonified from the opposite uncracked side of the plate. A numerical analysis of the backscattered field is carried out based on the elastic wave theory by the use of the boundary element method. The numerical analysis provides synthetic data for the training of the network. The training data have been calculated for cracks with specific increments of the experimental data which are different from the training data.

Streamflow predictions in Alpine Catchments by using artificial neural networks. Application in the Alto Genil Basin (South Spain)

NASA Astrophysics Data System (ADS)

Jimeno-Saez, Patricia; Pegalajar-Cuellar, Manuel; Pulido-Velazquez, David

2017-04-01

This study explores techniques of modeling water inflow series, focusing on techniques of short-term steamflow prediction. An appropriate estimation of streamflow in advance is necessary to anticipate measures to mitigate the impacts and risks related to drought conditions. This study analyzes the prediction of future streamflow of nineteen subbasins in the Alto-Genil basin in Granada (Southeast of Spain). Some of these basin streamflow have an important component of snowmelt due to part of the system is located in Sierra Nevada Mountain Range, the highest mountain of continental Spain. Streamflow prediction models have been calibrated using time series of historical natural streamflows. The available streamflow measurements have been downloaded from several public data sources. These original data have been preprocessed to turn them to the original natural regime, removing the anthropic effects. The missing values in the adopted horizon period to calibrate the prediction models have been estimated by using a Temez hydrological balance model, approaching the snowmelt processes with a hybrid degree day method. In the experimentation, ARIMA models are used as baseline method, and recurrent neural networks ELMAN and nonlinear autoregressive neural network (NAR) to test if the prediction accuracy can be improved. After performing the multiple experiments with these models, non-parametric statistical tests are applied to select the best of these techniques. In the experiments carried out with ARIMA, it is concluded that ARIMA models are not adequate in this case study due to the existence of a nonlinear component that cannot be modeled. Secondly, ELMAN and NAR neural networks with multi-start training is performed with each network structure to deal with the local optimum problem, since in neural network training there is a very strong dependence on the initial weights of the network. The obtained results suggest that both neural networks are efficient for the short term prediction, surpassing the limitations of the ARIMA models and, in general, the experiments showed that NAR networks are the ones with the greatest generalization capability. Therefore, NAR networks are chosen as the starting point for other works, in which we study the streamflow predictions incorporating exogenous variables (as the Snow Cover Area), the sensitivity of the prediction to the initial conditions, multivariate streamflow predictions considering the spatial correlation between the sub-basins streamflow and the synthetic generations to assess droughts statistic. This research has been partially supported by the CGL2013-48424-C2-2-R (MINECO) and the PMAFI/06/14 (UCAM) projects.

Artificial neural network (ANN) approach for modeling of Pb(II) adsorption from aqueous solution by Antep pistachio (Pistacia Vera L.) shells.

PubMed

Yetilmezsoy, Kaan; Demirel, Sevgi

2008-05-30

A three-layer artificial neural network (ANN) model was developed to predict the efficiency of Pb(II) ions removal from aqueous solution by Antep pistachio (Pistacia Vera L.) shells based on 66 experimental sets obtained in a laboratory batch study. The effect of operational parameters such as adsorbent dosage, initial concentration of Pb(II) ions, initial pH, operating temperature, and contact time were studied to optimise the conditions for maximum removal of Pb(II) ions. On the basis of batch test results, optimal operating conditions were determined to be an initial pH of 5.5, an adsorbent dosage of 1.0 g, an initial Pb(II) concentration of 30 ppm, and a temperature of 30 degrees C. Experimental results showed that a contact time of 45 min was generally sufficient to achieve equilibrium. After backpropagation (BP) training combined with principal component analysis (PCA), the ANN model was able to predict adsorption efficiency with a tangent sigmoid transfer function (tansig) at hidden layer with 11 neurons and a linear transfer function (purelin) at output layer. The Levenberg-Marquardt algorithm (LMA) was found as the best of 11 BP algorithms with a minimum mean squared error (MSE) of 0.000227875. The linear regression between the network outputs and the corresponding targets were proven to be satisfactory with a correlation coefficient of about 0.936 for five model variables used in this study.

An evaluation of the global network of field epidemiology and laboratory training programmes: a resource for improving public health capacity and increasing the number of public health professionals worldwide

PubMed Central

2013-01-01

Background Given that many infectious diseases spread rapidly, across borders and species, there is a growing worldwide need to increase the number of public health professionals skilled in controlling infectious epidemics. Needed also are more public health professionals skilled in non-communicable disease surveillance and interventions. As a result, we surveyed all 57 field epidemiology training programmes (FETPs) that are members of the Training Program in Epidemiology and Public Health Interventions Network (TEPHINET), to evaluate the progress of the FETPs, the only global applied epidemiology network, toward increasing public health capacity globally. Methods Data on the FETP programmes and the training they provide were abstracted from TEPHINET membership surveys and verified with FETP directors for all FETPs that were members of TEPHINET in 2012. Data on abstracts submitted to the recent TEPHINET Global Scientific Conference, on recent accomplishments by each FETP, and on quality improvement were also compiled to provide a worldwide view of the public health human resource capacity produced by these programmes. Results A total of 6980 public health professionals worldwide have graduated from an FETP or from the Center for Disease Control and Prevention’s Epidemiology Intelligence Service (EIS). FETP residents and graduates participate in key public health prevention, control, and response activities. Each FETP has adapted its curriculum and objectives over time to align with its country’s public health priorities. FETPs are well integrated into their national public health infrastructures, and they have many partners at the national, regional and global levels. Conclusion FETPs are a competent and diverse source of highly skilled public health professionals who contribute significantly to public health’s global human resource needs. This finding is evidenced by 1) the training curricula that were adapted over time to meet public health’s human resource needs, 2) the FETPs’ continued support from internal and external partners, 3) the increasing number of FETP residents and graduates and their increasing contribution to effective public health work, and 4) the increased quality improvement initiatives facilitated through the FETPs membership in one global network, TEPHINET. PMID:24053689

Sustainable development of a GCP-compliant clinical trials platform in Africa: the malaria clinical trials alliance perspective.

PubMed

Ogutu, Bernhards R; Baiden, Rita; Diallo, Diadier; Smith, Peter G; Binka, Fred N

2010-04-20

The Malaria Clinical Trials Alliance (MCTA), a programme of INDEPTH network of demographic surveillance centres, was launched in 2006 with two broad objectives: to facilitate the timely development of a network of centres in Africa with the capacity to conduct clinical trials of malaria vaccines and drugs under conditions of good clinical practice (GCP); and to support, strengthen and mentor the centres in the network to facilitate their progression towards self-sustaining clinical research centres. Sixteen research centres in 10 African malaria-endemic countries were selected that were already working with the Malaria Vaccine Initiative (MVI) or the Medicines for Malaria Venture (MMV). All centres were visited to assess their requirements for research capacity development through infrastructure strengthening and training. Support provided by MCTA included: laboratory and facility refurbishment; workshops on GCP, malaria diagnosis, strategic management and media training; and training to support staff to undertake accreditation examinations of the Association of Clinical Research Professionals (ACRP). Short attachments to other network centres were also supported to facilitate sharing practices within the Alliance. MCTA also played a key role in the creation of the African Media & Malaria Research Network (AMMREN), which aims to promote interaction between researchers and the media for appropriate publicity and media reporting of research and developments on malaria, including drug and vaccine trials. In three years, MCTA strengthened 13 centres to perform GCP-compliant drug and vaccine trials, including 11 centres that form the backbone of a large phase III malaria vaccine trial. MCTA activities have demonstrated that centres can be brought up to GCP compliance on this time scale, but the costs are substantial and there is a need for further support of other centres to meet the growing demand for clinical trial capacity. The MCTA experience also indicates that capacity development in clinical trials is best carried out in the context of preparation for specific trials. In this regard MCTA centres involved in the phase III malaria vaccine trial were, on average, more successful at consolidating the training and infrastructure support than those centres focussing only on drug trials.

Sustainable development of a GCP-compliant clinical trials platform in Africa: the Malaria Clinical Trials Alliance perspective

PubMed Central

2010-01-01

Background The Malaria Clinical Trials Alliance (MCTA), a programme of INDEPTH network of demographic surveillance centres, was launched in 2006 with two broad objectives: to facilitate the timely development of a network of centres in Africa with the capacity to conduct clinical trials of malaria vaccines and drugs under conditions of good clinical practice (GCP); and to support, strengthen and mentor the centres in the network to facilitate their progression towards self-sustaining clinical research centres. Case description Sixteen research centres in 10 African malaria-endemic countries were selected that were already working with the Malaria Vaccine Initiative (MVI) or the Medicines for Malaria Venture (MMV). All centres were visited to assess their requirements for research capacity development through infrastructure strengthening and training. Support provided by MCTA included: laboratory and facility refurbishment; workshops on GCP, malaria diagnosis, strategic management and media training; and training to support staff to undertake accreditation examinations of the Association of Clinical Research Professionals (ACRP). Short attachments to other network centres were also supported to facilitate sharing practices within the Alliance. MCTA also played a key role in the creation of the African Media & Malaria Research Network (AMMREN), which aims to promote interaction between researchers and the media for appropriate publicity and media reporting of research and developments on malaria, including drug and vaccine trials. Conclusion In three years, MCTA strengthened 13 centres to perform GCP-compliant drug and vaccine trials, including 11 centres that form the backbone of a large phase III malaria vaccine trial. MCTA activities have demonstrated that centres can be brought up to GCP compliance on this time scale, but the costs are substantial and there is a need for further support of other centres to meet the growing demand for clinical trial capacity. The MCTA experience also indicates that capacity development in clinical trials is best carried out in the context of preparation for specific trials. In this regard MCTA centres involved in the phase III malaria vaccine trial were, on average, more successful at consolidating the training and infrastructure support than those centres focussing only on drug trials. PMID:20406478

An adaptive critic-based scheme for consensus control of nonlinear multi-agent systems

NASA Astrophysics Data System (ADS)

Heydari, Ali; Balakrishnan, S. N.

2014-12-01

The problem of decentralised consensus control of a network of heterogeneous nonlinear systems is formulated as an optimal tracking problem and a solution is proposed using an approximate dynamic programming based neurocontroller. The neurocontroller training comprises an initial offline training phase and an online re-optimisation phase to account for the fact that the reference signal subject to tracking is not fully known and available ahead of time, i.e., during the offline training phase. As long as the dynamics of the agents are controllable, and the communication graph has a directed spanning tree, this scheme guarantees the synchronisation/consensus even under switching communication topology and directed communication graph. Finally, an aerospace application is selected for the evaluation of the performance of the method. Simulation results demonstrate the potential of the scheme.

Nanophotonic particle simulation and inverse design using artificial neural networks.

PubMed

Peurifoy, John; Shen, Yichen; Jing, Li; Yang, Yi; Cano-Renteria, Fidel; DeLacy, Brendan G; Joannopoulos, John D; Tegmark, Max; Soljačić, Marin

2018-06-01

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical.

Quantum Assisted Learning for Registration of MODIS Images

NASA Astrophysics Data System (ADS)

Pelissier, C.; Le Moigne, J.; Fekete, G.; Halem, M.

2017-12-01

The advent of the first large scale quantum annealer by D-Wave has led to an increased interest in quantum computing. However, the quantum annealing computer of the D-Wave is limited to either solving Quadratic Unconstrained Binary Optimization problems (QUBOs) or using the ground state sampling of an Ising system that can be produced by the D-Wave. These restrictions make it challenging to find algorithms to accelerate the computation of typical Earth Science applications. A major difficulty is that most applications have continuous real-valued parameters rather than binary. Here we present an exploratory study using the ground state sampling to train artificial neural networks (ANNs) to carry out image registration of MODIS images. The key idea to using the D-Wave to train networks is that the quantum chip behaves thermally like Boltzmann machines (BMs), and BMs are known to be successful at recognizing patterns in images. The ground state sampling of the D-Wave also depends on the dynamics of the adiabatic evolution and is subject to other non-thermal fluctuations, but the statistics are thought to be similar and ANNs tend to be robust under fluctuations. In light of this, the D-Wave ground state sampling is used to define a Boltzmann like generative model and is investigated to register MODIS images. Image intensities of MODIS images are transformed using a Discrete Cosine Transform and used to train a several layers network to learn how to align images to a reference image. The network layers consist of an initial sigmoid layer acting as a binary filter of the input followed by a strict binarization using Bernoulli sampling, and then fed into a Boltzmann machine. The output is then classified using a soft-max layer. Results are presented and discussed.

A new algorithm to detect earthquakes outside the seismic network: preliminary results

NASA Astrophysics Data System (ADS)

Giudicepietro, Flora; Esposito, Antonietta Maria; Ricciolino, Patrizia

2017-04-01

In this text we are going to present a new technique for detecting earthquakes outside the seismic network, which are often the cause of fault of automatic analysis system. Our goal is to develop a robust method that provides the discrimination result as quickly as possible. We discriminate local earthquakes from regional earthquakes, both recorded at SGG station, equipped with short period sensors, operated by Osservatorio Vesuviano (INGV) in the Southern Apennines (Italy). The technique uses a Multi Layer Perceptron (MLP) neural network with an architecture composed by an input layer, a hidden layer and a single node output layer. We pre-processed the data using the Linear Predictive Coding (LPC) technique to extract the spectral features of the signals in a compact form. We performed several experiments by shortening the signal window length. In particular, we used windows of 4, 2 and 1 seconds containing the onset of the local and the regional earthquakes. We used a dataset of 103 local earthquakes and 79 regional earthquakes, most of which occurred in Greece, Albania and Crete. We split the dataset into a training set, for the network training, and a testing set to evaluate the network's capacity of discrimination. In order to assess the network stability, we repeated this procedure six times, randomly changing the data composition of the training and testing set and the initial weights of the net. We estimated the performance of this method by calculating the average of correct detection percentages obtained for each of the six permutations. The average performances are 99.02%, 98.04% and 98.53%, which concern respectively the experiments carried out on 4, 2 and 1 seconds signal windows. The results show that our method is able to recognize the earthquakes outside the seismic network using only the first second of the seismic records, with a suitable percentage of correct detection. Therefore, this algorithm can be profitably used to make earthquake automatic analyses more robust and reliable. Finally, with appropriate tuning, it can be integrated in multi-parametric systems for monitoring high natural risk areas.

Fabric defect detection based on visual saliency using deep feature and low-rank recovery

NASA Astrophysics Data System (ADS)

Liu, Zhoufeng; Wang, Baorui; Li, Chunlei; Li, Bicao; Dong, Yan

2018-04-01

Fabric defect detection plays an important role in improving the quality of fabric product. In this paper, a novel fabric defect detection method based on visual saliency using deep feature and low-rank recovery was proposed. First, unsupervised training is carried out by the initial network parameters based on MNIST large datasets. The supervised fine-tuning of fabric image library based on Convolutional Neural Networks (CNNs) is implemented, and then more accurate deep neural network model is generated. Second, the fabric images are uniformly divided into the image block with the same size, then we extract their multi-layer deep features using the trained deep network. Thereafter, all the extracted features are concentrated into a feature matrix. Third, low-rank matrix recovery is adopted to divide the feature matrix into the low-rank matrix which indicates the background and the sparse matrix which indicates the salient defect. In the end, the iterative optimal threshold segmentation algorithm is utilized to segment the saliency maps generated by the sparse matrix to locate the fabric defect area. Experimental results demonstrate that the feature extracted by CNN is more suitable for characterizing the fabric texture than the traditional LBP, HOG and other hand-crafted features extraction method, and the proposed method can accurately detect the defect regions of various fabric defects, even for the image with complex texture.

Recruitment of Underrepresented Minority Researchers into HIV Prevention Research: The HIV Prevention Trials Network Scholars Program

PubMed Central

Hamilton, Erica L.; Griffith, Sam B.; Jennings, Larissa; Dyer, Typhanye V.; Mayer, Kenneth; Wheeler, Darrell

2018-01-01

Abstract Most U.S. investigators in the HIV Prevention Trials Network (HPTN) have been of majority race/ethnicity and sexual orientation. Research participants, in contrast, have been disproportionately from racial/ethnic minorities and men who have sex with men (MSM), reflecting the U.S. epidemic. We initiated and subsequently evaluated the HPTN Scholars Program that mentors early career investigators from underrepresented minority groups. Scholars were affiliated with the HPTN for 12–18 months, mentored by a senior researcher to analyze HPTN study data. Participation in scientific committees, trainings, protocol teams, and advisory groups was facilitated, followed by evaluative exit surveys. Twenty-six trainees have produced 17 peer-reviewed articles to date. Research topics typically explored health disparities and HIV prevention among black and Hispanic MSM and at-risk black women. Most scholars (81% in the first five cohorts) continued HIV research after program completion. Alumni reported program-related career benefits and subsequent funding successes. Their feedback also suggested that we must improve the scholars' abilities to engage new research protocols that are developed within the network. Mentored engagement can nurture the professional development of young researchers from racial/ethnic and sexual minority communities. Minority scientists can benefit from training and mentoring within research consortia, whereas the network research benefits from perspectives of underrepresented minority scientists. PMID:29145745

Measuring Pilot Knowledge in Training: The Pathfinder Network Scaling Technique

DTIC Science & Technology

2007-01-01

Network Scaling Technique Leah J. Rowe Roger W. Schvaneveldt L -3 Communications Arizona State University Mesa, AZ Mesa, AZ leah.rowe...7293 Page 2 of 8 Measuring Pilot Knowledge in Training: The Pathfinder Network Scaling Technique Leah J. Rowe Roger W. Schvaneveldt L -3...training. ABOUT THE AUTHORS Leah J. Rowe is a Training Research Specialist with L -3 Communications at the Air Force Research Laboratory

Tying up lions: multilateral initiative on malaria communications: the first chapter of a malaria research network in Africa.

PubMed

Royall, Julia; Bennett, Mark; van Schayk, Ingeborg; Alilio, Martin

2004-08-01

"When spider webs unite, they can tie up a lion" (Ethiopian folk adage). The Multilateral Initiative on Malaria Communications Network (MIMCom) facilitates a new way of doing research in Africa and African scientists' participation in the international scientific community. The MIMCom supports full access to the Internet and the resources of the WorldWide Web at 19 research sites in 11 African countries. Furthermore, the MIMCom project comprises two websites: one includes links to resources, databases, and publications as well as a document delivery service for full text journal articles, and the other is a research agenda specific website with a server for a research network desiring to share raw data. Other important components of MIMCom are training and evaluation components. The MIMCom was conceived in 1997 by African researchers and has been designed, implemented, and overseen by the U.S. National Library of Medicine in collaboration with partners in Africa, the United States, and the United Kingdom. This project demonstrates clearly that it can make a positive difference in the functioning of remote research sites in Africa, in terms of site growth and productivity and in the professional lives of individual researchers. This report reviews the project's background, methods of operation with an emphasis on local needs and priorities, cost effectiveness, and local responsibility; results focusing on a technical network; documentation of the system and two-way exchange of information; the MIMCom website; a network approach to research; and financial sustainability. The report concludes with summaries of evaluations by an independent panel, the Multilateral Initiative on Malaria Secretariat, and the U.S. National Library of Medicine. Copyright 2004 The American Society of Tropical Medicine and Hygiene

Nuevas tecnicas basadas en redes neuronales para el diseno de filtros de microondas multicapa apantallados

NASA Astrophysics Data System (ADS)

Pascual Garcia, Juan

In this PhD thesis one method of shielded multilayer circuit neural network based analysis has been developed. One of the most successful analysis procedures of these kind of structures is the Integral Equation technique (IE) solved by the Method of Moments (MoM). In order to solve the IE, in the version which uses the media relevant potentials, it is necessary to have a formulation of the Green's functions associated to the mentioned potentials. The main computational burden in the IE resolution lies on the numerical evaluation of the Green's functions. In this work, the circuit analysis has been drastically accelerated thanks to the approximation of the Green's functions by means of neural networks. Once trained, the neural networks substitute the Green's functions in the IE. Two different types of neural networks have been used: the Radial basis function neural networks (RBFNN) and the Chebyshev neural networks. Thanks mainly to two distinct operations the correct approximation of the Green's functions has been possible. On the one hand, a very effective input space division has been developed. On the other hand, the elimination of the singularity makes feasible the approximation of slow variation functions. Two different singularity elimination strategies have been developed. The first one is based on the multiplication by the source-observation points distance (rho). The second one outperforms the first one. It consists of the extraction of two layers of spatial images from the whole summation of images. With regard to the Chebyshev neural networks, the OLS training algorithm has been applied in a novel fashion. This method allows the optimum design in this kind of neural networks. In this way, the performance of these neural networks outperforms greatly the RBFNNs one. In both networks, the time gain reached makes the neural method profitable. The time invested in the input space division and in the neural training is negligible with only few circuit analysis. To show, in a practical way, the ability of the neural based analysis method, two new design procedures have been developed. The first method uses the Genetic Algorithms to optimize an initial filter which does not fulfill the established specifications. A new fitness function, specially well suited to design filters, has been defined in order to assure the correct convergence of the optimization process. This new function measures the fulfillment of the specifications and it also prevents the appearance of the premature convergence problem. The second method is found on the approximation, by means of neural networks, of the relations between the electrical parameters, which defined the circuit response, and the physical dimensions that synthesize the aforementioned parameters. The neural networks trained with these data can be used in the design of many circuits in a given structure. Both methods had been show their ability in the design of practical filters.

Developmental implications of children's brain networks and learning.

PubMed

Chan, John S Y; Wang, Yifeng; Yan, Jin H; Chen, Huafu

2016-10-01

The human brain works as a synergistic system where information exchanges between functional neuronal networks. Rudimentary networks are observed in the brain during infancy. In recent years, the question of how functional networks develop and mature in children has been a hotly discussed topic. In this review, we examined the developmental characteristics of functional networks and the impacts of skill training on children's brains. We first focused on the general rules of brain network development and on the typical and atypical development of children's brain networks. After that, we highlighted the essentials of neural plasticity and the effects of learning on brain network development. We also discussed two important theoretical and practical concerns in brain network training. Finally, we concluded by presenting the significance of network training in typically and atypically developed brains.

A European Master's Programme in Public Health Nutrition.

PubMed

Yngve, A; Warm, D; Landman, J; Sjöström, M

2001-12-01

Effective population-based strategies require people trained and competent in the discipline of Public Health Nutrition. Since 1997, a European Master's Programme in Public Health Nutrition has been undergoing planning and implementation, by establishing initial quality assurance systems with the aid of funding from the European Commission (DG SANCO/F3). Partners from 17 European countries have been involved in the process. A European Network of Public Health Nutrition has been developed and accredited by the European Commission.

The RAILER System for Maintenance Management of U.S. Army Railroad Networks: RAILER 1 Description and Use

DTIC Science & Technology

1988-09-01

the report. Field Testing Specific aspects of field procedures have been tested at Fort Devens , MA, and at the Consolidated Rail Corporation (Conrail...days of formalized training on the system, both field proce- dures and computer operations, were conducted by USA-CERL at Fort Devens , MA. Attendees...included representatives from TSC, Fort Devens , FORSCOM, and the T.K. Dyer Corp. Initial Track Segmenting and Component Identification The office work

Training of Self-Regulated Learning Skills on a Social Network System

ERIC Educational Resources Information Center

Cho, Kwangsu; Cho, Moon-Heum

2013-01-01

The purpose of this study was to investigate whether self-regulated learning (SRL) skills trained using a social network system (SNS) may be generalized outside the training session. A total of 29 undergraduate students participated in the study. During the training session, students in the experimental group were trained to practice…

Planning Training Loads for the 400 M Hurdles in Three-Month Mesocycles using Artificial Neural Networks.

PubMed

Przednowek, Krzysztof; Iskra, Janusz; Wiktorowicz, Krzysztof; Krzeszowski, Tomasz; Maszczyk, Adam

2017-12-01

This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes' training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period.

Planning Training Loads for the 400 M Hurdles in Three-Month Mesocycles using Artificial Neural Networks

PubMed Central

Iskra, Janusz; Wiktorowicz, Krzysztof; Krzeszowski, Tomasz; Maszczyk, Adam

2017-01-01

Abstract This paper presents a novel approach to planning training loads in hurdling using artificial neural networks. The neural models performed the task of generating loads for athletes’ training for the 400 meters hurdles. All the models were calculated based on the training data of 21 Polish National Team hurdlers, aged 22.25 ± 1.96, competing between 1989 and 2012. The analysis included 144 training plans that represented different stages in the annual training cycle. The main contribution of this paper is to develop neural models for planning training loads for the entire career of a typical hurdler. In the models, 29 variables were used, where four characterized the runner and 25 described the training process. Two artificial neural networks were used: a multi-layer perceptron and a network with radial basis functions. To assess the quality of the models, the leave-one-out cross-validation method was used in which the Normalized Root Mean Squared Error was calculated. The analysis shows that the method generating the smallest error was the radial basis function network with nine neurons in the hidden layer. Most of the calculated training loads demonstrated a non-linear relationship across the entire competitive period. The resulting model can be used as a tool to assist a coach in planning training loads during a selected training period. PMID:29339998

Satellite image analysis using neural networks

NASA Technical Reports Server (NTRS)

Sheldon, Roger A.

1990-01-01

The tremendous backlog of unanalyzed satellite data necessitates the development of improved methods for data cataloging and analysis. Ford Aerospace has developed an image analysis system, SIANN (Satellite Image Analysis using Neural Networks) that integrates the technologies necessary to satisfy NASA's science data analysis requirements for the next generation of satellites. SIANN will enable scientists to train a neural network to recognize image data containing scenes of interest and then rapidly search data archives for all such images. The approach combines conventional image processing technology with recent advances in neural networks to provide improved classification capabilities. SIANN allows users to proceed through a four step process of image classification: filtering and enhancement, creation of neural network training data via application of feature extraction algorithms, configuring and training a neural network model, and classification of images by application of the trained neural network. A prototype experimentation testbed was completed and applied to climatological data.

An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures

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

Schuman, Catherine D; Plank, James; Disney, Adam

2016-01-01

As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.

Advances in Artificial Neural Networks - Methodological Development and Application

USDA-ARS?s Scientific Manuscript database

Artificial neural networks as a major soft-computing technology have been extensively studied and applied during the last three decades. Research on backpropagation training algorithms for multilayer perceptron networks has spurred development of other neural network training algorithms for other ne...

Re-Engineering Alzheimer Clinical Trials: Global Alzheimer's Platform Network.

PubMed

Cummings, J; Aisen, P; Barton, R; Bork, J; Doody, R; Dwyer, J; Egan, J C; Feldman, H; Lappin, D; Truyen, L; Salloway, S; Sperling, R; Vradenburg, G

2016-06-01

Alzheimer's disease (AD) drug development is costly, time-consuming, and inefficient. Trial site functions, trial design, and patient recruitment for trials all require improvement. The Global Alzheimer Platform (GAP) was initiated in response to these challenges. Four GAP work streams evolved in the US to address different trial challenges: 1) registry-to-cohort web-based recruitment; 2) clinical trial site activation and site network construction (GAP-NET); 3) adaptive proof-of-concept clinical trial design; and 4) finance and fund raising. GAP-NET proposes to establish a standardized network of continuously funded trial sites that are highly qualified to perform trials (with established clinical, biomarker, imaging capability; certified raters; sophisticated management system. GAP-NET will conduct trials for academic and biopharma industry partners using standardized instrument versions and administration. Collaboration with the Innovative Medicines Initiative (IMI) European Prevention of Alzheimer's Disease (EPAD) program, the Canadian Consortium on Neurodegeneration in Aging (CCNA) and other similar international initiatives will allow conduct of global trials. GAP-NET aims to increase trial efficiency and quality, decrease trial redundancy, accelerate cohort development and trial recruitment, and decrease trial costs. The value proposition for sites includes stable funding and uniform training and trial execution; the value to trial sponsors is decreased trial costs, reduced time to execute trials, and enhanced data quality. The value for patients and society is the more rapid availability of new treatments for AD.

How Coke Added Life to its Video Network.

ERIC Educational Resources Information Center

Curran, Patrick D.

1981-01-01

Describes how Coca-Cola's training department identified problems in the use of a video training package and made improvements that expanded the potential of the corporation-wide training network. (SK)

Equilibrium point control of a monkey arm simulator by a fast learning tree structured artificial neural network.

PubMed

Dornay, M; Sanger, T D

1993-01-01

A planar 17 muscle model of the monkey's arm based on realistic biomechanical measurements was simulated on a Symbolics Lisp Machine. The simulator implements the equilibrium point hypothesis for the control of arm movements. Given initial and final desired positions, it generates a minimum-jerk desired trajectory of the hand and uses the backdriving algorithm to determine an appropriate sequence of motor commands to the muscles (Flash 1987; Mussa-Ivaldi et al. 1991; Dornay 1991b). These motor commands specify a temporal sequence of stable (attractive) equilibrium positions which lead to the desired hand movement. A strong disadvantage of the simulator is that it has no memory of previous computations. Determining the desired trajectory using the minimum-jerk model is instantaneous, but the laborious backdriving algorithm is slow, and can take up to one hour for some trajectories. The complexity of the required computations makes it a poor model for biological motor control. We propose a computationally simpler and more biologically plausible method for control which achieves the benefits of the backdriving algorithm. A fast learning, tree-structured network (Sanger 1991c) was trained to remember the knowledge obtained by the backdriving algorithm. The neural network learned the nonlinear mapping from a 2-dimensional cartesian planar hand position (x,y) to a 17-dimensional motor command space (u1, . . ., u17). Learning 20 training trajectories, each composed of 26 sample points [[x,y], [u1, . . ., u17] took only 20 min on a Sun-4 Sparc workstation. After the learning stage, new, untrained test trajectories as well as the original trajectories of the hand were given to the neural network as input. The network calculated the required motor commands for these movements. The resulting movements were close to the desired ones for both the training and test cases.

Nanophotonic particle simulation and inverse design using artificial neural networks

PubMed Central

Peurifoy, John; Shen, Yichen; Jing, Li; Cano-Renteria, Fidel; DeLacy, Brendan G.; Joannopoulos, John D.; Tegmark, Max

2018-01-01

We propose a method to use artificial neural networks to approximate light scattering by multilayer nanoparticles. We find that the network needs to be trained on only a small sampling of the data to approximate the simulation to high precision. Once the neural network is trained, it can simulate such optical processes orders of magnitude faster than conventional simulations. Furthermore, the trained neural network can be used to solve nanophotonic inverse design problems by using back propagation, where the gradient is analytical, not numerical. PMID:29868640

Decorrelated jet substructure tagging using adversarial neural networks

NASA Astrophysics Data System (ADS)

Shimmin, Chase; Sadowski, Peter; Baldi, Pierre; Weik, Edison; Whiteson, Daniel; Goul, Edward; Søgaard, Andreas

2017-10-01

We describe a strategy for constructing a neural network jet substructure tagger which powerfully discriminates boosted decay signals while remaining largely uncorrelated with the jet mass. This reduces the impact of systematic uncertainties in background modeling while enhancing signal purity, resulting in improved discovery significance relative to existing taggers. The network is trained using an adversarial strategy, resulting in a tagger that learns to balance classification accuracy with decorrelation. As a benchmark scenario, we consider the case where large-radius jets originating from a boosted resonance decay are discriminated from a background of nonresonant quark and gluon jets. We show that in the presence of systematic uncertainties on the background rate, our adversarially trained, decorrelated tagger considerably outperforms a conventionally trained neural network, despite having a slightly worse signal-background separation power. We generalize the adversarial training technique to include a parametric dependence on the signal hypothesis, training a single network that provides optimized, interpolatable decorrelated jet tagging across a continuous range of hypothetical resonance masses, after training on discrete choices of the signal mass.

Training Data Requirement for a Neural Network to Predict Aerodynamic Coefficients

NASA Technical Reports Server (NTRS)

Korsmeyer, David (Technical Monitor); Rajkumar, T.; Bardina, Jorge

2003-01-01

Basic aerodynamic coefficients are modeled as functions of angle of attack, speed brake deflection angle, Mach number, and side slip angle. Most of the aerodynamic parameters can be well-fitted using polynomial functions. We previously demonstrated that a neural network is a fast, reliable way of predicting aerodynamic coefficients. We encountered few under fitted and/or over fitted results during prediction. The training data for the neural network are derived from wind tunnel test measurements and numerical simulations. The basic questions that arise are: how many training data points are required to produce an efficient neural network prediction, and which type of transfer functions should be used between the input-hidden layer and hidden-output layer. In this paper, a comparative study of the efficiency of neural network prediction based on different transfer functions and training dataset sizes is presented. The results of the neural network prediction reflect the sensitivity of the architecture, transfer functions, and training dataset size.

Direct modulation of aberrant brain network connectivity through real-time NeuroFeedback

PubMed Central

Kimmich, Sara; Gonzalez-Castillo, Javier; Roopchansingh, Vinai; Popal, Haroon; White, Emily; Gotts, Stephen J; Martin, Alex

2017-01-01

The existence of abnormal connectivity patterns between resting state networks in neuropsychiatric disorders, including Autism Spectrum Disorder (ASD), has been well established. Traditional treatment methods in ASD are limited, and do not address the aberrant network structure. Using real-time fMRI neurofeedback, we directly trained three brain nodes in participants with ASD, in which the aberrant connectivity has been shown to correlate with symptom severity. Desired network connectivity patterns were reinforced in real-time, without participants’ awareness of the training taking place. This training regimen produced large, significant long-term changes in correlations at the network level, and whole brain analysis revealed that the greatest changes were focused on the areas being trained. These changes were not found in the control group. Moreover, changes in ASD resting state connectivity following the training were correlated to changes in behavior, suggesting that neurofeedback can be used to directly alter complex, clinically relevant network connectivity patterns. PMID:28917059

The PBRN Initiative

PubMed Central

Curro, F.A.; Vena, D.; Naftolin, F.; Terracio, L.; Thompson, V.P.

2012-01-01

The NIDCR-supported Practice-based Research Network initiative presents dentistry with an unprecedented opportunity by providing a pathway for modifying and advancing the profession. It encourages practitioner participation in the transfer of science into practice for the improvement of patient care. PBRNs vary in infrastructure and design, and sustaining themselves in the long term may involve clinical trial validation by regulatory agencies. This paper discusses the PBRN concept in general and uses the New York University College of Dentistry’s Practitioners Engaged in Applied Research and Learning (PEARL) Network as a model to improve patient outcomes. The PEARL Network is structured to ensure generalizability of results, data integrity, and to provide an infrastructure in which scientists can address clinical practitioner research interests. PEARL evaluates new technologies, conducts comparative effectiveness research, participates in multidisciplinary clinical studies, helps evaluate alternative models of healthcare, educates and trains future clinical faculty for academic positions, expands continuing education to include “benchmarking” as a form of continuous feedback to practitioners, adds value to dental schools’ educational programs, and collaborates with the oral health care and pharmaceutical industries and medical PBRNs to advance the dental profession and further the integration of dental research and practice into contemporary healthcare (NCT00867997, NCT01268605). PMID:22699662

Positive train control shared network.

DOT National Transportation Integrated Search

2015-05-01

The Interoperable Train Control (ITC) Positive : Train Control (PTC) Shared Network (IPSN) : project investigated anticipated industry benefits : and the level of support for the development of : a hosted technological platform for PTC : messaging ac...

New Models of Apprenticeship and Equal Employment Opportunity. Do Training Networks Enhance Fair Hiring Practices?

ERIC Educational Resources Information Center

Imdorf, Christian; Leemann, Regula J.

2012-01-01

This study investigates whether occupational training networks enable the selection of apprentices to be less discriminatory. Training networks are a new organisational form of VET that is becoming increasingly widespread in Switzerland, as well as in Germany and Austria. In the Swiss model, an intermediary lead organisation recruits the…

Burnet Project

PubMed Central

Masellis, A.; Atiyeh, B.

2009-01-01

Summary The BurNet project, a pilot project of the Eumedis initiative, has become true. The Eumedis (EUro MEDiterranean Information Society) initiative is part of the MEDA programme of the EU to develop the Information Society in the Mediterranean area. In the health care sector, the objective of Eumedis is: the deployment of network-based solutions to interconnect - using userfriendly and affordable solutions - the actors at all levels of the "health care system" of the Euro-Mediterranean region. The Bur Net project interconnects 17 Burn Centres (BC) in the Mediterranean Area through an information network both to standardize courses of action in the field of prevention, treatment, and functional and psychological rehabilitation of burn patients and to coordinate interactions between BC and emergency rooms in peripheral hospitals using training/information activities and telemedicine to optimize first aid provided to burn patients before referral to a BC. Shared procedure protocols for prevention and the care and rehabilitation of patients, both at individual and mass level, will help to create an international specialized database and a Webbased teleconsultation system. PMID:21991176

A Regularizer Approach for RBF Networks Under the Concurrent Weight Failure Situation.

PubMed

Leung, Chi-Sing; Wan, Wai Yan; Feng, Ruibin

2017-06-01

Many existing results on fault-tolerant algorithms focus on the single fault source situation, where a trained network is affected by one kind of weight failure. In fact, a trained network may be affected by multiple kinds of weight failure. This paper first studies how the open weight fault and the multiplicative weight noise degrade the performance of radial basis function (RBF) networks. Afterward, we define the objective function for training fault-tolerant RBF networks. Based on the objective function, we then develop two learning algorithms, one batch mode and one online mode. Besides, the convergent conditions of our online algorithm are investigated. Finally, we develop a formula to estimate the test set error of faulty networks trained from our approach. This formula helps us to optimize some tuning parameters, such as RBF width.

Prediction of air pollutant concentration based on sparse response back-propagation training feedforward neural networks.

PubMed

Ding, Weifu; Zhang, Jiangshe; Leung, Yee

2016-10-01

In this paper, we predict air pollutant concentration using a feedforward artificial neural network inspired by the mechanism of the human brain as a useful alternative to traditional statistical modeling techniques. The neural network is trained based on sparse response back-propagation in which only a small number of neurons respond to the specified stimulus simultaneously and provide a high convergence rate for the trained network, in addition to low energy consumption and greater generalization. Our method is evaluated on Hong Kong air monitoring station data and corresponding meteorological variables for which five air quality parameters were gathered at four monitoring stations in Hong Kong over 4 years (2012-2015). Our results show that our training method has more advantages in terms of the precision of the prediction, effectiveness, and generalization of traditional linear regression algorithms when compared with a feedforward artificial neural network trained using traditional back-propagation.

Digital intelligent booster for DCC miniature train networks

NASA Astrophysics Data System (ADS)

Ursu, M. P.; Condruz, D. A.

2017-08-01

Modern miniature trains are now driven by means of the DCC (Digital Command and Control) system, which allows the human operator or a personal computer to launch commands to each individual train or even to control different features of the same train. The digital command station encodes these commands and sends them to the trains by means of electrical pulses via the rails of the railway network. Due to the development of the miniature railway network, it may happen that the power requirement of the increasing number of digital locomotives, carriages and accessories exceeds the nominal output power of the digital command station. This digital intelligent booster relieves the digital command station from powering the entire railway network all by itself, and it automatically handles the multiple powered sections of the network. This electronic device is also able to detect and process short-circuits and overload conditions, without the intervention of the digital command station.

Building partnerships towards strengthening Makerere University College of Health Sciences: a stakeholder and sustainability analysis

PubMed Central

2011-01-01

Background Partnerships and networking are important for an institution of higher learning like Makerere University College of Health Sciences (MakCHS) to be competitive and sustainable. Methods A stakeholder and sustainability analysis of 25 key informant interviews was conducted among past, current and potential stakeholders of MakCHS to obtain their perspectives and contributions to sustainability of the College in its role to improve health outcomes. Results The College has multiple internal and external stakeholders. Stakeholders from Uganda wanted the College to use its enormous academic capacity to fulfil its vision, take initiative, and be innovative in conducting more research and training relevant to the country’s health needs. Many stakeholders felt that the initiative for collaboration currently came more from the stakeholders than the College. External stakeholders felt that MakCHS was insufficiently marketing itself and not directly engaging the private sector or Parliament. Stakeholders also identified the opportunity for MakCHS to embrace information technology in research, learning and training, and many also wanted MakCHS to start leadership and management training programmes in health systems. The need for MakCHS to be more vigorous in training to enhance professionalism and ethical conduct was also identified. Discussion As a constituent of a public university, MakCHS has relied on public funding, which has been inadequate to fulfill its mission. Broader networking, marketing to mobilize resources, and providing strong leadership and management support to inspire confidence among its current and potential stakeholders will be essential to MakCHS’ further growth. MakCHS’ relevance is hinged on generating research knowledge for solving the country’s contemporary health problems and starting relevant programs and embracing technologies. It should share new knowledge widely through publications and other forms of dissemination. Whether institutional leadership is best in the hands of academicians or professional managers is a debatable matter. Conclusions This study points towards the need for MakCHS and other African public universities to build a broad network of partnerships to strengthen their operations, relevance, and sustainability. Conducting stakeholder and sustainability analyses are instructive toward this end, and have provided information and perspectives on how to make long-range informed choices for success. PMID:21411001

Real-time Adaptive Control Using Neural Generalized Predictive Control

NASA Technical Reports Server (NTRS)

Haley, Pam; Soloway, Don; Gold, Brian

1999-01-01

The objective of this paper is to demonstrate the feasibility of a Nonlinear Generalized Predictive Control algorithm by showing real-time adaptive control on a plant with relatively fast time-constants. Generalized Predictive Control has classically been used in process control where linear control laws were formulated for plants with relatively slow time-constants. The plant of interest for this paper is a magnetic levitation device that is nonlinear and open-loop unstable. In this application, the reference model of the plant is a neural network that has an embedded nominal linear model in the network weights. The control based on the linear model provides initial stability at the beginning of network training. In using a neural network the control laws are nonlinear and online adaptation of the model is possible to capture unmodeled or time-varying dynamics. Newton-Raphson is the minimization algorithm. Newton-Raphson requires the calculation of the Hessian, but even with this computational expense the low iteration rate make this a viable algorithm for real-time control.

Training a whole-book LSTM-based recognizer with an optimal training set

NASA Astrophysics Data System (ADS)

Soheili, Mohammad Reza; Yousefi, Mohammad Reza; Kabir, Ehsanollah; Stricker, Didier

2018-04-01

Despite the recent progress in OCR technologies, whole-book recognition, is still a challenging task, in particular in case of old and historical books, that the unknown font faces or low quality of paper and print contributes to the challenge. Therefore, pre-trained recognizers and generic methods do not usually perform up to required standards, and usually the performance degrades for larger scale recognition tasks, such as of a book. Such reportedly low error-rate methods turn out to require a great deal of manual correction. Generally, such methodologies do not make effective use of concepts such redundancy in whole-book recognition. In this work, we propose to train Long Short Term Memory (LSTM) networks on a minimal training set obtained from the book to be recognized. We show that clustering all the sub-words in the book, and using the sub-word cluster centers as the training set for the LSTM network, we can train models that outperform any identical network that is trained with randomly selected pages of the book. In our experiments, we also show that although the sub-word cluster centers are equivalent to about 8 pages of text for a 101- page book, a LSTM network trained on such a set performs competitively compared to an identical network that is trained on a set of 60 randomly selected pages of the book.

A feasibility study of stateful automaton packet inspection for streaming application detection systems

NASA Astrophysics Data System (ADS)

Tseng, Kuo-Kun; Lo, Jiao; Liu, Yiming; Chang, Shih-Hao; Merabti, Madjid; Ng, Felix, C. K.; Wu, C. H.

2017-10-01

The rapid development of the internet has brought huge benefits and social impacts; however, internet security has also become a great problem for users, since traditional approaches to packet classification cannot achieve satisfactory detection performance due to their low accuracy and efficiency. In this paper, a new stateful packet inspection method is introduced, which can be embedded in the network gateway and used by a streaming application detection system. This new detection method leverages the inexact automaton approach, using part of the header field and part of the application layer data of a packet. Based on this approach, an advanced detection system is proposed for streaming applications. The workflow of the system involves two stages: the training stage and the detection stage. In the training stage, the system initially captures characteristic patterns from a set of application packet flows. After this training is completed, the detection stage allows the user to detect the target application by capturing new application flows. This new detection approach is also evaluated using experimental analysis; the results of this analysis show that this new approach not only simplifies the management of the state detection system, but also improves the accuracy of data flow detection, making it feasible for real-world network applications.

AcademyHealth's Delivery System Science Fellowship: Training Embedded Researchers to Design, Implement, and Evaluate New Models of Care.

PubMed

Kanani, Nisha; Hahn, Erin; Gould, Michael; Brunisholz, Kimberly; Savitz, Lucy; Holve, Erin

2017-07-01

AcademyHealth's Delivery System Science Fellowship (DSSF) provides a paid postdoctoral pragmatic learning experience to build capacity within learning healthcare systems to conduct research in applied settings. The fellowship provides hands-on training and professional leadership opportunities for researchers. Since its inception in 2012, the program has grown rapidly, with 16 health systems participating in the DSSF to date. In addition to specific projects conducted within health systems (and numerous publications associated with those initiatives), the DSSF has made several broader contributions to the field, including defining delivery system science, identifying a set of training objectives for researchers working in delivery systems, and developing a national collaborative network of care delivery organizations, operational leaders, and trainees. The DSSF is one promising approach to support higher-value care by promoting continuous learning and improvement in health systems. © 2017 Society of Hospital Medicine.

Functional electrical stimulation controlled by artificial neural networks: pilot experiments with simple movements are promising for rehabilitation applications.

PubMed

Ferrante, Simona; Pedrocchi, Alessandra; Iannò, Marco; De Momi, Elena; Ferrarin, Maurizio; Ferrigno, Giancarlo

2004-01-01

This study falls within the ambit of research on functional electrical stimulation for the design of rehabilitation training for spinal cord injured patients. In this context, a crucial issue is the control of the stimulation parameters in order to optimize the patterns of muscle activation and to increase the duration of the exercises. An adaptive control system (NEURADAPT) based on artificial neural networks (ANNs) was developed to control the knee joint in accordance with desired trajectories by stimulating quadriceps muscles. This strategy includes an inverse neural model of the stimulated limb in the feedforward line and a neural network trained on-line in the feedback loop. NEURADAPT was compared with a linear closed-loop proportional integrative derivative (PID) controller and with a model-based neural controller (NEUROPID). Experiments on two subjects (one healthy and one paraplegic) show the good performance of NEURADAPT, which is able to reduce the time lag introduced by the PID controller. In addition, control systems based on ANN techniques do not require complicated calibration procedures at the beginning of each experimental session. After the initial learning phase, the ANN, thanks to its generalization capacity, is able to cope with a certain range of variability of skeletal muscle properties.

Application of adaptive boosting to EP-derived multilayer feed-forward neural networks (MLFN) to improve benign/malignant breast cancer classification

NASA Astrophysics Data System (ADS)

Land, Walker H., Jr.; Masters, Timothy D.; Lo, Joseph Y.; McKee, Dan

2001-07-01

A new neural network technology was developed for improving the benign/malignant diagnosis of breast cancer using mammogram findings. A new paradigm, Adaptive Boosting (AB), uses a markedly different theory in solutioning Computational Intelligence (CI) problems. AB, a new machine learning paradigm, focuses on finding weak learning algorithm(s) that initially need to provide slightly better than random performance (i.e., approximately 55%) when processing a mammogram training set. Then, by successive development of additional architectures (using the mammogram training set), the adaptive boosting process improves the performance of the basic Evolutionary Programming derived neural network architectures. The results of these several EP-derived hybrid architectures are then intelligently combined and tested using a similar validation mammogram data set. Optimization focused on improving specificity and positive predictive value at very high sensitivities, where an analysis of the performance of the hybrid would be most meaningful. Using the DUKE mammogram database of 500 biopsy proven samples, on average this hybrid was able to achieve (under statistical 5-fold cross-validation) a specificity of 48.3% and a positive predictive value (PPV) of 51.8% while maintaining 100% sensitivity. At 97% sensitivity, a specificity of 56.6% and a PPV of 55.8% were obtained.

Mapping, Awareness, And Virtualization Network Administrator Training Tool Virtualization Module

DTIC Science & Technology

2016-03-01

AND VIRTUALIZATION NETWORK ADMINISTRATOR TRAINING TOOL VIRTUALIZATION MODULE by Erik W. Berndt March 2016 Thesis Advisor: John Gibson...REPORT TYPE AND DATES COVERED Master’s thesis 4. TITLE AND SUBTITLE MAPPING, AWARENESS, AND VIRTUALIZATION NETWORK ADMINISTRATOR TRAINING TOOL... VIRTUALIZATION MODULE 5. FUNDING NUMBERS 6. AUTHOR(S) Erik W. Berndt 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) Naval Postgraduate School

Social Networking in School Psychology Training Programs: A Survey of Faculty and Graduate Students

ERIC Educational Resources Information Center

Pham, Andy V.; Goforth, Anisa N.; Segool, Natasha; Burt, Isaac

2014-01-01

The increasing use of social networking sites has become an emerging focus in school psychology training, policy, and research. The purpose of the current study is to present data from a survey on social networking among faculty and graduate students in school psychology training programs. A total of 110 faculty and 112 graduate students in school…

West Hills College Cooperative Training Network. Final Performance and Financial Status Report.

ERIC Educational Resources Information Center

West Hills Community Coll., Coalinga, CA.

A cooperative training network was developed by West Hills Community College (Coalinga, California), in conjunction with government agencies/private businesses, to train students in truck driving skills. Emphasis was placed on training women, members of minority groups, and disadvantaged persons. During the project, an advisory council was…

West Hills College Cooperative Training Network. Truck Driving Program. Dissemination Workbook.

ERIC Educational Resources Information Center

West Hills Community Coll., Coalinga, CA.

A cooperative training network was developed by West Hills Community College (Coalinga, California) in conjunction with government agencies/private businesses to train students in truck driving skills. Emphasis was placed on training women, members of minority groups, and disadvantaged persons. During the project, an advisory council was…

DSN test and training system

NASA Technical Reports Server (NTRS)

Thorman, H. C.

1975-01-01

Key characteristics of the Deep Space Network Test and Training System were presented. Completion of the Mark III-75 system implementation is reported. Plans are summarized for upgrading the system to a Mark III-77 configuration to support Deep Space Network preparations for the Mariner Jupiter/Saturn 1977 and Pioneer Venus 1978 missions. A general description of the Deep Space Station, Ground Communications Facility, and Network Operations Control Center functions that comprise the Deep Space Network Test and Training System is also presented.

Application of Two-Dimensional AWE Algorithm in Training Multi-Dimensional Neural Network Model

DTIC Science & Technology

2003-07-01

hybrid scheme . the general neural network method (Table 3.1). The training process of the software- ACKNOWLEDGMENT "Neuralmodeler" is shown in Fig. 3.2...engineering. Artificial neural networks (ANNs) have emerged Training a neural network model is the key of as a powerful technique for modeling general neural...coefficients am, the derivatives method of moments (MoM). The variables in the of matrix I have to be generated . A closed form model are frequency

Training trajectories by continuous recurrent multilayer networks.

PubMed

Leistritz, L; Galicki, M; Witte, H; Kochs, E

2002-01-01

This paper addresses the problem of training trajectories by means of continuous recurrent neural networks whose feedforward parts are multilayer perceptrons. Such networks can approximate a general nonlinear dynamic system with arbitrary accuracy. The learning process is transformed into an optimal control framework where the weights are the controls to be determined. A training algorithm based upon a variational formulation of Pontryagin's maximum principle is proposed for such networks. Computer examples demonstrating the efficiency of the given approach are also presented.

Two neural network algorithms for designing optimal terminal controllers with open final time

NASA Technical Reports Server (NTRS)

Plumer, Edward S.

1992-01-01

Multilayer neural networks, trained by the backpropagation through time algorithm (BPTT), have been used successfully as state-feedback controllers for nonlinear terminal control problems. Current BPTT techniques, however, are not able to deal systematically with open final-time situations such as minimum-time problems. Two approaches which extend BPTT to open final-time problems are presented. In the first, a neural network learns a mapping from initial-state to time-to-go. In the second, the optimal number of steps for each trial run is found using a line-search. Both methods are derived using Lagrange multiplier techniques. This theoretical framework is used to demonstrate that the derived algorithms are direct extensions of forward/backward sweep methods used in N-stage optimal control. The two algorithms are tested on a Zermelo problem and the resulting trajectories compare favorably to optimal control results.

A statistical framework for evaluating neural networks to predict recurrent events in breast cancer

NASA Astrophysics Data System (ADS)

Gorunescu, Florin; Gorunescu, Marina; El-Darzi, Elia; Gorunescu, Smaranda

2010-07-01

Breast cancer is the second leading cause of cancer deaths in women today. Sometimes, breast cancer can return after primary treatment. A medical diagnosis of recurrent cancer is often a more challenging task than the initial one. In this paper, we investigate the potential contribution of neural networks (NNs) to support health professionals in diagnosing such events. The NN algorithms are tested and applied to two different datasets. An extensive statistical analysis has been performed to verify our experiments. The results show that a simple network structure for both the multi-layer perceptron and radial basis function can produce equally good results, not all attributes are needed to train these algorithms and, finally, the classification performances of all algorithms are statistically robust. Moreover, we have shown that the best performing algorithm will strongly depend on the features of the datasets, and hence, there is not necessarily a single best classifier.

Real-time camera-based face detection using a modified LAMSTAR neural network system

NASA Astrophysics Data System (ADS)

Girado, Javier I.; Sandin, Daniel J.; DeFanti, Thomas A.; Wolf, Laura K.

2003-03-01

This paper describes a cost-effective, real-time (640x480 at 30Hz) upright frontal face detector as part of an ongoing project to develop a video-based, tetherless 3D head position and orientation tracking system. The work is specifically targeted for auto-stereoscopic displays and projection-based virtual reality systems. The proposed face detector is based on a modified LAMSTAR neural network system. At the input stage, after achieving image normalization and equalization, a sub-window analyzes facial features using a neural network. The sub-window is segmented, and each part is fed to a neural network layer consisting of a Kohonen Self-Organizing Map (SOM). The output of the SOM neural networks are interconnected and related by correlation-links, and can hence determine the presence of a face with enough redundancy to provide a high detection rate. To avoid tracking multiple faces simultaneously, the system is initially trained to track only the face centered in a box superimposed on the display. The system is also rotationally and size invariant to a certain degree.

Determination of the mechanical and physical properties of cartilage by coupling poroelastic-based finite element models of indentation with artificial neural networks.

PubMed

Arbabi, Vahid; Pouran, Behdad; Campoli, Gianni; Weinans, Harrie; Zadpoor, Amir A

2016-03-21

One of the most widely used techniques to determine the mechanical properties of cartilage is based on indentation tests and interpretation of the obtained force-time or displacement-time data. In the current computational approaches, one needs to simulate the indentation test with finite element models and use an optimization algorithm to estimate the mechanical properties of cartilage. The modeling procedure is cumbersome, and the simulations need to be repeated for every new experiment. For the first time, we propose a method for fast and accurate estimation of the mechanical and physical properties of cartilage as a poroelastic material with the aid of artificial neural networks. In our study, we used finite element models to simulate the indentation for poroelastic materials with wide combinations of mechanical and physical properties. The obtained force-time curves are then divided into three parts: the first two parts of the data is used for training and validation of an artificial neural network, while the third part is used for testing the trained network. The trained neural network receives the force-time curves as the input and provides the properties of cartilage as the output. We observed that the trained network could accurately predict the properties of cartilage within the range of properties for which it was trained. The mechanical and physical properties of cartilage could therefore be estimated very fast, since no additional finite element modeling is required once the neural network is trained. The robustness of the trained artificial neural network in determining the properties of cartilage based on noisy force-time data was assessed by introducing noise to the simulated force-time data. We found that the training procedure could be optimized so as to maximize the robustness of the neural network against noisy force-time data. Copyright © 2016 Elsevier Ltd. All rights reserved.

Development of Innovative Technology to Provide Low-Cost Surface Atmospheric Observations

NASA Astrophysics Data System (ADS)

Kucera, Paul; Steinson, Martin

2016-04-01

Accurate and reliable real-time monitoring and dissemination of observations of surface weather conditions is critical for a variety of societal applications. Applications that provide local and regional information about temperature, precipitation, moisture, and winds, for example, are important for agriculture, water resource monitoring, health, and monitoring of hazard weather conditions. In many regions in Africa (and other global locations), surface weather stations are sparsely located and/or of poor quality. Existing stations have often been sited incorrectly, not well-maintained, and have limited communications established at the site for real-time monitoring. The US National Weather Service (NWS) International Activities Office (IAO) in partnership with University Corporation for Atmospheric Research (UCAR)/National Center for Atmospheric Research (NCAR) and funded by the United States Agency for International Development (USAID) Office of Foreign Disaster Assistance (OFDA) has started an initiative to develop and deploy low-cost weather instrumentation in sparsely observed regions of the world. The goal is to provide observations for environmental monitoring, and early warning alert systems that can be deployed at weather services in developing countries. Instrumentation is being designed using innovative new technologies such as 3D printers, Raspberry Pi computing systems, and wireless communications. The initial effort is focused on designing a surface network using GIS-based tools, deploying an initial network in Zambia, and providing training to Zambia Meteorological Department (ZMD) staff. The presentation will provide an overview of the project concepts, design of the low cost instrumentation, and initial experiences deploying a surface network deployment in Zambia.

The Medical and Nursing Education Partnership Initiatives.

PubMed

Goosby, Eric P; von Zinkernagel, Deborah

2014-08-01

The Medical Education Partnership Initiative (MEPI) and Nursing Education Partnership Initiative (NEPI) are innovative approaches to strengthening the academic and clinical training of physicians and nurses in Sub-Saharan African countries, which are heavily burdened by HIV/AIDS. Begun in 2010 by the U.S. President's Emergency Plan for AIDS Relief with the National Institutes of Health, investments in curricula, innovative learning technologies, clinical mentoring, and research opportunities are providing a strong base to advance high-quality education for growing numbers of urgently needed new physicians and nurses in these countries. The MEPI and NEPI focus on strengthening learning institutions is central to the vision for expanding the pool of health professionals to meet the full range of a country's health needs. A robust network of exchange between education institutions and training facilities, both within and across countries, is transforming the quality of medical education and augmenting a platform for research opportunities for faculty and clinicians, which also serves as an incentive to retain professionals in the country. Excellence in patient care and a spirit of professionalism, core to MEPI and NEPI, provide a strong foundation for the planning and delivery of health services in participating countries.

Evaluation of the impact of deep learning architectural components selection and dataset size on a medical imaging task

NASA Astrophysics Data System (ADS)

Dutta, Sandeep; Gros, Eric

2018-03-01

Deep Learning (DL) has been successfully applied in numerous fields fueled by increasing computational power and access to data. However, for medical imaging tasks, limited training set size is a common challenge when applying DL. This paper explores the applicability of DL to the task of classifying a single axial slice from a CT exam into one of six anatomy regions. A total of 29000 images selected from 223 CT exams were manually labeled for ground truth. An additional 54 exams were labeled and used as an independent test set. The network architecture developed for this application is composed of 6 convolutional layers and 2 fully connected layers with RELU non-linear activations between each layer. Max-pooling was used after every second convolutional layer, and a softmax layer was used at the end. Given this base architecture, the effect of inclusion of network architecture components such as Dropout and Batch Normalization on network performance and training is explored. The network performance as a function of training and validation set size is characterized by training each network architecture variation using 5,10,20,40,50 and 100% of the available training data. The performance comparison of the various network architectures was done for anatomy classification as well as two computer vision datasets. The anatomy classifier accuracy varied from 74.1% to 92.3% in this study depending on the training size and network layout used. Dropout layers improved the model accuracy for all training sizes.

Training the Trainers of Tomorrow Today - driving excellence in medical education.

PubMed

Fellow-Smith, Elizabeth; Beveridge, Ed; Hogben, Katy; Wilson, Graeme; Lowe, John; Abraham, Rachel; Ingle, Digby; Bennett, Danielle; Hernandez, Carol

2013-01-01

Training the Trainers of Tomorrow Today (T4) is a new way to deliver "Training for Trainers". Responding to local dissatisfaction with existing arrangements, T4 builds on 3 essential requirements for a future shape of training: 1. Clinical Leadership and a Collaborative Approach 2. Cross-Specialty Design and Participation 3. Local Delivery and Governance Networks Design principles also included: 3 levels of training to reflect differing needs of clinical supervisors, educational supervisors and medical education leader, mapping to GMC requirements and the London Deanery's Professional Development Framework; alignment of service, educational theory and research; recognition of challenges in delivering and ensuring attendance in busy acute and mental health settings, and the development of a faculty network. The delivery plan took into account census of professional development uptake and GMC Trainee Surveys. Strong engagement and uptake from the 11 Trusts in NW London has been achieved, with powerful penetration into all specialties. Attendance has exceeded expectations. Against an initial 12 month target of 350 attendances, 693 were achieved in the first 8 months. Evaluation of content demonstrates modules are pitched appropriately to attendees needs, with positive feedback from trainers new to the role. Delivery style has attracted high ratings of satisfaction: 87% attendees rating delivery as "good\\excellent". External evaluation of impact demonstrated improved training experiences through changes in supervision, the learning environment and understanding of learning styles. We have addressed sustainability of the programme by advertising and recruiting Local Faculty Development Trainers. Volunteer consultants and higher trainees are trained to deliver the programme on a cascade model, supported by the Specialty Tutors, individual coaching and educational bursaries. The Trainers are local champions for excellence in training, provide a communication between the programme and local providers, are a repository of expertise in their service, and trouble shoot local barriers to engagement.

UAV Trajectory Modeling Using Neural Networks

NASA Technical Reports Server (NTRS)

Xue, Min

2017-01-01

Large amount of small Unmanned Aerial Vehicles (sUAVs) are projected to operate in the near future. Potential sUAV applications include, but not limited to, search and rescue, inspection and surveillance, aerial photography and video, precision agriculture, and parcel delivery. sUAVs are expected to operate in the uncontrolled Class G airspace, which is at or below 500 feet above ground level (AGL), where many static and dynamic constraints exist, such as ground properties and terrains, restricted areas, various winds, manned helicopters, and conflict avoidance among sUAVs. How to enable safe, efficient, and massive sUAV operations at the low altitude airspace remains a great challenge. NASA's Unmanned aircraft system Traffic Management (UTM) research initiative works on establishing infrastructure and developing policies, requirement, and rules to enable safe and efficient sUAVs' operations. To achieve this goal, it is important to gain insights of future UTM traffic operations through simulations, where the accurate trajectory model plays an extremely important role. On the other hand, like what happens in current aviation development, trajectory modeling should also serve as the foundation for any advanced concepts and tools in UTM. Accurate models of sUAV dynamics and control systems are very important considering the requirement of the meter level precision in UTM operations. The vehicle dynamics are relatively easy to derive and model, however, vehicle control systems remain unknown as they are usually kept by manufactures as a part of intellectual properties. That brings challenges to trajectory modeling for sUAVs. How to model the vehicle's trajectories with unknown control system? This work proposes to use a neural network to model a vehicle's trajectory. The neural network is first trained to learn the vehicle's responses at numerous conditions. Once being fully trained, given current vehicle states, winds, and desired future trajectory, the neural network should be able to predict the vehicle's future states at next time step. A complete 4-D trajectory are then generated step by step using the trained neural network. Experiments in this work show that the neural network can approximate the sUAV's model and predict the trajectory accurately.

Beyond Fine Tuning: Adding capacity to leverage few labels

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

Hodas, Nathan O.; Shaffer, Kyle J.; Yankov, Artem

2017-12-09

In this paper we present a technique to train neural network models on small amounts of data. Current methods for training neural networks on small amounts of rich data typically rely on strategies such as fine-tuning a pre-trained neural networks or the use of domain-specific hand-engineered features. Here we take the approach of treating network layers, or entire networks, as modules and combine pre-trained modules with untrained modules, to learn the shift in distributions between data sets. The central impact of using a modular approach comes from adding new representations to a network, as opposed to replacing representations via fine-tuning.more » Using this technique, we are able surpass results using standard fine-tuning transfer learning approaches, and we are also able to significantly increase performance over such approaches when using smaller amounts of data.« less

Flexible body control using neural networks

NASA Technical Reports Server (NTRS)

Mccullough, Claire L.

1992-01-01

Progress is reported on the control of Control Structures Interaction suitcase demonstrator (a flexible structure) using neural networks and fuzzy logic. It is concluded that while control by neural nets alone (i.e., allowing the net to design a controller with no human intervention) has yielded less than optimal results, the neural net trained to emulate the existing fuzzy logic controller does produce acceptible system responses for the initial conditions examined. Also, a neural net was found to be very successful in performing the emulation step necessary for the anticipatory fuzzy controller for the CSI suitcase demonstrator. The fuzzy neural hybrid, which exhibits good robustness and noise rejection properties, shows promise as a controller for practical flexible systems, and should be further evaluated.

A Control Simulation Method of High-Speed Trains on Railway Network with Irregular Influence

NASA Astrophysics Data System (ADS)

Yang, Li-Xing; Li, Xiang; Li, Ke-Ping

2011-09-01

Based on the discrete time method, an effective movement control model is designed for a group of highspeed trains on a rail network. The purpose of the model is to investigate the specific traffic characteristics of high-speed trains under the interruption of stochastic irregular events. In the model, the high-speed rail traffic system is supposed to be equipped with the moving-block signalling system to guarantee maximum traversing capacity of the railway. To keep the safety of trains' movements, some operational strategies are proposed to control the movements of trains in the model, including traction operation, braking operation, and entering-station operation. The numerical simulations show that the designed model can well describe the movements of high-speed trains on the rail network. The research results can provide the useful information not only for investigating the propagation features of relevant delays under the irregular disturbance but also for rerouting and rescheduling trains on the rail network.

Artificial neural network prediction of aircraft aeroelastic behavior

NASA Astrophysics Data System (ADS)

Pesonen, Urpo Juhani

An Artificial Neural Network that predicts aeroelastic behavior of aircraft is presented. The neural net was designed to predict the shape of a flexible wing in static flight conditions using results from a structural analysis and an aerodynamic analysis performed with traditional computational tools. To generate reliable training and testing data for the network, an aeroelastic analysis code using these tools as components was designed and validated. To demonstrate the advantages and reliability of Artificial Neural Networks, a network was also designed and trained to predict airfoil maximum lift at low Reynolds numbers where wind tunnel data was used for the training. Finally, a neural net was designed and trained to predict the static aeroelastic behavior of a wing without the need to iterate between the structural and aerodynamic solvers.

Computer interpretation of thallium SPECT studies based on neural network analysis

NASA Astrophysics Data System (ADS)

Wang, David C.; Karvelis, K. C.

1991-06-01

A class of artificial intelligence (Al) programs known as neural networks are well suited to pattern recognition. A neural network is trained rather than programmed to recognize patterns. This differs from "expert system" Al programs in that it is not following an extensive set of rules determined by the programmer, but rather bases its decision on a gestalt interpretation of the image. The "bullseye" images from cardiac stress thallium tests performed on 50 male patients, as well as several simulated images were used to train the network. The network was able to accurately classify all patients in the training set. The network was then tested against 50 unknown patients and was able to correctly categorize 77% of the areas of ischemia and 92% of the areas of infarction. While not yet matching the ability of a trained physician, the neural network shows great promise in this area and has potential application in other areas of medical imaging.

Reward-based training of recurrent neural networks for cognitive and value-based tasks

PubMed Central

Song, H Francis; Yang, Guangyu R; Wang, Xiao-Jing

2017-01-01

Trained neural network models, which exhibit features of neural activity recorded from behaving animals, may provide insights into the circuit mechanisms of cognitive functions through systematic analysis of network activity and connectivity. However, in contrast to the graded error signals commonly used to train networks through supervised learning, animals learn from reward feedback on definite actions through reinforcement learning. Reward maximization is particularly relevant when optimal behavior depends on an animal’s internal judgment of confidence or subjective preferences. Here, we implement reward-based training of recurrent neural networks in which a value network guides learning by using the activity of the decision network to predict future reward. We show that such models capture behavioral and electrophysiological findings from well-known experimental paradigms. Our work provides a unified framework for investigating diverse cognitive and value-based computations, and predicts a role for value representation that is essential for learning, but not executing, a task. DOI: http://dx.doi.org/10.7554/eLife.21492.001 PMID:28084991

A "Quiet Revolution"? The Impact of Training Schools on Initial Teacher Training Partnerships

ERIC Educational Resources Information Center

Brooks, Val

2006-01-01

This paper discusses the impact on initial teacher training of a new policy initiative in England: the introduction of Training Schools. First, the Training School project is set in context by exploring the evolution of a partnership approach to initial teacher training in England. Ways in which Training Schools represent a break with established…

Fast temporal neural learning using teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Bahren, Jacob (Inventor)

1992-01-01

A neural network is trained to output a time dependent target vector defined over a predetermined time interval in response to a time dependent input vector defined over the same time interval by applying corresponding elements of the error vector, or difference between the target vector and the actual neuron output vector, to the inputs of corresponding output neurons of the network as corrective feedback. This feedback decreases the error and quickens the learning process, so that a much smaller number of training cycles are required to complete the learning process. A conventional gradient descent algorithm is employed to update the neural network parameters at the end of the predetermined time interval. The foregoing process is repeated in repetitive cycles until the actual output vector corresponds to the target vector. In the preferred embodiment, as the overall error of the neural network output decreasing during successive training cycles, the portion of the error fed back to the output neurons is decreased accordingly, allowing the network to learn with greater freedom from teacher forcing as the network parameters converge to their optimum values. The invention may also be used to train a neural network with stationary training and target vectors.

Fast temporal neural learning using teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad (Inventor); Bahren, Jacob (Inventor)

1995-01-01

A neural network is trained to output a time dependent target vector defined over a predetermined time interval in response to a time dependent input vector defined over the same time interval by applying corresponding elements of the error vector, or difference between the target vector and the actual neuron output vector, to the inputs of corresponding output neurons of the network as corrective feedback. This feedback decreases the error and quickens the learning process, so that a much smaller number of training cycles are required to complete the learning process. A conventional gradient descent algorithm is employed to update the neural network parameters at the end of the predetermined time interval. The foregoing process is repeated in repetitive cycles until the actual output vector corresponds to the target vector. In the preferred embodiment, as the overall error of the neural network output decreasing during successive training cycles, the portion of the error fed back to the output neurons is decreased accordingly, allowing the network to learn with greater freedom from teacher forcing as the network parameters converge to their optimum values. The invention may also be used to train a neural network with stationary training and target vectors.

Landslide Susceptibility Index Determination Using Aritificial Neural Network

NASA Astrophysics Data System (ADS)

Kawabata, D.; Bandibas, J.; Urai, M.

2004-12-01

The occurrence of landslide is the result of the interaction of complex and diverse environmental factors. The geomorphic features, rock types and geologic structure are especially important base factors of the landslide occurrence. Generating landslide susceptibility index by defining the relationship between landslide occurrence and that base factors using conventional mathematical and statistical methods is very difficult and inaccurate. This study focuses on generating landslide susceptibility index using artificial neural networks in Southern Japanese Alps. The training data are geomorphic (e.g. altitude, slope and aspect) and geologic parameters (e.g. rock type, distance from geologic boundary and geologic dip-strike angle) and landslides. Artificial neural network structure and training scheme are formulated to generate the index. Data from areas with and without landslide occurrences are used to train the network. The network is trained to output 1 when the input data are from areas with landslides and 0 when no landslide occurred. The trained network generates an output ranging from 0 to 1 reflecting the possibility of landslide occurrence based on the inputted data. Output values nearer to 1 means higher possibility of landslide occurrence. The artificial neural network model is incorporated into the GIS software to generate a landslide susceptibility map.

14 CFR 135.343 - Crewmember initial and recurrent training requirements.

Code of Federal Regulations, 2010 CFR

2010-01-01

... has completed the appropriate initial or recurrent training phase of the training program appropriate... 14 Aeronautics and Space 3 2010-01-01 2010-01-01 false Crewmember initial and recurrent training... Training § 135.343 Crewmember initial and recurrent training requirements. No certificate holder may use a...

Volunteer provision of long-term care for older people in Thailand and Costa Rica.

PubMed

Lloyd-Sherlock, Peter; Pot, Anne Margriet; Sasat, Siriphan; Morales-Martinez, Fernando

2017-11-01

Demand for long-term care services for older people is increasing rapidly in low- and middle-income countries. Countries need to establish national long-term care systems that are sustainable and equitable. The Governments of Costa Rica and Thailand have implemented broadly comparable interventions to deploy volunteers in long-term home care. Both countries trained older volunteers from local communities to make home visits to impoverished and vulnerable older people and to facilitate access to health services and other social services. Costa Rica and Thailand are upper-middle-income countries with strong traditions of community-based health services that they are now extending into long-term care for older people. Between 2003 and 2013 Thailand's programme trained over 51 000 volunteers, reaching almost 800 000 older people. Between 2010 and 2016 Costa Rica established 50 community care networks, serving around 10 000 people and involving over 5000 volunteers. Despite some evidence of benefits to the physical and mental health of older people and greater uptake of other services, a large burden of unmet care needs and signs of a growth of unregulated private services still exist. There is scope for low- and middle-income countries to develop large-scale networks of community-based long-term care volunteers. The capacity of volunteers to enhance the quality of life of clients is affected by the local availability of care services. Volunteer care networks should be complemented by other initiatives, including training about health in later life for volunteers, and investment in community long-term care services.

Collaborative Supervised Learning for Sensor Networks

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri L.; Rebbapragada, Umaa; Lane, Terran

2011-01-01

Collaboration methods for distributed machine-learning algorithms involve the specification of communication protocols for the learners, which can query other learners and/or broadcast their findings preemptively. Each learner incorporates information from its neighbors into its own training set, and they are thereby able to bootstrap each other to higher performance. Each learner resides at a different node in the sensor network and makes observations (collects data) independently of the other learners. After being seeded with an initial labeled training set, each learner proceeds to learn in an iterative fashion. New data is collected and classified. The learner can then either broadcast its most confident classifications for use by other learners, or can query neighbors for their classifications of its least confident items. As such, collaborative learning combines elements of both passive (broadcast) and active (query) learning. It also uses ideas from ensemble learning to combine the multiple responses to a given query into a single useful label. This approach has been evaluated against current non-collaborative alternatives, including training a single classifier and deploying it at all nodes with no further learning possible, and permitting learners to learn from their own most confident judgments, absent interaction with their neighbors. On several data sets, it has been consistently found that active collaboration is the best strategy for a distributed learner network. The main advantages include the ability for learning to take place autonomously by collaboration rather than by requiring intervention from an oracle (usually human), and also the ability to learn in a distributed environment, permitting decisions to be made in situ and to yield faster response time.

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.

Automated isotope identification algorithm using artificial neural networks

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

Kamuda, Mark; Stinnett, Jacob; Sullivan, Clair

There is a need to develop an algorithm that can determine the relative activities of radio-isotopes in a large dataset of low-resolution gamma-ray spectra that contains a mixture of many radio-isotopes. Low-resolution gamma-ray spectra that contain mixtures of radio-isotopes often exhibit feature over-lap, requiring algorithms that can analyze these features when overlap occurs. While machine learning and pattern recognition algorithms have shown promise for the problem of radio-isotope identification, their ability to identify and quantify mixtures of radio-isotopes has not been studied. Because machine learning algorithms use abstract features of the spectrum, such as the shape of overlapping peaks andmore » Compton continuum, they are a natural choice for analyzing radio-isotope mixtures. An artificial neural network (ANN) has be trained to calculate the relative activities of 32 radio-isotopes in a spectrum. Furthermore, the ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target radio-isotopes. In this paper we present our initial algorithms based on an ANN and evaluate them against a series measured and simulated spectra.« less

Automated isotope identification algorithm using artificial neural networks

DOE PAGES

Kamuda, Mark; Stinnett, Jacob; Sullivan, Clair

2017-04-12

There is a need to develop an algorithm that can determine the relative activities of radio-isotopes in a large dataset of low-resolution gamma-ray spectra that contains a mixture of many radio-isotopes. Low-resolution gamma-ray spectra that contain mixtures of radio-isotopes often exhibit feature over-lap, requiring algorithms that can analyze these features when overlap occurs. While machine learning and pattern recognition algorithms have shown promise for the problem of radio-isotope identification, their ability to identify and quantify mixtures of radio-isotopes has not been studied. Because machine learning algorithms use abstract features of the spectrum, such as the shape of overlapping peaks andmore » Compton continuum, they are a natural choice for analyzing radio-isotope mixtures. An artificial neural network (ANN) has be trained to calculate the relative activities of 32 radio-isotopes in a spectrum. Furthermore, the ANN is trained with simulated gamma-ray spectra, allowing easy expansion of the library of target radio-isotopes. In this paper we present our initial algorithms based on an ANN and evaluate them against a series measured and simulated spectra.« less

Training a Constitutional Dynamic Network for Effector Recognition: Storage, Recall, and Erasing of Information.

PubMed

Holub, Jan; Vantomme, Ghislaine; Lehn, Jean-Marie

2016-09-14

Constitutional dynamic libraries (CDLs) of hydrazones, acylhydrazones, and imines undergo reorganization and adaptation in response to chemical effectors (herein metal cations) via component exchange and selection. Such CDLs can be subjected to training by exposition to given effectors and keep memory of the information stored by interaction with a specific metal ion. The long-term storage of the acquired information into the set of constituents of the system allows for fast recognition on subsequent contacts with the same effector(s). Dynamic networks of constituents were designed to adapt orthogonally to different metal cations by up- and down-regulation of specific constituents in the final distribution. The memory may be erased by component exchange between the constituents so as to regenerate the initial (statistical) distribution. The libraries described represent constitutional dynamic systems capable of acting as information storage molecular devices, in which the presence of components linked by reversible covalent bonds in slow exchange and bearing adequate coordination sites allows for the adaptation to different metal ions by constitutional variation. The system thus performs information storage, recall, and erase processes.

The Effects of Long-term Abacus Training on Topological Properties of Brain Functional Networks.

PubMed

Weng, Jian; Xie, Ye; Wang, Chunjie; Chen, Feiyan

2017-08-18

Previous studies in the field of abacus-based mental calculation (AMC) training have shown that this training has the potential to enhance a wide variety of cognitive abilities. It can also generate specific changes in brain structure and function. However, there is lack of studies investigating the impact of AMC training on the characteristics of brain networks. In this study, utilizing graph-based network analysis, we compared topological properties of brain functional networks between an AMC group and a matched control group. Relative to the control group, the AMC group exhibited higher nodal degrees in bilateral calcarine sulcus and increased local efficiency in bilateral superior occipital gyrus and right cuneus. The AMC group also showed higher nodal local efficiency in right fusiform gyrus, which was associated with better math ability. However, no relationship was significant in the control group. These findings provide evidence that long-term AMC training may improve information processing efficiency in visual-spatial related regions, which extend our understanding of training plasticity at the brain network level.

Neural network computer simulation of medical aerosols.

PubMed

Richardson, C J; Barlow, D J

1996-06-01

Preliminary investigations have been conducted to assess the potential for using artificial neural networks to simulate aerosol behaviour, with a view to employing this type of methodology in the evaluation and design of pulmonary drug-delivery systems. Details are presented of the general purpose software developed for these tasks; it implements a feed-forward back-propagation algorithm with weight decay and connection pruning, the user having complete run-time control of the network architecture and mode of training. A series of exploratory investigations is then reported in which different network structures and training strategies are assessed in terms of their ability to simulate known patterns of fluid flow in simple model systems. The first of these involves simulations of cellular automata-generated data for fluid flow through a partially obstructed two-dimensional pipe. The artificial neural networks are shown to be highly successful in simulating the behaviour of this simple linear system, but with important provisos relating to the information content of the training data and the criteria used to judge when the network is properly trained. A second set of investigations is then reported in which similar networks are used to simulate patterns of fluid flow through aerosol generation devices, using training data furnished through rigorous computational fluid dynamics modelling. These more complex three-dimensional systems are modelled with equal success. It is concluded that carefully tailored, well trained networks could provide valuable tools not just for predicting but also for analysing the spatial dynamics of pharmaceutical aerosols.

Self-consistent determination of the spike-train power spectrum in a neural network with sparse connectivity.

PubMed

Dummer, Benjamin; Wieland, Stefan; Lindner, Benjamin

2014-01-01

A major source of random variability in cortical networks is the quasi-random arrival of presynaptic action potentials from many other cells. In network studies as well as in the study of the response properties of single cells embedded in a network, synaptic background input is often approximated by Poissonian spike trains. However, the output statistics of the cells is in most cases far from being Poisson. This is inconsistent with the assumption of similar spike-train statistics for pre- and postsynaptic cells in a recurrent network. Here we tackle this problem for the popular class of integrate-and-fire neurons and study a self-consistent statistics of input and output spectra of neural spike trains. Instead of actually using a large network, we use an iterative scheme, in which we simulate a single neuron over several generations. In each of these generations, the neuron is stimulated with surrogate stochastic input that has a similar statistics as the output of the previous generation. For the surrogate input, we employ two distinct approximations: (i) a superposition of renewal spike trains with the same interspike interval density as observed in the previous generation and (ii) a Gaussian current with a power spectrum proportional to that observed in the previous generation. For input parameters that correspond to balanced input in the network, both the renewal and the Gaussian iteration procedure converge quickly and yield comparable results for the self-consistent spike-train power spectrum. We compare our results to large-scale simulations of a random sparsely connected network of leaky integrate-and-fire neurons (Brunel, 2000) and show that in the asynchronous regime close to a state of balanced synaptic input from the network, our iterative schemes provide an excellent approximations to the autocorrelation of spike trains in the recurrent network.

Primary Care Providers’ Initial Treatment Decisions and Antidepressant Prescribing for Adolescent Depression

PubMed Central

Radovic, Ana; Farris, Coreen; Reynolds, Kerry; Reis, Evelyn C.; Miller, Elizabeth; Stein, Bradley D.

2014-01-01

OBJECTIVE Adolescent depression is a serious and undertreated public health problem. Nonetheless, pediatric primary care providers (PCPs) may have low rates of antidepressant prescribing due to structural and training barriers. We examined the impact of symptom severity and provider characteristics on initial depression treatment decisions in a setting with fewer structural barriers, an integrated behavioral health network. METHOD We administered a cross sectional survey to 58 PCPs within a large pediatric practice network. We compared PCP reports of initial treatment decisions in response to two vignettes describing depressed adolescents with either moderate or severe symptoms. We measured PCP depression knowledge, attitudes toward addressing psychosocial concerns, demographics, and practice characteristics. RESULTS Few PCPs (25% for moderate, 32% for severe) recommended an antidepressant. Compared with treatment recommendations for moderate depression, severe depression was associated with a greater likelihood of child psychiatry referral (OR 5.50[95% CI 2.47-12.2] p<.001). Depression severity did not affect the likelihood of antidepressant recommendation (OR 1.58[95% CI 0.80-3.11] p=.19). Antidepressants were more likely to be recommended by PCPs with greater depression knowledge (OR 1.72[95% CI 1.14-2.59] p=.009) and access to an on-site mental health provider (OR 5.13[95% CI 1.24-21.2] p=.02) and less likely to be recommended by PCPs who reported higher provider burden when addressing psychosocial concerns (OR 0.85[95% CI 0.75-0.98] p=.02). CONCLUSION PCPs infrequently recommended antidepressants for adolescents, regardless of depression severity. Continued PCP support through experiential training, accounting for provider burden when addressing psychosocial concerns, and co-management with mental health providers may increase PCPs’ antidepressant prescribing. PMID:24336091

Artificial intelligence modeling of cadmium(II) biosorption using rice straw

NASA Astrophysics Data System (ADS)

Nasr, Mahmoud; Mahmoud, Alaa El Din; Fawzy, Manal; Radwan, Ahmed

2017-05-01

The biosorption efficiency of Cd2+ using rice straw was investigated at room temperature (25 ± 4 °C), contact time (2 h) and agitation rate (5 Hz). Experiments studied the effect of three factors, biosorbent dose BD (0.1 and 0.5 g/L), pH (2 and 7) and initial Cd2+ concentration X (10 and 100 mg/L) at two levels "low" and "high". Results showed that, a variation in X from high to low revealed 31 % increase in the Cd2+ biosorption. However, a discrepancy in pH and BD from low to high achieved 28.60 and 23.61 % increase in the removal of Cd2+, respectively. From 23 factorial design, the effects of BD, pH and X achieved p value equals to 0.2248, 0.1881 and 0.1742, respectively, indicating that the influences are in the order X > pH > BD. Similarly, an adaptive neuro-fuzzy inference system indicated that X is the most influential with training and checking errors of 10.87 and 17.94, respectively. This trend was followed by "pH" with training error (15.80) and checking error (17.39), after that BD with training error (16.09) and checking error (16.29). A feed-forward back-propagation neural network with a configuration 3-6-1 achieved correlation ( R) of 0.99 (training), 0.82 (validation) and 0.97 (testing). Thus, the proposed network is capable of predicting Cd2+ biosorption with high accuracy, while the most significant variable was X.

Human ergology that promotes participatory approach to improving safety, health and working conditions at grassroots workplaces: achievements and actions.

PubMed

Kawakami, Tsuyoshi

2011-12-01

Participatory approaches are increasingly applied to improve safety, health and working conditions of grassroots workplaces in Asia. The core concepts and methods in human ergology research such as promoting real work life studies, relying on positive efforts of local people (daily life-technology), promoting active participation of local people to identify practical solutions, and learning from local human networks to reach grassroots workplaces, have provided useful viewpoints to devise such participatory training programmes. This study was aimed to study and analyze how human ergology approaches were applied in the actual development and application of three typical participatory training programmes: WISH (Work Improvement for Safe Home) with home workers in Cambodia, WISCON (Work Improvement in Small Construction Sites) with construction workers in Thailand, and WARM (Work Adjustment for Recycling and Managing Waste) with waste collectors in Fiji. The results revealed that all the three programmes, in the course of their developments, commonly applied direct observation methods of the work of target workers before devising the training programmes, learned from existing local good examples and efforts, and emphasized local human networks for cooperation. These methods and approaches were repeatedly applied in grassroots workplaces by taking advantage of their the sustainability and impacts. It was concluded that human ergology approaches largely contributed to the developments and expansion of participatory training programmes and could continue to support the self-help initiatives of local people for promoting human-centred work.

77 FR 7214 - Notice of Availability: Programmatic Environmental Assessment for Mail Processing Network...

Federal Register 2010, 2011, 2012, 2013, 2014

2012-02-10

... Network Rationalization Initiative (Formerly Known as the ``Network Optimization'' Initiative), Nationwide... Processing Network Rationalization Initiative (the ``Proposed Action''), which is national in scope. This PEA... Network Rationalization Initiative to create a more streamlined processing and distribution network using...

Role of physical and mental training in brain network configuration

PubMed Central

Foster, Philip P.

2015-01-01

It is hypothesized that the topology of brain networks is constructed by connecting nodes which may be continuously remodeled by appropriate training. Efficiency of physical and/or mental training on the brain relies on the flexibility of networks' architecture molded by local remodeling of proteins and synapses of excitatory neurons producing transformations in network topology. Continuous remodeling of proteins of excitatory neurons is fine-tuning the scaling and strength of excitatory synapses up or down via regulation of intra-cellular metabolic and regulatory networks of the genome-transcriptome-proteome interface. Alzheimer's disease is a model of “energy cost-driven small-world network disorder” with dysfunction of high-energy cost wiring as the network global efficiency is impaired by the deposition of an informed agent, the amyloid-β, selectively targeting high-degree nodes. In schizophrenia, the interconnectivity and density of rich-club networks are significantly reduced. Training-induced homeostatic synaptogenesis-enhancement, presumably via reconfiguration of brain networks into greater small-worldness, appears essential in learning, memory, and executive functions. A macroscopic cartography of creation-removal of synaptic connections in a macro-network, and at the intra-cellular scale, micro-networks regulate the physiological mechanisms for the preferential attachment of synapses. The strongest molecular relationship of exercise and functional connectivity was identified for brain-derived neurotrophic factor (BDNF). The allele variant, rs7294919, also shows a powerful relationship with the hippocampal volume. How the brain achieves this unique quest of reconfiguration remains a puzzle. What are the underlying mechanisms of synaptogenesis promoting communications brain ↔ muscle and brain ↔ brain in such trainings? What is the respective role of independent mental, physical, or combined-mental-physical trainings? Physical practice seems to be playing an instrumental role in the cognitive enhancement (brain ↔ muscle com.). However, mental training, meditation or virtual reality (films, games) require only minimal motor activity and cardio-respiratory stimulation. Therefore, other potential paths (brain ↔ brain com.) molding brain networks are nonetheless essential. Patients with motor neuron disease/injury (e.g., amyotrophic lateral sclerosis, traumatism) also achieve successful cognitive enhancement albeit they may only elicit mental practice. PMID:26157387

Role of physical and mental training in brain network configuration.

PubMed

Foster, Philip P

2015-01-01

It is hypothesized that the topology of brain networks is constructed by connecting nodes which may be continuously remodeled by appropriate training. Efficiency of physical and/or mental training on the brain relies on the flexibility of networks' architecture molded by local remodeling of proteins and synapses of excitatory neurons producing transformations in network topology. Continuous remodeling of proteins of excitatory neurons is fine-tuning the scaling and strength of excitatory synapses up or down via regulation of intra-cellular metabolic and regulatory networks of the genome-transcriptome-proteome interface. Alzheimer's disease is a model of "energy cost-driven small-world network disorder" with dysfunction of high-energy cost wiring as the network global efficiency is impaired by the deposition of an informed agent, the amyloid-β, selectively targeting high-degree nodes. In schizophrenia, the interconnectivity and density of rich-club networks are significantly reduced. Training-induced homeostatic synaptogenesis-enhancement, presumably via reconfiguration of brain networks into greater small-worldness, appears essential in learning, memory, and executive functions. A macroscopic cartography of creation-removal of synaptic connections in a macro-network, and at the intra-cellular scale, micro-networks regulate the physiological mechanisms for the preferential attachment of synapses. The strongest molecular relationship of exercise and functional connectivity was identified for brain-derived neurotrophic factor (BDNF). The allele variant, rs7294919, also shows a powerful relationship with the hippocampal volume. How the brain achieves this unique quest of reconfiguration remains a puzzle. What are the underlying mechanisms of synaptogenesis promoting communications brain ↔ muscle and brain ↔ brain in such trainings? What is the respective role of independent mental, physical, or combined-mental-physical trainings? Physical practice seems to be playing an instrumental role in the cognitive enhancement (brain ↔ muscle com.). However, mental training, meditation or virtual reality (films, games) require only minimal motor activity and cardio-respiratory stimulation. Therefore, other potential paths (brain ↔ brain com.) molding brain networks are nonetheless essential. Patients with motor neuron disease/injury (e.g., amyotrophic lateral sclerosis, traumatism) also achieve successful cognitive enhancement albeit they may only elicit mental practice.

The European Network of Coloproctology: a strategy towards the European research and healthcare system.

PubMed

Rubbini, Michele

2016-12-01

Many documents from the International Institutions point out that Health represents an engine of economic and social development. Based on these documents and concepts, the European Parliament decided to create a system of European Reference Networks as a synthesis of clinical and research activities, particularly in the field of rare diseases. This initiative, properly implemented, could be first step towards a new European health system. This article instead, wanting to deepen this perspective, postulates that the ERNs may also be related to widespread diseases, such as those of coloproctological interest, with the aim of setting up a European Network of Coloproctology (ENCP). Here are analyzed: (a) the documents related to ERNs and others related to research and training, the characteristics of the coloproctological diseases, and proposal of the ENCP; (b) a survey that involves 14 out of 25 of the National and Regional Representative of the European Society of Coloproctology. Hundred percent of the people interviewed agree to the ENCP project. The percentage of the approved proposed fields of activity of the ENCP are: Healthcare 71%, Research 100%, Training 86%, Support to legislation 78%, Professional Mobility 64%, Patient Database 71%, and Expenditure control 64%. From the analysis of the documents and the result of the survey, ERNs are appropriate not only in relation to rare diseases but also in those fields with higher diffusion and the creation of a European Network of Coloproctology is then postulated.

A Rationale for Music Training to Enhance Executive Functions in Parkinson's Disease: An Overview of the Problem.

PubMed

Lesiuk, Teresa; Bugos, Jennifer A; Murakami, Brea

2018-04-22

Music listening interventions such as Rhythmic Auditory Stimulation can improve mobility, balance, and gait in Parkinson’s Disease (PD). Yet, the impact of music training on executive functions is not yet known. Deficits in executive functions (e.g., attention, processing speed) in patients with PD result in gait interference, deficits in emotional processing, loss of functional capacity (e.g., intellectual activity, social participation), and reduced quality of life. The model of temporal prediction and timing suggests two networks collectively contribute to movement generation and execution: the basal ganglia-thalamocortical network (BGTC) and the cerebellar-thalamocortical network (CTC). Due to decreases in dopamine responsible for the disruption of the BGTC network in adults with PD, it is hypothesized that rhythmic auditory cues assist patients through recruiting an alternate network, the CTC, which extends to the supplementary motor areas (SMA) and the frontal cortices. In piano training, fine motor finger movements activate the cerebellum and SMA, thereby exercising the CTC network. We hypothesize that exercising the CTC network through music training will contribute to enhanced executive functions. Previous research suggested that music training enhances cognitive performance (i.e., working memory and processing speed) in healthy adults and adults with cognitive impairments. This review and rationale provides support for the use of music training to enhance cognitive outcomes in patients with Parkinson’s Disease (PD).

Circuity analyses of HSR network and high-speed train paths in China

PubMed Central

Zhao, Shuo; Huang, Jie; Shan, Xinghua

2017-01-01

Circuity, defined as the ratio of the shortest network distance to the Euclidean distance between one origin–destination (O-D) pair, can be adopted as a helpful evaluation method of indirect degrees of train paths. In this paper, the maximum circuity of the paths of operated trains is set to be the threshold value of the circuity of high-speed train paths. For the shortest paths of any node pairs, if their circuity is not higher than the threshold value, the paths can be regarded as the reasonable paths. With the consideration of a certain relative or absolute error, we cluster the reasonable paths on the basis of their inclusion relationship and the center path of each class represents a passenger transit corridor. We take the high-speed rail (HSR) network in China at the end of 2014 as an example, and obtain 51 passenger transit corridors, which are alternative sets of train paths. Furthermore, we analyze the circuity distribution of paths of all node pairs in the network. We find that the high circuity of train paths can be decreased with the construction of a high-speed railway line, which indicates that the structure of the HSR network in China tends to be more complete and the HSR network can make the Chinese railway network more efficient. PMID:28945757

Neural-Network Object-Recognition Program

NASA Technical Reports Server (NTRS)

Spirkovska, L.; Reid, M. B.

1993-01-01

HONTIOR computer program implements third-order neural network exhibiting invariance under translation, change of scale, and in-plane rotation. Invariance incorporated directly into architecture of network. Only one view of each object needed to train network for two-dimensional-translation-invariant recognition of object. Also used for three-dimensional-transformation-invariant recognition by training network on only set of out-of-plane rotated views. Written in C language.

Looking for underlying features in automatic and reviewed seismic bulletins through a neural network

NASA Astrophysics Data System (ADS)

Carluccio, R.; Console, R.; Chiappini, M.; Chiappini, S.

2009-12-01

SEL1 bulletins are, among all IDC products, a fundamental tool for NDCs in their task of national assessment of compliance with the CTBT. This is because SEL1s are expected to be disseminated within 2 hours from the occurrence of any detected waveform event, and the National Authorities are supposed to take a political decision in nearly real time, especially in the case when the event could triggers the request for an on site inspection. In this context not only the rapidity, but also the reliability of the SEL1 is a fundamental requirement. Our last years experience gained in the comparison between SEL1 and Italian Seismic Bulletin events has shown that SEL1s usually contain a big fraction of bogus events (sometimes close to 50%). This is due to many factors, all related to the availability of processing data and to the fast automatic algorithms involved. On the other hand, REBs are much more reliable as proved by our experience. Therefore, in spite of their relevant time delay by which they are distributed, which prevents their real-time use, REBs can be still useful in a retrospective way as reference information for comparison with SEL1s. This study tries to set up a sort of logical filter on the SEL1s that, while maintaining the rapidity requirements, improves their reliability. Our idea is based on the assumption that the SEL1s are produced by systematic algorithm of phase association and therefore some patterns among the input and output data could exist and be recognized. Our approach was initially based on a set of rules suggested by human experts on their personal experience, and its application on large datasets on a global scale. Other approaches not involving human interaction (data mining techniques) do exist. This study refers specifically to a semi-automatic approach: fitting of multi-parametric relationships hidden in the data set, through the application of neural networks by an algorithm of supervised learning. Full SEL1 and REB bulletins from Jan 2005 to Oct 2008 have been inserted in a database, together with IMS stations availability information. Part of these data have been used to create two sets of independent data (learning and verifying) used to train a "feed-forward" supervised neural network. A network supervised training algorithm using "confirmation flag" values has been used. In order to optimize network training input a significant, not redundant subset of input parameters has been looked for with the help of a genetic algorithm search tool. A suitable 12 input subset has been found and a network architecture of 12-20-1 has thus been chosen and trained on a 15094 records data set. Different runs of training sequences have been conducted, all showing CCR (Correct Classification Rate) values of the order of 75% - 80%. The trained network behavior is shown in term of ROC curve and input-out success-error matrices. The results of the analysis on our testing and validating data groups appear promising.

Accelerating deep neural network training with inconsistent stochastic gradient descent.

PubMed

Wang, Linnan; Yang, Yi; Min, Renqiang; Chakradhar, Srimat

2017-09-01

Stochastic Gradient Descent (SGD) updates Convolutional Neural Network (CNN) with a noisy gradient computed from a random batch, and each batch evenly updates the network once in an epoch. This model applies the same training effort to each batch, but it overlooks the fact that the gradient variance, induced by Sampling Bias and Intrinsic Image Difference, renders different training dynamics on batches. In this paper, we develop a new training strategy for SGD, referred to as Inconsistent Stochastic Gradient Descent (ISGD) to address this problem. The core concept of ISGD is the inconsistent training, which dynamically adjusts the training effort w.r.t the loss. ISGD models the training as a stochastic process that gradually reduces down the mean of batch's loss, and it utilizes a dynamic upper control limit to identify a large loss batch on the fly. ISGD stays on the identified batch to accelerate the training with additional gradient updates, and it also has a constraint to penalize drastic parameter changes. ISGD is straightforward, computationally efficient and without requiring auxiliary memories. A series of empirical evaluations on real world datasets and networks demonstrate the promising performance of inconsistent training. Copyright © 2017 Elsevier Ltd. All rights reserved.

Sea ice classification using fast learning neural networks

NASA Technical Reports Server (NTRS)

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

1992-01-01

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

Two papers on feed-forward networks

NASA Technical Reports Server (NTRS)

Buntine, Wray L.; Weigend, Andreas S.

1991-01-01

Connectionist feed-forward networks, trained with back-propagation, can be used both for nonlinear regression and for (discrete one-of-C) classification, depending on the form of training. This report contains two papers on feed-forward networks. The papers can be read independently. They are intended for the theoretically-aware practitioner or algorithm-designer; however, they also contain a review and comparison of several learning theories so they provide a perspective for the theoretician. The first paper works through Bayesian methods to complement back-propagation in the training of feed-forward networks. The second paper addresses a problem raised by the first: how to efficiently calculate second derivatives on feed-forward networks.

A neural network approach for image reconstruction in electron magnetic resonance tomography.

PubMed

Durairaj, D Christopher; Krishna, Murali C; Murugesan, Ramachandran

2007-10-01

An object-oriented, artificial neural network (ANN) based, application system for reconstruction of two-dimensional spatial images in electron magnetic resonance (EMR) tomography is presented. The standard back propagation algorithm is utilized to train a three-layer sigmoidal feed-forward, supervised, ANN to perform the image reconstruction. The network learns the relationship between the 'ideal' images that are reconstructed using filtered back projection (FBP) technique and the corresponding projection data (sinograms). The input layer of the network is provided with a training set that contains projection data from various phantoms as well as in vivo objects, acquired from an EMR imager. Twenty five different network configurations are investigated to test the ability of the generalization of the network. The trained ANN then reconstructs two-dimensional temporal spatial images that present the distribution of free radicals in biological systems. Image reconstruction by the trained neural network shows better time complexity than the conventional iterative reconstruction algorithms such as multiplicative algebraic reconstruction technique (MART). The network is further explored for image reconstruction from 'noisy' EMR data and the results show better performance than the FBP method. The network is also tested for its ability to reconstruct from limited-angle EMR data set.

The collaborative African genomics network training program: A trainee perspective on training the next generation of African scientists

USDA-ARS?s Scientific Manuscript database

The Collaborative African Genomics Network (CAfGEN) aims to establish sustainable genomics research programs in Botswana and Uganda through long-term training of PhD students from these countries at Baylor College of Medicine. Here, we present an overview of the CAfGEN PhD training program alongside...

Cooperative VET in Training Networks: Analysing the Free-Rider Problem in a Sociology-of-Conventions Perspective

ERIC Educational Resources Information Center

Leemann, Regula Julia; Imdorf, Christian

2015-01-01

In training networks, particularly small and medium-sized enterprises pool their resources to train apprentices within the framework of the dual VET system, while an intermediary organisation is tasked with managing operations. Over the course of their apprenticeship, the apprentices switch from one training company to another on a (half-) yearly…

Neural-Network Computer Transforms Coordinates

NASA Technical Reports Server (NTRS)

Josin, Gary M.

1990-01-01

Numerical simulation demonstrated ability of conceptual neural-network computer to generalize what it has "learned" from few examples. Ability to generalize achieved with even simple neural network (relatively few neurons) and after exposure of network to only few "training" examples. Ability to obtain fairly accurate mappings after only few training examples used to provide solutions to otherwise intractable mapping problems.

Quantitative analysis of volatile organic compounds using ion mobility spectra and cascade correlation neural networks

NASA Technical Reports Server (NTRS)

Harrington, Peter DEB.; Zheng, Peng

1995-01-01

Ion Mobility Spectrometry (IMS) is a powerful technique for trace organic analysis in the gas phase. Quantitative measurements are difficult, because IMS has a limited linear range. Factors that may affect the instrument response are pressure, temperature, and humidity. Nonlinear calibration methods, such as neural networks, may be ideally suited for IMS. Neural networks have the capability of modeling complex systems. Many neural networks suffer from long training times and overfitting. Cascade correlation neural networks train at very fast rates. They also build their own topology, that is a number of layers and number of units in each layer. By controlling the decay parameter in training neural networks, reproducible and general models may be obtained.

Classification capacity of a modular neural network implementing neurally inspired architecture and training rules.

PubMed

Poirazi, Panayiota; Neocleous, Costas; Pattichis, Costantinos S; Schizas, Christos N

2004-05-01

A three-layer neural network (NN) with novel adaptive architecture has been developed. The hidden layer of the network consists of slabs of single neuron models, where neurons within a slab--but not between slabs--have the same type of activation function. The network activation functions in all three layers have adaptable parameters. The network was trained using a biologically inspired, guided-annealing learning rule on a variety of medical data. Good training/testing classification performance was obtained on all data sets tested. The performance achieved was comparable to that of SVM classifiers. It was shown that the adaptive network architecture, inspired from the modular organization often encountered in the mammalian cerebral cortex, can benefit classification performance.

The application of neural networks to the SSME startup transient

NASA Technical Reports Server (NTRS)

Meyer, Claudia M.; Maul, William A.

1991-01-01

Feedforward neural networks were used to model three parameters during the Space Shuttle Main Engine startup transient. The three parameters were the main combustion chamber pressure, a controlled parameter, the high pressure oxidizer turbine discharge temperature, a redlined parameter, and the high pressure fuel pump discharge pressure, a failure-indicating performance parameter. Network inputs consisted of time windows of data from engine measurements that correlated highly to the modeled parameter. A standard backpropagation algorithm was used to train the feedforward networks on two nominal firings. Each trained network was validated with four additional nominal firings. For all three parameters, the neural networks were able to accurately predict the data in the validation sets as well as the training set.

Neuroimaging Study of Alpha and Beta EEG Biofeedback Effects on Neural Networks.

PubMed

Shtark, Mark B; Kozlova, Lyudmila I; Bezmaternykh, Dmitriy D; Mel'nikov, Mikhail Ye; Savelov, Andrey A; Sokhadze, Estate M

2018-06-01

Neural networks interaction was studied in healthy men (20-35 years old) who underwent 20 sessions of EEG biofeedback training outside the MRI scanner, with concurrent fMRI-EEG scans at the beginning, middle, and end of the course. The study recruited 35 subjects for EEG biofeedback, but only 18 of them were considered as "successful" in self-regulation of target EEG bands during the whole course of training. Results of fMRI analysis during EEG biofeedback are reported only for these "successful" trainees. The experimental group (N = 23 total, N = 13 "successful") upregulated the power of alpha rhythm, while the control group (N = 12 total, N = 5 "successful") beta rhythm, with the protocol instructions being as for alpha training in both. The acquisition of the stable skills of alpha self-regulation was followed by the weakening of the irrelevant links between the cerebellum and visuospatial network (VSN), as well as between the VSN, the right executive control network (RECN), and the cuneus. It was also found formation of a stable complex based on the interaction of the precuneus, the cuneus, the VSN, and the high level visuospatial network (HVN), along with the strengthening of the interaction of the anterior salience network (ASN) with the precuneus. In the control group, beta enhancement training was accompanied by weakening of interaction between the precuneus and the default mode network, and a decrease in connectivity between the cuneus and the primary visual network (PVN). The differences between the alpha training group and the control group increased successively during training. Alpha training was characterized by a less pronounced interaction of the network formed by the PVN and the HVN, as well as by an increased interaction of the cerebellum with the precuneus and the RECN. The study demonstrated the differences in the structure and interaction of neural networks involved into alpha and beta generating systems forming and functioning, which should be taken into account during planning neurofeedback interventions. Possibility of using fMRI-guided biofeedback organized according to the described neural networks interaction may advance more accurate targeting specific symptoms during neurotherapy.

Protocol for a randomized controlled trial of piano training on cognitive and psychosocial outcomes.

PubMed

Bugos, Jennifer

2018-05-09

Age-related cognitive decline and cognitive impairment represent the fastest growing health epidemic worldwide among those over 60. There is a critical need to identify effective and novel complex cognitive interventions to promote successful aging. Since piano training engages cognitive and bimanual sensorimotor processing, we hypothesize that piano training may serve as an effective cognitive intervention, as it requires sustained attention and engages an executive network that supports generalized cognition and emotional control. Here, I describe the protocol of a randomized controlled trial (RCT) to evaluate the impact of piano training on cognitive performance in adulthood, a period associated with decreased neuroplasticity. In this cluster RCT, healthy older adults (age 60-80) were recruited and screened to control for confounding variables. Eligible participants completed an initial 3-h assessment of standardized cognitive and psychosocial measures. Participants were stratified by age, education, and estimate of intelligence and randomly assigned to one of three groups: piano training, computer brain training, or a no-treatment control group. Computer brain training consisted of progressively difficult auditory cognitive exercises (Brain HQ; Posit Science, 2010). Participants assigned to training groups completed a 16-week program that met twice a week for 90 minutes. Upon program completion and at a 3-month follow-up, training participants and no-treatment controls completed a posttest visit lasting 2.5 hours. © 2018 New York Academy of Sciences.

Changes in default mode network as automaticity develops in a categorization task.

PubMed

Shamloo, Farzin; Helie, Sebastien

2016-10-15

The default mode network (DMN) is a set of brain regions in which blood oxygen level dependent signal is suppressed during attentional focus on the external environment. Because automatic task processing requires less attention, development of automaticity in a rule-based categorization task may result in less deactivation and altered functional connectivity of the DMN when compared to the initial learning stage. We tested this hypothesis by re-analyzing functional magnetic resonance imaging data of participants trained in rule-based categorization for over 10,000 trials (Helie et al., 2010) [12,13]. The results show that some DMN regions are deactivated in initial training but not after automaticity has developed. There is also a significant decrease in DMN deactivation after extensive practice. Seed-based functional connectivity analyses with the precuneus, medial prefrontal cortex (two important DMN regions) and Brodmann area 6 (an important region in automatic categorization) were also performed. The results show increased functional connectivity with both DMN and non-DMN regions after the development of automaticity, and a decrease in functional connectivity between the medial prefrontal cortex and ventromedial orbitofrontal cortex. Together, these results further support the hypothesis of a strategy shift in automatic categorization and bridge the cognitive and neuroscientific conceptions of automaticity in showing that the reduced need for cognitive resources in automatic processing is accompanied by a disinhibition of the DMN and stronger functional connectivity between DMN and task-related brain regions. Copyright © 2016 Elsevier B.V. All rights reserved.

Exercise training protects against aging-induced mitochondrial fragmentation in mouse skeletal muscle in a PGC-1α dependent manner.

PubMed

Halling, Jens Frey; Ringholm, Stine; Olesen, Jesper; Prats, Clara; Pilegaard, Henriette

2017-10-01

Aging is associated with impaired mitochondrial function, whereas exercise training enhances mitochondrial content and function in part through activation of PGC-1α. Mitochondria form dynamic networks regulated by fission and fusion with profound effects on mitochondrial functions, yet the effects of aging and exercise training on mitochondrial network structure remain unclear. This study examined the effects of aging and exercise training on mitochondrial network structure using confocal microscopy on mitochondria-specific stains in single muscle fibers from PGC-1α KO and WT mice. Hyperfragmentation of mitochondrial networks was observed in aged relative to young animals while exercise training normalized mitochondrial network structure in WT, but not in PGC-1α KO. Mitochondrial fission protein content (FIS1 and DRP1) relative to mitochondrial content was increased with aging in both WT and PGC-1α KO mice, while exercise training lowered mitochondrial fission protein content relative to mitochondrial content only in WT. Mitochondrial fusion protein content (MFN1/2 and OPA1) was unaffected by aging and lifelong exercise training in both PGC-1α KO and WT mice. The present results provide evidence that exercise training rescues aging-induced mitochondrial fragmentation in skeletal muscle by suppressing mitochondrial fission protein expression in a PGC-1α dependent manner. Copyright © 2017 Elsevier Inc. All rights reserved.

Generative adversarial networks for brain lesion detection

NASA Astrophysics Data System (ADS)

Alex, Varghese; Safwan, K. P. Mohammed; Chennamsetty, Sai Saketh; Krishnamurthi, Ganapathy

2017-02-01

Manual segmentation of brain lesions from Magnetic Resonance Images (MRI) is cumbersome and introduces errors due to inter-rater variability. This paper introduces a semi-supervised technique for detection of brain lesion from MRI using Generative Adversarial Networks (GANs). GANs comprises of a Generator network and a Discriminator network which are trained simultaneously with the objective of one bettering the other. The networks were trained using non lesion patches (n=13,000) from 4 different MR sequences. The network was trained on BraTS dataset and patches were extracted from regions excluding tumor region. The Generator network generates data by modeling the underlying probability distribution of the training data, (PData). The Discriminator learns the posterior probability P (Label Data) by classifying training data and generated data as "Real" or "Fake" respectively. The Generator upon learning the joint distribution, produces images/patches such that the performance of the Discriminator on them are random, i.e. P (Label Data = GeneratedData) = 0.5. During testing, the Discriminator assigns posterior probability values close to 0.5 for patches from non lesion regions, while patches centered on lesion arise from a different distribution (PLesion) and hence are assigned lower posterior probability value by the Discriminator. On the test set (n=14), the proposed technique achieves whole tumor dice score of 0.69, sensitivity of 91% and specificity of 59%. Additionally the generator network was capable of generating non lesion patches from various MR sequences.

Development of Artificial Neural Network Model for Diesel Fuel Properties Prediction using Vibrational Spectroscopy.

PubMed

Bolanča, Tomislav; Marinović, Slavica; Ukić, Sime; Jukić, Ante; Rukavina, Vinko

2012-06-01

This paper describes development of artificial neural network models which can be used to correlate and predict diesel fuel properties from several FTIR-ATR absorbances and Raman intensities as input variables. Multilayer feed forward and radial basis function neural networks have been used to rapid and simultaneous prediction of cetane number, cetane index, density, viscosity, distillation temperatures at 10% (T10), 50% (T50) and 90% (T90) recovery, contents of total aromatics and polycyclic aromatic hydrocarbons of commercial diesel fuels. In this study two-phase training procedures for multilayer feed forward networks were applied. While first phase training algorithm was constantly the back propagation one, two second phase training algorithms were varied and compared, namely: conjugate gradient and quasi Newton. In case of radial basis function network, radial layer was trained using K-means radial assignment algorithm and three different radial spread algorithms: explicit, isotropic and K-nearest neighbour. The number of hidden layer neurons and experimental data points used for the training set have been optimized for both neural networks in order to insure good predictive ability by reducing unnecessary experimental work. This work shows that developed artificial neural network models can determine main properties of diesel fuels simultaneously based on a single and fast IR or Raman measurement.

Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback.

PubMed

Orhan, A Emin; Ma, Wei Ji

2017-07-26

Animals perform near-optimal probabilistic inference in a wide range of psychophysical tasks. Probabilistic inference requires trial-to-trial representation of the uncertainties associated with task variables and subsequent use of this representation. Previous work has implemented such computations using neural networks with hand-crafted and task-dependent operations. We show that generic neural networks trained with a simple error-based learning rule perform near-optimal probabilistic inference in nine common psychophysical tasks. In a probabilistic categorization task, error-based learning in a generic network simultaneously explains a monkey's learning curve and the evolution of qualitative aspects of its choice behavior. In all tasks, the number of neurons required for a given level of performance grows sublinearly with the input population size, a substantial improvement on previous implementations of probabilistic inference. The trained networks develop a novel sparsity-based probabilistic population code. Our results suggest that probabilistic inference emerges naturally in generic neural networks trained with error-based learning rules.Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task specific operations.

Application of a neural network for reflectance spectrum classification

NASA Astrophysics Data System (ADS)

Yang, Gefei; Gartley, Michael

2017-05-01

Traditional reflectance spectrum classification algorithms are based on comparing spectrum across the electromagnetic spectrum anywhere from the ultra-violet to the thermal infrared regions. These methods analyze reflectance on a pixel by pixel basis. Inspired by high performance that Convolution Neural Networks (CNN) have demonstrated in image classification, we applied a neural network to analyze directional reflectance pattern images. By using the bidirectional reflectance distribution function (BRDF) data, we can reformulate the 4-dimensional into 2 dimensions, namely incident direction × reflected direction × channels. Meanwhile, RIT's micro-DIRSIG model is utilized to simulate additional training samples for improving the robustness of the neural networks training. Unlike traditional classification by using hand-designed feature extraction with a trainable classifier, neural networks create several layers to learn a feature hierarchy from pixels to classifier and all layers are trained jointly. Hence, the our approach of utilizing the angular features are different to traditional methods utilizing spatial features. Although training processing typically has a large computational cost, simple classifiers work well when subsequently using neural network generated features. Currently, most popular neural networks such as VGG, GoogLeNet and AlexNet are trained based on RGB spatial image data. Our approach aims to build a directional reflectance spectrum based neural network to help us to understand from another perspective. At the end of this paper, we compare the difference among several classifiers and analyze the trade-off among neural networks parameters.

Exploiting the potential of unlabeled endoscopic video data with self-supervised learning.

PubMed

Ross, Tobias; Zimmerer, David; Vemuri, Anant; Isensee, Fabian; Wiesenfarth, Manuel; Bodenstedt, Sebastian; Both, Fabian; Kessler, Philip; Wagner, Martin; Müller, Beat; Kenngott, Hannes; Speidel, Stefanie; Kopp-Schneider, Annette; Maier-Hein, Klaus; Maier-Hein, Lena

2018-06-01

Surgical data science is a new research field that aims to observe all aspects of the patient treatment process in order to provide the right assistance at the right time. Due to the breakthrough successes of deep learning-based solutions for automatic image annotation, the availability of reference annotations for algorithm training is becoming a major bottleneck in the field. The purpose of this paper was to investigate the concept of self-supervised learning to address this issue. Our approach is guided by the hypothesis that unlabeled video data can be used to learn a representation of the target domain that boosts the performance of state-of-the-art machine learning algorithms when used for pre-training. Core of the method is an auxiliary task based on raw endoscopic video data of the target domain that is used to initialize the convolutional neural network (CNN) for the target task. In this paper, we propose the re-colorization of medical images with a conditional generative adversarial network (cGAN)-based architecture as auxiliary task. A variant of the method involves a second pre-training step based on labeled data for the target task from a related domain. We validate both variants using medical instrument segmentation as target task. The proposed approach can be used to radically reduce the manual annotation effort involved in training CNNs. Compared to the baseline approach of generating annotated data from scratch, our method decreases exploratively the number of labeled images by up to 75% without sacrificing performance. Our method also outperforms alternative methods for CNN pre-training, such as pre-training on publicly available non-medical (COCO) or medical data (MICCAI EndoVis2017 challenge) using the target task (in this instance: segmentation). As it makes efficient use of available (non-)public and (un-)labeled data, the approach has the potential to become a valuable tool for CNN (pre-)training.

Management training in global health education: a Health Innovation Fellowship training program to bring healthcare to low-income communities in Central America.

PubMed

Prado, Andrea M; Pearson, Andy A; Bertelsen, Nathan S

2018-01-01

Interprofessional education is increasingly recognized as essential for health education worldwide. Although effective management, innovation, and entrepreneurship are necessary to improve health systems, business schools have been underrepresented in global health education. Central America needs more health professionals trained in health management and innovation to respond to health disparities, especially in rural communities. This paper explores the impact of the Health Innovation Fellowship (HIF), a new training program for practicing health professionals offered jointly by the Central American Healthcare Initiative and INCAE Business School, Costa Rica. Launched in 2014, HIF's goal is to create a network of highly trained interdisciplinary health professionals in competencies to improve health of Central American communities through better health management. The program's fellows carried out innovative healthcare projects in their local regions. The first three annual cohorts (total of 43 fellows) represented all health-related professions and sectors (private, public, and civil society) from six Central American countries. All fellows attended four 1-week, on-site modular training sessions, received ongoing mentorship, and stayed connected through formal and informal networks and webinars through which they exchange knowledge and support each other. CAHI stakeholders supported HIF financially. Impact evaluation of the three-year pilot training program is positive: fellows improved their health management skills and more than 50% of the projects found either financial or political support for their implementation. HIF's strengths include that both program leaders and trainees come from the Global South, and that HIF offers a platform to collaborate with partners in the Global North. By focusing on promoting innovation and management at a top business school in the region, HIF constitutes a novel capacity-building effort within global health education. HIF is a capacity-building effort that can be scaled up in the region and other low- and middle-income countries.

Networking among young global health researchers through an intensive training approach: a mixed methods exploratory study.

PubMed

Lenters, Lindsey M; Cole, Donald C; Godoy-Ruiz, Paula

2014-01-25

Networks are increasingly regarded as essential in health research aimed at influencing practice and policies. Less research has focused on the role networking can play in researchers' careers and its broader impacts on capacity strengthening in health research. We used the Canadian Coalition for Global Health Research (CCGHR) annual Summer Institute for New Global Health Researchers (SIs) as an opportunity to explore networking among new global health researchers. A mixed-methods exploratory study was conducted among SI alumni and facilitators who had participated in at least one SI between 2004 and 2010. Alumni and facilitators completed an online short questionnaire, and a subset participated in an in-depth interview. Thematic analysis of the qualitative data was triangulated with quantitative results and CCGHR reports on SIs. Synthesis occurred through the development of a process model relevant to networking through the SIs. Through networking at the SIs, participants experienced decreased isolation and strengthened working relationships. Participants accessed new knowledge, opportunities, and resources through networking during the SI. Post-SI, participants reported ongoing contact and collaboration, although most participants desired more opportunities for interaction. They made suggestions for structural supports to networking among new global health researchers. Networking at the SI contributed positively to opportunities for individuals, and contributed to the formation of a network of global health researchers. Intentional inclusion of networking in health research capacity strengthening initiatives, with supportive resources and infrastructure could create dynamic, sustainable networks accessible to global health researchers around the world.

Higher-Order Neural Networks Recognize Patterns

NASA Technical Reports Server (NTRS)

Reid, Max B.; Spirkovska, Lilly; Ochoa, Ellen

1996-01-01

Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.

Method and apparatus for in-process sensing of manufacturing quality

DOEpatents

Hartman, Daniel A [Santa Fe, NM; Dave, Vivek R [Los Alamos, NM; Cola, Mark J [Santa Fe, NM; Carpenter, Robert W [Los Alamos, NM

2005-02-22

A method for determining the quality of an examined weld joint comprising the steps of providing acoustical data from the examined weld joint, and performing a neural network operation on the acoustical data determine the quality of the examined weld joint produced by a friction weld process. The neural network may be trained by the steps of providing acoustical data and observable data from at least one test weld joint, and training the neural network based on the acoustical data and observable data to form a trained neural network so that the trained neural network is capable of determining the quality of a examined weld joint based on acoustical data from the examined weld joint. In addition, an apparatus having a housing, acoustical sensors mounted therein, and means for mounting the housing on a friction weld device so that the acoustical sensors do not contact the weld joint. The apparatus may sample the acoustical data necessary for the neural network to determine the quality of a weld joint.

Mnemonic training reshapes brain networks to support superior memory

PubMed Central

Dresler, Martin; Shirer, William R.; Konrad, Boris N.; Müller, Nils C.J.; Wagner, Isabella C.; Fernández, Guillén; Czisch, Michael; Greicius, Michael D.

2017-01-01

Summary Memory skills strongly differ across the general population, however little is known about the brain characteristics supporting superior memory performance. Here, we assess functional brain network organization of 23 of the world’s most successful memory athletes and matched controls by fMRI during both task-free resting state baseline and active memory encoding. We demonstrate that in a group of naïve controls, functional connectivity changes induced by six weeks of mnemonic training were correlated with the network organization that distinguishes athletes from controls. During rest, this effect was mainly driven by connections between rather than within the visual, medial temporal lobe and default mode networks, whereas during task it was driven by connectivity within these networks. Similarity with memory athlete connectivity patterns predicted memory improvements up to 4 months after training. In conclusion, mnemonic training drives distributed rather than regional changes, reorganizing the brain’s functional network organization to enable superior memory performance. PMID:28279356

Method and Apparatus for In-Process Sensing of Manufacturing Quality

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

Hartman, D.A.; Dave, V.R.; Cola, M.J.

2005-02-22

A method for determining the quality of an examined weld joint comprising the steps of providing acoustical data from the examined weld joint, and performing a neural network operation on the acoustical data determine the quality of the examined weld joint produced by a friction weld process. The neural network may be trained by the steps of providing acoustical data and observable data from at least one test weld joint, and training the neural network based on the acoustical data and observable data to form a trained neural network so that the trained neural network is capable of determining themore » quality of a examined weld joint based on acoustical data from the examined weld joint. In addition, an apparatus having a housing, acoustical sensors mounted therein, and means for mounting the housing on a friction weld device so that the acoustical sensors do not contact the weld joint. The apparatus may sample the acoustical data necessary for the neural network to determine the quality of a weld joint.« less

Contemporary social network sites: Relevance in anesthesiology teaching, training, and research

PubMed Central

Haldar, Rudrashish; Kaushal, Ashutosh; Samanta, Sukhen; Ambesh, Paurush; Srivastava, Shashi; Singh, Prabhat K.

2016-01-01

Objective: The phenomenal popularity of social networking sites has been used globally by medical professionals to boost professional associations and scientific developments. They have tremendous potential to forge professional liaisons, generate employment,upgrading skills and publicizing scientific achievements. We highlight the role of social networking mediums in influencing teaching, training and research in anaesthesiology. Background: The growth of social networking sites have been prompted by the limitations of previous facilities in terms of ease of data and interface sharing and the amalgamation of audio visual aids on common platforms in the newer facilities. Review: Contemporary social networking sites like Facebook, Twitter, Tumblr,Linkedn etc and their respective features based on anaesthesiology training or practice have been discussed. A host of advantages which these sites confer are also discussed. Likewise the potential pitfalls and drawbacks of these facilities have also been addressed. Conclusion: Social networking sites have immense potential for development of training and research in Anaesthesiology. However responsible and cautious utilization is advocated. PMID:27625491

Contemporary social network sites: Relevance in anesthesiology teaching, training, and research.

PubMed

Haldar, Rudrashish; Kaushal, Ashutosh; Samanta, Sukhen; Ambesh, Paurush; Srivastava, Shashi; Singh, Prabhat K

2016-01-01

The phenomenal popularity of social networking sites has been used globally by medical professionals to boost professional associations and scientific developments. They have tremendous potential to forge professional liaisons, generate employment,upgrading skills and publicizing scientific achievements. We highlight the role of social networking mediums in influencing teaching, training and research in anaesthesiology. The growth of social networking sites have been prompted by the limitations of previous facilities in terms of ease of data and interface sharing and the amalgamation of audio visual aids on common platforms in the newer facilities. Contemporary social networking sites like Facebook, Twitter, Tumblr,Linkedn etc and their respective features based on anaesthesiology training or practice have been discussed. A host of advantages which these sites confer are also discussed. Likewise the potential pitfalls and drawbacks of these facilities have also been addressed. Social networking sites have immense potential for development of training and research in Anaesthesiology. However responsible and cautious utilization is advocated.

Temporal course of gene expression during motor memory formation in primary motor cortex of rats.

PubMed

Hertler, B; Buitrago, M M; Luft, A R; Hosp, J A

2016-12-01

Motor learning is associated with plastic reorganization of neural networks in primary motor cortex (M1) that depends on changes in gene expression. Here, we investigate the temporal profile of these changes during motor memory formation in response to a skilled reaching task in rats. mRNA-levels were measured 1h, 7h and 24h after the end of a training session using microarray technique. To assure learning specificity, trained animals were compared to a control group. In response to motor learning, genes are sequentially regulated with high time-point specificity and a shift from initial suppression to later activation. The majority of regulated genes can be linked to learning-related plasticity. In the gene-expression cascade following motor learning, three different steps can be defined: (1) an initial suppression of genes influencing gene transcription. (2) Expression of genes that support translation of mRNA in defined compartments. (3) Expression of genes that immediately mediates plastic changes. Gene expression peaks after 24h - this is a much slower time-course when compared to hippocampus-dependent learning, where peaks of gene-expression can be observed 6-12h after training ended. Copyright © 2016 Elsevier Inc. All rights reserved.

Temporal neural networks and transient analysis of complex engineering systems

NASA Astrophysics Data System (ADS)

Uluyol, Onder

A theory is introduced for a multi-layered Local Output Gamma Feedback (LOGF) neural network within the paradigm of Locally-Recurrent Globally-Feedforward neural networks. It is developed for the identification, prediction, and control tasks of spatio-temporal systems and allows for the presentation of different time scales through incorporation of a gamma memory. It is initially applied to the tasks of sunspot and Mackey-Glass series prediction as benchmarks, then it is extended to the task of power level control of a nuclear reactor at different fuel cycle conditions. The developed LOGF neuron model can also be viewed as a Transformed Input and State (TIS) Gamma memory for neural network architectures for temporal processing. The novel LOGF neuron model extends the static neuron model by incorporating into it a short-term memory structure in the form of a digital gamma filter. A feedforward neural network made up of LOGF neurons can thus be used to model dynamic systems. A learning algorithm based upon the Backpropagation-Through-Time (BTT) approach is derived. It is applicable for training a general L-layer LOGF neural network. The spatial and temporal weights and parameters of the network are iteratively optimized for a given problem using the derived learning algorithm.

Prediction of protein tertiary structure from sequences using a very large back-propagation neural network

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

Liu, X.; Wilcox, G.L.

1993-12-31

We have implemented large scale back-propagation neural networks on a 544 node Connection Machine, CM-5, using the C language in MIMD mode. The program running on 512 processors performs backpropagation learning at 0.53 Gflops, which provides 76 million connection updates per second. We have applied the network to the prediction of protein tertiary structure from sequence information alone. A neural network with one hidden layer and 40 million connections is trained to learn the relationship between sequence and tertiary structure. The trained network yields predicted structures of some proteins on which it has not been trained given only their sequences.more » Presentation of the Fourier transform of the sequences accentuates periodicity in the sequence and yields good generalization with greatly increased training efficiency. Training simulations with a large, heterologous set of protein structures (111 proteins from CM-5 time) to solutions with under 2% RMS residual error within the training set (random responses give an RMS error of about 20%). Presentation of 15 sequences of related proteins in a testing set of 24 proteins yields predicted structures with less than 8% RMS residual error, indicating good apparent generalization.« less

Method for neural network control of motion using real-time environmental feedback

NASA Technical Reports Server (NTRS)

Buckley, Theresa M. (Inventor)

1997-01-01

A method of motion control for robotics and other automatically controlled machinery using a neural network controller with real-time environmental feedback. The method is illustrated with a two-finger robotic hand having proximity sensors and force sensors that provide environmental feedback signals. The neural network controller is taught to control the robotic hand through training sets using back- propagation methods. The training sets are created by recording the control signals and the feedback signal as the robotic hand or a simulation of the robotic hand is moved through a representative grasping motion. The data recorded is divided into discrete increments of time and the feedback data is shifted out of phase with the control signal data so that the feedback signal data lag one time increment behind the control signal data. The modified data is presented to the neural network controller as a training set. The time lag introduced into the data allows the neural network controller to account for the temporal component of the robotic motion. Thus trained, the neural network controlled robotic hand is able to grasp a wide variety of different objects by generalizing from the training sets.

Artificial neural network classification using a minimal training set - Comparison to conventional supervised classification

NASA Technical Reports Server (NTRS)

Hepner, George F.; Logan, Thomas; Ritter, Niles; Bryant, Nevin

1990-01-01

Recent research has shown an artificial neural network (ANN) to be capable of pattern recognition and the classification of image data. This paper examines the potential for the application of neural network computing to satellite image processing. A second objective is to provide a preliminary comparison and ANN classification. An artificial neural network can be trained to do land-cover classification of satellite imagery using selected sites representative of each class in a manner similar to conventional supervised classification. One of the major problems associated with recognition and classifications of pattern from remotely sensed data is the time and cost of developing a set of training sites. This reseach compares the use of an ANN back propagation classification procedure with a conventional supervised maximum likelihood classification procedure using a minimal training set. When using a minimal training set, the neural network is able to provide a land-cover classification superior to the classification derived from the conventional classification procedure. This research is the foundation for developing application parameters for further prototyping of software and hardware implementations for artificial neural networks in satellite image and geographic information processing.

QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms.

PubMed

Zwartjes, Ardjan; Havinga, Paul J M; Smit, Gerard J M; Hurink, Johann L

2016-10-01

In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.

Linear Vector Quantisation and Uniform Circular Arrays based decoupled two-dimensional angle of arrival estimation

NASA Astrophysics Data System (ADS)

Ndaw, Joseph D.; Faye, Andre; Maïga, Amadou S.

2017-05-01

Artificial neural networks (ANN)-based models are efficient ways of source localisation. However very large training sets are needed to precisely estimate two-dimensional Direction of arrival (2D-DOA) with ANN models. In this paper we present a fast artificial neural network approach for 2D-DOA estimation with reduced training sets sizes. We exploit the symmetry properties of Uniform Circular Arrays (UCA) to build two different datasets for elevation and azimuth angles. Linear Vector Quantisation (LVQ) neural networks are then sequentially trained on each dataset to separately estimate elevation and azimuth angles. A multilevel training process is applied to further reduce the training sets sizes.

A Novel User Classification Method for Femtocell Network by Using Affinity Propagation Algorithm and Artificial Neural Network

PubMed Central

Ahmed, Afaz Uddin; Tariqul Islam, Mohammad; Ismail, Mahamod; Kibria, Salehin; Arshad, Haslina

2014-01-01

An artificial neural network (ANN) and affinity propagation (AP) algorithm based user categorization technique is presented. The proposed algorithm is designed for closed access femtocell network. ANN is used for user classification process and AP algorithm is used to optimize the ANN training process. AP selects the best possible training samples for faster ANN training cycle. The users are distinguished by using the difference of received signal strength in a multielement femtocell device. A previously developed directive microstrip antenna is used to configure the femtocell device. Simulation results show that, for a particular house pattern, the categorization technique without AP algorithm takes 5 indoor users and 10 outdoor users to attain an error-free operation. While integrating AP algorithm with ANN, the system takes 60% less training samples reducing the training time up to 50%. This procedure makes the femtocell more effective for closed access operation. PMID:25133214

A novel user classification method for femtocell network by using affinity propagation algorithm and artificial neural network.

PubMed

Ahmed, Afaz Uddin; Islam, Mohammad Tariqul; Ismail, Mahamod; Kibria, Salehin; Arshad, Haslina

2014-01-01

An artificial neural network (ANN) and affinity propagation (AP) algorithm based user categorization technique is presented. The proposed algorithm is designed for closed access femtocell network. ANN is used for user classification process and AP algorithm is used to optimize the ANN training process. AP selects the best possible training samples for faster ANN training cycle. The users are distinguished by using the difference of received signal strength in a multielement femtocell device. A previously developed directive microstrip antenna is used to configure the femtocell device. Simulation results show that, for a particular house pattern, the categorization technique without AP algorithm takes 5 indoor users and 10 outdoor users to attain an error-free operation. While integrating AP algorithm with ANN, the system takes 60% less training samples reducing the training time up to 50%. This procedure makes the femtocell more effective for closed access operation.

Training a Network of Electronic Neurons for Control of a Mobile Robot

NASA Astrophysics Data System (ADS)

Vromen, T. G. M.; Steur, E.; Nijmeijer, H.

An adaptive training procedure is developed for a network of electronic neurons, which controls a mobile robot driving around in an unknown environment while avoiding obstacles. The neuronal network controls the angular velocity of the wheels of the robot based on the sensor readings. The nodes in the neuronal network controller are clusters of neurons rather than single neurons. The adaptive training procedure ensures that the input-output behavior of the clusters is identical, even though the constituting neurons are nonidentical and have, in isolation, nonidentical responses to the same input. In particular, we let the neurons interact via a diffusive coupling, and the proposed training procedure modifies the diffusion interaction weights such that the neurons behave synchronously with a predefined response. The working principle of the training procedure is experimentally validated and results of an experiment with a mobile robot that is completely autonomously driving in an unknown environment with obstacles are presented.

Early results from a multi-component French public-private partnership initiative to improve participation in clinical research - CeNGEPS: a prospective before-after study.

PubMed

Bordet, Régis; Lang, Marie; Dieu, Christelle; Billon, Nathalie; Duffet, Jean-Pierre

2015-08-19

A public-private (51/49 %) partnership was initiated in 2007 in France to improve the attractiveness of French sites in industry-sponsored international clinical trials. This initiative developed and implemented a combination of structuring actions and support actions. Here we report the assessment of the impact after 6 years on participation of French study sites in industry-sponsored clinical trials. We performed a prospective before-after study of clinical research activities in French public hospitals to assess the impact of actions developed and implemented by CeNGEPS. The programme involved a combination of structuring actions (establishment of sites of excellence, national networks and dedicated clinical research assistants (CRAs)), support actions (tools, templates and training) and competitive budget allocation for sites or networks based on performance. The impact was assessed using the following performance criteria: 1) reduction of the delay to contract signature to ≤ 60 days for 80 % of the trial sites; 2) inclusion of ≥80 % of the planned number of patients by at least 80 % of trial sites; 3) closure of <15 % of trials sites without patients enrolled. In 2013, the median delay to contract signature was: 55 days, compared with 76 days in 2008 (27.6 % reduction), 50.5 % of all sites and 58 % of sites with a dedicated CRA included ≥80 % of the planned number of patients compared with 44.8 % in 2008 (12.7 % increase) and 21.3 % of all sites and 9 % of sites with a dedicated CRA closed with no patients included, compared with 26.4 % in 2008 (19.3 and 65.9 %, respectively). These results provide evidence that it is possible to improve a country's attractiveness for industry-sponsored clinical research. The two main actions, i.e. establishing sites of excellence throughout the country with well-trained, dedicated staff and establishing a national network of clinical investigators, could be adapted to other countries in Western Europe to improve Europe's attractiveness to industry-funded trials.

Evaluation of a parallel implementation of the learning portion of the backward error propagation neural network: experiments in artifact identification.

PubMed Central

Sittig, D. F.; Orr, J. A.

1991-01-01

Various methods have been proposed in an attempt to solve problems in artifact and/or alarm identification including expert systems, statistical signal processing techniques, and artificial neural networks (ANN). ANNs consist of a large number of simple processing units connected by weighted links. To develop truly robust ANNs, investigators are required to train their networks on huge training data sets, requiring enormous computing power. We implemented a parallel version of the backward error propagation neural network training algorithm in the widely portable parallel programming language C-Linda. A maximum speedup of 4.06 was obtained with six processors. This speedup represents a reduction in total run-time from approximately 6.4 hours to 1.5 hours. We conclude that use of the master-worker model of parallel computation is an excellent method for obtaining speedups in the backward error propagation neural network training algorithm. PMID:1807607

Recruiting general practitioners for surveys: reflections on the difficulties and some lessons learned.

PubMed

Parkinson, Anne; Jorm, Louisa; Douglas, Kirsty A; Gee, Alison; Sargent, Ginny M; Lujic, Sanja; McRae, Ian S

2015-01-01

Surveys of GPs are essential to facilitate future planning and delivery of health services. However, recruitment of GPs into research has been disappointing with response rates declining over recent years. This study identified factors that facilitated or hampered GP recruitment in a recent survey of Australian GPs where a range of strategies were used to improve recruitment following poor initial responses. GP response rates for different stages of the survey were examined and compared with reasons GPs and leaders of university research networks cited for non-participation. Poor initial response rates were improved by including a questionnaire in the mail-out, changing the mail-out source from an unknown research team to locally known network leaders, approaching a group of GPs known to have research and training interests, and offering financial compensation. Response rates increased from below 1% for the first wave to 14.5% in the final wave. Using a known and trusted network of professionals to endorse the survey combined with an explicit compensation payment significantly enhanced GP response rates. To obtain response rates for surveys of GPs that are high enough to sustain external validity requires an approach that persuades GPs and their gatekeepers that it is worth their time to participate.

TRAIN-UNIX. Training Records And Information Network UNIX Version

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

Lawrence, M.E.; Crires, J.T.; Johnston, M.

1995-12-01

TRAIN-UNIX is used to track training requirements, qualifications, training completion and schedule training, classrooms and instructors. TRAIN-UNIX is a requirements-based system. When the identified training requirements for specific jobs are entered into the system, the employees manager or responsible training person assigns jobs to an employee. TRAIN-UNIX will then assemble an Individual Training Plan (ITP) with all courses required. ITP`s can also be modified to add any special training directed or identified by management, best business practices, procedures, etc. TRAIN-UNIX also schedules and tracks conferences, seminars, and required reading. TRAIN-UNIX is a secure database system on a server accessible viamore » the network. Access to the user functions (scheduling, data entry, ITP modification etc.) within TRAIN-UNIX are granted by function, as needed, by the system administrator. An additional level of security allows those who access TRAIN-UNIX to only add, modify or view information for the organizations to which they belong. TRAIN-UNIX scheduling function allows network access to scheduling of students. As a function of the scheduling process, TRAIN-UNIX checks to insure that the student is a valid employee, not double booked, and the instructor and classroom are not double booked. TRAIN-UNIX will report pending lapse of courses or qualifications. This ability to know the lapse of training along with built in training requesting function allows the training deliverers to forecast training needs.« less

Supporting Quality in Vocational Training through Networking. CEDEFOP Panorama.

ERIC Educational Resources Information Center

Seyfried, Erwin; Kohlmeyer, Klaus; Furth-Riedesser, Rafael

The extent to which network cooperation between the general education system, vocational training institutions, business enterprises, social partners, and political decision makers affects quality development in vocational training was examined through a literature review and synthesis of eight case studies in the following seven European…

Advanced helmet mounted display (AHMD)

NASA Astrophysics Data System (ADS)

Sisodia, Ashok; Bayer, Michael; Townley-Smith, Paul; Nash, Brian; Little, Jay; Cassarly, William; Gupta, Anurag

2007-04-01

Due to significantly increased U.S. military involvement in deterrent, observer, security, peacekeeping and combat roles around the world, the military expects significant future growth in the demand for deployable virtual reality trainers with networked simulation capability of the battle space visualization process. The use of HMD technology in simulated virtual environments has been initiated by the demand for more effective training tools. The AHMD overlays computer-generated data (symbology, synthetic imagery, enhanced imagery) augmented with actual and simulated visible environment. The AHMD can be used to support deployable reconfigurable training solutions as well as traditional simulation requirements, UAV augmented reality, air traffic control and Command, Control, Communications, Computers, Intelligence, Surveillance, and Reconnaissance (C4ISR) applications. This paper will describe the design improvements implemented for production of the AHMD System.

Analysis Resilient Algorithm on Artificial Neural Network Backpropagation

NASA Astrophysics Data System (ADS)

Saputra, Widodo; Tulus; Zarlis, Muhammad; Widia Sembiring, Rahmat; Hartama, Dedy

2017-12-01

Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. This is a reason to improve a method to accelerate the training. One of Artificial Neural Network (ANN) Backpropagation method is a resilient method. Resilient method of changing weights and bias network with direct adaptation process of weighting based on local gradient information from every learning iteration. Predicting data result of Istanbul Stock Exchange training getting better. Mean Square Error (MSE) value is getting smaller and increasing accuracy.

Teaching artificial neural systems to drive: Manual training techniques for autonomous systems

NASA Technical Reports Server (NTRS)

Shepanski, J. F.; Macy, S. A.

1987-01-01

A methodology was developed for manually training autonomous control systems based on artificial neural systems (ANS). In applications where the rule set governing an expert's decisions is difficult to formulate, ANS can be used to extract rules by associating the information an expert receives with the actions taken. Properly constructed networks imitate rules of behavior that permits them to function autonomously when they are trained on the spanning set of possible situations. This training can be provided manually, either under the direct supervision of a system trainer, or indirectly using a background mode where the networks assimilates training data as the expert performs its day-to-day tasks. To demonstrate these methods, an ANS network was trained to drive a vehicle through simulated freeway traffic.

Resting-state low-frequency fluctuations reflect individual differences in spoken language learning.

PubMed

Deng, Zhizhou; Chandrasekaran, Bharath; Wang, Suiping; Wong, Patrick C M

2016-03-01

A major challenge in language learning studies is to identify objective, pre-training predictors of success. Variation in the low-frequency fluctuations (LFFs) of spontaneous brain activity measured by resting-state functional magnetic resonance imaging (RS-fMRI) has been found to reflect individual differences in cognitive measures. In the present study, we aimed to investigate the extent to which initial spontaneous brain activity is related to individual differences in spoken language learning. We acquired RS-fMRI data and subsequently trained participants on a sound-to-word learning paradigm in which they learned to use foreign pitch patterns (from Mandarin Chinese) to signal word meaning. We performed amplitude of spontaneous low-frequency fluctuation (ALFF) analysis, graph theory-based analysis, and independent component analysis (ICA) to identify functional components of the LFFs in the resting-state. First, we examined the ALFF as a regional measure and showed that regional ALFFs in the left superior temporal gyrus were positively correlated with learning performance, whereas ALFFs in the default mode network (DMN) regions were negatively correlated with learning performance. Furthermore, the graph theory-based analysis indicated that the degree and local efficiency of the left superior temporal gyrus were positively correlated with learning performance. Finally, the default mode network and several task-positive resting-state networks (RSNs) were identified via the ICA. The "competition" (i.e., negative correlation) between the DMN and the dorsal attention network was negatively correlated with learning performance. Our results demonstrate that a) spontaneous brain activity can predict future language learning outcome without prior hypotheses (e.g., selection of regions of interest--ROIs) and b) both regional dynamics and network-level interactions in the resting brain can account for individual differences in future spoken language learning success. Copyright © 2015 Elsevier Ltd. All rights reserved.

Resting-state low-frequency fluctuations reflect individual differences in spoken language learning

PubMed Central

Deng, Zhizhou; Chandrasekaran, Bharath; Wang, Suiping; Wong, Patrick C.M.

2016-01-01

A major challenge in language learning studies is to identify objective, pre-training predictors of success. Variation in the low-frequency fluctuations (LFFs) of spontaneous brain activity measured by resting-state functional magnetic resonance imaging (RS-fMRI) has been found to reflect individual differences in cognitive measures. In the present study, we aimed to investigate the extent to which initial spontaneous brain activity is related to individual differences in spoken language learning. We acquired RS-fMRI data and subsequently trained participants on a sound-to-word learning paradigm in which they learned to use foreign pitch patterns (from Mandarin Chinese) to signal word meaning. We performed amplitude of spontaneous low-frequency fluctuation (ALFF) analysis, graph theory-based analysis, and independent component analysis (ICA) to identify functional components of the LFFs in the resting-state. First, we examined the ALFF as a regional measure and showed that regional ALFFs in the left superior temporal gyrus were positively correlated with learning performance, whereas ALFFs in the default mode network (DMN) regions were negatively correlated with learning performance. Furthermore, the graph theory-based analysis indicated that the degree and local efficiency of the left superior temporal gyrus were positively correlated with learning performance. Finally, the default mode network and several task-positive resting-state networks (RSNs) were identified via the ICA. The “competition” (i.e., negative correlation) between the DMN and the dorsal attention network was negatively correlated with learning performance. Our results demonstrate that a) spontaneous brain activity can predict future language learning outcome without prior hypotheses (e.g., selection of regions of interest – ROIs) and b) both regional dynamics and network-level interactions in the resting brain can account for individual differences in future spoken language learning success. PMID:26866283

ST-Elevation myocardial infarction network: systematization in 205 cases reduced clinical events in the public health care system.

PubMed

Caluza, Ana Christina Vellozo; Barbosa, Adriano H; Gonçalves, Iran; Oliveira, Carlos Alexandre L de; Matos, Lívia Nascimento de; Zeefried, Claus; Moreno, Antonio Célio C; Tarkieltaub, Elcio; Alves, Cláudia Maria R; Carvalho, Antonio Carlos

2012-11-01

The major cause of death in the city of São Paulo (SP) is cardiac events. At its periphery, in-hospital mortality in acute myocardial infarction is estimated to range between 15% and 20% due to difficulties inherent in large metropoles. To describe in-hospital mortality in ST-segment elevation acute myocardial infarction (STEMI) of patients admitted via ambulance or peripheral hospitals, which are part of a structured training network (STEMI Network). Health care teams of four emergency services (Ermelino Matarazzo, Campo Limpo, Tatuapé and Saboya) of the periphery of the city of São Paulo and advanced ambulances of the Emergency Mobile Health Care Service (abbreviation in Portuguese, SAMU) were trained to use tenecteplase or to refer for primary angioplasty. A central office for electrocardiogram reading was used. After thrombolysis, the patient was sent to a tertiary reference hospital to undergo cardiac catheterization immediately (in case of failed thrombolysis) or in 6 to 24 hours, if the patient was stable. Quantitative and qualitative variables were assessed by use of uni- and multivariate analysis. From January 2010 to June 2011, 205 consecutive patients used the STEMI Network, and the findings were as follows: 87 anterior wall infarctions; 11 left bundle-branch blocks; 14 complete atrioventricular blocks; and 14 resuscitations after initial cardiorespiratory arrest. In-hospital mortality was 6.8% (14 patients), most of which due to cardiogenic shock, one hemorrhagic cerebrovascular accident, and one bleeding. The organization in the public health care system of a network for the treatment of STEMI, involving diagnosis, reperfusion, immediate transfer, and tertiary reference hospital, resulted in immediate improvement of STEMI outcomes.

Improving Care for Children With Cancer in Low- and Middle-Income Countries--a SIOP PODC Initiative.

PubMed

Arora, Ramandeep Singh; Challinor, Julia M; Howard, Scott C; Israels, Trijn

2016-03-01

The Paediatric Oncology in Developing Countries (PODC) committee of International Society of Paediatric Oncology (SIOP) has 10 working groups that provide a forum for individuals to engage, network, and implement improvements in the care of children with cancer in low- and middle-income countries. The development of adapted guidelines (medulloblastoma, retinoblastoma, Wilms tumor, neuroblastoma, retinoblastoma, Burkitt lymphoma, supportive care), advocacy and awareness (on hospital detention and essential drugs), education and training, and global mapping (nutritional practice, abandonment rates, and twinning collaborations) have been the initial areas of focus, and the impact of some of these activities is evident, for example, in the SIOP Africa PODC Collaborative Wilms tumor project. © 2015 Wiley Periodicals, Inc.

Machine Learning Topological Invariants with Neural Networks

NASA Astrophysics Data System (ADS)

Zhang, Pengfei; Shen, Huitao; Zhai, Hui

2018-02-01

In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

How does investment in research training affect the development of research networks and collaborations?

PubMed

Paina, Ligia; Ssengooba, Freddie; Waswa, Douglas; M'imunya, James M; Bennett, Sara

2013-05-20

Whether and how research training programs contribute to research network development is underexplored. The Fogarty International Center (FIC) has supported overseas research training programs for over two decades. FIC programs could provide an entry point in the development of research networks and collaborations. We examine whether FIC's investment in research training contributed to the development of networks and collaborations in two countries with longstanding FIC investments - Uganda and Kenya - and the factors which facilitated this process. As part of two case studies at Uganda's Makerere University and Kenya's University of Nairobi, we conducted 53 semi-structured in-depth interviews and nine focus group discussions. To expand on our case study findings, we conducted a focused bibliometric analysis on two purposively selected topic areas to examine scientific productivity and used online network illustration tools to examine the resulting network structures. FIC support made important contributions to network development. Respondents from both Uganda and Kenya confirmed that FIC programs consistently provided trainees with networking skills and exposure to research collaborations, primarily within the institutions implementing FIC programs. In both countries, networks struggled with inclusiveness, particularly in HIV/AIDS research. Ugandan respondents perceived their networks to be more cohesive than Kenyan respondents did. Network cohesiveness was positively correlated with the magnitude and longevity of FIC's programs. Support from FIC grants to local and regional research network development and networking opportunities, such as conferences, was rare. Synergies between FIC programs and research grants helped to solidify and maintain research collaborations. Networks developed where FIC's programs focused on a particular institution, there was a critical mass of trainees with similar interests, and investments for network development were available from early implementation. Networks were less likely to emerge where FIC efforts were thinly scattered across multiple institutions. The availability of complementary research grants created opportunities for researchers to collaborate in grant writing, research implementation, and publications. FIC experiences in Uganda and Kenya showcase the important role of research training programs in creating and sustaining research networks. FIC programs should consider including support to research networks more systematically in their capacity development agenda.

Training Records And Information Network UNIX Version

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

Johnston, Michael

1996-12-01

TRAIN-UNIX is used to track training requirements, qualifications, training completion and schedule training, classrooms and instructors. TRAIN-UNIX is a requirements-based system. When the identified training requirements for specific jobs are entered into the system, the employees manager or responsible training person assigns jobs to an employee. TRAIN-UNIX will then assemble an Individual Training Plan (ITP) with all courses required. ITP''s can also be modified to add any special training directed or identified by management, best business practices, procedures, etc. TRAIN-UNIX also schedules and tracks conferences, seminars, and required reading. TRAIN-UNIX is a secure database system on a server accessible viamore » the network. Access to the user functions (scheduling, data entry, ITP modification etc.) within TRAIN-UNIX are granted by function, as needed, by the system administrator. An additional level of security allows those who access TRAIN-UNIX to only add, modify or view information for the organizations to which they belong. TRAIN-UNIX scheduling function allows network access to scheduling of students. As a function of the scheduling process, TRAIN-UNIX checks to insure that the student is a valid employee, not double booked, and the instructor and classroom are not double booked. TRAIN-UNIX will report pending lapse of courses or qualifications. This ability to know the lapse of training along with built in training requesting function allows the training deliverers to forecast training needs.« less

Models of initial training and pathways to registration: a selective review of policy in professional regulation.

PubMed

Fealy, Gerard M; Carney, Marie; Drennan, Jonathan; Treacy, Margaret; Burke, Jacqueline; O'Connell, Dympna; Howley, Breeda; Clancy, Alison; McHugh, Aine; Patton, Declan; Sheerin, Fintan

2009-09-01

To provide a synthesis of literature on international policy concerning professional regulation in nursing and midwifery, with reference to routes of entry into training and pathways to licensure. Internationally, there is evidence of multiple points of entry into initial training, multiple divisions of the professional register and multiple pathways to licensure. Policy documents and commentary articles concerned with models of initial training and pathways to licensure were reviewed. Item selection, quality appraisal and data extraction were undertaken and documentary analysis was performed on all retrieved texts. Case studies of five Western countries indicate no single uniform system of routes of entry into initial training and no overall consensus regarding the optimal model of initial training. Multiple regulatory systems, with multiple routes of entry into initial training and multiple pathways to licensure pose challenges, in terms of achieving commonly-agreed understandings of practice competence. The variety of models of initial training present nursing managers with challenges in the recruitment and deployment of personnel trained in many different jurisdictions. Nursing managers need to consider the potential for considerable variation in competency repertoires among nurses trained in generic and specialist initial training models.

A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain

NASA Technical Reports Server (NTRS)

Hall, Lawrence O.; Bensaid, Amine M.; Clarke, Laurence P.; Velthuizen, Robert P.; Silbiger, Martin S.; Bezdek, James C.

1992-01-01

Magnetic resonance (MR) brain section images are segmented and then synthetically colored to give visual representations of the original data with three approaches: the literal and approximate fuzzy c-means unsupervised clustering algorithms and a supervised computational neural network, a dynamic multilayered perception trained with the cascade correlation learning algorithm. Initial clinical results are presented on both normal volunteers and selected patients with brain tumors surrounded by edema. Supervised and unsupervised segmentation techniques provide broadly similar results. Unsupervised fuzzy algorithms were visually observed to show better segmentation when compared with raw image data for volunteer studies. However, for a more complex segmentation problem with tumor/edema or cerebrospinal fluid boundary, where the tissues have similar MR relaxation behavior, inconsistency in rating among experts was observed.

Climate Voices: Bridging Scientist Citizens and Local Communities across the United States

NASA Astrophysics Data System (ADS)

Wegner, K.; Ristvey, J. D., Jr.

2016-12-01

Based out of the University Corporation for Atmospheric Research (UCAR), the Climate Voices Science Speakers Network (climatevoices.org) has more than 400 participants across the United States that volunteer their time as scientist citizens in their local communities. Climate Voices experts engage in nonpartisan conversations about the local impacts of climate change with groups such as Rotary clubs, collaborate with faith-based groups on climate action initiatives, and disseminate their research findings to K-12 teachers and classrooms through webinars. To support their participants, Climate Voices develops partnerships with networks of community groups, provides trainings on how to engage these communities, and actively seeks community feedback. In this presentation, we will share case studies of science-community collaborations, including meta-analyses of collaborations and lessons learned.

The TOPOMOD-ITN project: unravel the origin of Earth's topography from modelling deep-surface processes

NASA Astrophysics Data System (ADS)

Faccenna, C.; Funiciello, F.

2012-04-01

EC-Marie Curie Initial Training Networks (ITN) projects aim to improve the career perspectives of young generations of researchers. Institutions from both academic and industry sectors form a collaborative network to recruit research fellows and provide them with opportunities to undertake research in the context of a joint research training program. In this frame, TOPOMOD - one of the training activities of EPOS, the new-born European Research Infrastructure for Geosciences - is a funded ITN project designed to investigate and model how surface processes interact with crustal tectonics and mantle convection to originate and develop topography of the continents over a wide range of spatial and temporal scales. The multi-disciplinary approach combines geophysics, geochemistry, tectonics and structural geology with advanced geodynamic numerical/analog modelling. TOPOMOD involves 8 European research teams internationally recognized for their excellence in complementary fields of Earth Sciences (Roma TRE, Utrecht, GFZ, ETH, Cambridge, Durham, Rennes, Barcelona), to which are associated 5 research institutions (CNR-Italy, Univ. Parma, Univ. Lausanne, Univ. Montpellier, Univ. Mainz) , 3 high-technology enterprises (Malvern Instruments, TNO, G.O. Logical Consulting) and 1 large multinational oil and gas company (ENI). This unique network places emphasis in experience-based training increasing the impact and international visibility of European research in modeling. Long-term collaboration and synergy are established among the overmentioned research teams through 15 cross-disciplinary research projects that combine case studies in well-chosen target areas from the Mediterranean, the Middle and Far East, west Africa, and South America, with new developments in structural geology, geomorphology, seismology, geochemistry, InSAR, laboratory and numerical modelling of geological processes from the deep mantle to the surface. These multidisciplinary projects altogether aim to answer a key question in earth Sciences: how do deep and surface processes interact to shape and control the topographic evolution of our planet.

Robust artificial neural network for reliability and sensitivity analyses of complex non-linear systems.

PubMed

Oparaji, Uchenna; Sheu, Rong-Jiun; Bankhead, Mark; Austin, Jonathan; Patelli, Edoardo

2017-12-01

Artificial Neural Networks (ANNs) are commonly used in place of expensive models to reduce the computational burden required for uncertainty quantification, reliability and sensitivity analyses. ANN with selected architecture is trained with the back-propagation algorithm from few data representatives of the input/output relationship of the underlying model of interest. However, different performing ANNs might be obtained with the same training data as a result of the random initialization of the weight parameters in each of the network, leading to an uncertainty in selecting the best performing ANN. On the other hand, using cross-validation to select the best performing ANN based on the ANN with the highest R 2 value can lead to biassing in the prediction. This is as a result of the fact that the use of R 2 cannot determine if the prediction made by ANN is biased. Additionally, R 2 does not indicate if a model is adequate, as it is possible to have a low R 2 for a good model and a high R 2 for a bad model. Hence, in this paper, we propose an approach to improve the robustness of a prediction made by ANN. The approach is based on a systematic combination of identical trained ANNs, by coupling the Bayesian framework and model averaging. Additionally, the uncertainties of the robust prediction derived from the approach are quantified in terms of confidence intervals. To demonstrate the applicability of the proposed approach, two synthetic numerical examples are presented. Finally, the proposed approach is used to perform a reliability and sensitivity analyses on a process simulation model of a UK nuclear effluent treatment plant developed by National Nuclear Laboratory (NNL) and treated in this study as a black-box employing a set of training data as a test case. This model has been extensively validated against plant and experimental data and used to support the UK effluent discharge strategy. Copyright © 2017 Elsevier Ltd. All rights reserved.

Training and mobility: a priority for the Organisation of the European Cancer Institutes. How a national mobility initiative could enhance EU cooperation in cancer research contributing to the development of an European Research Area: the example of The Italian Comprehensive Cancer Centers' Network "Alleanza Contro il Cancro".

PubMed

Lombardo, Claudio; Albanese, Daniela; Belardelli, Filippo; d'Alessandro, Francesca; Giacomini, Mauro; Rondanina, Tania; Spagnoli, Luigi G

2008-01-01

It is widely recognized that productivity gains, sustained economic growth and employment are largely determined by technological progress, innovation and human capital. The 2000 Lisbon strategy to make Europe a competitive knowledge-based economy by 2010 and, more specifically, the Barcelona objectives agreed upon in 2002 to increase R&D investment in the EU to approach 3% of GDP, ensuring that there are sufficient human resources for research, are a preliminary step in this direction. If we want to reach this goal we have to succeed in retaining the best researchers, creating the right environment where they can perform their activities and develop their careers. To this aim the Organization of European Cancer Institutes (OECI) has set up a working group on Education and Training with the mandate to encourage continuing education in cancer research and applications and to verify the feasibility to promote mobility programs inside the network and in association with industries. Until now only few OECI training programs have been launched and a full mobility program has not been developed yet due to limited budget resources. The Italian Network of Comprehensive Cancer Centers, Alleanza Contro il Cancro, has planned the launch of a mobility program awarding 70 annual fellowships over a period of 36 months. This program, which will be open to the world research community, could represent a first interaction through mobility among the members of the OECI network also involving industries. The program is a tangible approach to sustain the translational process needed for the development of an European Research Area in the field of cancer and its related biomedical disciplines, thus providing a practical answer to the 2005 renewed Lisbon Strategy.

Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation

NASA Astrophysics Data System (ADS)

Gaonkar, Bilwaj; Hovda, David; Martin, Neil; Macyszyn, Luke

2016-03-01

Deep Learning, refers to large set of neural network based algorithms, have emerged as promising machine- learning tools in the general imaging and computer vision domains. Convolutional neural networks (CNNs), a specific class of deep learning algorithms, have been extremely effective in object recognition and localization in natural images. A characteristic feature of CNNs, is the use of a locally connected multi layer topology that is inspired by the animal visual cortex (the most powerful vision system in existence). While CNNs, perform admirably in object identification and localization tasks, typically require training on extremely large datasets. Unfortunately, in medical image analysis, large datasets are either unavailable or are extremely expensive to obtain. Further, the primary tasks in medical imaging are organ identification and segmentation from 3D scans, which are different from the standard computer vision tasks of object recognition. Thus, in order to translate the advantages of deep learning to medical image analysis, there is a need to develop deep network topologies and training methodologies, that are geared towards medical imaging related tasks and can work in a setting where dataset sizes are relatively small. In this paper, we present a technique for stacked supervised training of deep feed forward neural networks for segmenting organs from medical scans. Each `neural network layer' in the stack is trained to identify a sub region of the original image, that contains the organ of interest. By layering several such stacks together a very deep neural network is constructed. Such a network can be used to identify extremely small regions of interest in extremely large images, inspite of a lack of clear contrast in the signal or easily identifiable shape characteristics. What is even more intriguing is that the network stack achieves accurate segmentation even when it is trained on a single image with manually labelled ground truth. We validate this approach,using a publicly available head and neck CT dataset. We also show that a deep neural network of similar depth, if trained directly using backpropagation, cannot acheive the tasks achieved using our layer wise training paradigm.

Single-shot T2 mapping using overlapping-echo detachment planar imaging and a deep convolutional neural network.

PubMed

Cai, Congbo; Wang, Chao; Zeng, Yiqing; Cai, Shuhui; Liang, Dong; Wu, Yawen; Chen, Zhong; Ding, Xinghao; Zhong, Jianhui

2018-04-24

An end-to-end deep convolutional neural network (CNN) based on deep residual network (ResNet) was proposed to efficiently reconstruct reliable T 2 mapping from single-shot overlapping-echo detachment (OLED) planar imaging. The training dataset was obtained from simulations that were carried out on SPROM (Simulation with PRoduct Operator Matrix) software developed by our group. The relationship between the original OLED image containing two echo signals and the corresponding T 2 mapping was learned by ResNet training. After the ResNet was trained, it was applied to reconstruct the T 2 mapping from simulation and in vivo human brain data. Although the ResNet was trained entirely on simulated data, the trained network was generalized well to real human brain data. The results from simulation and in vivo human brain experiments show that the proposed method significantly outperforms the echo-detachment-based method. Reliable T 2 mapping with higher accuracy is achieved within 30 ms after the network has been trained, while the echo-detachment-based OLED reconstruction method took approximately 2 min. The proposed method will facilitate real-time dynamic and quantitative MR imaging via OLED sequence, and deep convolutional neural network has the potential to reconstruct maps from complex MRI sequences efficiently. © 2018 International Society for Magnetic Resonance in Medicine.

Identification of the connections in biologically inspired neural networks

NASA Technical Reports Server (NTRS)

Demuth, H.; Leung, K.; Beale, M.; Hicklin, J.

1990-01-01

We developed an identification method to find the strength of the connections between neurons from their behavior in small biologically-inspired artificial neural networks. That is, given the network external inputs and the temporal firing pattern of the neurons, we can calculate a solution for the strengths of the connections between neurons and the initial neuron activations if a solution exists. The method determines directly if there is a solution to a particular neural network problem. No training of the network is required. It should be noted that this is a first pass at the solution of a difficult problem. The neuron and network models chosen are related to biology but do not contain all of its complexities, some of which we hope to add to the model in future work. A variety of new results have been obtained. First, the method has been tailored to produce connection weight matrix solutions for networks with important features of biological neural (bioneural) networks. Second, a computationally efficient method of finding a robust central solution has been developed. This later method also enables us to find the most consistent solution in the presence of noisy data. Prospects of applying our method to identify bioneural network connections are exciting because such connections are almost impossible to measure in the laboratory. Knowledge of such connections would facilitate an understanding of bioneural networks and would allow the construction of the electronic counterparts of bioneural networks on very large scale integrated (VLSI) circuits.

Advancing research opportunities and promoting pathways in graduate education: a systemic approach to BUILD training at California State University, Long Beach (CSULB).

PubMed

Urizar, Guido G; Henriques, Laura; Chun, Chi-Ah; Buonora, Paul; Vu, Kim-Phuong L; Galvez, Gino; Kingsford, Laura

2017-01-01

First-generation college graduates, racial and ethnic minorities, people with disabilities, and those from disadvantaged backgrounds are gravely underrepresented in the health research workforce representing behavioral health sciences and biomedical sciences and engineering (BHS/BSE). Furthermore, relative to their peers, very few students from these underrepresented groups (URGs) earn scientific bachelor's degrees with even fewer earning doctorate degrees. Therefore, programs that engage and retain URGs in health-related research careers early on in their career path are imperative to promote the diversity of well-trained research scientists who have the ability to address the nation's complex health challenges in an interdisciplinary way. The purpose of this paper is to describe the challenges, lessons learned, and sustainability of implementing a large-scale, multidisciplinary research infrastructure at California State University, Long Beach (CSULB) - a minority-serving institution - through federal funding received by the National Institutes of Health (NIH) Building Infrastructure Leading to Diversity (BUILD) Initiative. The CSULB BUILD initiative consists of developing a research infrastructure designed to engage and retain URGs on the research career path by providing them with the research training and skills needed to make them highly competitive for doctoral programs and entry into the research workforce. This initiative unites many research disciplines using basic, applied, and translational approaches to offer insights and develop technologies addressing prominent community and national health issues from a multidisciplinary perspective. Additionally, this initiative brings together local (e.g., high school, community college, doctoral research institutions) and national (e.g., National Research Mentoring Network) collaborative partners to alter how we identify, develop, and implement resources to enhance student and faculty research. Finally, this initiative establishes a student research training program that engages URGs earlier in their academic development, is larger and multidisciplinary in scope, and is responsive to the life contexts and promotes the cultural capital that URGs bring to their career path. Although there have been many challenges to planning for and developing CSULB BUILD's large-scale, multidisciplinary research infrastructure, there have been many lessons learned in the process that could aid other campuses in the development and sustainability of similar research programs.

Hydrological education and training needs in sub-Saharan Africa: requirements, constraints and progress

NASA Astrophysics Data System (ADS)

Hughes, D. A.

2012-03-01

This paper represents a perspective on the education and training needs related to hydrology and water resources science within the sub-Saharan Africa region and discusses the requirements of the region, some of the relatively recent developments and initiatives and some of the constraints that exist and remain difficult to surmount. The requirements include the development of academic research capacity and technical skill for both the private and public sector at a variety of levels. Some of the constraints that exist include a lack of adequate funding, lack of follow-up after short training courses, lack of institutional support to continue training, and competition for major water resources development projects from organizations outside the region. One of the main conclusions is that to sustain both educational and practical expertise in hydrology and water resources science within the region there is a need to build a "critical mass" of local expertise. Part of this could be achieved by increasing networking within the region and promoting the sharing of information, tools and expertise. There is also a need to promote institutional support.

Hydrological education and training needs in Sub-Saharan Africa: requirements, constraints and progress

NASA Astrophysics Data System (ADS)

Hughes, D. A.

2011-12-01

This paper represents a perspective on the education and training needs related to hydrology and water resources science within the sub-Saharan Africa region and discusses the requirements of the region, some of the relatively recent developments and initiatives and some of the constraints that exist and remain difficult to surmount. The requirements include the development of academic research capacity and technical skill for both the private and public sector at a variety of levels. Some of the constraints that exist include a lack of adequate funding, lack of follow-up after short training courses, lack of institutional support to continue training, and competition for major water resources development projects from organizations outside the region. One of the main conclusions is that to sustain both educational and practical expertise in hydrology and water resources science within the region there is a need to build a "critical mass" of local expertise. Part of this could be achieved by increasing networking within the region and promoting the sharing of information, tools and expertise. There is also a need to promote institutional support.

Antenna analysis using neural networks

NASA Technical Reports Server (NTRS)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern shaping. The interesting thing about D-C synthesis is that the side lobes have the same amplitude. Five-element arrays were used. Again, 41 pattern samples were used for the input. Nine actual D-C patterns ranging from -10 dB to -30 dB side lobe levels were used to train the network. A comparison between simulated and actual D-C techniques for a pattern with -22 dB side lobe level is shown. The goal for this research was to evaluate the performance of neural network computing with antennas. Future applications will employ the backpropagation training algorithm to drastically reduce the computational complexity involved in performing EM compensation for surface errors in large space reflector antennas.

Antenna analysis using neural networks

NASA Astrophysics Data System (ADS)

Smith, William T.

1992-09-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary).

Do pre-trained deep learning models improve computer-aided classification of digital mammograms?

NASA Astrophysics Data System (ADS)

Aboutalib, Sarah S.; Mohamed, Aly A.; Zuley, Margarita L.; Berg, Wendie A.; Luo, Yahong; Wu, Shandong

2018-02-01

Digital mammography screening is an important exam for the early detection of breast cancer and reduction in mortality. False positives leading to high recall rates, however, results in unnecessary negative consequences to patients and health care systems. In order to better aid radiologists, computer-aided tools can be utilized to improve distinction between image classifications and thus potentially reduce false recalls. The emergence of deep learning has shown promising results in the area of biomedical imaging data analysis. This study aimed to investigate deep learning and transfer learning methods that can improve digital mammography classification performance. In particular, we evaluated the effect of pre-training deep learning models with other imaging datasets in order to boost classification performance on a digital mammography dataset. Two types of datasets were used for pre-training: (1) a digitized film mammography dataset, and (2) a very large non-medical imaging dataset. By using either of these datasets to pre-train the network initially, and then fine-tuning with the digital mammography dataset, we found an increase in overall classification performance in comparison to a model without pre-training, with the very large non-medical dataset performing the best in improving the classification accuracy.

The Long-Term Benefits of Positive Self-Presentation via Profile Pictures, Number of Friends and the Initiation of Relationships on Facebook for Adolescents' Self-Esteem and the Initiation of Offline Relationships.

PubMed

Metzler, Anna; Scheithauer, Herbert

2017-01-01

Social networking sites are a substantial part of adolescents' daily lives. By using a longitudinal approach the current study examined the impact of (a) positive self-presentation, (b) number of friends, and (c) the initiation of online relationships on Facebook on adolescents' self-esteem and their initiation of offline relationships, as well as the mediating role of positive feedback. Questionnaire data were obtained from 217 adolescents (68% girls, mean age 16.7 years) in two waves. Adolescents' positive self-presentation and number of friends were found to be related to a higher frequency of receiving positive feedback, which in turn was negatively associated with self-esteem. However, the number of Facebook friends had a positive impact on self-esteem, and the initiation of online relationships positively influenced the initiation of offline relationships over time, demonstrating that Facebook may be a training ground for increasing adolescents' social skills. Implications and suggestions for future research are provided.

The Long-Term Benefits of Positive Self-Presentation via Profile Pictures, Number of Friends and the Initiation of Relationships on Facebook for Adolescents’ Self-Esteem and the Initiation of Offline Relationships

PubMed Central

Metzler, Anna; Scheithauer, Herbert

2017-01-01

Social networking sites are a substantial part of adolescents’ daily lives. By using a longitudinal approach the current study examined the impact of (a) positive self-presentation, (b) number of friends, and (c) the initiation of online relationships on Facebook on adolescents’ self-esteem and their initiation of offline relationships, as well as the mediating role of positive feedback. Questionnaire data were obtained from 217 adolescents (68% girls, mean age 16.7 years) in two waves. Adolescents’ positive self-presentation and number of friends were found to be related to a higher frequency of receiving positive feedback, which in turn was negatively associated with self-esteem. However, the number of Facebook friends had a positive impact on self-esteem, and the initiation of online relationships positively influenced the initiation of offline relationships over time, demonstrating that Facebook may be a training ground for increasing adolescents’ social skills. Implications and suggestions for future research are provided. PMID:29187827

Transfer of Training: Adding Insight through Social Network Analysis

ERIC Educational Resources Information Center

Van den Bossche, Piet; Segers, Mien

2013-01-01

This article reviews studies which apply a social network perspective to examine transfer of training. The theory behind social networks focuses on the interpersonal mechanisms and social structures that exist among interacting units such as people within an organization. A premise of this perspective is that individual's behaviors and outcomes…

Information dissemination and training: two key issues for consolidating and strengthening the results of health telematic projects.

PubMed

Arcarese, T; Boi, S; Gagliardi, R

2000-01-01

The concepts expressed in this paper concerns the activities to be developed within HEALTHLINE, a European project under the Telematics Application programme. HEALTHLINE is an umbrella project which takes initiatives and provides links to other international projects on health telematics. The projects involved are NIVEMES and RISE; they represent the starting point from which a common approach will be developed. The experience gained from these projects has highlighted two emerging requirements: information dissemination and training. To fulfil the needs of information, an Internet corner will be set up; it will allow citizens and health professionals to find and exchange information as well as to discuss themes concerning health care. Due to the most advanced technologies recently introduced, the Health care sector has had to modify its traditional ways of working to aid professionals in exploiting new training techniques and Health Care provision methods. HEALTHLINE will focus on training and on the development of the use of new tools and services. Furthermore, the project will exploit the training methodologies based on multimedia technology for developing training-on-the-job modules. The entire system, in its final stage, will consist of a network for co-operating training and information dissemination; European sites in the project will share information, training material and provide education and information on tele-health, medical and health-care issues to health care providers, beneficiaries and the general public.

VLSI synthesis of digital application specific neural networks

NASA Technical Reports Server (NTRS)

Beagles, Grant; Winters, Kel

1991-01-01

Neural networks tend to fall into two general categories: (1) software simulations, or (2) custom hardware that must be trained. The scope of this project is the merger of these two classifications into a system whereby a software model of a network is trained to perform a specific task and the results used to synthesize a standard cell realization of the network using automated tools.

European health telematics networks for positron emission tomography

NASA Astrophysics Data System (ADS)

Kontaxakis, George; Pozo, Miguel Angel; Ohl, Roland; Visvikis, Dimitris; Sachpazidis, Ilias; Ortega, Fernando; Guerra, Pedro; Cheze-Le Rest, Catherine; Selby, Peter; Pan, Leyun; Diaz, Javier; Dimitrakopoulou-Strauss, Antonia; Santos, Andres; Strauss, Ludwig; Sakas, Georgios

2006-12-01

A pilot network of positron emission tomography centers across Europe has been setup employing telemedicine services. The primary aim is to bring all PET centers in Europe (and beyond) closer, by integrating advanced medical imaging technology and health telematics networks applications into a single, easy to operate health telematics platform, which allows secure transmission of medical data via a variety of telecommunications channels and fosters the cooperation between professionals in the field. The platform runs on PCs with Windows 2000/XP and incorporates advanced techniques for image visualization, analysis and fusion. The communication between two connected workstations is based on a TCP/IP connection secured by secure socket layers and virtual private network or jabber protocols. A teleconsultation can be online (with both physicians physically present) or offline (via transmission of messages which contain image data and other information). An interface sharing protocol enables online teleconsultations even over low bandwidth connections. This initiative promotes the cooperation and improved communication between nuclear medicine professionals, offering options for second opinion and training. It permits physicians to remotely consult patient data, even if they are away from the physical examination site.

Creating and testing the concept of an academic NGO for enhancing health equity: a new mode of knowledge production?

PubMed

Robinson, Vivian; Tugwell, Peter; Walker, Peter; Ter Kuile, Aleida A; Neufeld, Vic; Hatcher-Roberts, Janet; Amaratunga, Carol; Andersson, Neil; Doull, Marion; Labonte, Ron; Muckle, Wendy; Murangira, Felicite; Nyamai, Caroline; Ralph-Robinson, Dawn; Simpson, Don; Sitthi-Amorn, Chitr; Turnbull, Jeff; Walker, Joelle; Wood, Chris

2007-08-01

Collaborative action is required to address persistent and systematic health inequities which exist for most diseases in most countries of the world. The Academic NGO initiative (ACANGO) described in this paper was set up as a focused network giving priority to twinned partnerships between Academic research centres and community-based NGOs. ACANGO aims to capture the strengths of both in order to build consensus among stakeholders, engage the community, focus on leadership training, shared management and resource development and deployment. A conceptual model was developed through a series of community consultations. This model was tested with four academic-community challenge projects based in Kenya, Canada, Thailand and Rwanda and an online forum and coordinating hub based at the University of Ottawa. Between February 2005 and February 2007, each of the four challenge projects was able to show specific outputs, outcomes and impacts related to enhancing health equity through the relevant production and application of knowledge. The ACANGO initiative model and network has demonstrated success in enhancing the production and use of knowledge in program design and implementation for vulnerable populations.

Implementing the WHO/UNICEF Baby Friendly Initiative in the community: a 'hearts and minds' approach.

PubMed

Thomson, Gill; Bilson, Andy; Dykes, Fiona

2012-04-01

to describe a 'hearts and minds' approach to community Baby Friendly Initiative implementation developed from the views of multidisciplinary professionals. a qualitative descriptive study utilising focus groups and interviews, with thematic networks analysis conducted. forty-seven professionals were consulted from two primary health-care facilities located in the North-West of England. thematic networks analysis generated a global theme of a 'hearts and minds approach' to BFI implementation, which embodies emotional and rational engagement. The three underpinning organising themes (and their associated basic themes): 'credible leadership', 'engagement of key partners' and 'changing attitudes and practice' reflect the context, processes and outcomes of a 'hearts and minds' approach. a 'hearts and minds' approach transcends the prescriptive aspects of a macro-level intervention with its emphasis upon audits, training, statistics and 'hard' evidence through valuing other professionals and engaging staff at all levels. It offers insights into how organisational change may move beyond traditional top-down mechanisms for driving change to incorporate ways that value others and promote cooperation and reflection. Copyright © 2011 Elsevier Ltd. All rights reserved.

Smooth function approximation using neural networks.

PubMed

Ferrari, Silvia; Stengel, Robert F

2005-01-01

An algebraic approach for representing multidimensional nonlinear functions by feedforward neural networks is presented. In this paper, the approach is implemented for the approximation of smooth batch data containing the function's input, output, and possibly, gradient information. The training set is associated to the network adjustable parameters by nonlinear weight equations. The cascade structure of these equations reveals that they can be treated as sets of linear systems. Hence, the training process and the network approximation properties can be investigated via linear algebra. Four algorithms are developed to achieve exact or approximate matching of input-output and/or gradient-based training sets. Their application to the design of forward and feedback neurocontrollers shows that algebraic training is characterized by faster execution speeds and better generalization properties than contemporary optimization techniques.

Real time coarse orientation detection in MR scans using multi-planar deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Bhatia, Parmeet S.; Reda, Fitsum; Harder, Martin; Zhan, Yiqiang; Zhou, Xiang Sean

2017-02-01

Automatically detecting anatomy orientation is an important task in medical image analysis. Specifically, the ability to automatically detect coarse orientation of structures is useful to minimize the effort of fine/accurate orientation detection algorithms, to initialize non-rigid deformable registration algorithms or to align models to target structures in model-based segmentation algorithms. In this work, we present a deep convolution neural network (DCNN)-based method for fast and robust detection of the coarse structure orientation, i.e., the hemi-sphere where the principal axis of a structure lies. That is, our algorithm predicts whether the principal orientation of a structure is in the northern hemisphere or southern hemisphere, which we will refer to as UP and DOWN, respectively, in the remainder of this manuscript. The only assumption of our method is that the entire structure is located within the scan's field-of-view (FOV). To efficiently solve the problem in 3D space, we formulated it as a multi-planar 2D deep learning problem. In the training stage, a large number coronal-sagittal slice pairs are constructed as 2-channel images to train a DCNN to classify whether a scan is UP or DOWN. During testing, we randomly sample a small number of coronal-sagittal 2-channel images and pass them through our trained network. Finally, coarse structure orientation is determined using majority voting. We tested our method on 114 Elbow MR Scans. Experimental results suggest that only five 2-channel images are sufficient to achieve a high success rate of 97.39%. Our method is also extremely fast and takes approximately 50 milliseconds per 3D MR scan. Our method is insensitive to the location of the structure in the FOV.

Combining deep residual neural network features with supervised machine learning algorithms to classify diverse food image datasets.

PubMed

McAllister, Patrick; Zheng, Huiru; Bond, Raymond; Moorhead, Anne

2018-04-01

Obesity is increasing worldwide and can cause many chronic conditions such as type-2 diabetes, heart disease, sleep apnea, and some cancers. Monitoring dietary intake through food logging is a key method to maintain a healthy lifestyle to prevent and manage obesity. Computer vision methods have been applied to food logging to automate image classification for monitoring dietary intake. In this work we applied pretrained ResNet-152 and GoogleNet convolutional neural networks (CNNs), initially trained using ImageNet Large Scale Visual Recognition Challenge (ILSVRC) dataset with MatConvNet package, to extract features from food image datasets; Food 5K, Food-11, RawFooT-DB, and Food-101. Deep features were extracted from CNNs and used to train machine learning classifiers including artificial neural network (ANN), support vector machine (SVM), Random Forest, and Naive Bayes. Results show that using ResNet-152 deep features with SVM with RBF kernel can accurately detect food items with 99.4% accuracy using Food-5K validation food image dataset and 98.8% with Food-5K evaluation dataset using ANN, SVM-RBF, and Random Forest classifiers. Trained with ResNet-152 features, ANN can achieve 91.34%, 99.28% when applied to Food-11 and RawFooT-DB food image datasets respectively and SVM with RBF kernel can achieve 64.98% with Food-101 image dataset. From this research it is clear that using deep CNN features can be used efficiently for diverse food item image classification. The work presented in this research shows that pretrained ResNet-152 features provide sufficient generalisation power when applied to a range of food image classification tasks. Copyright © 2018 Elsevier Ltd. All rights reserved.

[First aid and management of multiple trauma: in-hospital trauma care].

PubMed

Boschin, Matthias; Vordemvenne, Thomas

2012-11-01

Injuries remain the leading cause of death in children and young adults. Management of multiple trauma patients has improved in recent years by quality initiatives (trauma network, S3 guideline "Polytrauma"). On this basis, strong links with preclinical management, structured treatment algorithms, training standards (ATLS®), clear diagnostic rules and an established risk- and quality management are the important factors of a modern emergency room trauma care. We describe the organizational components that lead to successful management of trauma in hospital. © Georg Thieme Verlag Stuttgart · New York.

Recursive least-squares learning algorithms for neural networks

NASA Astrophysics Data System (ADS)

Lewis, Paul S.; Hwang, Jenq N.

1990-11-01

This paper presents the development of a pair of recursive least squares (ItLS) algorithms for online training of multilayer perceptrons which are a class of feedforward artificial neural networks. These algorithms incorporate second order information about the training error surface in order to achieve faster learning rates than are possible using first order gradient descent algorithms such as the generalized delta rule. A least squares formulation is derived from a linearization of the training error function. Individual training pattern errors are linearized about the network parameters that were in effect when the pattern was presented. This permits the recursive solution of the least squares approximation either via conventional RLS recursions or by recursive QR decomposition-based techniques. The computational complexity of the update is 0(N2) where N is the number of network parameters. This is due to the estimation of the N x N inverse Hessian matrix. Less computationally intensive approximations of the ilLS algorithms can be easily derived by using only block diagonal elements of this matrix thereby partitioning the learning into independent sets. A simulation example is presented in which a neural network is trained to approximate a two dimensional Gaussian bump. In this example RLS training required an order of magnitude fewer iterations on average (527) than did training with the generalized delta rule (6 1 BACKGROUND Artificial neural networks (ANNs) offer an interesting and potentially useful paradigm for signal processing and pattern recognition. The majority of ANN applications employ the feed-forward multilayer perceptron (MLP) network architecture in which network parameters are " trained" by a supervised learning algorithm employing the generalized delta rule (GDIt) [1 2]. The GDR algorithm approximates a fixed step steepest descent algorithm using derivatives computed by error backpropagatiori. The GDII algorithm is sometimes referred to as the backpropagation algorithm. However in this paper we will use the term backpropagation to refer only to the process of computing error derivatives. While multilayer perceptrons provide a very powerful nonlinear modeling capability GDR training can be very slow and inefficient. In linear adaptive filtering the analog of the GDR algorithm is the leastmean- squares (LMS) algorithm. Steepest descent-based algorithms such as GDR or LMS are first order because they use only first derivative or gradient information about the training error to be minimized. To speed up the training process second order algorithms may be employed that take advantage of second derivative or Hessian matrix information. Second order information can be incorporated into MLP training in different ways. In many applications especially in the area of pattern recognition the training set is finite. In these cases block learning can be applied using standard nonlinear optimization techniques [3 4 5].

Application of an artificial neural network and morphing techniques in the redesign of dysplastic trochlea.

PubMed

Cho, Kyung Jin; Müller, Jacobus H; Erasmus, Pieter J; DeJour, David; Scheffer, Cornie

2014-01-01

Segmentation and computer assisted design tools have the potential to test the validity of simulated surgical procedures, e.g., trochleoplasty. A repeatable measurement method for three dimensional femur models that enables quantification of knee parameters of the distal femur is presented. Fifteen healthy knees are analysed using the method to provide a training set for an artificial neural network. The aim is to use this artificial neural network for the prediction of parameter values that describe the shape of a normal trochlear groove geometry. This is achieved by feeding the artificial neural network with the unaffected parameters of a dysplastic knee. Four dysplastic knees (Type A through D) are virtually redesigned by way of morphing the groove geometries based on the suggested shape from the artificial neural network. Each of the four resulting shapes is analysed and compared to its initial dysplastic shape in terms of three anteroposterior dimensions: lateral, central and medial. For the four knees the trochlear depth is increased, the ventral trochlear prominence reduced and the sulcus angle corrected to within published normal ranges. The results show a lateral facet elevation inadequate, with a sulcus deepening or a depression trochleoplasty more beneficial to correct trochlear dysplasia.

Development and Validation of a Deep Neural Network Model for Prediction of Postoperative In-hospital Mortality.

PubMed

Lee, Christine K; Hofer, Ira; Gabel, Eilon; Baldi, Pierre; Cannesson, Maxime

2018-04-17

The authors tested the hypothesis that deep neural networks trained on intraoperative features can predict postoperative in-hospital mortality. The data used to train and validate the algorithm consists of 59,985 patients with 87 features extracted at the end of surgery. Feed-forward networks with a logistic output were trained using stochastic gradient descent with momentum. The deep neural networks were trained on 80% of the data, with 20% reserved for testing. The authors assessed improvement of the deep neural network by adding American Society of Anesthesiologists (ASA) Physical Status Classification and robustness of the deep neural network to a reduced feature set. The networks were then compared to ASA Physical Status, logistic regression, and other published clinical scores including the Surgical Apgar, Preoperative Score to Predict Postoperative Mortality, Risk Quantification Index, and the Risk Stratification Index. In-hospital mortality in the training and test sets were 0.81% and 0.73%. The deep neural network with a reduced feature set and ASA Physical Status classification had the highest area under the receiver operating characteristics curve, 0.91 (95% CI, 0.88 to 0.93). The highest logistic regression area under the curve was found with a reduced feature set and ASA Physical Status (0.90, 95% CI, 0.87 to 0.93). The Risk Stratification Index had the highest area under the receiver operating characteristics curve, at 0.97 (95% CI, 0.94 to 0.99). Deep neural networks can predict in-hospital mortality based on automatically extractable intraoperative data, but are not (yet) superior to existing methods.

Detection of high-grade small bowel obstruction on conventional radiography with convolutional neural networks.

PubMed

Cheng, Phillip M; Tejura, Tapas K; Tran, Khoa N; Whang, Gilbert

2018-05-01

The purpose of this pilot study is to determine whether a deep convolutional neural network can be trained with limited image data to detect high-grade small bowel obstruction patterns on supine abdominal radiographs. Grayscale images from 3663 clinical supine abdominal radiographs were categorized into obstructive and non-obstructive categories independently by three abdominal radiologists, and the majority classification was used as ground truth; 74 images were found to be consistent with small bowel obstruction. Images were rescaled and randomized, with 2210 images constituting the training set (39 with small bowel obstruction) and 1453 images constituting the test set (35 with small bowel obstruction). Weight parameters for the final classification layer of the Inception v3 convolutional neural network, previously trained on the 2014 Large Scale Visual Recognition Challenge dataset, were retrained on the training set. After training, the neural network achieved an AUC of 0.84 on the test set (95% CI 0.78-0.89). At the maximum Youden index (sensitivity + specificity-1), the sensitivity of the system for small bowel obstruction is 83.8%, with a specificity of 68.1%. The results demonstrate that transfer learning with convolutional neural networks, even with limited training data, may be used to train a detector for high-grade small bowel obstruction gas patterns on supine radiographs.

SCADA Protocol Anomaly Detection Utilizing Compression (SPADUC) 2013

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

Gordon Rueff; Lyle Roybal; Denis Vollmer

2013-01-01

There is a significant need to protect the nation’s energy infrastructures from malicious actors using cyber methods. Supervisory, Control, and Data Acquisition (SCADA) systems may be vulnerable due to the insufficient security implemented during the design and deployment of these control systems. This is particularly true in older legacy SCADA systems that are still commonly in use. The purpose of INL’s research on the SCADA Protocol Anomaly Detection Utilizing Compression (SPADUC) project was to determine if and how data compression techniques could be used to identify and protect SCADA systems from cyber attacks. Initially, the concept was centered on howmore » to train a compression algorithm to recognize normal control system traffic versus hostile network traffic. Because large portions of the TCP/IP message traffic (called packets) are repetitive, the concept of using compression techniques to differentiate “non-normal” traffic was proposed. In this manner, malicious SCADA traffic could be identified at the packet level prior to completing its payload. Previous research has shown that SCADA network traffic has traits desirable for compression analysis. This work investigated three different approaches to identify malicious SCADA network traffic using compression techniques. The preliminary analyses and results presented herein are clearly able to differentiate normal from malicious network traffic at the packet level at a very high confidence level for the conditions tested. Additionally, the master dictionary approach used in this research appears to initially provide a meaningful way to categorize and compare packets within a communication channel.« less

Flight control with adaptive critic neural network

NASA Astrophysics Data System (ADS)

Han, Dongchen

2001-10-01

In this dissertation, the adaptive critic neural network technique is applied to solve complex nonlinear system control problems. Based on dynamic programming, the adaptive critic neural network can embed the optimal solution into a neural network. Though trained off-line, the neural network forms a real-time feedback controller. Because of its general interpolation properties, the neurocontroller has inherit robustness. The problems solved here are an agile missile control for U.S. Air Force and a midcourse guidance law for U.S. Navy. In the first three papers, the neural network was used to control an air-to-air agile missile to implement a minimum-time heading-reverse in a vertical plane corresponding to following conditions: a system without constraint, a system with control inequality constraint, and a system with state inequality constraint. While the agile missile is a one-dimensional problem, the midcourse guidance law is the first test-bed for multiple-dimensional problem. In the fourth paper, the neurocontroller is synthesized to guide a surface-to-air missile to a fixed final condition, and to a flexible final condition from a variable initial condition. In order to evaluate the adaptive critic neural network approach, the numerical solutions for these cases are also obtained by solving two-point boundary value problem with a shooting method. All of the results showed that the adaptive critic neural network could solve complex nonlinear system control problems.

Big Data: A Parallel Particle Swarm Optimization-Back-Propagation Neural Network Algorithm Based on MapReduce.

PubMed

Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan

2016-01-01

A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.

A simple method to derive bounds on the size and to train multilayer neural networks

NASA Technical Reports Server (NTRS)

Sartori, Michael A.; Antsaklis, Panos J.

1991-01-01

A new derivation is presented for the bounds on the size of a multilayer neural network to exactly implement an arbitrary training set; namely, the training set can be implemented with zero error with two layers and with the number of the hidden-layer neurons equal to no.1 is greater than p - 1. The derivation does not require the separation of the input space by particular hyperplanes, as in previous derivations. The weights for the hidden layer can be chosen almost arbitrarily, and the weights for the output layer can be found by solving no.1 + 1 linear equations. The method presented exactly solves (M), the multilayer neural network training problem, for any arbitrary training set.

Working memory training in congenitally blind individuals results in an integration of occipital cortex in functional networks.

PubMed

Gudi-Mindermann, Helene; Rimmele, Johanna M; Nolte, Guido; Bruns, Patrick; Engel, Andreas K; Röder, Brigitte

2018-04-12

The functional relevance of crossmodal activation (e.g. auditory activation of occipital brain regions) in congenitally blind individuals is still not fully understood. The present study tested whether the occipital cortex of blind individuals is integrated into a challenged functional network. A working memory (WM) training over four sessions was implemented. Congenitally blind and matched sighted participants were adaptively trained with an n-back task employing either voices (auditory training) or tactile stimuli (tactile training). In addition, a minimally demanding 1-back task served as an active control condition. Power and functional connectivity of EEG activity evolving during the maintenance period of an auditory 2-back task were analyzed, run prior to and after the WM training. Modality-specific (following auditory training) and modality-independent WM training effects (following both auditory and tactile training) were assessed. Improvements in auditory WM were observed in all groups, and blind and sighted individuals did not differ in training gains. Auditory and tactile training of sighted participants led, relative to the active control group, to an increase in fronto-parietal theta-band power, suggesting a training-induced strengthening of the existing modality-independent WM network. No power effects were observed in the blind. Rather, after auditory training the blind showed a decrease in theta-band connectivity between central, parietal, and occipital electrodes compared to the blind tactile training and active control groups. Furthermore, in the blind auditory training increased beta-band connectivity between fronto-parietal, central and occipital electrodes. In the congenitally blind, these findings suggest a stronger integration of occipital areas into the auditory WM network. Copyright © 2018 Elsevier B.V. All rights reserved.

Enhanced oscillatory activity in the hippocampal-prefrontal network is related to short-term memory function after early-life seizures

PubMed Central

Kleen, Jonathan K.; Wu, Edie X.; Holmes, Gregory L.; Scott, Rod C.; Lenck-Santini, Pierre-Pascal

2011-01-01

Neurological insults during development are associated with later impairments in learning and memory. Although remedial training can help restore cognitive function, the neural mechanisms of this recovery in memory systems are largely unknown. To examine this issue we measured electrophysiological oscillatory activity in the hippocampus (both CA3 and CA1) and prefrontal cortex of adult rats that had experienced repeated seizures in the first weeks of life, while they were remedially trained on a delayed-nonmatch-to-sample memory task. Seizure-exposed rats showed initial difficulties learning the task but performed similar to control rats after extra training. Whole-session analyses illustrated enhanced theta power in all three structures while seizure rats learned response tasks prior to the memory task. Whilst performing the memory task, dynamic oscillation patterns revealed that prefrontal cortex theta power was increased among seizure-exposed rats. This enhancement appeared after the first memory training steps using short delays and plateaued at the most difficult steps which included both short and long delays. Further, seizure rats showed enhanced CA1-prefrontal theta coherence in correct trials compared to incorrect trials when long delays were imposed, suggesting increased hippocampal-prefrontal synchrony for the task in this group when memory demand was high. Seizure-exposed rats also showed heightened gamma power and coherence among all three structures during the trials. Our results demonstrate the first evidence of hippocampal-prefrontal enhancements following seizures in early development. Dynamic compensatory changes in this network and interconnected circuits may underpin cognitive rehabilitation following other neurological insults to higher cognitive systems. PMID:22031886

Public health initiatives in South Africa in the 1940s and 1950s: lessons for a post-apartheid era.

PubMed Central

Yach, D; Tollman, S M

1993-01-01

Inspiration drawn from South African public health initiatives in the 1940s played an important role in the development of the network of community and migrant health centers in the United States. The first such center at Pholela in Natal emphasized the need for a comprehensive (preventive and curative) service that based its practices on empirical data derived from epidemiological and anthropological research. In addition, community consultation preceded the introduction of new service or research initiatives. The Institute of Family and Community Health in Durban pioneered community-based multidisciplinary training and developed Pholela and other sites as centers for service, teaching, and research. Several important lessons for South African health professionals emerge from the Pholela experience. First, public health models of the past need to be reintroduced locally; second, the training of public health professionals needs to be upgraded and reoriented; third, appropriate research programs need to respond to community needs and address service demands; fourth, community involvement strategies need to be implemented early on; and fifth, funding sources for innovation in health service provision should be sought. Images p1044-a p1044-b p1045-a p1046-a p1046-b p1047-a PMID:8328604

Correcting Evaluation Bias of Relational Classifiers with Network Cross Validation

DTIC Science & Technology

2010-01-01

classi- fication algorithms: simple random resampling (RRS), equal-instance random resampling (ERS), and network cross-validation ( NCV ). The first two... NCV procedure that eliminates overlap between test sets altogether. The procedure samples for k disjoint test sets that will be used for evaluation...propLabeled ∗ S) nodes from train Pool in f erenceSet =network − trainSet F = F ∪ < trainSet, test Set, in f erenceSet > end for output: F NCV addresses

14 CFR 121.420 - Flight navigators: Initial and transition ground training.

Code of Federal Regulations, 2010 CFR

2010-01-01

... ground training. 121.420 Section 121.420 Aeronautics and Space FEDERAL AVIATION ADMINISTRATION... § 121.420 Flight navigators: Initial and transition ground training. (a) Initial and transition ground.... (7) Any other instruction as necessary to ensure his competence. (b) Initial ground training for...

14 CFR 121.420 - Flight navigators: Initial and transition ground training.

Code of Federal Regulations, 2011 CFR

2011-01-01

... ground training. 121.420 Section 121.420 Aeronautics and Space FEDERAL AVIATION ADMINISTRATION... § 121.420 Flight navigators: Initial and transition ground training. (a) Initial and transition ground.... (7) Any other instruction as necessary to ensure his competence. (b) Initial ground training for...

14 CFR 121.421 - Flight attendants: Initial and transition ground training.

Code of Federal Regulations, 2011 CFR

2011-01-01

... ground training. 121.421 Section 121.421 Aeronautics and Space FEDERAL AVIATION ADMINISTRATION... § 121.421 Flight attendants: Initial and transition ground training. (a) Initial and transition ground... equipment and the controls for cabin heat and ventilation. (b) Initial and transition ground training for...

14 CFR 121.421 - Flight attendants: Initial and transition ground training.

Code of Federal Regulations, 2010 CFR

2010-01-01

... ground training. 121.421 Section 121.421 Aeronautics and Space FEDERAL AVIATION ADMINISTRATION... § 121.421 Flight attendants: Initial and transition ground training. (a) Initial and transition ground... equipment and the controls for cabin heat and ventilation. (b) Initial and transition ground training for...

Interacting neural networks.

PubMed

Metzler, R; Kinzel, W; Kanter, I

2000-08-01

Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.

Interacting neural networks

NASA Astrophysics Data System (ADS)

Metzler, R.; Kinzel, W.; Kanter, I.

2000-08-01

Several scenarios of interacting neural networks which are trained either in an identical or in a competitive way are solved analytically. In the case of identical training each perceptron receives the output of its neighbor. The symmetry of the stationary state as well as the sensitivity to the used training algorithm are investigated. Two competitive perceptrons trained on mutually exclusive learning aims and a perceptron which is trained on the opposite of its own output are examined analytically. An ensemble of competitive perceptrons is used as decision-making algorithms in a model of a closed market (El Farol Bar problem or the Minority Game. In this game, a set of agents who have to make a binary decision is considered.); each network is trained on the history of minority decisions. This ensemble of perceptrons relaxes to a stationary state whose performance can be better than random.

Solving differential equations with unknown constitutive relations as recurrent neural networks

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

Hagge, Tobias J.; Stinis, Panagiotis; Yeung, Enoch H.

We solve a system of ordinary differential equations with an unknown functional form of a sink (reaction rate) term. We assume that the measurements (time series) of state variables are partially available, and use a recurrent neural network to “learn” the reaction rate from this data. This is achieved by including discretized ordinary differential equations as part of a recurrent neural network training problem. We extend TensorFlow’s recurrent neural network architecture to create a simple but scalable and effective solver for the unknown functions, and apply it to a fedbatch bioreactor simulation problem. Use of techniques from recent deep learningmore » literature enables training of functions with behavior manifesting over thousands of time steps. Our networks are structurally similar to recurrent neural networks, but differ in purpose, and require modified training strategies.« less

Railway obstacle detection algorithm using neural network

NASA Astrophysics Data System (ADS)

Yu, Mingyang; Yang, Peng; Wei, Sen

2018-05-01

Aiming at the difficulty of detection of obstacle in outdoor railway scene, a data-oriented method based on neural network to obtain image objects is proposed. First, we mark objects of images(such as people, trains, animals) acquired on the Internet. and then use the residual learning units to build Fast R-CNN framework. Then, the neural network is trained to get the target image characteristics by using stochastic gradient descent algorithm. Finally, a well-trained model is used to identify an outdoor railway image. if it includes trains and other objects, it will issue an alert. Experiments show that the correct rate of warning reached 94.85%.

Fine-tuning convolutional deep features for MRI based brain tumor classification

NASA Astrophysics Data System (ADS)

Ahmed, Kaoutar B.; Hall, Lawrence O.; Goldgof, Dmitry B.; Liu, Renhao; Gatenby, Robert A.

2017-03-01

Prediction of survival time from brain tumor magnetic resonance images (MRI) is not commonly performed and would ordinarily be a time consuming process. However, current cross-sectional imaging techniques, particularly MRI, can be used to generate many features that may provide information on the patient's prognosis, including survival. This information can potentially be used to identify individuals who would benefit from more aggressive therapy. Rather than using pre-defined and hand-engineered features as with current radiomics methods, we investigated the use of deep features extracted from pre-trained convolutional neural networks (CNNs) in predicting survival time. We also provide evidence for the power of domain specific fine-tuning in improving the performance of a pre-trained CNN's, even though our data set is small. We fine-tuned a CNN initially trained on a large natural image recognition dataset (Imagenet ILSVRC) and transferred the learned feature representations to the survival time prediction task, obtaining over 81% accuracy in a leave one out cross validation.

Logic circuit detects both present and missing negative pulses in superimposed wave trains

NASA Technical Reports Server (NTRS)

Rice, R. E.

1967-01-01

Pulse divide and determination network provides a logical determination of pulse presence within a data train. The network uses digital logic circuitry to divide positive and negative pulses, to shape the separated pulses, and to determine, by means of coincidence logic, if negative pulses are missing from the pulse train.

What Influences Transfer of Training in an African Agricultural Research Network?

ERIC Educational Resources Information Center

Muthoni, Rachel Andriatsitohaina; Miiro, Richard Fred

2017-01-01

Purpose: This study determined the extent to which transfer of training among trainees from national partners of an international bean research network in Africa was perceived to have taken place; including determining the factors that predicted transfer of training back to the job. Methodology/approach: Online data collection using the Learning…

A Multimedia Telematics Network for On-the-Job Training, Tutoring and Assessment.

ERIC Educational Resources Information Center

Ferreira, J. M. Martins; MacKinnon, Lachlan; Desmulliez, Marc; Foulk, Patrick

This paper describes an educational multimedia network developed in Advanced Software for Training and Evaluation of Processes (ASTEP). ASTEP started in February 1998 and was set up by a mixed industry-academia consortium with the objective of meeting the educational/training demands of the highly competitive microelectronics/semiconductor…

14 CFR 91.1099 - Crewmember initial and recurrent training requirements.

Code of Federal Regulations, 2010 CFR

2010-01-01

... subpart unless that crewmember has completed the appropriate initial or recurrent training phase of the... 14 Aeronautics and Space 2 2010-01-01 2010-01-01 false Crewmember initial and recurrent training... Ownership Operations Program Management § 91.1099 Crewmember initial and recurrent training requirements. No...

"Getting Practical" and the National Network of Science Learning Centres

ERIC Educational Resources Information Center

Chapman, Georgina; Langley, Mark; Skilling, Gus; Walker, John

2011-01-01

The national network of Science Learning Centres is a co-ordinating partner in the Getting Practical--Improving Practical Work in Science programme. The principle of training provision for the "Getting Practical" programme is a cascade model. Regional trainers employed by the national network of Science Learning Centres trained the cohort of local…

Neural Networks for the Beginner.

ERIC Educational Resources Information Center

Snyder, Robin M.

Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…

Educational Networking as Key Factor of Specialist Training in Universities

ERIC Educational Resources Information Center

Safargaliev, Ernst Raisovich; Vinogradov, Vladislav Lvovich

2015-01-01

The paper considers the problems of science and education space and network formation between business and education. The productive form of integration between the parties is revealed. The authors address employment as an evaluation criterion for networking between university and business. Special emphasis is on active training methods as a way…

Navigating Social Networking and Social Media in School Psychology: Ethical and Professional Considerations in Training Programs

ERIC Educational Resources Information Center

Pham, Andy V.

2014-01-01

Social networking and social media have undoubtedly proliferated within the past decade, allowing widespread communication and dissemination of user-generated content and information. Some psychology graduate programs, including school psychology, have started to embrace social networking and media for instructional and training purposes; however,…

Neural network pattern recognition of thermal-signature spectra for chemical defense

NASA Astrophysics Data System (ADS)

Carrieri, Arthur H.; Lim, Pascal I.

1995-05-01

We treat infrared patterns of absorption or emission by nerve and blister agent compounds (and simulants of this chemical group) as features for the training of neural networks to detect the compounds' liquid layers on the ground or their vapor plumes during evaporation by external heating. Training of a four-layer network architecture is composed of a backward-error-propagation algorithm and a gradient-descent paradigm. We conduct testing by feed-forwarding preprocessed spectra through the network in a scaled format consistent with the structure of the training-data-set representation. The best-performance weight matrix (spectral filter) evolved from final network training and testing with software simulation trials is electronically transferred to a set of eight artificial intelligence integrated circuits (ICs') in specific modular form (splitting of weight matrices). This form makes full use of all input-output IC nodes. This neural network computer serves an important real-time detection function when it is integrated into pre-and postprocessing data-handling units of a tactical prototype thermoluminescence sensor now under development at the Edgewood Research, Development, and Engineering Center.

A function approximation approach to anomaly detection in propulsion system test data

NASA Technical Reports Server (NTRS)

Whitehead, Bruce A.; Hoyt, W. A.

1993-01-01

Ground test data from propulsion systems such as the Space Shuttle Main Engine (SSME) can be automatically screened for anomalies by a neural network. The neural network screens data after being trained with nominal data only. Given the values of 14 measurements reflecting external influences on the SSME at a given time, the neural network predicts the expected nominal value of a desired engine parameter at that time. We compared the ability of three different function-approximation techniques to perform this nominal value prediction: a novel neural network architecture based on Gaussian bar basis functions, a conventional back propagation neural network, and linear regression. These three techniques were tested with real data from six SSME ground tests containing two anomalies. The basis function network trained more rapidly than back propagation. It yielded nominal predictions with, a tight enough confidence interval to distinguish anomalous deviations from the nominal fluctuations in an engine parameter. Since the function-approximation approach requires nominal training data only, it is capable of detecting unknown classes of anomalies for which training data is not available.

Functional approximation using artificial neural networks in structural mechanics

NASA Technical Reports Server (NTRS)

Alam, Javed; Berke, Laszlo

1993-01-01

The artificial neural networks (ANN) methodology is an outgrowth of research in artificial intelligence. In this study, the feed-forward network model that was proposed by Rumelhart, Hinton, and Williams was applied to the mapping of functions that are encountered in structural mechanics problems. Several different network configurations were chosen to train the available data for problems in materials characterization and structural analysis of plates and shells. By using the recall process, the accuracy of these trained networks was assessed.

Inverse kinematics problem in robotics using neural networks

NASA Technical Reports Server (NTRS)

Choi, Benjamin B.; Lawrence, Charles

1992-01-01

In this paper, Multilayer Feedforward Networks are applied to the robot inverse kinematic problem. The networks are trained with endeffector position and joint angles. After training, performance is measured by having the network generate joint angles for arbitrary endeffector trajectories. A 3-degree-of-freedom (DOF) spatial manipulator is used for the study. It is found that neural networks provide a simple and effective way to both model the manipulator inverse kinematics and circumvent the problems associated with algorithmic solution methods.

Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach.

DTIC Science & Technology

1998-05-01

Coverage Probability with a Random Optimization Procedure: An Artificial Neural Network Approach by Biing T. Guan, George Z. Gertner, and Alan B...Modeling Training Site Vegetation Coverage Probability with a Random Optimizing Procedure: An Artificial Neural Network Approach 6. AUTHOR(S) Biing...coverage based on past coverage. Approach A literature survey was conducted to identify artificial neural network analysis techniques applicable for

Student beats the teacher: deep neural networks for lateral ventricles segmentation in brain MR

NASA Astrophysics Data System (ADS)

Ghafoorian, Mohsen; Teuwen, Jonas; Manniesing, Rashindra; Leeuw, Frank-Erik d.; van Ginneken, Bram; Karssemeijer, Nico; Platel, Bram

2018-03-01

Ventricular volume and its progression are known to be linked to several brain diseases such as dementia and schizophrenia. Therefore accurate measurement of ventricle volume is vital for longitudinal studies on these disorders, making automated ventricle segmentation algorithms desirable. In the past few years, deep neural networks have shown to outperform the classical models in many imaging domains. However, the success of deep networks is dependent on manually labeled data sets, which are expensive to acquire especially for higher dimensional data in the medical domain. In this work, we show that deep neural networks can be trained on muchcheaper-to-acquire pseudo-labels (e.g., generated by other automated less accurate methods) and still produce more accurate segmentations compared to the quality of the labels. To show this, we use noisy segmentation labels generated by a conventional region growing algorithm to train a deep network for lateral ventricle segmentation. Then on a large manually annotated test set, we show that the network significantly outperforms the conventional region growing algorithm which was used to produce the training labels for the network. Our experiments report a Dice Similarity Coefficient (DSC) of 0.874 for the trained network compared to 0.754 for the conventional region growing algorithm (p < 0.001).

Membership generation using multilayer neural network

NASA Technical Reports Server (NTRS)

Kim, Jaeseok

1992-01-01

There has been intensive research in neural network applications to pattern recognition problems. Particularly, the back-propagation network has attracted many researchers because of its outstanding performance in pattern recognition applications. In this section, we describe a new method to generate membership functions from training data using a multilayer neural network. The basic idea behind the approach is as follows. The output values of a sigmoid activation function of a neuron bear remarkable resemblance to membership values. Therefore, we can regard the sigmoid activation values as the membership values in fuzzy set theory. Thus, in order to generate class membership values, we first train a suitable multilayer network using a training algorithm such as the back-propagation algorithm. After the training procedure converges, the resulting network can be treated as a membership generation network, where the inputs are feature values and the outputs are membership values in the different classes. This method allows fairly complex membership functions to be generated because the network is highly nonlinear in general. Also, it is to be noted that the membership functions are generated from a classification point of view. For pattern recognition applications, this is highly desirable, although the membership values may not be indicative of the degree of typicality of a feature value in a particular class.

Why would Musical Training Benefit the Neural Encoding of Speech? The OPERA Hypothesis.

PubMed

Patel, Aniruddh D

2011-01-01

Mounting evidence suggests that musical training benefits the neural encoding of speech. This paper offers a hypothesis specifying why such benefits occur. The "OPERA" hypothesis proposes that such benefits are driven by adaptive plasticity in speech-processing networks, and that this plasticity occurs when five conditions are met. These are: (1) Overlap: there is anatomical overlap in the brain networks that process an acoustic feature used in both music and speech (e.g., waveform periodicity, amplitude envelope), (2) Precision: music places higher demands on these shared networks than does speech, in terms of the precision of processing, (3) Emotion: the musical activities that engage this network elicit strong positive emotion, (4) Repetition: the musical activities that engage this network are frequently repeated, and (5) Attention: the musical activities that engage this network are associated with focused attention. According to the OPERA hypothesis, when these conditions are met neural plasticity drives the networks in question to function with higher precision than needed for ordinary speech communication. Yet since speech shares these networks with music, speech processing benefits. The OPERA hypothesis is used to account for the observed superior subcortical encoding of speech in musically trained individuals, and to suggest mechanisms by which musical training might improve linguistic reading abilities.

Displacement back analysis for a high slope of the Dagangshan Hydroelectric Power Station based on BP neural network and particle swarm optimization.

PubMed

Liang, Zhengzhao; Gong, Bin; Tang, Chunan; Zhang, Yongbin; Ma, Tianhui

2014-01-01

The right bank high slope of the Dagangshan Hydroelectric Power Station is located in complicated geological conditions with deep fractures and unloading cracks. How to obtain the mechanical parameters and then evaluate the safety of the slope are the key problems. This paper presented a displacement back analysis for the slope using an artificial neural network model (ANN) and particle swarm optimization model (PSO). A numerical model was established to simulate the displacement increment results, acquiring training data for the artificial neural network model. The backpropagation ANN model was used to establish a mapping function between the mechanical parameters and the monitoring displacements. The PSO model was applied to initialize the weights and thresholds of the backpropagation (BP) network model and determine suitable values of the mechanical parameters. Then the elastic moduli of the rock masses were obtained according to the monitoring displacement data at different excavation stages, and the BP neural network model was proved to be valid by comparing the measured displacements, the displacements predicted by the BP neural network model, and the numerical simulation using the back-analyzed parameters. The proposed model is useful for rock mechanical parameters determination and instability investigation of rock slopes.

Assessing needs and assets for building a regional network infrastructure to reduce cancer related health disparities.

PubMed

Wells, Kristen J; Lima, Diana S; Meade, Cathy D; Muñoz-Antonia, Teresita; Scarinci, Isabel; McGuire, Allison; Gwede, Clement K; Pledger, W Jack; Partridge, Edward; Lipscomb, Joseph; Matthews, Roland; Matta, Jaime; Flores, Idhaliz; Weiner, Roy; Turner, Timothy; Miele, Lucio; Wiese, Thomas E; Fouad, Mona; Moreno, Carlos S; Lacey, Michelle; Christie, Debra W; Price-Haywood, Eboni G; Quinn, Gwendolyn P; Coppola, Domenico; Sodeke, Stephen O; Green, B Lee; Lichtveld, Maureen Y

2014-06-01

Significant cancer health disparities exist in the United States and Puerto Rico. While numerous initiatives have been implemented to reduce cancer disparities, regional coordination of these efforts between institutions is often limited. To address cancer health disparities nation-wide, a series of regional transdisciplinary networks through the Geographic Management Program (GMaP) and the Minority Biospecimen/Biobanking Geographic Management Program (BMaP) were established in six regions across the country. This paper describes the development of the Region 3 GMaP/BMaP network composed of over 100 investigators from nine institutions in five Southeastern states and Puerto Rico to develop a state-of-the-art network for cancer health disparities research and training. We describe a series of partnership activities that led to the formation of the infrastructure for this network, recount the participatory processes utilized to develop and implement a needs and assets assessment and implementation plan, and describe our approach to data collection. Completion, by all nine institutions, of the needs and assets assessment resulted in several beneficial outcomes for Region 3 GMaP/BMaP. This network entails ongoing commitment from the institutions and institutional leaders, continuous participatory and engagement activities, and effective coordination and communication centered on team science goals. Copyright © 2014 Elsevier Ltd. All rights reserved.

Displacement Back Analysis for a High Slope of the Dagangshan Hydroelectric Power Station Based on BP Neural Network and Particle Swarm Optimization

PubMed Central

Liang, Zhengzhao; Gong, Bin; Tang, Chunan; Zhang, Yongbin; Ma, Tianhui

2014-01-01

The right bank high slope of the Dagangshan Hydroelectric Power Station is located in complicated geological conditions with deep fractures and unloading cracks. How to obtain the mechanical parameters and then evaluate the safety of the slope are the key problems. This paper presented a displacement back analysis for the slope using an artificial neural network model (ANN) and particle swarm optimization model (PSO). A numerical model was established to simulate the displacement increment results, acquiring training data for the artificial neural network model. The backpropagation ANN model was used to establish a mapping function between the mechanical parameters and the monitoring displacements. The PSO model was applied to initialize the weights and thresholds of the backpropagation (BP) network model and determine suitable values of the mechanical parameters. Then the elastic moduli of the rock masses were obtained according to the monitoring displacement data at different excavation stages, and the BP neural network model was proved to be valid by comparing the measured displacements, the displacements predicted by the BP neural network model, and the numerical simulation using the back-analyzed parameters. The proposed model is useful for rock mechanical parameters determination and instability investigation of rock slopes. PMID:25140345

Assessing Needs and Assets for Building a Regional Network Infrastructure to Reduce Cancer Related Health Disparities

PubMed Central

Wells, Kristen J.; Lima, Diana S.; Meade, Cathy D.; Muñoz-Antonia, Teresita; Scarinci, Isabel; McGuire, Allison; Gwede, Clement K.; Pledger, W. Jack; Partridge, Edward; Lipscomb, Joseph; Matthews, Roland; Matta, Jaime; Flores, Idhaliz; Weiner, Roy; Turner, Timothy; Miele, Lucio; Wiese, Thomas E.; Fouad, Mona; Moreno, Carlos S.; Lacey, Michelle; Christie, Debra W.; Price-Haywood, Eboni G.; Quinn, Gwendolyn P.; Coppola, Domenico; Sodeke, Stephen O.; Green, B. Lee; Lichtveld, Maureen Y.

2015-01-01

Significant cancer health disparities exist in the United States and Puerto Rico. While numerous initiatives have been implemented to reduce cancer disparities, regional coordination of these efforts between institutions is often limited. To address cancer health disparities nationwide, a series of regional transdisciplinary networks through the Geographic Management Program (GMaP) and the Minority Biospecimen/Biobanking Geographic Management Program (BMaP) were established in six regions across the country. This paper describes the development of the Region 3 GMaP/BMaP network composed of over 100 investigators from nine institutions in five Southeastern states and Puerto Rico to develop a state-of-the-art network for cancer health disparities research and training. We describe a series of partnership activities that led to the formation of the infrastructure for this network, recount the participatory processes utilized to develop and implement a needs and assets assessment and implementation plan, and describe our approach to data collection. Completion, by all nine institutions, of the needs and assets assessment resulted in several beneficial outcomes for Region 3 GMaP/BMaP. This network entails ongoing commitment from the institutions and institutional leaders, continuous participatory and engagement activities, and effective coordination and communication centered on team science goals. PMID:24486917

Using deep neural networks to augment NIF post-shot analysis

NASA Astrophysics Data System (ADS)

Humbird, Kelli; Peterson, Luc; McClarren, Ryan; Field, John; Gaffney, Jim; Kruse, Michael; Nora, Ryan; Spears, Brian

2017-10-01

Post-shot analysis of National Ignition Facility (NIF) experiments is the process of determining which simulation inputs yield results consistent with experimental observations. This analysis is typically accomplished by running suites of manually adjusted simulations, or Monte Carlo sampling surrogate models that approximate the response surfaces of the physics code. These approaches are expensive and often find simulations that match only a small subset of observables simultaneously. We demonstrate an alternative method for performing post-shot analysis using inverse models, which map directly from experimental observables to simulation inputs with quantified uncertainties. The models are created using a novel machine learning algorithm which automates the construction and initialization of deep neural networks to optimize predictive accuracy. We show how these neural networks, trained on large databases of post-shot simulations, can rigorously quantify the agreement between simulation and experiment. This work performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.

Wavelet neural networks: a practical guide.

PubMed

Alexandridis, Antonios K; Zapranis, Achilleas D

2013-06-01

Wavelet networks (WNs) are a new class of networks which have been used with great success in a wide range of applications. However a general accepted framework for applying WNs is missing from the literature. In this study, we present a complete statistical model identification framework in order to apply WNs in various applications. The following subjects were thoroughly examined: the structure of a WN, training methods, initialization algorithms, variable significance and variable selection algorithms, model selection methods and finally methods to construct confidence and prediction intervals. In addition the complexity of each algorithm is discussed. Our proposed framework was tested in two simulated cases, in one chaotic time series described by the Mackey-Glass equation and in three real datasets described by daily temperatures in Berlin, daily wind speeds in New York and breast cancer classification. Our results have shown that the proposed algorithms produce stable and robust results indicating that our proposed framework can be applied in various applications. Copyright © 2013 Elsevier Ltd. All rights reserved.

14 CFR 135.349 - Flight attendants: Initial and transition ground training.

Code of Federal Regulations, 2011 CFR

2011-01-01

... ground training. 135.349 Section 135.349 Aeronautics and Space FEDERAL AVIATION ADMINISTRATION... ON BOARD SUCH AIRCRAFT Training § 135.349 Flight attendants: Initial and transition ground training. Initial and transition ground training for flight attendants must include instruction in at least the...

14 CFR 135.349 - Flight attendants: Initial and transition ground training.

Code of Federal Regulations, 2010 CFR

2010-01-01

... ground training. 135.349 Section 135.349 Aeronautics and Space FEDERAL AVIATION ADMINISTRATION... ON BOARD SUCH AIRCRAFT Training § 135.349 Flight attendants: Initial and transition ground training. Initial and transition ground training for flight attendants must include instruction in at least the...

Personality Traits and Training Initiation Process: Intention, Planning, and Action Initiation

PubMed Central

Laguna, Mariola; Purc, Ewelina

2016-01-01

The article aims at investigating the role of personality traits in relation to training initiation. Training initiation is conceptualized as a goal realization process, and explained using goal theories. There are three stages of the process analyzed: intention to undertake training, plan formulation, and actual training undertaking. Two studies tested the relationships between five personality traits, defined according to the five factor model, and the stages of the goal realization process. In Study 1, which explains training intention and training plans’ formulation, 155 employees participated. In Study 2, which was time-lagged with two measurement points, and which explains intention, plans, and training actions undertaken, the data from 176 employees was collected at 3 month intervals. The results of these studies show that personality traits, mainly openness to experience, predict the training initiation process to some degree: intention, plans, and actual action initiation. The findings allow us to provide recommendations for practitioners responsible for human resource development. The assessment of openness to experience in employees helps predict their motivation to participate in training activities. To increase training motivation it is vital to strengthen intentions to undertake training, and to encourage training action planning. PMID:27909414

Personality Traits and Training Initiation Process: Intention, Planning, and Action Initiation.

PubMed

Laguna, Mariola; Purc, Ewelina

2016-01-01

The article aims at investigating the role of personality traits in relation to training initiation. Training initiation is conceptualized as a goal realization process, and explained using goal theories. There are three stages of the process analyzed: intention to undertake training, plan formulation, and actual training undertaking. Two studies tested the relationships between five personality traits, defined according to the five factor model, and the stages of the goal realization process. In Study 1, which explains training intention and training plans' formulation, 155 employees participated. In Study 2, which was time-lagged with two measurement points, and which explains intention, plans, and training actions undertaken, the data from 176 employees was collected at 3 month intervals. The results of these studies show that personality traits, mainly openness to experience, predict the training initiation process to some degree: intention, plans, and actual action initiation. The findings allow us to provide recommendations for practitioners responsible for human resource development. The assessment of openness to experience in employees helps predict their motivation to participate in training activities. To increase training motivation it is vital to strengthen intentions to undertake training, and to encourage training action planning.

Long-term intensive gymnastic training induced changes in intra- and inter-network functional connectivity: an independent component analysis.

PubMed

Huang, Huiyuan; Wang, Junjing; Seger, Carol; Lu, Min; Deng, Feng; Wu, Xiaoyan; He, Yuan; Niu, Chen; Wang, Jun; Huang, Ruiwang

2018-01-01

Long-term intensive gymnastic training can induce brain structural and functional reorganization. Previous studies have identified structural and functional network differences between world class gymnasts (WCGs) and non-athletes at the whole-brain level. However, it is still unclear how interactions within and between functional networks are affected by long-term intensive gymnastic training. We examined both intra- and inter-network functional connectivity of gymnasts relative to non-athletes using resting-state fMRI (R-fMRI). R-fMRI data were acquired from 13 WCGs and 14 non-athlete controls. Group-independent component analysis (ICA) was adopted to decompose the R-fMRI data into spatial independent components and associated time courses. An automatic component identification method was used to identify components of interest associated with resting-state networks (RSNs). We identified nine RSNs, the basal ganglia network (BG), sensorimotor network (SMN), cerebellum (CB), anterior and posterior default mode networks (aDMN/pDMN), left and right fronto-parietal networks (lFPN/rFPN), primary visual network (PVN), and extrastriate visual network (EVN). Statistical analyses revealed that the intra-network functional connectivity was significantly decreased within the BG, aDMN, lFPN, and rFPN, but increased within the EVN in the WCGs compared to the controls. In addition, the WCGs showed uniformly decreased inter-network functional connectivity between SMN and BG, CB, and PVN, BG and PVN, and pDMN and rFPN compared to the controls. We interpret this generally weaker intra- and inter-network functional connectivity in WCGs during the resting state as a result of greater efficiency in the WCGs' brain associated with long-term motor skill training.

Classification of 2-dimensional array patterns: assembling many small neural networks is better than using a large one.

PubMed

Chen, Liang; Xue, Wei; Tokuda, Naoyuki

2010-08-01

In many pattern classification/recognition applications of artificial neural networks, an object to be classified is represented by a fixed sized 2-dimensional array of uniform type, which corresponds to the cells of a 2-dimensional grid of the same size. A general neural network structure, called an undistricted neural network, which takes all the elements in the array as inputs could be used for problems such as these. However, a districted neural network can be used to reduce the training complexity. A districted neural network usually consists of two levels of sub-neural networks. Each of the lower level neural networks, called a regional sub-neural network, takes the elements in a region of the array as its inputs and is expected to output a temporary class label, called an individual opinion, based on the partial information of the entire array. The higher level neural network, called an assembling sub-neural network, uses the outputs (opinions) of regional sub-neural networks as inputs, and by consensus derives the label decision for the object. Each of the sub-neural networks can be trained separately and thus the training is less expensive. The regional sub-neural networks can be trained and performed in parallel and independently, therefore a high speed can be achieved. We prove theoretically in this paper, using a simple model, that a districted neural network is actually more stable than an undistricted neural network in noisy environments. We conjecture that the result is valid for all neural networks. This theory is verified by experiments involving gender classification and human face recognition. We conclude that a districted neural network is highly recommended for neural network applications in recognition or classification of 2-dimensional array patterns in highly noisy environments. Copyright (c) 2010 Elsevier Ltd. All rights reserved.

Convolutional neural network with transfer learning for rice type classification

NASA Astrophysics Data System (ADS)

Patel, Vaibhav Amit; Joshi, Manjunath V.

2018-04-01

Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

Convolutional networks for vehicle track segmentation

NASA Astrophysics Data System (ADS)

Quach, Tu-Thach

2017-10-01

Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple and fast models to label track pixels. These models, however, are unable to capture natural track features, such as continuity and parallelism. More powerful but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3×3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate in low power and have limited training data. As a result, we aim for small and efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our six-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.

A Deep Learning based Approach to Reduced Order Modeling of Fluids using LSTM Neural Networks

NASA Astrophysics Data System (ADS)

Mohan, Arvind; Gaitonde, Datta

2017-11-01

Reduced Order Modeling (ROM) can be used as surrogates to prohibitively expensive simulations to model flow behavior for long time periods. ROM is predicated on extracting dominant spatio-temporal features of the flow from CFD or experimental datasets. We explore ROM development with a deep learning approach, which comprises of learning functional relationships between different variables in large datasets for predictive modeling. Although deep learning and related artificial intelligence based predictive modeling techniques have shown varied success in other fields, such approaches are in their initial stages of application to fluid dynamics. Here, we explore the application of the Long Short Term Memory (LSTM) neural network to sequential data, specifically to predict the time coefficients of Proper Orthogonal Decomposition (POD) modes of the flow for future timesteps, by training it on data at previous timesteps. The approach is demonstrated by constructing ROMs of several canonical flows. Additionally, we show that statistical estimates of stationarity in the training data can indicate a priori how amenable a given flow-field is to this approach. Finally, the potential and limitations of deep learning based ROM approaches will be elucidated and further developments discussed.

Simulations in Cyber-Security: A Review of Cognitive Modeling of Network Attackers, Defenders, and Users.

PubMed

Veksler, Vladislav D; Buchler, Norbou; Hoffman, Blaine E; Cassenti, Daniel N; Sample, Char; Sugrim, Shridat

2018-01-01

Computational models of cognitive processes may be employed in cyber-security tools, experiments, and simulations to address human agency and effective decision-making in keeping computational networks secure. Cognitive modeling can addresses multi-disciplinary cyber-security challenges requiring cross-cutting approaches over the human and computational sciences such as the following: (a) adversarial reasoning and behavioral game theory to predict attacker subjective utilities and decision likelihood distributions, (b) human factors of cyber tools to address human system integration challenges, estimation of defender cognitive states, and opportunities for automation, (c) dynamic simulations involving attacker, defender, and user models to enhance studies of cyber epidemiology and cyber hygiene, and (d) training effectiveness research and training scenarios to address human cyber-security performance, maturation of cyber-security skill sets, and effective decision-making. Models may be initially constructed at the group-level based on mean tendencies of each subject's subgroup, based on known statistics such as specific skill proficiencies, demographic characteristics, and cultural factors. For more precise and accurate predictions, cognitive models may be fine-tuned to each individual attacker, defender, or user profile, and updated over time (based on recorded behavior) via techniques such as model tracing and dynamic parameter fitting.

DEFI Photonique: a French national training project for optics and photonics industry

NASA Astrophysics Data System (ADS)

Boéri, E.; Cormier, E.

2014-07-01

The French government supports a structuring project for French Photonics. This project name DEFI Photonique is carried by the CNOP (National Committee for Optics and Photonics) for a period of 5 years (2013-2017). One of the most important tasks is dedicated to training for industry, particularly SMEs. The project aims at elaborating a training offer based on the experience of PYLA, the Bordeaux training facility for Optics and Photonics, and create a national network throughout all the French Photonics clusters. The project plans to initiate, develop and coordinate training courses based on the players skills in the sector, in particular regional clusters, depending on their field of excellence. This deployment of training courses should enable a mesh structure both thematically and geographically. Collaborative work between training players in each pole, including joint actions, will facilitate access to training courses for companies, especially SMEs. A market survey is already being conducted in 2013 in photonics industry and application sectors. Implementation of actions involves all French photonics clusters as well as professional organizations. We will rely on the feedback we have with PYLA to show how training courses can be a strategic tool for development of technologies and industries. At this stage of the DEFI Photonique project we will be able to present the results of different analyses that have been conducted in key sectors and plans that will be implemented for the realization of the first actions.

Networking among young global health researchers through an intensive training approach: a mixed methods exploratory study

PubMed Central

2014-01-01

Background Networks are increasingly regarded as essential in health research aimed at influencing practice and policies. Less research has focused on the role networking can play in researchers’ careers and its broader impacts on capacity strengthening in health research. We used the Canadian Coalition for Global Health Research (CCGHR) annual Summer Institute for New Global Health Researchers (SIs) as an opportunity to explore networking among new global health researchers. Methods A mixed-methods exploratory study was conducted among SI alumni and facilitators who had participated in at least one SI between 2004 and 2010. Alumni and facilitators completed an online short questionnaire, and a subset participated in an in-depth interview. Thematic analysis of the qualitative data was triangulated with quantitative results and CCGHR reports on SIs. Synthesis occurred through the development of a process model relevant to networking through the SIs. Results Through networking at the SIs, participants experienced decreased isolation and strengthened working relationships. Participants accessed new knowledge, opportunities, and resources through networking during the SI. Post-SI, participants reported ongoing contact and collaboration, although most participants desired more opportunities for interaction. They made suggestions for structural supports to networking among new global health researchers. Conclusions Networking at the SI contributed positively to opportunities for individuals, and contributed to the formation of a network of global health researchers. Intentional inclusion of networking in health research capacity strengthening initiatives, with supportive resources and infrastructure could create dynamic, sustainable networks accessible to global health researchers around the world. PMID:24460819

VoIP attacks detection engine based on neural network

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Slachta, Jiri

2015-05-01

The security is crucial for any system nowadays, especially communications. One of the most successful protocols in the field of communication over IP networks is Session Initiation Protocol. It is an open-source project used by different kinds of applications, both open-source and proprietary. High penetration and text-based principle made SIP number one target in IP telephony infrastructure, so security of SIP server is essential. To keep up with hackers and to detect potential malicious attacks, security administrator needs to monitor and evaluate SIP traffic in the network. But monitoring and following evaluation could easily overwhelm the security administrator in networks, typically in networks with a number of SIP servers, users and logically or geographically separated networks. The proposed solution lies in automatic attack detection systems. The article covers detection of VoIP attacks through a distributed network of nodes. Then the gathered data analyze aggregation server with artificial neural network. Artificial neural network means multilayer perceptron network trained with a set of collected attacks. Attack data could also be preprocessed and verified with a self-organizing map. The source data is detected by distributed network of detection nodes. Each node contains a honeypot application and traffic monitoring mechanism. Aggregation of data from each node creates an input for neural networks. The automatic classification on a centralized server with low false positive detection reduce the cost of attack detection resources. The detection system uses modular design for easy deployment in final infrastructure. The centralized server collects and process detected traffic. It also maintains all detection nodes.

Neural networks in data analysis and modeling for detecting littoral oil-spills by airborne laser fluorosensor remote sensing

NASA Astrophysics Data System (ADS)

Lin, Bin; An, Jubai; Brown, Carl E.; Chen, Weiwei

2003-05-01

In this paper an artificial neural network (ANN) approach, which is based on flexible nonlinear models for a very broad class of transfer functions, is applied for multi-spectral data analysis and modeling of airborne laser fluorosensor in order to differentiate between classes of oil on water surface. We use three types of algorithm: Perceptron Network, Back-Propagation (B-P) Network and Self-Organizing feature Maps (SOM) Network. Using the data in form of 64-channel spectra as inputs, the ANN presents the analysis and estimation results of the oil type on the basis of the type of background materials as outputs. The ANN is trained and tested using sample data set to the network. The results of the above 3 types of network are compared in this paper. It is proved that the training has developed a network that not only fits the training data, but also fits real-world data that the network will process operationally. The ANN model would play a significant role in the ocean oil-spill identification in the future.

Increased Resting-State Functional Connectivity in the Cingulo-Opercular Cognitive-Control Network after Intervention in Children with Reading Difficulties

PubMed Central

Horowitz-Kraus, Tzipi; Toro-Serey, Claudio; DiFrancesco, Mark

2015-01-01

Dyslexia, or reading difficulty, is characterized by slow, inaccurate reading accompanied by executive dysfunction. Reading training using the Reading Acceleration Program improves reading and executive functions in both children with dyslexia and typical readers. This improvement is associated with increased activation in and functional connectivity between the anterior cingulate cortex, part of the cingulo-opercular cognitive-control network, and the fusiform gyrus during a reading task after training. The objective of the current study was to determine whether the training also has an effect on functional connectivity of the cingulo-opercular and fronto-parietal cognitive-control networks during rest in children with dyslexia and typical readers. Fifteen children with reading difficulty and 17 typical readers (8-12 years old) were included in the study. Reading and executive functions behavioral measures and resting-state functional magnetic resonance imaging data were collected before and after reading training. Imaging data were analyzed using a graphical network-modeling tool. Both reading groups had increased reading and executive-functions scores after training, with greater gains among the dyslexia group. Training may have less effect on cognitive control in typical readers and a more direct effect on the visual area, as previously reported. Statistical analysis revealed that compared to typical readers, children with reading difficulty had significantly greater functional connectivity in the cingulo-opercular network after training, which may demonstrate the importance of cognitive control during reading in this population. These results support previous findings of increased error-monitoring activation after reading training in children with dyslexia and confirm greater gains with training in this group. PMID:26197049

Convolution neural networks for real-time needle detection and localization in 2D ultrasound.

PubMed

Mwikirize, Cosmas; Nosher, John L; Hacihaliloglu, Ilker

2018-05-01

We propose a framework for automatic and accurate detection of steeply inserted needles in 2D ultrasound data using convolution neural networks. We demonstrate its application in needle trajectory estimation and tip localization. Our approach consists of a unified network, comprising a fully convolutional network (FCN) and a fast region-based convolutional neural network (R-CNN). The FCN proposes candidate regions, which are then fed to a fast R-CNN for finer needle detection. We leverage a transfer learning paradigm, where the network weights are initialized by training with non-medical images, and fine-tuned with ex vivo ultrasound scans collected during insertion of a 17G epidural needle into freshly excised porcine and bovine tissue at depth settings up to 9 cm and [Formula: see text]-[Formula: see text] insertion angles. Needle detection results are used to accurately estimate needle trajectory from intensity invariant needle features and perform needle tip localization from an intensity search along the needle trajectory. Our needle detection model was trained and validated on 2500 ex vivo ultrasound scans. The detection system has a frame rate of 25 fps on a GPU and achieves 99.6% precision, 99.78% recall rate and an [Formula: see text] score of 0.99. Validation for needle localization was performed on 400 scans collected using a different imaging platform, over a bovine/porcine lumbosacral spine phantom. Shaft localization error of [Formula: see text], tip localization error of [Formula: see text] mm, and a total processing time of 0.58 s were achieved. The proposed method is fully automatic and provides robust needle localization results in challenging scanning conditions. The accurate and robust results coupled with real-time detection and sub-second total processing make the proposed method promising in applications for needle detection and localization during challenging minimally invasive ultrasound-guided procedures.

Networked simulation for team training of Space Station astronauts, ground controllers, and scientists - A training and development environment

NASA Technical Reports Server (NTRS)

Hajare, Ankur R.; Wick, Daniel T.; Bovenzi, James J.

1991-01-01

The purpose of this paper is to describe plans for the Space Station Training Facility (SSTF) which has been designed to meet the envisioned training needs for Space Station Freedom. To meet these needs, the SSTF will integrate networked simulators with real-world systems in five training modes: Stand-Alone, Combined, Joint-Combined, Integrated, and Joint-Integrated. This paper describes the five training modes within the context of three training scenaries. In addition, this paper describes an authoring system which will support the rapid integration of new real-world system changes in the Space Station Freedom Program.

Nonlinear calibration for petroleum water content measurement using PSO

NASA Astrophysics Data System (ADS)

Li, Mingbao; Zhang, Jiawei

2008-10-01

A new algorithmic for strapdown inertial navigation system (SINS) state estimation based on neural networks is introduced. In training strategy, the error vector and its delay are introduced. This error vector is made of the position and velocity difference between the estimations of system and the outputs of GPS. After state prediction and state update, the states of the system are estimated. After off-line training, the network can approach the status switching of SINS and after on-line training, the state estimate precision can be improved further by reducing network output errors. Then the network convergence is discussed. In the end, several simulations with different noise are given. The results show that the neural network state estimator has lower noise sensitivity and better noise immunity than Kalman filter.

Scaling of counter-current imbibition recovery curves using artificial neural networks

NASA Astrophysics Data System (ADS)

Jafari, Iman; Masihi, Mohsen; Nasiri Zarandi, Masoud

2018-06-01

Scaling imbibition curves are of great importance in the characterization and simulation of oil production from naturally fractured reservoirs. Different parameters such as matrix porosity and permeability, oil and water viscosities, matrix dimensions, and oil/water interfacial tensions have an effective on the imbibition process. Studies on the scaling imbibition curves along with the consideration of different assumptions have resulted in various scaling equations. In this work, using an artificial neural network (ANN) method, a novel technique is presented for scaling imbibition recovery curves, which can be used for scaling the experimental and field-scale imbibition cases. The imbibition recovery curves for training and testing the neural network were gathered through the simulation of different scenarios using a commercial reservoir simulator. In this ANN-based method, six parameters were assumed to have an effect on the imbibition process and were considered as the inputs for training the network. Using the ‘Bayesian regularization’ training algorithm, the network was trained and tested. Training and testing phases showed superior results in comparison with the other scaling methods. It is concluded that using the new technique is useful for scaling imbibition recovery curves, especially for complex cases, for which the common scaling methods are not designed.

The effects of initial participation motivations on learning engagement in transition training for future general practitioners in rural China: perceived deterrents as mediator

PubMed Central

Cui, Guan-yu; Yao, Mei-lin; Zhang, Xia; Guo, Yan-kui; Li, Hui-min; Yao, Xiu-ping

2016-01-01

Background For the shortage of high-quality general practitioners (GPs) in China's rural areas, Chinese government has taken steps to encourage rural specialists to participate in transition training for future GPs. Specialists’ initial participation motivations and their perceived deterrents during training may play important roles for their learning engagement in the transition training. This study aimed at revealing the relationships among the variables of initial participation motivations, perceived deterrents in training, and learning engagement. Methods A questionnaire survey was used in this study. A total of 156 rural specialists who participated in transition training for future GPs filled out the questionnaire, which consisted of the measurements of initial participation motivations, perceived deterrents, and learning engagement in training. The data about specialists’ demographic variables were collected at the same time. Results The variance of initial escape/stimulations motivation significantly predicted the variance of learning engagement through the full mediating role of perceived deterrents in training. In addition, initial educational preparation motivations predicted the variance of learning engagement directly. Conclusions Specialists’ initial participation motivations and perceived deterrents in training played important roles for learning engagement in the transition training. PMID:27340086

Method Accelerates Training Of Some Neural Networks

NASA Technical Reports Server (NTRS)

Shelton, Robert O.

1992-01-01

Three-layer networks trained faster provided two conditions are satisfied: numbers of neurons in layers are such that majority of work done in synaptic connections between input and hidden layers, and number of neurons in input layer at least as great as number of training pairs of input and output vectors. Based on modified version of back-propagation method.

Mapping, Awareness, and Virtualization Network Administrator Training Tool (MAVNATT) Architecture and Framework

DTIC Science & Technology

2015-06-01

unit may setup and teardown the entire tactical infrastructure multiple times per day. This tactical network administrator training is a critical...language and runs on Linux and Unix based systems. All provisioning is based around the Nagios Core application, a powerful backend solution for network...start up a large number of virtual machines quickly. CORE supports the simulation of fixed and mobile networks. CORE is open-source, written in Python

GMES Initial Operations - Network for Earth Observation Research Training (GIONET)

NASA Astrophysics Data System (ADS)

Nicolas-Perea, V.; Balzter, H.

2012-12-01

GMES Initial Operations - Network for Earth Observation Research Training (GIONET) is a Marie Curie funded project that aims to establish the first of a kind European Centre of Excellence for Earth Observation Research Training. GIONET is a partnership of leading Universities, research institutes and private companies from across Europe aiming to cultivate a community of early stage researchers in the areas of optical and radar remote sensing skilled for the emerging GMES land monitoring services during the GMES Initial Operations period (2011-2013) and beyond. GIONET is expected to satisfy the demand for highly skilled researchers and provide personnel for operational phase of the GMES and monitoring and emergency services. It will achieve this by: -Providing postgraduate training in Earth Observation Science that exposes students to different research disciplines and complementary skills, providing work experiences in the private and academic sectors, and leading to a recognized qualification (Doctorate). -Enabling access to first class training in both fundamental and applied research skills to early-stage researchers at world-class academic centers and market leaders in the private sector. -Building on the experience from previous GMES research and development projects in the land monitoring and emergency information services. The training program through supervised research focuses on 14 research topics (each carried out by an Early Stage Researchers based in one of the partner organization) divided in 5 main areas: Forest monitoring: Global biomass information systems Forest Monitoring of the Congo Basin using Synthetic Aperture radar (SAR) Multi-concept Earth Observation Capabilities for Biomass Mapping and Change Detection: Synergy of Multi-temporal and Multi-frequency Interferometric Radar and Optical Satellite Data Land cover and change: Multi-scale Remote Sensing Synergy for Land Process Studies: from field Spectrometry to Airborne Hyperspectral and Lidar Campaigns to Radar-Optical Satellite Data Multi-temporal, multi-frequency SAR for landscape dynamics Coastal zone and freshwater monitoring: Optical and SAR-based EO in support of Integrated Coastal Zone Management Dynamics and conservation ecology of emergent and submerged macrophytes in Lake Balaton using airborne remote sensing Satellite remote sensing of water quality (chlorophyll and suspended sediment) using MODIS and ship-mounted LIDAR Geohazards and emergency response: Methods for detection and monitoring of small scale land surface feature changes in complex crisis situations Monitoring landslide displacements with Radar Interferometry DINSAR/PSI hybrid methodologies for ground-motion monitoring Climate adaptation and emergency response: Earth Observation based analysis of regional impact of climate change induced water stress patterns fuelling human crisis and conflict situations in semi dry climate regimes Satellite Derived Information for Drought Detection and Estimation of the Water Balance GIONET will also cover methodologies including (i) modelling fundamental radiative processes determining the satellite signal, (ii) atmospheric correction and calibration, (iii) processing higher-order data products, (iii) developing information products from satellite data to meet user requirements, and (iv) statistical methods for assessing the quality and accuracy of data products.

The Effectiveness of Using Virtual Laboratories to Teach Computer Networking Skills in Zambia

ERIC Educational Resources Information Center

Lampi, Evans

2013-01-01

The effectiveness of using virtual labs to train students in computer networking skills, when real equipment is limited or unavailable, is uncertain. The purpose of this study was to determine the effectiveness of using virtual labs to train students in the acquisition of computer network configuration and troubleshooting skills. The study was…

Neural Network and Response Surface Methodology for Rocket Engine Component Optimization

NASA Technical Reports Server (NTRS)

Vaidyanathan, Rajkumar; Papita, Nilay; Shyy, Wei; Tucker, P. Kevin; Griffin, Lisa W.; Haftka, Raphael; Fitz-Coy, Norman; McConnaughey, Helen (Technical Monitor)

2000-01-01

The goal of this work is to compare the performance of response surface methodology (RSM) and two types of neural networks (NN) to aid preliminary design of two rocket engine components. A data set of 45 training points and 20 test points obtained from a semi-empirical model based on three design variables is used for a shear coaxial injector element. Data for supersonic turbine design is based on six design variables, 76 training, data and 18 test data obtained from simplified aerodynamic analysis. Several RS and NN are first constructed using the training data. The test data are then employed to select the best RS or NN. Quadratic and cubic response surfaces. radial basis neural network (RBNN) and back-propagation neural network (BPNN) are compared. Two-layered RBNN are generated using two different training algorithms, namely solverbe and solverb. A two layered BPNN is generated with Tan-Sigmoid transfer function. Various issues related to the training of the neural networks are addressed including number of neurons, error goals, spread constants and the accuracy of different models in representing the design space. A search for the optimum design is carried out using a standard gradient-based optimization algorithm over the response surfaces represented by the polynomials and trained neural networks. Usually a cubic polynominal performs better than the quadratic polynomial but exceptions have been noticed. Among the NN choices, the RBNN designed using solverb yields more consistent performance for both engine components considered. The training of RBNN is easier as it requires linear regression. This coupled with the consistency in performance promise the possibility of it being used as an optimization strategy for engineering design problems.

Reorganization of large-scale cognitive networks during automation of imagination of a complex sequential movement.

PubMed

Sauvage, C; De Greef, N; Manto, M; Jissendi, P; Nioche, C; Habas, C

2015-04-01

We investigated the functional reconfiguration of the cerebral networks involved in imagination of sequential movements of the left foot, both performed at regular and fast speed after mental imagery training. Thirty-five volunteers were scanned with a 3T MRI while they imagined a sequence of ankle movements (dorsiflexion, plantar flexion, varus and valgus) before and after mental practice. Subjects were distributed in two groups: the first group executed regular movements whereas the second group made fast movements. We applied the general linear model (GLM) and model-free, exploratory tensorial independent component analytic (TICA) approaches to identify plastic post-training effects on brain activation. GLM showed that post-training imagination of movement was accompanied by a dual effect: a specific recruitment of a medial prefronto-cingulo-parietal circuit reminiscent of the default-mode network, with the left putamen, and a decreased activity of a lateral fronto-parietal network. Training-related subcortical changes only consisted in an increased activity in the left striatum. Unexpectedly, no difference was observed in the cerebellum. TICA also revealed involvement of the left executive network, and of the dorsal control executive network but no significant differences were found between pre- and post-training phases. Therefore, repetitive motor mental imagery induced specific putamen (motor rehearsal) recruitment that one previously observed during learning of overt movements, and, simultaneously, a specific shift of activity from the dorsolateral prefrontal cortex (attention, working memory) to the medial posterior parietal and cingulate cortices (mental imagery and memory rehearsal). Our data complement and confirm the notion that differential and coupled recruitment of cognitive networks can constitute a neural marker of training effects. Copyright © 2014 Elsevier Masson SAS. All rights reserved.

Training Deep Spiking Neural Networks Using Backpropagation.

PubMed

Lee, Jun Haeng; Delbruck, Tobi; Pfeiffer, Michael

2016-01-01

Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.

Generating Seismograms with Deep Neural Networks

NASA Astrophysics Data System (ADS)

Krischer, L.; Fichtner, A.

2017-12-01

The recent surge of successful uses of deep neural networks in computer vision, speech recognition, and natural language processing, mainly enabled by the availability of fast GPUs and extremely large data sets, is starting to see many applications across all natural sciences. In seismology these are largely confined to classification and discrimination tasks. In this contribution we explore the use of deep neural networks for another class of problems: so called generative models.Generative modelling is a branch of statistics concerned with generating new observed data samples, usually by drawing from some underlying probability distribution. Samples with specific attributes can be generated by conditioning on input variables. In this work we condition on seismic source (mechanism and location) and receiver (location) parameters to generate multi-component seismograms.The deep neural networks are trained on synthetic data calculated with Instaseis (http://instaseis.net, van Driel et al. (2015)) and waveforms from the global ShakeMovie project (http://global.shakemovie.princeton.edu, Tromp et al. (2010)). The underlying radially symmetric or smoothly three dimensional Earth structures result in comparatively small waveform differences from similar events or at close receivers and the networks learn to interpolate between training data samples.Of particular importance is the chosen misfit functional. Generative adversarial networks (Goodfellow et al. (2014)) implement a system in which two networks compete: the generator network creates samples and the discriminator network distinguishes these from the true training examples. Both are trained in an adversarial fashion until the discriminator can no longer distinguish between generated and real samples. We show how this can be applied to seismograms and in particular how it compares to networks trained with more conventional misfit metrics. Last but not least we attempt to shed some light on the black-box nature of neural networks by estimating the quality and uncertainties of the generated seismograms.

Reconstruction of initial pressure from limited view photoacoustic images using deep learning

NASA Astrophysics Data System (ADS)

Waibel, Dominik; Gröhl, Janek; Isensee, Fabian; Kirchner, Thomas; Maier-Hein, Klaus; Maier-Hein, Lena

2018-02-01

Quantification of tissue properties with photoacoustic (PA) imaging typically requires a highly accurate representation of the initial pressure distribution in tissue. Almost all PA scanners reconstruct the PA image only from a partial scan of the emitted sound waves. Especially handheld devices, which have become increasingly popular due to their versatility and ease of use, only provide limited view data because of their geometry. Owing to such limitations in hardware as well as to the acoustic attenuation in tissue, state-of-the-art reconstruction methods deliver only approximations of the initial pressure distribution. To overcome the limited view problem, we present a machine learning-based approach to the reconstruction of initial pressure from limited view PA data. Our method involves a fully convolutional deep neural network based on a U-Net-like architecture with pixel-wise regression loss on the acquired PA images. It is trained and validated on in silico data generated with Monte Carlo simulations. In an initial study we found an increase in accuracy over the state-of-the-art when reconstructing simulated linear-array scans of blood vessels.

Studies with spike initiators - Linearization by noise allows continuous signal modulation in neural networks

NASA Technical Reports Server (NTRS)

Yu, Xiaolong; Lewis, Edwin R.

1989-01-01

It is shown that noise can be an important element in the translation of neuronal generator potentials (summed inputs) to neuronal spike trains (outputs), creating or expanding a range of amplitudes over which the spike rate is proportional to the generator potential amplitude. Noise converts the basically nonlinear operation of a spike initiator into a nearly linear modulation process. This linearization effect of noise is examined in a simple intuitive model of a static threshold and in a more realistic computer simulation of spike initiator based on the Hodgkin-Huxley (HH) model. The results are qualitatively similar; in each case larger noise amplitude results in a larger range of nearly linear modulation. The computer simulation of the HH model with noise shows linear and nonlinear features that were earlier observed in spike data obtained from the VIIIth nerve of the bullfrog. This suggests that these features can be explained in terms of spike initiator properties, and it also suggests that the HH model may be useful for representing basic spike initiator properties in vertebrates.